Merge branch 'fix/dup-dedup' into issue/324-Switch-from-NVD-data-feeds-to-API

33 files changed, 2426 insertions, 914 deletions

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 316e8679..961a1058 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -16,6 +16,10 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: "3.8"
+          cache: "pip"
+          cache-dependency-path: |
+            requirements/requirements.txt
+            requirements/test_requirements.txt
       - name: Install python dependencies
         run: |
           pip install -r requirements/requirements.txt
diff --git a/docs/quickstart.md b/docs/quickstart.md
index d916bc5a..1088e51a 100644
--- a/docs/quickstart.md
+++ b/docs/quickstart.md
@@ -6,7 +6,7 @@
 1. Install the latest version with `pip install -U sec-certs && python -m spacy download en_core_web_sm` (see [installation](installation.md)).
 2. In your Python interpreter, type
 ```python
-from sec_certs.dataset import CCDataset
+from sec_certs.dataset.cc import CCDataset
 
 dset = CCDataset.from_web_latest()
 ```
@@ -19,7 +19,7 @@ to obtain to obtain freshly processed dataset from [seccerts.org](https://seccer
 1. Install the latest version with `pip install -U sec-certs && python -m spacy download en_core_web_sm` (see [installation](installation.md)).
 2. In your Python interpreter, type
 ```python
-from sec_certs.dataset import FIPSDataset
+from sec_certs.dataset.fips import FIPSDataset
 
 dset = FIPSDataset.from_web_latest()
 ```
diff --git a/notebooks/fips/in_process.ipynb b/notebooks/fips/in_process.ipynb
index 00ff5eb1..d127d854 100644
--- a/notebooks/fips/in_process.ipynb
+++ b/notebooks/fips/in_process.ipynb
@@ -7,18 +7,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from itertools import takewhile\n",
+    "from operator import itemgetter\n",
+    "\n",
     "from sec_certs.dataset.fips_mip import MIPDataset\n",
     "from sec_certs.dataset.fips_iut import IUTDataset\n",
     "from sec_certs.sample.fips_mip import MIPStatus\n",
+    "from sec_certs.model.fips_matching import FIPSProcessMatcher\n",
+    "from sec_certs.dataset.fips import FIPSDataset\n",
+    "from sec_certs.configuration import config\n",
     "import pandas as pd\n",
     "import seaborn as sns\n",
     "import matplotlib.pyplot as plt\n",
-    "import math\n",
     "import numpy as np\n",
-    "import tqdm\n",
+    "from tqdm import tqdm\n",
     "import matplotlib.ticker as mtick\n",
     "import warnings\n",
-    "from pathlib import Path\n",
     "\n",
     "plt.style.use(\"seaborn-whitegrid\")\n",
     "sns.set_palette(\"deep\")\n",
@@ -28,6 +32,20 @@
    ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "fips = FIPSDataset.from_web_latest()\n"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
    "cell_type": "markdown",
    "id": "bd5f0fd6",
    "metadata": {},
@@ -97,10 +115,10 @@
     "\n",
     "iut_first_seen = {}\n",
     "iut_last_seen = {}\n",
-    "for snapshot in sorted(iut_dset.snapshots, key=lambda x: x.timestamp):\n",
+    "for snapshot in tqdm(sorted(iut_dset.snapshots, key=lambda x: x.timestamp)):\n",
     "    snapshot_date = snapshot.timestamp.date()\n",
     "    for entry in snapshot.entries:\n",
-    "        entry_key = entry #iut_key(entry) # or entry here\n",
+    "        entry_key = entry # iut_key(entry) # or entry here\n",
     "        if entry_key not in iut_first_seen:\n",
     "            iut_first_seen[entry_key] = snapshot_date\n",
     "        if entry_key not in iut_last_seen or iut_last_seen[entry_key] < snapshot_date:\n",
@@ -183,6 +201,33 @@
   },
   {
    "cell_type": "markdown",
+   "source": [
+    "### IUT - Certificate mapping"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "first_snapshot = iut_dset.snapshots[-1]\n",
+    "matches = FIPSProcessMatcher.match_snapshot(first_snapshot, fips)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "markdown",
    "id": "cbc02977",
    "metadata": {},
    "source": [
@@ -338,6 +383,33 @@
     "    g.set_titles(\"{col_name}\")\n",
     "    plt.show()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### MIP - Certificate matching"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "first_snapshot = mip_dset.snapshots[-1]\n",
+    "matches = FIPSProcessMatcher.match_snapshot(first_snapshot, fips)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
   }
  ],
  "metadata": {
@@ -366,4 +438,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}
\ No newline at end of file
diff --git a/src/sec_certs/cli.py b/src/sec_certs/cli.py
index d1a1eb90..9bd74108 100644
--- a/src/sec_certs/cli.py
+++ b/src/sec_certs/cli.py
@@ -12,8 +12,9 @@ import click
 from pydantic import ValidationError
 
 from sec_certs.configuration import config
-from sec_certs.dataset import CCDataset, FIPSDataset
+from sec_certs.dataset.cc import CCDataset
 from sec_certs.dataset.dataset import Dataset
+from sec_certs.dataset.fips import FIPSDataset
 from sec_certs.utils.helpers import warn_if_missing_poppler, warn_if_missing_tesseract
 
 logger = logging.getLogger(__name__)
diff --git a/src/sec_certs/configuration.py b/src/sec_certs/configuration.py
index 44523c7f..f4883dbd 100644
--- a/src/sec_certs/configuration.py
+++ b/src/sec_certs/configuration.py
@@ -79,6 +79,12 @@ class Configuration(BaseSettings):
         "https://seccerts.org/cpe/cpe_match_dataset.json.gz",
         description="URL for the latest snapshot of cpe match json.",
     )
+    fips_matching_threshold: int = Field(
+        90,
+        description="Level of required similarity before FIPS IUT/MIP entry is considered to match a FIPS certificate.",
+        ge=0,
+        le=100,
+    )
     minimal_token_length: int = Field(
         3,
         description="Minimal length of a string that will be considered as a token during keyword extraction in CVE matching",
@@ -94,7 +100,12 @@ class Configuration(BaseSettings):
     cc_reference_annotator_should_train: bool = Field(
         True, description="True if new reference annotator model shall be build, False otherwise."
     )
-
+    cc_matching_threshold: int = Field(
+        90,
+        description="Level of required similarity before CC scheme entry is considered to match a CC certificate.",
+        ge=0,
+        le=100,
+    )
     enable_progress_bars: bool = Field(
         True, description="If true, progress bars will be printed to stdout during computation."
     )
diff --git a/src/sec_certs/constants.py b/src/sec_certs/constants.py
index 56910307..b28b925d 100644
--- a/src/sec_certs/constants.py
+++ b/src/sec_certs/constants.py
@@ -69,8 +69,9 @@ GARBAGE_EVERY_SECOND_CHAR_THRESHOLD = 15
 GARBAGE_ALPHA_CHARS_THRESHOLD = 0.5
 
 CC_AUSTRALIA_BASE_URL = "https://www.cyber.gov.au"
-CC_AUSTRALIA_CERTIFIED_URL = (
-    CC_AUSTRALIA_BASE_URL + "/acsc/view-all-content/programs/australian-information-security-evaluation-program"
+CC_AUSTRALIA_INEVAL_URL = (
+    CC_AUSTRALIA_BASE_URL
+    + "/resources-business-and-government/assessment-and-evaluation-programs/australian-information-security-evaluation-program-aisep"
 )
 CC_CANADA_CERTIFIED_URL = "https://www.cyber.gc.ca/en/tools-services/common-criteria/certified-products"
 CC_CANADA_INEVAL_URL = "https://www.cyber.gc.ca/en/tools-services/common-criteria/products-evaluation"
@@ -81,32 +82,36 @@ CC_BSI_CERTIFIED_URL = (
     CC_BSI_BASE_URL
     + "EN/Themen/Unternehmen-und-Organisationen/Standards-und-Zertifizierung/Zertifizierung-und-Anerkennung/Listen/Zertifizierte-Produkte-nach-CC/zertifizierte-produkte-nach-cc_node.html"
 )
-CC_INDIA_CERTIFIED_URL = "https://www.commoncriteria-india.gov.in/product-certified"
-CC_INDIA_ARCHIVED_URL = "https://www.commoncriteria-india.gov.in/archived-prod-cer"
+CC_INDIA_BASE_URL = "https://www.commoncriteria-india.gov.in"
+CC_INDIA_CERTIFIED_URL = CC_INDIA_BASE_URL + "/Products-Certified"
+CC_INDIA_ARCHIVED_URL = CC_INDIA_BASE_URL + "/Products-Archived"
 CC_ITALY_BASE_URL = "https://www.ocsi.gov.it"
 CC_ITALY_CERTIFIED_URL = CC_ITALY_BASE_URL + "/index.php/elenchi-certificazioni/prodotti-certificati.html"
 CC_ITALY_INEVAL_URL = CC_ITALY_BASE_URL + "/index.php/elenchi-certificazioni/in-corso-di-valutazione.html"
-CC_JAPAN_BASE_URL = "https://www.ipa.go.jp/security/jisec/jisec_e"
+CC_JAPAN_BASE_URL = "https://www.ipa.go.jp/en/security/jisec"
 CC_JAPAN_CERT_BASE_URL = CC_JAPAN_BASE_URL + "/certified_products"
-CC_JAPAN_CERTIFIED_URL = CC_JAPAN_BASE_URL + "/certified_products/certfy_list_e31.html"
-CC_JAPAN_ARCHIVED_URL = CC_JAPAN_BASE_URL + "/certified_products/certfy_list_e_archive.html"
-CC_JAPAN_INEVAL_URL = CC_JAPAN_BASE_URL + "/prdct_in_eval.html"
+CC_JAPAN_CERTIFIED_SW_URL = CC_JAPAN_BASE_URL + "/software/certified-cert/index.html"
+CC_JAPAN_CERTIFIED_HW_URL = CC_JAPAN_BASE_URL + "/hardware/certified-cert/index.html"
+CC_JAPAN_ARCHIVED_SW_URL = CC_JAPAN_BASE_URL + "/software/certified-cert/archive.html"
+CC_JAPAN_INEVAL_URL = CC_JAPAN_BASE_URL + "/prdct-in-eval/in_eval_list.html"
 CC_MALAYSIA_BASE_URL = "https://iscb.cybersecurity.my"
 CC_MALAYSIA_CERTIFIED_URL = (
-    CC_MALAYSIA_BASE_URL + "/en/index.php/certification/product-certification/mycc/certified-products-and-systems"
+    CC_MALAYSIA_BASE_URL + "/index.php/certification/product-certification/mycc/certified-products-and-systems"
 )
 CC_MALAYSIA_INEVAL_URL = (
     CC_MALAYSIA_BASE_URL
-    + "/en/index.php/certification/product-certification/mycc/list-of-products-and-systems-under-evaluation-or-maintenance"
+    + "/index.php/certification/product-certification/mycc/list-of-products-and-systems-under-evaluation-or-maintenance"
 )
 CC_NETHERLANDS_BASE_URL = "https://www.tuv-nederland.nl/common-criteria"
 CC_NETHERLANDS_CERTIFIED_URL = CC_NETHERLANDS_BASE_URL + "/certificates.html"
 CC_NETHERLANDS_INEVAL_URL = CC_NETHERLANDS_BASE_URL + "/ongoing-certifications.html"
-CC_NORWAY_CERTIFIED_URL = "https://sertit.no/certified-products/category1919.html"
-CC_NORWAY_ARCHIVED_URL = "https://sertit.no/certified-products/product-archive/"
-CC_KOREA_EN_URL = "https://itscc.kr/main/main.do?accessMode=home_en"
-CC_KOREA_CERTIFIED_URL = "https://itscc.kr/certprod/list.do"
-CC_KOREA_PRODUCT_URL = "https://itscc.kr/certprod/view.do?product_id={}&product_class=1"
+CC_NORWAY_BASE_URL = "https://sertit.no"
+CC_NORWAY_CERTIFIED_URL = CC_NORWAY_BASE_URL + "/certified-products/category1919.html"
+CC_NORWAY_ARCHIVED_URL = CC_NORWAY_BASE_URL + "/certified-products/product-archive/"
+CC_KOREA_BASE_URL = "https://itscc.kr"
+CC_KOREA_EN_URL = CC_KOREA_BASE_URL + "/main/main.do?accessMode=home_en"
+CC_KOREA_CERTIFIED_URL = CC_KOREA_BASE_URL + "/certprod/list.do"
+CC_KOREA_PRODUCT_URL = CC_KOREA_BASE_URL + "/certprod/view.do?product_id={}&product_class=1"
 CC_SINGAPORE_BASE_URL = "https://www.csa.gov.sg"
 CC_SINGAPORE_CERTIFIED_URL = (
     CC_SINGAPORE_BASE_URL + "/Programmes/certification-and-labelling-schemes/csa-common-criteria/product-list"
@@ -114,6 +119,11 @@ CC_SINGAPORE_CERTIFIED_URL = (
 CC_SINGAPORE_ARCHIVED_URL = (
     CC_SINGAPORE_BASE_URL + "/Programmes/certification-and-labelling-schemes/csa-common-criteria/product-archives"
 )
+CC_SINGAPORE_API_URL = CC_SINGAPORE_BASE_URL + "/api/CsaCommonProductCriteria/getProduct"
+CC_SINGAPORE_INEVAL_URL = (
+    CC_SINGAPORE_BASE_URL
+    + "/our-programmes/certification-and-labelling-schemes/singapore-common-criteria-scheme/product-list/in-evaluation"
+)
 CC_SPAIN_BASE_URL = "https://oc.ccn.cni.es"
 CC_SPAIN_CERTIFIED_URL = CC_SPAIN_BASE_URL + "/en/certified-products/certified-products"
 CC_SWEDEN_BASE_URL = "https://www.fmv.se"
@@ -122,6 +132,7 @@ CC_SWEDEN_INEVAL_URL = CC_SWEDEN_BASE_URL + "/verksamhet/ovrig-verksamhet/csec/p
 CC_SWEDEN_ARCHIVED_URL = CC_SWEDEN_BASE_URL + "/verksamhet/ovrig-verksamhet/csec/arkiverade-certifikat-aldre-an-5-ar/"
 CC_TURKEY_ARCHIVED_URL = "https://statik.tse.org.tr/upload/tr/dosya/icerikyonetimi/3300/03112021143434-2.pdf"
 CC_USA_BASE_URL = "https://www.niap-ccevs.org"
+CC_USA_PRODUCT_URL = CC_USA_BASE_URL + "/Product/"
 CC_USA_CERTIFIED_URL = CC_USA_BASE_URL + "/Product/PCL.cfm"
 CC_USA_INEVAL_URL = CC_USA_BASE_URL + "/Product/PINE.cfm"
 CC_USA_ARCHIVED_URL = CC_USA_BASE_URL + "/Product/Archived.cfm"
diff --git a/src/sec_certs/dataset/__init__.py b/src/sec_certs/dataset/__init__.py
index c557c630..c6407d40 100644
--- a/src/sec_certs/dataset/__init__.py
+++ b/src/sec_certs/dataset/__init__.py
@@ -1,6 +1,7 @@
 """This package exposes Datasets of various Samples, both primary (Common Criteria, FIPS) and auxiliary (CVEs, CPEs, ...)"""
 
-from sec_certs.dataset.cc import CCDataset, CCDatasetMaintenanceUpdates, CCSchemeDataset
+from sec_certs.dataset.cc import CCDataset, CCDatasetMaintenanceUpdates
+from sec_certs.dataset.cc_scheme import CCSchemeDataset
 from sec_certs.dataset.cpe import CPEDataset
 from sec_certs.dataset.cve import CVEDataset
 from sec_certs.dataset.fips import FIPSDataset
diff --git a/src/sec_certs/dataset/cc.py b/src/sec_certs/dataset/cc.py
index c2d9ca0c..3ca3dff7 100644
--- a/src/sec_certs/dataset/cc.py
+++ b/src/sec_certs/dataset/cc.py
@@ -11,27 +11,28 @@ from typing import ClassVar, Iterator, cast
 
 import numpy as np
 import pandas as pd
-import requests
-from bs4 import BeautifulSoup, NavigableString, Tag
+from bs4 import BeautifulSoup, Tag
 
 import sec_certs.utils.sanitization
 from sec_certs import constants
 from sec_certs.configuration import config
+from sec_certs.dataset.cc_scheme import CCSchemeDataset
 from sec_certs.dataset.cpe import CPEDataset
 from sec_certs.dataset.cve import CVEDataset
 from sec_certs.dataset.dataset import AuxiliaryDatasets, Dataset, logger
 from sec_certs.dataset.protection_profile import ProtectionProfileDataset
+from sec_certs.model.cc_matching import CCSchemeMatcher
 from sec_certs.model.reference_finder import ReferenceFinder
 from sec_certs.model.sar_transformer import SARTransformer
 from sec_certs.model.transitive_vulnerability_finder import TransitiveVulnerabilityFinder
 from sec_certs.sample.cc import CCCertificate
 from sec_certs.sample.cc_certificate_id import CertificateId
 from sec_certs.sample.cc_maintenance_update import CCMaintenanceUpdate
+from sec_certs.sample.cc_scheme import EntryType
 from sec_certs.sample.protection_profile import ProtectionProfile
 from sec_certs.serialization.json import ComplexSerializableType, serialize
 from sec_certs.utils import helpers
 from sec_certs.utils import parallel_processing as cert_processing
-from sec_certs.utils.sanitization import sanitize_navigable_string as sns
 
 
 @dataclass
@@ -40,6 +41,7 @@ class CCAuxiliaryDatasets(AuxiliaryDatasets):
     cve_dset: CVEDataset | None = None
     pp_dset: ProtectionProfileDataset | None = None
     mu_dset: CCDatasetMaintenanceUpdates | None = None
+    scheme_dset: CCSchemeDataset | None = None
 
 
 class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializableType):
@@ -140,7 +142,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
     @property
     def pp_dataset_path(self) -> Path:
         """
-        Returns directory that holds files associated with Protection profiles
+        Returns a path to the dataset of Protection Profiles
         """
         return self.auxiliary_datasets_dir / "pp_dataset.json"
 
@@ -154,10 +156,17 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
     @property
     def mu_dataset_path(self) -> Path:
         """
-        Returns json that holds the datase of maintenance updates
+        Returns a path to the dataset of maintenance updates
         """
         return self.mu_dataset_dir / "maintenance_updates.json"
 
+    @property
+    def scheme_dataset_path(self) -> Path:
+        """
+        Returns a path to the scheme dataset
+        """
+        return self.auxiliary_datasets_dir / "scheme_dataset.json"
+
     BASE_URL: ClassVar[str] = "https://www.commoncriteriaportal.org"
 
     HTML_PRODUCTS_URL = {
@@ -345,7 +354,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
 
         # TODO: Now skipping bad lines, smarter heuristics to be built for dumb files
         df = pd.read_csv(file, engine="python", encoding="windows-1252", on_bad_lines="skip")
-        df = df.rename(columns={x: y for (x, y) in zip(list(df.columns), csv_header)})
+        df = df.rename(columns=dict(zip(list(df.columns), csv_header)))
 
         df["is_maintenance"] = ~df.maintenance_title.isnull()
         df = df.fillna(value="")
@@ -496,7 +505,7 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
             "Products for Digital Signatures",
             "Trusted Computing",
         ]
-        cat_dict = {x: y for (x, y) in zip(cc_table_ids, cc_categories)}
+        cat_dict = dict(zip(cc_table_ids, cc_categories))
 
         with file.open("r") as handle:
             soup = BeautifulSoup(handle, "html5lib")
@@ -734,11 +743,12 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
     def process_auxiliary_datasets(self, download_fresh: bool = False) -> None:
         """
         Processes all auxiliary datasets needed during computation. On top of base-class processing,
-        CC handles protection profiles and maintenance updates.
+        CC handles protection profiles, maintenance updates and schemes.
         """
         super().process_auxiliary_datasets(download_fresh)
         self.auxiliary_datasets.pp_dset = self.process_protection_profiles(to_download=download_fresh)
         self.auxiliary_datasets.mu_dset = self.process_maintenance_updates(to_download=download_fresh)
+        self.auxiliary_datasets.scheme_dset = self.process_schemes(to_download=download_fresh)
 
     def process_protection_profiles(
         self, to_download: bool = True, keep_metadata: bool = True
@@ -799,6 +809,30 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
 
         return update_dset
 
+    def process_schemes(self, to_download: bool = True, only_schemes: set[str] | None = None) -> CCSchemeDataset:
+        """
+        Downloads or loads from json a dataset of CC scheme data.
+        """
+        logger.info("Processing CC schemes")
+
+        self.auxiliary_datasets_dir.mkdir(parents=True, exist_ok=True)
+
+        if to_download or not self.scheme_dataset_path.exists():
+            scheme_dset = CCSchemeDataset.from_web(only_schemes)
+            scheme_dset.to_json(self.scheme_dataset_path)
+        else:
+            scheme_dset = CCSchemeDataset.from_json(self.scheme_dataset_path)
+
+        for scheme in scheme_dset:
+            certified = scheme.lists.get(EntryType.Certified)
+            if certified:
+                matches = CCSchemeMatcher.match_all(certified, scheme.country, self)
+                for dgst, match in matches.items():
+                    self[dgst].heuristics.scheme_data = match
+            # TODO: Archived??
+
+        return scheme_dset
+
 
 class CCDatasetMaintenanceUpdates(CCDataset, ComplexSerializableType):
     """
@@ -884,762 +918,3 @@ class CCDatasetMaintenanceUpdates(CCDataset, ComplexSerializableType):
         main_dates.maintenance_date = main_dates.maintenance_date.map(lambda x: [x])
         main_dates.index.name = "dgst"
         return main_dates.groupby("related_cert_digest").maintenance_date.agg("sum").rename("maintenance_dates")
-
-
-class CCSchemeDataset:
-    @staticmethod
-    def _download_page(url, session=None):
-        conn = session if session else requests
-        resp = conn.get(url, headers={"User-Agent": "seccerts.org"}, verify=False)
-        if resp.status_code != requests.codes.ok:
-            raise ValueError(f"Unable to download: status={resp.status_code}")
-        return BeautifulSoup(resp.content, "html5lib")
-
-    @staticmethod
-    def get_australia_in_evaluation():
-        # TODO: Information could be expanded by following url.
-        soup = CCSchemeDataset._download_page(constants.CC_AUSTRALIA_CERTIFIED_URL)
-        header = soup.find("h2", text="Products in evaluation")
-        table = header.find_next_sibling("table")
-        results = []
-        for tr in table.find_all("tr"):
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            cert = {
-                "vendor": sns(tds[0].text),
-                "product": sns(tds[1].text),
-                "url": constants.CC_AUSTRALIA_BASE_URL + tds[1].find("a")["href"],
-                "level": sns(tds[2].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_canada_certified():
-        soup = CCSchemeDataset._download_page(constants.CC_CANADA_CERTIFIED_URL)
-        tbody = soup.find("table").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr"):
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            cert = {
-                "product": sns(tds[0].text),
-                "vendor": sns(tds[1].text),
-                "level": sns(tds[2].text),
-                "certification_date": sns(tds[3].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_canada_in_evaluation():
-        soup = CCSchemeDataset._download_page(constants.CC_CANADA_INEVAL_URL)
-        tbody = soup.find("table").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr"):
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            cert = {
-                "product": sns(tds[0].text),
-                "vendor": sns(tds[1].text),
-                "level": sns(tds[2].text),
-                "cert_lab": sns(tds[3].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_france_certified():
-        # TODO: Information could be expanded by following product link.
-        base_soup = CCSchemeDataset._download_page(constants.CC_ANSSI_CERTIFIED_URL)
-        category_nav = base_soup.find("ul", class_="nav-categories")
-        results = []
-        for li in category_nav.find_all("li"):
-            a = li.find("a")
-            url = a["href"]
-            category_name = sns(a.text)
-            soup = CCSchemeDataset._download_page(constants.CC_ANSSI_BASE_URL + url)
-            table = soup.find("table", class_="produits-liste cc")
-            if not table:
-                continue
-            tbody = table.find("tbody")
-            for tr in tbody.find_all("tr"):
-                tds = tr.find_all("td")
-                if not tds:
-                    continue
-                cert = {
-                    "product": sns(tds[0].text),
-                    "vendor": sns(tds[1].text),
-                    "level": sns(tds[2].text),
-                    "id": sns(tds[3].text),
-                    "certification_date": sns(tds[4].text),
-                    "category": category_name,
-                    "url": constants.CC_ANSSI_BASE_URL + tds[0].find("a")["href"],
-                }
-                results.append(cert)
-        return results
-
-    @staticmethod
-    def get_germany_certified():
-        # TODO: Information could be expanded by following url.
-        base_soup = CCSchemeDataset._download_page(constants.CC_BSI_CERTIFIED_URL)
-        category_nav = base_soup.find("ul", class_="no-bullet row")
-        results = []
-        for li in category_nav.find_all("li"):
-            a = li.find("a")
-            url = a["href"]
-            category_name = sns(a.text)
-            soup = CCSchemeDataset._download_page(constants.CC_BSI_BASE_URL + url)
-            content = soup.find("div", class_="content").find("div", class_="column")
-            for table in content.find_all("table"):
-                tbody = table.find("tbody")
-                header = table.find_parent("div", class_="wrapperTable").find_previous_sibling("h2")
-                for tr in tbody.find_all("tr"):
-                    tds = tr.find_all("td")
-                    if len(tds) != 4:
-                        continue
-                    cert = {
-                        "cert_id": sns(tds[0].text),
-                        "product": sns(tds[1].text),
-                        "vendor": sns(tds[2].text),
-                        "certification_date": sns(tds[3].text),
-                        "category": category_name,
-                        "url": constants.CC_BSI_BASE_URL + tds[0].find("a")["href"],
-                    }
-                    if header is not None:
-                        cert["subcategory"] = sns(header.text)
-                    results.append(cert)
-        return results
-
-    @staticmethod
-    def get_india_certified():
-        pages = {0}
-        seen_pages = set()
-        results = []
-        while pages:
-            page = pages.pop()
-            seen_pages.add(page)
-            url = constants.CC_INDIA_CERTIFIED_URL + f"?page={page}"
-            soup = CCSchemeDataset._download_page(url)
-
-            # Update pages
-            pager = soup.find("ul", class_="pager")
-            for li in pager.find_all("li"):
-                try:
-                    new_page = int(li.text) - 1
-                except Exception:
-                    continue
-                if new_page not in seen_pages:
-                    pages.add(new_page)
-
-            # Parse table
-            tbody = soup.find("div", class_="view-content").find("table").find("tbody")
-            for tr in tbody.find_all("tr"):
-                tds = tr.find_all("td")
-                if not tds:
-                    continue
-                report_a = tds[5].find("a")
-                target_a = tds[6].find("a")
-                cert_a = tds[7].find("a")
-                cert = {
-                    "serial_number": sns(tds[0].text),
-                    "product": sns(tds[1].text),
-                    "sponsor": sns(tds[2].text),
-                    "developer": sns(tds[3].text),
-                    "level": sns(tds[4].text),
-                    "report_link": report_a["href"],
-                    "report_name": sns(report_a.text),
-                    "target_link": target_a["href"],
-                    "target_name": sns(target_a.text),
-                    "cert_link": cert_a["href"],
-                    "cert_name": sns(cert_a.text),
-                }
-                results.append(cert)
-        return results
-
-    @staticmethod
-    def get_india_archived():
-        pages = {0}
-        seen_pages = set()
-        results = []
-        while pages:
-            page = pages.pop()
-            seen_pages.add(page)
-            url = constants.CC_INDIA_ARCHIVED_URL + f"?page={page}"
-            soup = CCSchemeDataset._download_page(url)
-
-            # Update pages
-            pager = soup.find("ul", class_="pager")
-            if pager:
-                for li in pager.find_all("li"):
-                    try:
-                        new_page = int(li.text) - 1
-                    except Exception:
-                        continue
-                    if new_page not in seen_pages:
-                        pages.add(new_page)
-
-            # Parse table
-            tbody = soup.find("div", class_="view-content").find("table").find("tbody")
-            for tr in tbody.find_all("tr"):
-                tds = tr.find_all("td")
-                if not tds:
-                    continue
-                report_a = tds[5].find("a")
-                target_a = tds[6].find("a")
-                cert_a = tds[7].find("a")
-                cert = {
-                    "serial_number": sns(tds[0].text),
-                    "product": sns(tds[1].text),
-                    "sponsor": sns(tds[2].text),
-                    "developer": sns(tds[3].text),
-                    "level": sns(tds[4].text),
-                    "report_link": report_a["href"],
-                    "report_name": sns(report_a.text),
-                    "target_link": target_a["href"],
-                    "target_name": sns(target_a.text),
-                    "cert_link": cert_a["href"],
-                    "cert_name": sns(cert_a.text),
-                    "certification_date": sns(tds[8].text),
-                }
-                results.append(cert)
-        return results
-
-    @staticmethod
-    def get_italy_certified():  # noqa: C901
-        soup = CCSchemeDataset._download_page(constants.CC_ITALY_CERTIFIED_URL)
-        div = soup.find("div", class_="certificati")
-        results = []
-        for cert_div in div.find_all("div", recursive=False):
-            title = cert_div.find("h3").text
-            data_div = cert_div.find("div", class_="collapse")
-            cert = {"title": title}
-            for data_p in data_div.find_all("p"):
-                p_text = sns(data_p.text)
-                if ":" not in p_text:
-                    continue
-                p_name, p_data = p_text.split(":")
-                p_data = p_data
-                p_link = data_p.find("a")
-                if "Fornitore" in p_name:
-                    cert["supplier"] = p_data
-                elif "Livello di garanzia" in p_name:
-                    cert["level"] = p_data
-                elif "Data emissione certificato" in p_name:
-                    cert["certification_date"] = p_data
-                elif "Data revisione" in p_name:
-                    cert["revision_date"] = p_data
-                elif "Rapporto di Certificazione" in p_name and p_link:
-                    cert["report_link_it"] = constants.CC_ITALY_BASE_URL + p_link["href"]
-                elif "Certification Report" in p_name and p_link:
-                    cert["report_link_en"] = constants.CC_ITALY_BASE_URL + p_link["href"]
-                elif "Traguardo di Sicurezza" in p_name and p_link:
-                    cert["target_link"] = constants.CC_ITALY_BASE_URL + p_link["href"]
-                elif "Nota su" in p_name and p_link:
-                    cert["vulnerability_note_link"] = constants.CC_ITALY_BASE_URL + p_link["href"]
-                elif "Nota di chiarimento" in p_name and p_link:
-                    cert["clarification_note_link"] = constants.CC_ITALY_BASE_URL + p_link["href"]
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_italy_in_evaluation():
-        soup = CCSchemeDataset._download_page(constants.CC_ITALY_INEVAL_URL)
-        div = soup.find("div", class_="valutazioni")
-        results = []
-        for cert_div in div.find_all("div", recursive=False):
-            title = cert_div.find("h3").text
-            data_div = cert_div.find("div", class_="collapse")
-            cert = {"title": title}
-            for data_p in data_div.find_all("p"):
-                p_text = sns(data_p.text)
-                if ":" not in p_text:
-                    continue
-                p_name, p_data = p_text.split(":")
-                p_data = p_data
-                if "Committente" in p_name:
-                    cert["client"] = p_data
-                elif "Livello di garanzia" in p_name:
-                    cert["level"] = p_data
-                elif "Tipologia prodotto" in p_name:
-                    cert["product_type"] = p_data
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_japan_certified():
-        # TODO: Information could be expanded by following toe link.
-        soup = CCSchemeDataset._download_page(constants.CC_JAPAN_CERTIFIED_URL)
-        table = soup.find("div", id="cert_list").find("table")
-        results = []
-        trs = list(table.find_all("tr"))
-        for tr in trs:
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            if len(tds) == 6:
-                cert = {
-                    "cert_id": sns(tds[0].text),
-                    "supplier": sns(tds[1].text),
-                    "toe_overseas_name": sns(tds[2].text),
-                    "certification_date": sns(tds[3].text),
-                    "claim": sns(tds[4].text),
-                }
-                toe_a = tds[2].find("a")
-                if toe_a and "href" in toe_a.attrs:
-                    cert["toe_overseas_link"] = constants.CC_JAPAN_CERT_BASE_URL + "/" + toe_a["href"]
-                results.append(cert)
-            if len(tds) == 1:
-                cert = results[-1]
-                cert["toe_japan_name"] = sns(tds[0].text)
-                toe_a = tds[0].find("a")
-                if toe_a and "href" in toe_a.attrs:
-                    cert["toe_japan_link"] = constants.CC_JAPAN_CERT_BASE_URL + "/" + toe_a["href"]
-        return results
-
-    @staticmethod
-    def get_japan_archived():
-        # TODO: Information could be expanded by following toe link.
-        soup = CCSchemeDataset._download_page(constants.CC_JAPAN_ARCHIVED_URL)
-        table = soup.find("table")
-        results = []
-        trs = list(table.find_all("tr"))
-        for tr in trs:
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            if len(tds) == 6:
-                cert = {
-                    "cert_id": sns(tds[0].text),
-                    "supplier": sns(tds[1].text),
-                    "toe_overseas_name": sns(tds[2].text),
-                    "certification_date": sns(tds[3].text),
-                    "claim": sns(tds[4].text),
-                }
-                toe_a = tds[2].find("a")
-                if toe_a and "href" in toe_a.attrs:
-                    cert["toe_overseas_link"] = constants.CC_JAPAN_CERT_BASE_URL + "/" + toe_a["href"]
-                results.append(cert)
-            if len(tds) == 1:
-                cert = results[-1]
-                cert["toe_japan_name"] = sns(tds[0].text)
-                toe_a = tds[0].find("a")
-                if toe_a and "href" in toe_a.attrs:
-                    cert["toe_japan_link"] = constants.CC_JAPAN_CERT_BASE_URL + "/" + toe_a["href"]
-        return results
-
-    @staticmethod
-    def get_japan_in_evaluation():
-        # TODO: Information could be expanded by following toe link.
-        soup = CCSchemeDataset._download_page(constants.CC_JAPAN_INEVAL_URL)
-        table = soup.find("table")
-        results = []
-        for tr in table.find_all("tr"):
-            tds = tr.find_all("td")
-            if not tds:
-                continue
-            toe_a = tds[1].find("a")
-            cert = {
-                "supplier": sns(tds[0].text),
-                "toe_name": sns(toe_a.text),
-                "toe_link": constants.CC_JAPAN_BASE_URL + "/" + toe_a["href"],
-                "claim": sns(tds[2].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_malaysia_certified():
-        soup = CCSchemeDataset._download_page(constants.CC_MALAYSIA_CERTIFIED_URL)
-        main_div = soup.find("div", attrs={"itemprop": "articleBody"})
-        tables = main_div.find_all("table", recursive=False)
-        results = []
-        for table in tables:
-            category_name = sns(table.find_previous_sibling("h3").text)
-            for tr in table.find_all("tr")[1:]:
-                tds = tr.find_all("td")
-                if len(tds) != 6:
-                    continue
-                cert = {
-                    "category": category_name,
-                    "level": sns(tds[0].text),
-                    "cert_id": sns(tds[1].text),
-                    "certification_date": sns(tds[2].text),
-                    "product": sns(tds[3].text),
-                    "developer": sns(tds[4].text),
-                }
-                results.append(cert)
-        return results
-
-    @staticmethod
-    def get_malaysia_in_evaluation():
-        soup = CCSchemeDataset._download_page(constants.CC_MALAYSIA_INEVAL_URL)
-        main_div = soup.find("div", attrs={"itemprop": "articleBody"})
-        tables = main_div.find_all("table", recursive=False)
-        results = []
-        for table in tables:
-            category_name = sns(table.find_previous_sibling("h3").text)
-            for tr in table.find_all("tr")[1:]:
-                tds = tr.find_all("td")
-                if len(tds) != 5:
-                    continue
-                cert = {
-                    "category": category_name,
-                    "level": sns(tds[0].text),
-                    "project_id": sns(tds[1].text),
-                    "toe_name": sns(tds[2].text),
-                    "developer": sns(tds[3].text),
-                    "expected_completion": sns(tds[4].text),
-                }
-                results.append(cert)
-        return results
-
-    @staticmethod
-    def get_netherlands_certified():
-        soup = CCSchemeDataset._download_page(constants.CC_NETHERLANDS_CERTIFIED_URL)
-        main_div = soup.select("body > main > div > div > div > div:nth-child(2) > div.col-lg-9 > div:nth-child(3)")[0]
-        rows = main_div.find_all("div", class_="row", recursive=False)
-        modals = main_div.find_all("div", class_="modal", recursive=False)
-        results = []
-        for row, modal in zip(rows, modals):
-            row_entries = row.find_all("a")
-            modal_trs = modal.find_all("tr")
-            cert = {
-                "manufacturer": sns(row_entries[0].text),
-                "product": sns(row_entries[1].text),
-                "scheme": sns(row_entries[2].text),
-                "cert_id": sns(row_entries[3].text),
-            }
-            for tr in modal_trs:
-                th_text = tr.find("th").text
-                td = tr.find("td")
-                if "Manufacturer website" in th_text:
-                    cert["manufacturer_link"] = td.find("a")["href"]
-                elif "Assurancelevel" in th_text:
-                    cert["level"] = sns(td.text)
-                elif "Certificate" in th_text:
-                    cert["cert_link"] = constants.CC_NETHERLANDS_BASE_URL + td.find("a")["href"]
-                elif "Certificationreport" in th_text:
-                    cert["report_link"] = constants.CC_NETHERLANDS_BASE_URL + td.find("a")["href"]
-                elif "Securitytarget" in th_text:
-                    cert["target_link"] = constants.CC_NETHERLANDS_BASE_URL + td.find("a")["href"]
-                elif "Maintenance report" in th_text:
-                    cert["maintenance_link"] = constants.CC_NETHERLANDS_BASE_URL + td.find("a")["href"]
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_netherlands_in_evaluation():
-        soup = CCSchemeDataset._download_page(constants.CC_NETHERLANDS_INEVAL_URL)
-        table = soup.find("table")
-        results = []
-        for tr in table.find_all("tr")[1:]:
-            tds = tr.find_all("td")
-            cert = {
-                "developer": sns(tds[0].text),
-                "product": sns(tds[1].text),
-                "category": sns(tds[2].text),
-                "level": sns(tds[3].text),
-                "certification_id": sns(tds[4].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def _get_norway(url):
-        # TODO: Information could be expanded by following product link.
-        soup = CCSchemeDataset._download_page(url)
-        results = []
-        for tr in soup.find_all("tr", class_="certified-product"):
-            tds = tr.find_all("td")
-            cert = {
-                "product": sns(tds[0].text),
-                "product_link": tds[0].find("a")["href"],
-                "category": sns(tds[1].find("p", class_="value").text),
-                "developer": sns(tds[2].find("p", class_="value").text),
-                "certification_date": sns(tds[3].find("time").text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_norway_certified():
-        return CCSchemeDataset._get_norway(constants.CC_NORWAY_CERTIFIED_URL)
-
-    @staticmethod
-    def get_norway_archived():
-        return CCSchemeDataset._get_norway(constants.CC_NORWAY_ARCHIVED_URL)
-
-    @staticmethod
-    def _get_korea(product_class):
-        # TODO: Information could be expanded by following product link.
-        session = requests.session()
-        session.get(constants.CC_KOREA_EN_URL)
-        # Get base page
-        url = constants.CC_KOREA_CERTIFIED_URL + f"?product_class={product_class}"
-        soup = CCSchemeDataset._download_page(url, session=session)
-        seen_pages = set()
-        pages = {1}
-        results = []
-        while pages:
-            page = pages.pop()
-            csrf = soup.find("form", id="fm").find("input", attrs={"name": "csrf"})["value"]
-            resp = session.post(url, data={"csrf": csrf, "selectPage": page, "product_class": product_class})
-            soup = BeautifulSoup(resp.content, "html5lib")
-            tbody = soup.find("table", class_="cpl").find("tbody")
-            for tr in tbody.find_all("tr"):
-                tds = tr.find_all("td")
-                if len(tds) != 6:
-                    continue
-                link = tds[0].find("a")
-                id = link["id"].split("-")[1]
-                cert = {
-                    "product": sns(tds[0].text),
-                    "cert_id": sns(tds[1].text),
-                    "product_link": constants.CC_KOREA_PRODUCT_URL.format(id),
-                    "vendor": sns(tds[2].text),
-                    "level": sns(tds[3].text),
-                    "category": sns(tds[4].text),
-                    "certification_date": sns(tds[5].text),
-                }
-                results.append(cert)
-            seen_pages.add(page)
-            page_links = soup.find("div", class_="paginate").find_all("a", class_="number_off")
-            for page_link in page_links:
-                try:
-                    new_page = int(page_link.text)
-                    if new_page not in seen_pages:
-                        pages.add(new_page)
-                except Exception:
-                    pass
-        return results
-
-    @staticmethod
-    def get_korea_certified():
-        return CCSchemeDataset._get_korea(product_class=1)
-
-    @staticmethod
-    def get_korea_suspended():
-        return CCSchemeDataset._get_korea(product_class=2)
-
-    @staticmethod
-    def get_korea_archived():
-        return CCSchemeDataset._get_korea(product_class=4)
-
-    @staticmethod
-    def _get_singapore(url):
-        soup = CCSchemeDataset._download_page(url)
-        table = soup.find("table")
-        skip = False
-        results = []
-        category_name = None
-        for tr in table.find_all("tr"):
-            if skip:
-                skip = False
-                continue
-            tds = tr.find_all("td")
-            if len(tds) == 1:
-                category_name = sns(tds[0].text)
-                skip = True
-                continue
-
-            cert = {
-                "product": sns(tds[0].text.split()[0]),
-                "vendor": sns(tds[1].text),
-                "level": sns(tds[2].text),
-                "certification_date": sns(tds[3].text),
-                "expiration_date": sns(tds[4].text),
-                "category": category_name,
-            }
-            for link in tds[0].find_all("a"):
-                link_text = sns(link.text)
-                if link_text == "Certificate":
-                    cert["cert_link"] = constants.CC_SINGAPORE_BASE_URL + link["href"]
-                elif link_text in ("Certificate Report", "Certification Report"):
-                    cert["report_link"] = constants.CC_SINGAPORE_BASE_URL + link["href"]
-                elif link_text == "Security Target":
-                    cert["target_link"] = constants.CC_SINGAPORE_BASE_URL + link["href"]
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_singapore_certified():
-        return CCSchemeDataset._get_singapore(constants.CC_SINGAPORE_CERTIFIED_URL)
-
-    @staticmethod
-    def get_singapore_in_evaluation():
-        soup = CCSchemeDataset._download_page(constants.CC_SINGAPORE_CERTIFIED_URL)
-        header = soup.find(lambda x: x.name == "h3" and x.text == "In Evaluation")
-        table = header.find_next("table")
-        results = []
-        for tr in table.find_all("tr")[1:]:
-            tds = tr.find_all("td")
-            cert = {
-                "name": sns(tds[0].text),
-                "vendor": sns(tds[1].text),
-                "level": sns(tds[2].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_singapore_archived():
-        return CCSchemeDataset._get_singapore(constants.CC_SINGAPORE_ARCHIVED_URL)
-
-    @staticmethod
-    def get_spain_certified():
-        soup = CCSchemeDataset._download_page(constants.CC_SPAIN_CERTIFIED_URL)
-        tbody = soup.find("table", class_="djc_items_table").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr", recursive=False):
-            tds = tr.find_all("td")
-            cert = {
-                "product": sns(tds[0].text),
-                "product_link": constants.CC_SPAIN_BASE_URL + tds[0].find("a")["href"],
-                "category": sns(tds[1].text),
-                "manufacturer": sns(tds[2].text),
-                "certification_date": sns(tds[3].find("td", class_="djc_value").text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def _get_sweden(url):
-        # TODO: Information could be expanded by following product link.
-        soup = CCSchemeDataset._download_page(url)
-        nav = soup.find("main").find("nav", class_="component-nav-box__list")
-        results = []
-        for link in nav.find_all("a"):
-            cert = {"product": sns(link.text), "product_link": constants.CC_SWEDEN_BASE_URL + link["href"]}
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_sweden_certified():
-        return CCSchemeDataset._get_sweden(constants.CC_SWEDEN_CERTIFIED_URL)
-
-    @staticmethod
-    def get_sweden_in_evaluation():
-        return CCSchemeDataset._get_sweden(constants.CC_SWEDEN_INEVAL_URL)
-
-    @staticmethod
-    def get_sweden_archived():
-        return CCSchemeDataset._get_sweden(constants.CC_SWEDEN_ARCHIVED_URL)
-
-    @staticmethod
-    def get_turkey_certified():
-        import tabula
-
-        results = []
-        with tempfile.TemporaryDirectory() as tmpdir:
-            pdf_path = Path(tmpdir) / "turkey.pdf"
-            resp = requests.get(constants.CC_TURKEY_ARCHIVED_URL)
-            if resp.status_code != requests.codes.ok:
-                raise ValueError(f"Unable to download: status={resp.status_code}")
-            with pdf_path.open("wb") as f:
-                f.write(resp.content)
-            dfs = tabula.read_pdf(str(pdf_path), pages="all")
-            for df in dfs:
-                for line in df.values:
-                    cert = {
-                        # TODO: Split item number and generate several dicts for a range they include.
-                        "item_no": line[0],
-                        "developer": line[1],
-                        "product": line[2],
-                        "cc_version": line[3],
-                        "level": line[4],
-                        "cert_lab": line[5],
-                        "certification_date": line[6],
-                        "expiration_date": line[7],
-                        # TODO: Parse "Ongoing Evaluation" out of this field as well.
-                        "archived": isinstance(line[9], str) and "Archived" in line[9],
-                    }
-                    results.append(cert)
-        return results
-
-    @staticmethod
-    def get_usa_certified():
-        # TODO: Information could be expanded by following product link.
-        # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
-        soup = CCSchemeDataset._download_page(constants.CC_USA_CERTIFIED_URL)
-        tbody = soup.find("table", class_="tablesorter").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr"):
-            tds = tr.find_all("td")
-            vendor_span = tds[0].find("span", class_="b u")
-            product_link = tds[0].find("a")
-            scheme_img = tds[6].find("img")
-            # Only return the US certifications.
-            if scheme_img["title"] != "USA":
-                continue
-            cert = {
-                "product": sns(product_link.text),
-                "vendor": sns(vendor_span.text),
-                "product_link": product_link["href"],
-                "id": sns(tds[1].text),
-                "cc_claim": sns(tds[2].text),
-                "cert_lab": sns(tds[3].text),
-                "certification_date": sns(tds[4].text),
-                "assurance_maintenance_date": sns(tds[5].text),
-            }
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_usa_in_evaluation():
-        # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
-        soup = CCSchemeDataset._download_page(constants.CC_USA_INEVAL_URL)
-        tbody = soup.find("table", class_="tablesorter").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr"):
-            tds = tr.find_all("td")
-            vendor_span = tds[0].find("span", class_="b u")
-            product_name = None
-            for child in tds[0].children:
-                if isinstance(child, NavigableString):
-                    product_name = sns(child)
-                    break
-            cert = {
-                "vendor": sns(vendor_span.text),
-                "id": sns(tds[1].text),
-                "cc_claim": sns(tds[2].text),
-                "cert_lab": sns(tds[3].text),
-                "kickoff_date": sns(tds[4].text),
-            }
-            if product_name:
-                cert["product"] = product_name
-            results.append(cert)
-        return results
-
-    @staticmethod
-    def get_usa_archived():
-        # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
-        soup = CCSchemeDataset._download_page(constants.CC_USA_ARCHIVED_URL)
-        tbody = soup.find("table", class_="tablesorter").find("tbody")
-        results = []
-        for tr in tbody.find_all("tr"):
-            tds = tr.find_all("td")
-            scheme_img = tds[5].find("img")
-            # Only return the US certifications.
-            if scheme_img["title"] != "USA":
-                continue
-            vendor_span = tds[0].find("span", class_="b u")
-            product_name = None
-            for child in tds[0].children:
-                if isinstance(child, NavigableString):
-                    product_name = sns(child)
-                    break
-            cert = {
-                "vendor": sns(vendor_span.text),
-                "id": sns(tds[1].text),
-                "cc_claim": sns(tds[2].text),
-                "cert_lab": sns(tds[3].text),
-                "certification_date": sns(tds[4].text),
-            }
-            if product_name:
-                cert["product"] = product_name
-            results.append(cert)
-        return results
diff --git a/src/sec_certs/dataset/cc_scheme.py b/src/sec_certs/dataset/cc_scheme.py
new file mode 100644
index 00000000..5ac23dc4
--- /dev/null
+++ b/src/sec_certs/dataset/cc_scheme.py
@@ -0,0 +1,60 @@
+# This code is not a place of honor... no highly esteemed deed is commemorated here... nothing valued is here.
+# What follows is a repulsive wall of BeautifulSoup garbage parsing code.
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+from typing import Mapping
+
+from sec_certs import constants
+from sec_certs.dataset.json_path_dataset import JSONPathDataset
+from sec_certs.sample.cc_scheme import CCScheme
+from sec_certs.serialization.json import ComplexSerializableType
+
+logger = logging.getLogger()
+
+
+class CCSchemeDataset(JSONPathDataset, ComplexSerializableType):
+    """
+    A dataset of data from CC scheme websites.
+
+    Each `.get_*` method returns a list of dict entries from the given scheme.
+    The entries do not share many keys, but each one has at least some form
+    of a product name and most have a vendor/developer/manufacturer field.
+    """
+
+    def __init__(self, schemes: dict[str, CCScheme], json_path: str | Path = constants.DUMMY_NONEXISTING_PATH):
+        self.schemes = schemes
+        self.json_path = Path(json_path)
+
+    @property
+    def serialized_attributes(self) -> list[str]:
+        return ["schemes"]
+
+    def __iter__(self):
+        yield from self.schemes.values()
+
+    def __getitem__(self, scheme: str):
+        return self.schemes.__getitem__(scheme.upper())
+
+    def __setitem__(self, key: str, value):
+        self.schemes.__setitem__(key.upper(), value)
+
+    def __len__(self) -> int:
+        return len(self.schemes)
+
+    def to_dict(self):
+        return {"schemes": self.schemes}
+
+    @classmethod
+    def from_dict(cls, dct: Mapping) -> CCSchemeDataset:
+        return cls(dct["schemes"])
+
+    @classmethod
+    def from_web(cls, only_schemes: set[str] | None = None) -> CCSchemeDataset:
+        schemes = {}
+        for scheme, sources in CCScheme.methods.items():
+            if only_schemes is not None and scheme not in only_schemes:
+                continue
+            schemes[scheme] = CCScheme.from_web(scheme, sources.keys())
+        return cls(schemes)
diff --git a/src/sec_certs/dataset/fips_algorithm.py b/src/sec_certs/dataset/fips_algorithm.py
index df113381..fbc8351a 100644
--- a/src/sec_certs/dataset/fips_algorithm.py
+++ b/src/sec_certs/dataset/fips_algorithm.py
@@ -12,7 +12,7 @@ from bs4 import BeautifulSoup
 
 from sec_certs import constants
 from sec_certs.dataset.json_path_dataset import JSONPathDataset
-from sec_certs.sample import FIPSAlgorithm
+from sec_certs.sample.fips_algorithm import FIPSAlgorithm
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.utils import helpers
 
diff --git a/src/sec_certs/dataset/fips_mip.py b/src/sec_certs/dataset/fips_mip.py
index 1b0d2032..dd61e60e 100644
--- a/src/sec_certs/dataset/fips_mip.py
+++ b/src/sec_certs/dataset/fips_mip.py
@@ -1,6 +1,8 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
+from datetime import date
+from operator import attrgetter
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 from typing import Iterator, Mapping
@@ -11,7 +13,7 @@ from sec_certs import constants
 from sec_certs.configuration import config
 from sec_certs.dataset.dataset import logger
 from sec_certs.dataset.json_path_dataset import JSONPathDataset
-from sec_certs.sample.fips_mip import MIPSnapshot
+from sec_certs.sample.fips_mip import MIPFlow, MIPSnapshot, MIPStatus
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.utils.tqdm import tqdm
 
@@ -64,3 +66,36 @@ class MIPDataset(JSONPathDataset, ComplexSerializableType):
         with NamedTemporaryFile() as tmpfile:
             tmpfile.write(mip_resp.content)
             return cls.from_json(tmpfile.name)
+
+    def compute_flows(self) -> list[MIPFlow]:
+        """
+        Compute the MIPFlows, deduplicating the MIPEntries in the snapshots
+        and computing their state-changes.
+
+        :return: The MIPFlows.
+        """
+        flows: dict[tuple[str, str, str], list[tuple[date, MIPStatus]]] = {}
+        for snapshot in sorted(self.snapshots, key=attrgetter("timestamp")):
+            snapshot_date = snapshot.timestamp.date()
+            entries: dict[tuple[str, str, str], set] = {}
+            for entry in snapshot:
+                key = (entry.module_name, entry.vendor_name, entry.standard)
+                s = entries.setdefault(key, set())
+                s.add(entry)
+
+            for key, dups in entries.items():
+                if len(dups) > 1:
+                    logger.warning(f"Duplicate MIPEntry when computing MIPFlow, {key}.")
+                entry = sorted(dups)[0]
+                entry_flows = flows.setdefault(key, [])
+                if entry_flows:
+                    last_state_change = entry_flows[-1]
+                    last_date, last_status = last_state_change
+                    if last_status != entry.status:
+                        entry_flows.append((snapshot_date, entry.status))
+                    else:
+                        entry_flows[-1] = (snapshot_date, entry.status)
+                else:
+                    entry_flows.append((snapshot_date, entry.status))
+
+        return [MIPFlow(*key, value) for key, value in flows.items()]
diff --git a/src/sec_certs/model/__init__.py b/src/sec_certs/model/__init__.py
index fe1024f9..3c5ea459 100644
--- a/src/sec_certs/model/__init__.py
+++ b/src/sec_certs/model/__init__.py
@@ -3,9 +3,18 @@ This package exposes model (mostly transformers and classifiers) that apply comp
 leveraged by members of Dataset package and are directly applied on members of Sample class (or on built-in objects).
 """
 
+from sec_certs.model.cc_matching import CCSchemeMatcher
 from sec_certs.model.cpe_matching import CPEClassifier
+from sec_certs.model.fips_matching import FIPSProcessMatcher
 from sec_certs.model.reference_finder import ReferenceFinder
 from sec_certs.model.sar_transformer import SARTransformer
 from sec_certs.model.transitive_vulnerability_finder import TransitiveVulnerabilityFinder
 
-__all__ = ["CPEClassifier", "ReferenceFinder", "TransitiveVulnerabilityFinder", "SARTransformer"]
+__all__ = [
+    "CPEClassifier",
+    "CCSchemeMatcher",
+    "FIPSProcessMatcher",
+    "ReferenceFinder",
+    "TransitiveVulnerabilityFinder",
+    "SARTransformer",
+]
diff --git a/src/sec_certs/model/cc_matching.py b/src/sec_certs/model/cc_matching.py
new file mode 100644
index 00000000..350a2e9d
--- /dev/null
+++ b/src/sec_certs/model/cc_matching.py
@@ -0,0 +1,100 @@
+from __future__ import annotations
+
+from typing import Any, Iterable, Mapping, Sequence
+
+from sec_certs.configuration import config
+from sec_certs.model.matching import AbstractMatcher
+from sec_certs.sample.cc import CCCertificate
+from sec_certs.sample.cc_certificate_id import CertificateId
+from sec_certs.utils.strings import fully_sanitize_string
+
+
+class CCSchemeMatcher(AbstractMatcher[CCCertificate]):
+    """
+    A heuristic matcher between entries on CC scheme websites (see CCSchemeDataset) and
+    CC certificates from the Common Criteria portal (as in CCDataset).
+    """
+
+    def __init__(self, entry: Mapping, scheme: str):
+        self.entry = entry
+        self.scheme = scheme
+        self._prepare()
+
+    def _get_from_entry(self, *keys: str) -> str | None:
+        for key in keys:
+            if val := self.entry.get(key):
+                return val
+        if e := self.entry.get("enhanced"):
+            for key in keys:
+                if val := e.get(key):
+                    return val
+        return None
+
+    def _prepare(self):
+        self._canonical_cert_id = None
+        if cert_id := self._get_from_entry("cert_id", "id"):
+            self._canonical_cert_id = CertificateId(self.scheme, cert_id).canonical
+
+        self._product = None
+        if product_name := self._get_from_entry("product", "title", "name"):
+            self._product = fully_sanitize_string(product_name)
+
+        self._vendor = None
+        if vendor_name := self._get_from_entry("vendor", "developer", "manufacturer", "supplier"):
+            self._vendor = fully_sanitize_string(vendor_name)
+
+        self._report_hash = self._get_from_entry("report_hash")
+        self._target_hash = self._get_from_entry("target_hash")
+
+    def match(self, cert: CCCertificate) -> float:
+        """
+        Compute the match of this matcher to the certificate, a float from 0 to 100.
+
+        A 100 is a certificate ID match that should be always correct, assuming correct
+        data in the entry and certificate.
+
+        :param cert: The certificate to match against.
+        :return: The match score.
+        """
+        # This one is full of magic numbers, there is some idea to it but adjust as necessary.
+        # We want to match the same scheme.
+        if self.scheme != cert.scheme:
+            return 0
+        # If we have a perfect cert_id match, take it.
+        if self._canonical_cert_id and cert.heuristics.cert_id == self._canonical_cert_id:
+            return 100
+        # We need to have something to match to.
+        if self._product is None or self._vendor is None or cert.name is None or cert.manufacturer is None:
+            return 0
+        cert_name = fully_sanitize_string(cert.name)
+        cert_manufacturer = fully_sanitize_string(cert.manufacturer)
+        # If we match exactly, return early.
+        if self._product == cert.name and self._vendor == cert.manufacturer:
+            return 99
+        # If we match the report hash, return early.
+        if cert.state.report_pdf_hash == self._report_hash and self._report_hash is not None:
+            return 95
+        # If we match the target hash, return early.
+        if cert.state.st_pdf_hash == self._target_hash and self._target_hash is not None:
+            return 93
+
+        # Fuzzy match at the end with some penalization.
+        product_rating = self._compute_match(self._product, cert_name)
+        vendor_rating = self._compute_match(self._vendor, cert_manufacturer)
+        return max((0, product_rating * 0.5 + vendor_rating * 0.5 - 2))
+
+    @classmethod
+    def match_all(
+        cls, entries: list[dict[str, Any]], scheme: str, certificates: Iterable[CCCertificate]
+    ) -> dict[str, dict[str, Any]]:
+        """
+        Match all entries of a given CC scheme to certificates from the dataset.
+
+        :param entries: The entries from the scheme, obtained from CCSchemeDataset.
+        :param scheme: The scheme, e.g. "DE".
+        :param certificates: The certificates to match against.
+        :return: A mapping of certificate digests to entries, without duplicates, not all entries may be present.
+        """
+        certs: list[CCCertificate] = list(filter(lambda cert: cert.scheme == scheme, certificates))
+        matchers: Sequence[CCSchemeMatcher] = [CCSchemeMatcher(entry, scheme) for entry in entries]
+        return cls._match_certs(matchers, certs, config.cc_matching_threshold)  # type: ignore
diff --git a/src/sec_certs/model/cpe_matching.py b/src/sec_certs/model/cpe_matching.py
index 1a02008b..754ba7a9 100644
--- a/src/sec_certs/model/cpe_matching.py
+++ b/src/sec_certs/model/cpe_matching.py
@@ -10,6 +10,13 @@ from rapidfuzz import fuzz
 
 from sec_certs import cert_rules, constants
 from sec_certs.sample.cpe import CPE
+from sec_certs.utils.strings import (
+    discard_trademark_symbols,
+    fully_sanitize_string,
+    lemmatize_product_name,
+    load_spacy_model,
+    standardize_version_in_cert_name,
+)
 from sec_certs.utils.tqdm import tqdm
 
 logger = logging.getLogger(__name__)
@@ -27,11 +34,10 @@ class CPEClassifier:
     vendors_: set[str]
 
     def __init__(self, match_threshold: int = 80, n_max_matches: int = 10, spacy_model_to_use: str = "en_core_web_sm"):
-        import spacy
 
         self.match_threshold = match_threshold
         self.n_max_matches = n_max_matches
-        self.nlp = spacy.load(spacy_model_to_use, disable=["parser", "ner"])
+        self.nlp = load_spacy_model(spacy_model_to_use)
 
     def fit(self, X: list[CPE], y: list[str] | None = None) -> CPEClassifier:
         """
@@ -106,9 +112,9 @@ class CPEClassifier:
         :param bool relax_title: See step 7 above, defaults to False
         :return Optional[Set[str]]: Set of matching CPE uris, None if no matches found
         """
-        lemmatized_product_name = self._lemmatize_product_name(product_name)
+        lemmatized_product_name = lemmatize_product_name(self.nlp, product_name)
         candidate_vendors = self._get_candidate_list_of_vendors(
-            CPEClassifier._discard_trademark_symbols(vendor).lower() if vendor else vendor
+            discard_trademark_symbols(vendor).lower() if vendor else vendor
         )
         candidates = self._get_candidate_cpe_matches(candidate_vendors, versions)
         candidates = self._filter_candidates_by_platform(candidates, product_name)
@@ -208,15 +214,15 @@ class CPEClassifier:
         """
         if relax_title:
             sanitized_title = (
-                CPEClassifier._fully_sanitize_string(cpe.title)
+                fully_sanitize_string(cpe.title)
                 if cpe.title
-                else CPEClassifier._fully_sanitize_string(
+                else fully_sanitize_string(
                     cpe.vendor + " " + cpe.item_name + " " + cpe.version + " " + cpe.update + " " + cpe.target_hw
                 )
             )
         else:
             if cpe.title:
-                sanitized_title = CPEClassifier._fully_sanitize_string(cpe.title)
+                sanitized_title = fully_sanitize_string(cpe.title)
             else:
                 return 0
 
@@ -224,12 +230,12 @@ class CPEClassifier:
         if len(sanitized_title) < 5:
             return 0
 
-        sanitized_item_name = CPEClassifier._fully_sanitize_string(cpe.item_name)
+        sanitized_item_name = fully_sanitize_string(cpe.item_name)
         sanitized_cpe_stripped_manufacturer = re.sub(r"\b" + rf"{cpe.vendor}" + r"\b", "", sanitized_title)
-        standard_version_product_name = self._standardize_version_in_cert_name(product_name, versions)
+        standard_version_product_name = standardize_version_in_cert_name(product_name, versions)
 
         # The expression below is currently unused, it could assist with some matches though
-        # cert_stripped = CPEClassifier._strip_manufacturer_and_version(product_name, candidate_vendors, versions)
+        # cert_stripped = strip_manufacturer_and_version(product_name, candidate_vendors, versions)
 
         # On some ratings, we require 100 match regardless of the treshold in settings.
         ratings = [
@@ -252,34 +258,6 @@ class CPEClassifier:
 
         return max(ratings)
 
-    @staticmethod
-    def _fully_sanitize_string(string: str) -> str:
-        return CPEClassifier._replace_special_chars_with_space(
-            CPEClassifier._discard_trademark_symbols(string.lower())
-        ).strip()
-
-    @staticmethod
-    def _replace_special_chars_with_space(string: str) -> str:
-        return re.sub(r"[^a-zA-Z0-9 \n\.]", " ", string)
-
-    @staticmethod
-    def _discard_trademark_symbols(string: str) -> str:
-        return string.replace("®", "").replace("™", "")
-
-    @staticmethod
-    def _strip_manufacturer_and_version(string: str, manufacturers: set[str] | None, versions: set[str]) -> str:
-        to_strip = versions | manufacturers if manufacturers else versions
-        for x in to_strip:
-            string = string.lower().replace(CPEClassifier._replace_special_chars_with_space(x.lower()), " ").strip()
-        return string
-
-    @staticmethod
-    def _standardize_version_in_cert_name(string: str, detected_versions: set[str]) -> str:
-        for ver in detected_versions:
-            version_regex = r"(" + r"(\bversion)\s*" + ver + r"+) | (\bv\s*" + ver + r"+)"
-            string = re.sub(version_regex, " " + ver + " ", string, flags=re.IGNORECASE)
-        return string
-
     def _process_manufacturer(self, manufacturer: str, result: set) -> set[str]:
         tokenized = manufacturer.split()
         if tokenized[0] in self.vendors_:
@@ -392,8 +370,3 @@ class CPEClassifier:
             if candidate_vendor_version_pairs
             else []
         )
-
-    def _lemmatize_product_name(self, product_name: str) -> str:
-        if not product_name:
-            return product_name
-        return " ".join([token.lemma_ for token in self.nlp(CPEClassifier._fully_sanitize_string(product_name))])
diff --git a/src/sec_certs/model/fips_matching.py b/src/sec_certs/model/fips_matching.py
new file mode 100644
index 00000000..50079611
--- /dev/null
+++ b/src/sec_certs/model/fips_matching.py
@@ -0,0 +1,78 @@
+from __future__ import annotations
+
+import typing
+from datetime import date
+from typing import Iterable, Mapping, Sequence
+
+from sec_certs.configuration import config
+from sec_certs.model.matching import AbstractMatcher
+from sec_certs.sample.fips import FIPSCertificate
+from sec_certs.utils.strings import fully_sanitize_string
+
+if typing.TYPE_CHECKING:
+    from sec_certs.sample.fips_iut import IUTEntry, IUTSnapshot
+    from sec_certs.sample.fips_mip import MIPEntry, MIPSnapshot
+
+
+class FIPSProcessMatcher(AbstractMatcher[FIPSCertificate]):
+    """
+    A heuristic matcher between entries on the FIPS IUT/MIP lists and
+    the FIPS certificates.
+    """
+
+    def __init__(self, entry: MIPEntry | IUTEntry, date: date | None = None):
+        self.entry = entry
+        self._prepare(date)
+
+    def _prepare(self, date):
+        self._date = date or getattr(self.entry, "status_since", None) or getattr(self.entry, "iut_date", None)
+        self._product = fully_sanitize_string(self.entry.module_name)
+        self._vendor = fully_sanitize_string(self.entry.vendor_name)
+        self._standard = self.entry.standard
+
+    def match(self, cert: FIPSCertificate) -> float:
+        """
+        Compute the match of this matcher to the certificate, a float from 0 to 100.
+
+        :param cert: The certificate to match against.
+        :return: The match score.
+        """
+        # We want to match the same standard.
+        if cert.web_data.standard != self._standard:
+            return 0
+        # We need to have something to match to.
+        if cert.name is None or cert.manufacturer is None:
+            return 0
+        # We can't match to a cert that predates us (MIP or IUT always predates the cert).
+        if cert.web_data.validation_history and not any(
+            validation_entry.date > self._date for validation_entry in cert.web_data.validation_history
+        ):
+            return 0
+        # If we match exactly, return early.
+        cert_name = fully_sanitize_string(cert.name)
+        cert_manufacturer = fully_sanitize_string(cert.manufacturer)
+        if self._product == cert_name and self._vendor == cert_manufacturer:
+            return 99
+
+        # Fuzzy match at the end with some penalization.
+        product_rating = self._compute_match(self._product, cert_name)
+        vendor_rating = self._compute_match(self._vendor, cert_manufacturer)
+        return max((0, product_rating * 0.5 + vendor_rating * 0.5 - 2))
+
+    @classmethod
+    def match_snapshot(
+        cls, snapshot: IUTSnapshot | MIPSnapshot, certificates: Iterable[FIPSCertificate]
+    ) -> Mapping[IUTEntry | MIPEntry, FIPSCertificate | None]:
+        """
+        Match a whole snapshot of IUT/MIP entries to a FIPS certificate dataset.
+
+        :param snapshot: The snapshot to match the entries of.
+        :param certificates: The certificates to match against.
+        :return: A mapping of certificate digests to entries, without duplicates, not all entries may be present.
+        """
+        certs: list[FIPSCertificate] = list(certificates)
+        matchers: Sequence[FIPSProcessMatcher] = [
+            FIPSProcessMatcher(entry, snapshot.timestamp.date()) for entry in snapshot
+        ]
+        # mypy is ridiculous
+        return cls._match_certs(matchers, certs, config.fips_matching_threshold)  # type: ignore
diff --git a/src/sec_certs/model/matching.py b/src/sec_certs/model/matching.py
new file mode 100644
index 00000000..b298e316
--- /dev/null
+++ b/src/sec_certs/model/matching.py
@@ -0,0 +1,55 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from heapq import heappop, heappush
+from typing import Any, Generic, Sequence, TypeVar
+
+from rapidfuzz import fuzz
+
+from sec_certs.sample.certificate import Certificate
+
+CertSubType = TypeVar("CertSubType", bound=Certificate)
+
+
+class AbstractMatcher(Generic[CertSubType], ABC):
+    entry: Any
+
+    @abstractmethod
+    def match(self, cert: CertSubType) -> float:
+        raise NotImplementedError
+
+    def _compute_match(self, one: str, other: str) -> float:
+        return max(
+            [
+                fuzz.token_set_ratio(one, other),
+                fuzz.partial_token_sort_ratio(one, other, score_cutoff=100),
+                fuzz.partial_ratio(one, other, score_cutoff=100),
+            ]
+        )
+
+    @staticmethod
+    def _match_certs(matchers: Sequence["AbstractMatcher"], certs: list[CertSubType], threshold: float):
+        scores: list[tuple[float, int, int]] = []
+        matched_is: set[int] = set()
+        matched_js: set[int] = set()
+        for i, cert in enumerate(certs):
+            for j, matcher in enumerate(matchers):
+                score = matcher.match(cert)
+                triple = (100 - score, i, j)
+                heappush(scores, triple)
+        results = {}
+        for triple in (heappop(scores) for _ in range(len(scores))):
+            inv_score, i, j = triple
+            # Do not match already matched entries/certs.
+            if i in matched_is or j in matched_js:
+                continue
+            # Compute the actual score from the inverse.
+            score = 100 - inv_score
+            # Do not match if we are below threshold, all the following will be as well.
+            if score < threshold:
+                break
+            # Match cert dgst to entry
+            cert = certs[i]
+            entry = matchers[j].entry
+            results[cert.dgst] = entry
+        return results
diff --git a/src/sec_certs/sample/cc.py b/src/sec_certs/sample/cc.py
index 9f73aefa..c89f67c6 100644
--- a/src/sec_certs/sample/cc.py
+++ b/src/sec_certs/sample/cc.py
@@ -437,6 +437,7 @@ class CCCertificate(
         extracted_sars: set[SAR] | None = field(default=None)
         direct_transitive_cves: set[str] | None = field(default=None)
         indirect_transitive_cves: set[str] | None = field(default=None)
+        scheme_data: dict[str, Any] | None = field(default=None)
 
         @property
         def serialized_attributes(self) -> list[str]:
diff --git a/src/sec_certs/sample/cc_certificate_id.py b/src/sec_certs/sample/cc_certificate_id.py
index 428ca73b..3e28dfc8 100644
--- a/src/sec_certs/sample/cc_certificate_id.py
+++ b/src/sec_certs/sample/cc_certificate_id.py
@@ -16,13 +16,13 @@ class CertificateId:
     def _canonical_fr(self) -> str:
         new_cert_id = self.clean
         rules = [
-            "(?:Rapport de certification|Certification Report) ([0-9]+[/-_][0-9]+(?:v[1-9])?(?:[_/-][MSR][0-9]+)?)",
-            "(?:ANSS[Ii]|DCSSI)(?:-CC)?[- ]([0-9]+[/-_][0-9]+(?:v[1-9])?(?:[_/-][MSR][0-9]+)?)",
-            "([0-9]+[/-_][0-9]+(?:v[1-9])?(?:[_/-][MSR][0-9]+)?)",
+            "(?:Rapport de certification|Certification Report) ([0-9]+[/-_][0-9]+(?:[vV][1-9])?(?:[_/-][MSR][0-9]+)?)",
+            "(?:ANSS[Ii]|DCSSI)(?:-CC)?[- ]([0-9]+[/-_][0-9]+(?:[vV][1-9])?(?:[_/-][MSR][0-9]+)?)",
+            "([0-9]+[/-_][0-9]+(?:[vV][1-9])?(?:[_/-][MSR][0-9]+)?)",
         ]
         for rule in rules:
             if match := re.match(rule, new_cert_id):
-                return "ANSSI-CC-" + match.group(1).replace("_", "/")
+                return "ANSSI-CC-" + match.group(1).replace("_", "/").replace("V", "v")
 
         return new_cert_id
 
diff --git a/src/sec_certs/sample/cc_scheme.py b/src/sec_certs/sample/cc_scheme.py
new file mode 100644
index 00000000..ceaf5860
--- /dev/null
+++ b/src/sec_certs/sample/cc_scheme.py
@@ -0,0 +1,1573 @@
+from __future__ import annotations
+
+import hashlib
+import tempfile
+import warnings
+from dataclasses import dataclass
+from datetime import datetime
+from enum import Enum
+from pathlib import Path
+from typing import Any, Callable, ClassVar, Iterable
+from urllib.parse import urljoin
+
+import requests
+import tabula
+from bs4 import BeautifulSoup, NavigableString, Tag
+from requests import Response
+from urllib3.connectionpool import InsecureRequestWarning
+
+from sec_certs import constants
+from sec_certs.serialization.json import ComplexSerializableType
+from sec_certs.utils.sanitization import sanitize_navigable_string as sns
+from sec_certs.utils.tqdm import tqdm
+
+__all__ = [
+    "get_australia_in_evaluation",
+    "get_canada_certified",
+    "get_canada_in_evaluation",
+    "get_france_certified",
+    "get_germany_certified",
+    "get_india_certified",
+    "get_india_archived",
+    "get_italy_certified",
+    "get_italy_in_evaluation",
+    "get_japan_certified",
+    "get_japan_archived",
+    "get_japan_in_evaluation",
+    "get_malaysia_certified",
+    "get_malaysia_in_evaluation",
+    "get_netherlands_certified",
+    "get_netherlands_in_evaluation",
+    "get_norway_certified",
+    "get_norway_archived",
+    "get_korea_certified",
+    "get_korea_suspended",
+    "get_korea_archived",
+    "get_singapore_certified",
+    "get_singapore_in_evaluation",
+    "get_singapore_archived",
+    "get_spain_certified",
+    "get_sweden_certified",
+    "get_sweden_in_evaluation",
+    "get_sweden_archived",
+    "get_turkey_certified",
+    "get_usa_certified",
+    "get_usa_in_evaluation",
+    "get_usa_archived",
+    "EntryType",
+    "CCScheme",
+]
+
+
+def _get(url: str, session, **kwargs) -> Response:
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", category=InsecureRequestWarning)
+        conn = session if session else requests
+        resp = conn.get(url, headers={"User-Agent": "seccerts.org"}, verify=False, **kwargs)
+    resp.raise_for_status()
+    return resp
+
+
+def _get_page(url: str, session=None) -> BeautifulSoup:
+    return BeautifulSoup(_get(url, session).content, "html5lib")
+
+
+def _get_hash(url: str, session=None) -> bytes:
+    resp = _get(url, session)
+    h = hashlib.sha256()
+    for chunk in resp.iter_content():
+        h.update(chunk)
+    return h.digest()
+
+
+def get_australia_in_evaluation(enhanced: bool = True) -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get Australia "products in evaluation" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_AUSTRALIA_INEVAL_URL)
+    header = soup.find("h2", string="Products in evaluation")
+    table = header.find_next_sibling("table")
+    results = []
+    for tr in tqdm(table.find_all("tr"), desc="Get AU scheme in evaluation."):
+        tds = tr.find_all("td")
+        if not tds:
+            continue
+        cert: dict[str, Any] = {
+            "vendor": sns(tds[0].text),
+            "product": sns(tds[1].text),
+            "url": urljoin(constants.CC_AUSTRALIA_BASE_URL, tds[1].find("a")["href"]),
+            "level": sns(tds[2].text),
+        }
+        if enhanced:
+            e: dict[str, Any] = {}
+            cert_page = _get_page(cert["url"])
+            article = cert_page.find("article", attrs={"role": "article"})
+            blocks = article.find("div").find_all("div", class_="flex", recursive=False)
+            for h2 in blocks[0].find_all("h2"):
+                val = sns(h2.find_next_sibling("span").text)
+                h_text = sns(h2.text)
+                if not h_text:
+                    continue
+                if "Version:" in h_text:
+                    e["version"] = val
+                elif "Product type:" in h_text:
+                    e["product_type"] = val
+                elif "Product status:" in h_text:
+                    e["product_status"] = val
+                elif "Assurance level:" in h_text:
+                    e["assurance_level"] = val
+            sides = blocks[1].find_all("div", recursive=False)
+            for div in sides[0].find_all("div", recursive=False):
+                h2 = div.find("h2")
+                h_text = sns(h2.text)
+                if not h_text:
+                    continue
+                if "epl-vendor-token" in div.get("class"):
+                    vendor_address = [h_text]
+                    vendor_address.extend([sns(elem.text) for elem in h2.find_next_siblings("div")])  # type: ignore
+                    e["vendor"] = "\n".join(vendor_address)
+                else:
+                    val = sns(h2.find_next_sibling("span").text)
+                    if "Evaluation Facility:" in h_text:
+                        e["evaluation_facility"] = val
+                    elif "Certification Progress:" in h_text:
+                        e["certification_progress"] = val
+                    elif "Estimated Approval" in h_text:
+                        e["estimated_approval"] = val
+            e["contacts"] = [sns(p.text) for p in sides[1].find_all("p")]
+            e["description"] = sns(blocks[2].find("span").text)
+            cert["enhanced"] = e
+        results.append(cert)
+    return results
+
+
+def get_canada_certified() -> list[dict[str, Any]]:
+    """
+    Get Canada "certified product" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_CANADA_CERTIFIED_URL)
+    tbody = soup.find("table").find("tbody")
+    results = []
+    for tr in tqdm(tbody.find_all("tr"), desc="Get CA scheme certified."):
+        tds = tr.find_all("td")
+        if not tds:
+            continue
+        cert = {
+            "product": sns(tds[0].text),
+            "vendor": sns(tds[1].text),
+            "level": sns(tds[2].text),
+            "certification_date": sns(tds[3].text),
+        }
+        results.append(cert)
+    return results
+
+
+def get_canada_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Canada "products in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_CANADA_INEVAL_URL)
+    tbody = soup.find("table").find("tbody")
+    results = []
+    for tr in tqdm(tbody.find_all("tr"), desc="Get CA scheme in evaluation."):
+        tds = tr.find_all("td")
+        if not tds:
+            continue
+        cert = {
+            "product": sns(tds[0].text),
+            "vendor": sns(tds[1].text),
+            "level": sns(tds[2].text),
+            "cert_lab": sns(tds[3].text),
+        }
+        results.append(cert)
+    return results
+
+
+def get_france_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get French "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    base_soup = _get_page(constants.CC_ANSSI_CERTIFIED_URL)
+    category_nav = base_soup.find("ul", class_="nav-categories")
+    results = []
+    for li in tqdm(category_nav.find_all("li"), desc="Get FR scheme certified."):
+        a = li.find("a")
+        url = a["href"]
+        category_name = sns(a.text)
+        soup = _get_page(urljoin(constants.CC_ANSSI_BASE_URL, url))
+        table = soup.find("table", class_="produits-liste cc")
+        if not table:
+            continue
+        tbody = table.find("tbody")
+        for tr in tqdm(tbody.find_all("tr")):
+            tds = tr.find_all("td")
+            if not tds:
+                continue
+            cert: dict[str, Any] = {
+                "product": sns(tds[0].text),
+                "vendor": sns(tds[1].text),
+                "level": sns(tds[2].text),
+                "id": sns(tds[3].text),
+                "certification_date": sns(tds[4].text),
+                "category": category_name,
+                "url": urljoin(constants.CC_ANSSI_BASE_URL, tds[0].find("a")["href"]),
+            }
+            if enhanced:
+                e: dict[str, Any] = {}
+                cert_page = _get_page(cert["url"])
+                ref = cert_page.find("div", class_="ref-date")
+                for ref_li in ref.find_all("li"):
+                    title, value = (sns(span.text) for span in ref_li.find_all("span", recursive=False))
+                    if not title:
+                        continue
+                    if "Référence" in title:
+                        e["id"] = value
+                    elif "Date de certification" in title:
+                        e["certification_date"] = value
+                    elif "Date de fin de validité" in title:
+                        e["expiration_date"] = value
+                details = cert_page.find("div", class_="details")
+                for detail_li in details.find_all("li"):
+                    title, value = (sns(span.text) for span in detail_li.find_all("span", recursive=False))
+                    if not title:
+                        continue
+                    if "Catégorie" in title:
+                        e["category"] = value
+                    elif "Référentiel" in title:
+                        e["cc_version"] = value
+                    elif "Niveau" in title:
+                        e["level"] = value
+                    elif "Augmentations" in title:
+                        e["augmentations"] = value
+                    elif "Profil de protection" in title:
+                        e["protection_profile"] = value
+                    elif "Développeur" in title:
+                        e["developer"] = value
+                    elif "Centre d'évaluation" in title:
+                        e["evaluation_facility"] = value
+                    elif "Accords de reconnaissance" in title:
+                        e["recognition"] = value
+                e["description"] = sns(cert_page.find("div", class_="box-produit-descriptif").text)
+                links = cert_page.find("div", class_="box-produit-telechargements")
+                for link_li in links.find_all("li"):
+                    a = link_li.find("a")
+                    href = urljoin(constants.CC_ANSSI_BASE_URL, a["href"])
+                    title = sns(a.text)
+                    if not title:
+                        continue
+                    if "Rapport de certification" in title:
+                        e["report_link"] = href
+                        if artifacts:
+                            e["report_hash"] = _get_hash(href).hex()
+                    elif "Security target" in title:
+                        e["target_link"] = href
+                        if artifacts:
+                            e["target_hash"] = _get_hash(href).hex()
+                    elif "Certificat" in title:
+                        e["cert_link"] = href
+                        if artifacts:
+                            e["cert_hash"] = _get_hash(href).hex()
+                cert["enhanced"] = e
+            results.append(cert)
+    return results
+
+
+def get_germany_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get German "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    base_soup = _get_page(constants.CC_BSI_CERTIFIED_URL)
+    category_nav = base_soup.find("ul", class_="no-bullet row")
+    results = []
+    for li in tqdm(category_nav.find_all("li"), desc="Get DE scheme certified."):
+        a = li.find("a")
+        url = a["href"]
+        category_name = sns(a.text)
+        soup = _get_page(urljoin(constants.CC_BSI_BASE_URL, url))
+        content = soup.find("div", class_="content").find("div", class_="column")
+        for table in tqdm(content.find_all("table")):
+            tbody = table.find("tbody")
+            header = table.find_parent("div", class_="wrapperTable").find_previous_sibling("h2")
+            for tr in tqdm(tbody.find_all("tr")):
+                tds = tr.find_all("td")
+                if len(tds) != 4:
+                    continue
+                cert: dict[str, Any] = {
+                    "cert_id": sns(tds[0].text),
+                    "product": sns(tds[1].text),
+                    "vendor": sns(tds[2].text),
+                    "certification_date": sns(tds[3].text),
+                    "category": category_name,
+                    "url": urljoin(constants.CC_BSI_BASE_URL, tds[0].find("a")["href"]),
+                }
+                if enhanced:
+                    e: dict[str, Any] = {}
+                    cert_page = _get_page(cert["url"])
+                    content = cert_page.find("div", id="content").find("div", class_="column")
+                    head = content.find("h1", class_="c-intro__headline")
+                    e["product"] = sns(head.next_sibling.text)
+                    details = content.find("table")
+                    for details_tr in details.find_all("tr"):
+                        details_tds = details_tr.find_all("td")
+                        title = sns(details_tds[0].find("span", attrs={"lang": "en-GB"}).text)
+                        if not title:
+                            continue
+                        value = sns(details_tds[1].text)
+                        if "Applicant" in title:
+                            e["applicant"] = value
+                        elif "Evaluation Facility" in title:
+                            e["evaluation_facility"] = value
+                        elif "Assurance" in title:
+                            e["assurance_level"] = value
+                        elif "Protection Profile" in title:
+                            e["protection_profile"] = value
+                        elif "Certification Date" in title:
+                            e["certification_date"] = value
+                        elif "valid until" in title:
+                            e["expiration_date"] = value
+                    links = content.find("ul")
+                    if links:
+                        # has multiple entries/recertifications
+                        e["entries"] = []
+                        for link_li in links.find_all("li"):
+                            first_child = next(iter(link_li.children))
+                            if isinstance(first_child, Tag):
+                                link_id = sns(first_child.text)
+                            elif isinstance(first_child, NavigableString):
+                                link_id = sns(first_child.text).split(" ")[0]  # type: ignore
+                            else:
+                                link_id = None
+                            entry = {"id": link_id}
+                            en_spans = link_li.find_all("span", attrs={"lang": "en-GB"})
+                            if en_spans:
+                                entry["description"] = sns(en_spans[-1].text)
+                            # TODO: Could parse the links to documents here
+                            e["entries"].append(entry)
+                    doc_links = content.find_all("a", title=lambda title: cert["cert_id"] in title)
+                    for doc_link in doc_links:
+                        href = urljoin(constants.CC_BSI_BASE_URL, doc_link["href"])
+                        title = sns(doc_link["title"])
+                        if not title:
+                            continue
+                        if "Certification Report" in title:
+                            e["report_link"] = href
+                            if artifacts:
+                                e["report_hash"] = _get_hash(href).hex()
+                        elif "Security Target" in title:
+                            e["target_link"] = href
+                            if artifacts:
+                                e["target_hash"] = _get_hash(href).hex()
+                        elif "Certificate" in title:
+                            e["cert_link"] = href
+                            if artifacts:
+                                e["cert_hash"] = _get_hash(href).hex()
+                    description = content.find("div", attrs={"lang": "en"})
+                    if description:
+                        e["description"] = sns(description.text)
+                    cert["enhanced"] = e
+                if header is not None:
+                    cert["subcategory"] = sns(header.text)
+                results.append(cert)
+    return results
+
+
+def _fix_india_link(link: str) -> str:
+    return link.replace("/index.php", "")
+
+
+def get_india_certified() -> list[dict[str, Any]]:
+    """
+    Get Indian "certified product" entries.
+
+    :return: The entries.
+    """
+    pages = {0}
+    seen_pages = set()
+    results = []
+    while pages:
+        page = pages.pop()
+        seen_pages.add(page)
+        url = constants.CC_INDIA_CERTIFIED_URL + f"?page={page}"
+        soup = _get_page(url)
+
+        # Update pages
+        pager = soup.find("ul", class_="pager__items")
+        for li in pager.find_all("li"):
+            try:
+                new_page = int(li.text) - 1
+            except Exception:
+                continue
+            if new_page not in seen_pages:
+                pages.add(new_page)
+
+        # Parse table
+        tbody = soup.find("div", class_="view-content").find("table").find("tbody")
+        for tr in tbody.find_all("tr"):
+            tds = tr.find_all("td")
+            if not tds:
+                continue
+            report_a = tds[6].find("a")
+            target_a = tds[7].find("a")
+            cert_a = tds[8].find("a")
+            cert = {
+                "serial_number": sns(tds[0].text),
+                "product": sns(tds[1].text),
+                "sponsor": sns(tds[2].text),
+                "developer": sns(tds[3].text),
+                "level": sns(tds[4].text),
+                "issuance_date": sns(tds[5].text),
+                "report_link": urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(report_a["href"])),
+                "report_name": sns(report_a.text),
+                "target_link": urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(target_a["href"])),
+                "target_name": sns(target_a.text),
+                "cert_link": urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(cert_a["href"])),
+                "cert_name": sns(cert_a.text),
+            }
+            results.append(cert)
+    return results
+
+
+def get_india_archived() -> list[dict[str, Any]]:
+    """
+    Get Indian "archived product" entries.
+
+    :return: The entries.
+    """
+    pages = {0}
+    seen_pages = set()
+    results = []
+    while pages:
+        page = pages.pop()
+        seen_pages.add(page)
+        url = constants.CC_INDIA_ARCHIVED_URL + f"?page={page}"
+        soup = _get_page(url)
+
+        # Update pages
+        pager = soup.find("ul", class_="pager__items")
+        if pager:
+            for li in pager.find_all("li"):
+                try:
+                    new_page = int(li.text) - 1
+                except Exception:
+                    continue
+                if new_page not in seen_pages:
+                    pages.add(new_page)
+
+        # Parse table
+        tbody = soup.find("div", class_="view-content").find("table").find("tbody")
+        for tr in tbody.find_all("tr"):
+            tds = tr.find_all("td")
+            if not tds:
+                continue
+            report_a = tds[5].find("a")
+            target_a = tds[6].find("a")
+            cert_a = tds[7].find("a")
+            cert = {
+                "serial_number": sns(tds[0].text),
+                "product": sns(tds[1].text),
+                "sponsor": sns(tds[2].text),
+                "developer": sns(tds[3].text),
+                "level": sns(tds[4].text),
+                "target_link": urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(target_a["href"])),
+                "target_name": sns(target_a.text),
+                "cert_link": urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(cert_a["href"])),
+                "cert_name": sns(cert_a.text),
+                "certification_date": sns(tds[8].text),
+            }
+            if report_a:
+                cert["report_link"] = urljoin(constants.CC_INDIA_BASE_URL, _fix_india_link(report_a["href"]))
+                cert["report_name"] = sns(report_a.text)
+            results.append(cert)
+    return results
+
+
+def get_italy_certified() -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get Italian "certified product" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_ITALY_CERTIFIED_URL)
+    div = soup.find("div", class_="certificati")
+    results = []
+    for cert_div in div.find_all("div", recursive=False):
+        title = cert_div.find("h3").text
+        data_div = cert_div.find("div", class_="collapse")
+        cert = {"title": title}
+        for data_p in data_div.find_all("p"):
+            p_text = sns(data_p.text)
+            if not p_text or ":" not in p_text:
+                continue
+            p_name, p_data = p_text.split(":")
+            p_data = p_data
+            p_link = data_p.find("a")
+            if "Fornitore" in p_name:
+                cert["supplier"] = p_data
+            elif "Livello di garanzia" in p_name:
+                cert["level"] = p_data
+            elif "Data emissione certificato" in p_name:
+                cert["certification_date"] = p_data
+            elif "Data revisione" in p_name:
+                cert["revision_date"] = p_data
+            elif "Rapporto di Certificazione" in p_name and p_link:
+                cert["report_link_it"] = urljoin(constants.CC_ITALY_BASE_URL, p_link["href"])
+            elif "Certification Report" in p_name and p_link:
+                cert["report_link_en"] = urljoin(constants.CC_ITALY_BASE_URL, p_link["href"])
+            elif "Traguardo di Sicurezza" in p_name and p_link:
+                cert["target_link"] = urljoin(constants.CC_ITALY_BASE_URL, p_link["href"])
+            elif "Nota su" in p_name and p_link:
+                cert["vulnerability_note_link"] = urljoin(constants.CC_ITALY_BASE_URL, p_link["href"])
+            elif "Nota di chiarimento" in p_name and p_link:
+                cert["clarification_note_link"] = urljoin(constants.CC_ITALY_BASE_URL, p_link["href"])
+        results.append(cert)
+    return results
+
+
+def get_italy_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Italian "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_ITALY_INEVAL_URL)
+    div = soup.find("div", class_="valutazioni")
+    results = []
+    for cert_div in div.find_all("div", recursive=False):
+        title = cert_div.find("h3").text
+        data_div = cert_div.find("div", class_="collapse")
+        cert = {"title": title}
+        for data_p in data_div.find_all("p"):
+            p_text = sns(data_p.text)
+            if not p_text or ":" not in p_text:
+                continue
+            p_name, p_data = p_text.split(":")
+            p_data = p_data
+            if "Committente" in p_name:
+                cert["client"] = p_data
+            elif "Livello di garanzia" in p_name:
+                cert["level"] = p_data
+            elif "Tipologia prodotto" in p_name:
+                cert["product_type"] = p_data
+        results.append(cert)
+    return results
+
+
+def _get_japan(url, enhanced, artifacts) -> list[dict[str, Any]]:  # noqa: C901
+    soup = _get_page(url)
+    table = soup.find("table", class_="cert-table")
+    results = []
+    trs = list(table.find_all("tr"))
+    for tr in trs:
+        tds = tr.find_all("td")
+        if not tds:
+            continue
+        if len(tds) == 6:
+            cert: dict[str, Any] = {
+                "cert_id": sns(tds[0].text),
+                "supplier": sns(tds[1].text),
+                "toe_overseas_name": sns(tds[2].text),
+                "claim": sns(tds[4].text),
+            }
+            cert_date = sns(tds[3].text)
+            toe_a = tds[2].find("a")
+            if toe_a and "href" in toe_a.attrs:
+                toe_link = urljoin(constants.CC_JAPAN_CERT_BASE_URL, toe_a["href"])
+            else:
+                toe_link = None
+            if cert_date and "Assurance Continuity" in cert_date:
+                cert["revalidations"] = [{"date": cert_date.split("(")[0], "link": toe_link}]
+            else:
+                cert["certification_date"] = cert_date
+                cert["toe_overseas_link"] = toe_link
+            results.append(cert)
+        if len(tds) == 1:
+            cert = results[-1]
+            cert["toe_japan_name"] = sns(tds[0].text)
+            toe_a = tds[0].find("a")
+            if toe_a and "href" in toe_a.attrs:
+                cert["toe_japan_link"] = urljoin(constants.CC_JAPAN_CERT_BASE_URL, toe_a["href"])
+        if len(tds) == 2:
+            cert = results[-1]
+            cert["certification_date"] = sns(tds[1].text)
+            toe_a = tds[0].find("a")
+            if toe_a and "href" in toe_a.attrs:
+                toe_link = urljoin(constants.CC_JAPAN_CERT_BASE_URL, toe_a["href"])
+            else:
+                toe_link = None
+            cert["toe_overseas_link"] = toe_link
+    if enhanced:
+        for cert in results:
+            e: dict[str, Any] = {}
+            cert_link = cert.get("toe_overseas_link") or cert.get("toe_japan_link")
+            if not cert_link:
+                continue
+            cert_page = _get_page(cert_link)
+            main = cert_page.find("div", id="main")
+            left = main.find("div", id="left")
+            for dl in left.find_all("dl"):
+                dt = dl.find("dt")
+                title = sns(dt.text)
+                value = sns(dt.find_next_sibling().text)
+                if not title:
+                    continue
+                if "Product Name" in title:
+                    e["product"] = value
+                elif "Version of TOE" in title:
+                    e["toe_version"] = value
+                elif "Product Type" in title:
+                    e["product_type"] = value
+                elif "Certification Identification" in title:
+                    e["cert_id"] = value
+                elif "Version of Common Criteria" in title:
+                    e["cc_version"] = value
+                elif "Date" in title:
+                    e["certification_date"] = value
+                elif "Conformance Claim" in title:
+                    e["assurance_level"] = value
+                elif "PP Identifier" in title and value != "None":
+                    e["protection_profile"] = value
+            right = main.find("div", id="right")
+            for dl in right.find_all("dl", recursive=False):
+                title = sns(dl.find("dt").text)
+                value = sns(dl.find("dd").text)
+                if not title:
+                    continue
+                if "Vendor" in title:
+                    e["vendor"] = value
+                elif "Evaluation Facility" in title:
+                    e["evaluation_facility"] = value
+            pdfbox = main.find("div", id="pdfbox")
+            if pdfbox:
+                for li in pdfbox.find_all("li"):
+                    li_a = li.find("a")
+                    name = sns(li_a.text)
+                    if not name:
+                        continue
+                    if "Report" in name:
+                        e["report_link"] = urljoin(constants.CC_JAPAN_BASE_URL, li_a["href"])
+                        if artifacts:
+                            e["report_hash"] = _get_hash(e["report_link"]).hex()
+                    elif "Certificate" in name:
+                        e["cert_link"] = urljoin(constants.CC_JAPAN_BASE_URL, li_a["href"])
+                        if artifacts:
+                            e["cert_hash"] = _get_hash(e["cert_link"]).hex()
+                    elif "Target" in name:
+                        e["target_link"] = urljoin(constants.CC_JAPAN_BASE_URL, li_a["href"])
+                        if artifacts:
+                            e["target_hash"] = _get_hash(e["target_link"]).hex()
+            e["description"] = sns(main.find("div", id="overviewsbox").text)
+            cert["enhanced"] = e
+    return results
+
+
+def get_japan_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Japanese "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    japan_hw = _get_japan(constants.CC_JAPAN_CERTIFIED_HW_URL, enhanced, artifacts)
+    japan_sw = _get_japan(constants.CC_JAPAN_CERTIFIED_SW_URL, enhanced, artifacts)
+    return japan_sw + japan_hw
+
+
+def get_japan_archived(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Japanese "archived product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_japan(constants.CC_JAPAN_ARCHIVED_SW_URL, enhanced, artifacts)
+
+
+def get_japan_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Japanese "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_JAPAN_INEVAL_URL)
+    table = soup.find("table")
+    results = []
+    for tr in table.find_all("tr"):
+        tds = tr.find_all("td")
+        if not tds:
+            continue
+        toe_a = tds[1].find("a")
+        cert = {
+            "supplier": sns(tds[0].text),
+            "toe_name": sns(toe_a.text),
+            "toe_link": urljoin(constants.CC_JAPAN_BASE_URL, toe_a["href"]),
+            "claim": sns(tds[2].text),
+        }
+        results.append(cert)
+    return results
+
+
+def get_malaysia_certified() -> list[dict[str, Any]]:
+    """
+    Get Malaysian "certified product" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_MALAYSIA_CERTIFIED_URL)
+    sections = soup.find("div", attrs={"itemprop": "articleBody"}).find_all("section", class_="sppb-section")
+    results = []
+    for section in sections:
+        table = section.find("table")
+        if table is None:
+            continue
+        heading = section.find("h5")
+        if heading is None:
+            continue
+        category_name = sns(heading.text)
+        tbody = table.find("tbody")
+        for tr in tbody.find_all("tr", recursive=False):
+            tds = tr.find_all("td", recursive=False)
+            if len(tds) != 6:
+                continue
+            cert = {
+                "category": category_name,
+                "level": sns(tds[0].text),
+                "cert_id": sns(tds[1].text),
+                "certification_date": sns(tds[2].text),
+                "product": sns(tds[3].text),
+                "developer": sns(tds[4].text),
+            }
+            results.append(cert)
+    return results
+
+
+def get_malaysia_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Malaysian "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_MALAYSIA_INEVAL_URL)
+    main_div = soup.find("div", attrs={"itemprop": "articleBody"})
+    table = main_div.find("table")
+    results = []
+    for tr in table.find_all("tr")[1:]:
+        tds = tr.find_all("td")
+        if len(tds) != 5:
+            continue
+        cert = {
+            "level": sns(tds[0].text),
+            "project_id": sns(tds[1].text),
+            "toe_name": sns(tds[2].text),
+            "developer": sns(tds[3].text),
+            "expected_completion": sns(tds[4].text),
+        }
+        results.append(cert)
+    return results
+
+
+def get_netherlands_certified(artifacts: bool = False) -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get Dutch "certified product" entries.
+
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_NETHERLANDS_CERTIFIED_URL)
+    main_div = soup.select("body > main > div > div > div > div:nth-child(2) > div.col-lg-9 > div:nth-child(3)")[0]
+    rows = main_div.find_all("div", class_="row", recursive=False)
+    modals = main_div.find_all("div", class_="modal", recursive=False)
+    results = []
+    for row, modal in zip(rows, modals):
+        row_entries = row.find_all("a")
+        modal_trs = modal.find_all("tr")
+        cert: dict[str, Any] = {
+            "manufacturer": sns(row_entries[0].text),
+            "product": sns(row_entries[1].text),
+            "scheme": sns(row_entries[2].text),
+            "cert_id": sns(row_entries[3].text),
+        }
+        for tr in modal_trs:
+            th_text = tr.find("th").text
+            td = tr.find("td")
+            if "Manufacturer website" in th_text:
+                cert["manufacturer_link"] = td.find("a")["href"]
+            elif "Assurancelevel" in th_text:
+                cert["level"] = sns(td.text)
+            elif "Certificate" in th_text:
+                cert["cert_link"] = urljoin(constants.CC_NETHERLANDS_BASE_URL, td.find("a")["href"])
+                if artifacts:
+                    cert["cert_hash"] = _get_hash(cert["cert_link"]).hex()
+            elif "Certificationreport" in th_text:
+                cert["report_link"] = urljoin(constants.CC_NETHERLANDS_BASE_URL, td.find("a")["href"])
+                if artifacts:
+                    cert["report_hash"] = _get_hash(cert["report_link"]).hex()
+            elif "Securitytarget" in th_text:
+                cert["target_link"] = urljoin(constants.CC_NETHERLANDS_BASE_URL, td.find("a")["href"])
+                if artifacts:
+                    cert["target_hash"] = _get_hash(cert["target_link"]).hex()
+            elif "Maintenance report" in th_text:
+                cert["maintenance_link"] = urljoin(constants.CC_NETHERLANDS_BASE_URL, td.find("a")["href"])
+                if artifacts:
+                    cert["maintenance_hash"] = _get_hash(cert["maintenance_link"]).hex()
+        results.append(cert)
+    return results
+
+
+def get_netherlands_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Dutch "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_NETHERLANDS_INEVAL_URL)
+    table = soup.find("table")
+    results = []
+    for tr in table.find_all("tr")[1:]:
+        tds = tr.find_all("td")
+        cert = {
+            "developer": sns(tds[0].text),
+            "product": sns(tds[1].text),
+            "category": sns(tds[2].text),
+            "level": sns(tds[3].text),
+            "certification_id": sns(tds[4].text),
+        }
+        results.append(cert)
+    return results
+
+
+def _get_norway(url: str, enhanced: bool, artifacts: bool) -> list[dict[str, Any]]:  # noqa: C901
+    soup = _get_page(url)
+    results = []
+    for tr in soup.find_all("tr", class_="certified-product"):
+        tds = tr.find_all("td")
+        cert: dict[str, Any] = {
+            "product": sns(tds[0].text),
+            "url": tds[0].find("a")["href"],
+            "category": sns(tds[1].find("p", class_="value").text),
+            "developer": sns(tds[2].find("p", class_="value").text),
+            "certification_date": sns(tds[3].find("time").text),
+        }
+        if enhanced:
+            e: dict[str, Any] = {}
+            cert_page = _get_page(cert["url"])
+            content = cert_page.find("div", class_="main-content")
+            body = content.find("div", class_="articleelement")
+            if body:
+                e["description"] = sns(body.text)
+            specs = content.find("div", class_="specifications")
+            for row in specs.find_all("div", class_="row"):
+                title = sns(row.find("div", class_="label").text)
+                value = sns(row.find("div", class_="value").text)
+                if not title:
+                    continue
+                if "Certificate No." in title:
+                    e["id"] = value
+                elif "Mutual Recognition" in title:
+                    e["mutual_recognition"] = value
+                elif "Product" in title:
+                    e["product"] = value
+                elif "Category" in title:
+                    e["category"] = value
+                elif "Sponsor" in title:
+                    e["sponsor"] = value
+                elif "Developer" in title:
+                    e["developer"] = value
+                elif "Evaluation Facility" in title:
+                    e["evaluation_facility"] = value
+                elif "Certification Date" in title:
+                    e["certification_date"] = value
+                elif "Evaluation Level" in title:
+                    e["level"] = value
+                elif "Protection Profile" in title:
+                    e["protection_profile"] = value
+            docs = content.find("div", class_="documents").find("div", class_="card-body")
+            e["documents"] = {}
+            for doc_collection in docs.find_all("div", class_="document-collection"):
+                head = sns(doc_collection.find("div", class_="header").text)
+                links = doc_collection.find_all("li")
+                if not head:
+                    continue
+                if "Certificates" in head:
+                    doc_type = "cert"
+                elif "Security targets" in head:
+                    doc_type = "target"
+                elif "Certification reports" in head:
+                    doc_type = "report"
+                elif "Maintenance report" in head:
+                    doc_type = "maintenance"
+                else:
+                    continue
+                entries = []
+                for link in links:
+                    a = link.find("a")
+                    entry = {"href": urljoin(constants.CC_NORWAY_BASE_URL, a["href"])}
+                    if artifacts:
+                        entry["hash"] = _get_hash(entry["href"]).hex()
+                    entries.append(entry)
+                e["documents"][doc_type] = entries
+            cert["enhanced"] = e
+        results.append(cert)
+    return results
+
+
+def get_norway_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Norwegian "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_norway(constants.CC_NORWAY_CERTIFIED_URL, enhanced, artifacts)
+
+
+def get_norway_archived(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Norwegian "archived product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_norway(constants.CC_NORWAY_ARCHIVED_URL, enhanced, artifacts)
+
+
+def _get_korea(product_class: int, enhanced: bool, artifacts: bool) -> list[dict[str, Any]]:  # noqa: C901
+    session = requests.session()
+    session.get(constants.CC_KOREA_EN_URL)
+    # Get base page
+    url = constants.CC_KOREA_CERTIFIED_URL + f"?product_class={product_class}"
+    soup = _get_page(url, session=session)
+    seen_pages = set()
+    pages = {1}
+    results = []
+    while pages:
+        page = pages.pop()
+        csrf = soup.find("form", id="fm").find("input", attrs={"name": "csrf"})["value"]
+        resp = session.post(url, data={"csrf": csrf, "selectPage": page, "product_class": product_class})
+        soup = BeautifulSoup(resp.content, "html5lib")
+        tbody = soup.find("table", class_="cpl").find("tbody")
+        for tr in tbody.find_all("tr"):
+            tds = tr.find_all("td")
+            if len(tds) != 6:
+                continue
+            link = tds[0].find("a")
+            id = link["id"].split("-")[1]
+            cert: dict[str, Any] = {
+                "product": sns(tds[0].text),
+                "cert_id": sns(tds[1].text),
+                "product_link": constants.CC_KOREA_PRODUCT_URL.format(id),
+                "vendor": sns(tds[2].text),
+                "level": sns(tds[3].text),
+                "category": sns(tds[4].text),
+                "certification_date": sns(tds[5].text),
+            }
+            if enhanced:
+                e: dict[str, Any] = {}
+                if not cert["product_link"]:
+                    continue
+                cert_page = _get_page(cert["product_link"], session)
+                main = cert_page.find("div", class_="mainContent")
+                table = main.find("table", class_="shortenedWidth")
+                v = e
+                for tr in table.find_all("tr"):
+                    th = tr.find("th")
+                    td = tr.find("td")
+                    if not th:
+                        mus = e.setdefault("maintenance_update", [])
+                        v = {"name": sns(td.text)}
+                        mus.append(v)
+                        continue
+                    title = sns(th.text)
+                    value = sns(td.text)
+                    a = td.find("a")
+                    if not title:
+                        continue
+                    if "Product Name" in title:
+                        v["product"] = value
+                    elif "Common Criteria" in title:
+                        v["cc_version"] = value
+                    elif "Date of Certification" in title or "Date issued" in title:
+                        v["certification_date"] = value
+                    elif "EvaluationAssurance Level" in title:
+                        v["assurance_level"] = value
+                    elif "Expiry Date" in title:
+                        v["expiration_date"] = value
+                    elif "Type of Product" in title:
+                        v["product_type"] = value
+                    elif "Certification No." in title:
+                        v["cert_id"] = value
+                    elif "Protection Profile" in title:
+                        v["protection_profile"] = value
+                    elif "Developer" in title:
+                        v["developer"] = value
+                    elif "Certificate Holder" in title:
+                        v["holder"] = value
+                    elif "Certificate" in title and a:
+                        v["cert_link"] = urljoin(constants.CC_KOREA_BASE_URL, a["href"])
+                        if artifacts:
+                            v["cert_hash"] = _get_hash(v["cert_link"], session).hex()
+                    elif "Security Target" in title and a:
+                        v["target_link"] = urljoin(constants.CC_KOREA_BASE_URL, a["href"])
+                        if artifacts:
+                            v["target_hash"] = _get_hash(v["target_link"], session).hex()
+                    elif "Certification Report" in title and a:
+                        v["report_link"] = urljoin(constants.CC_KOREA_BASE_URL, a["href"])
+                        if artifacts:
+                            v["report_hash"] = _get_hash(v["report_link"], session).hex()
+                    elif "Maintenance Report" in title and a:
+                        v["maintenance_link"] = urljoin(constants.CC_KOREA_BASE_URL, a["href"])
+                        if artifacts:
+                            v["maintenance_hash"] = _get_hash(v["maintenance_link"], session).hex()
+                cert["enhanced"] = e
+            results.append(cert)
+        seen_pages.add(page)
+        page_links = soup.find("div", class_="paginate").find_all("a", class_="number_off")
+        for page_link in page_links:
+            try:
+                new_page = int(page_link.text)
+                if new_page not in seen_pages:
+                    pages.add(new_page)
+            except Exception:
+                pass
+    return results
+
+
+def get_korea_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Korean "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_korea(product_class=1, enhanced=enhanced, artifacts=artifacts)
+
+
+def get_korea_suspended(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Korean "suspended product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_korea(product_class=2, enhanced=enhanced, artifacts=artifacts)
+
+
+def get_korea_archived(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Korean "product in evaluation" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_korea(product_class=4, enhanced=enhanced, artifacts=artifacts)
+
+
+def _get_singapore(url: str, artifacts: bool) -> list[dict[str, Any]]:
+    soup = _get_page(url)
+    page_id = str(soup.find("input", id="CurrentPageId").value)
+    page = 1
+    api_call = requests.post(
+        constants.CC_SINGAPORE_API_URL,
+        data={
+            "PassSortFilter": False,
+            "currentPageId": page_id,
+            "page": page,
+            "limit": 15,
+            "ProductDeveloperName": "",
+        },
+    )
+    api_json = api_call.json()
+    total = api_json["total"]
+    results: list[dict[str, Any]] = []
+    while len(results) != total:
+        for obj in api_json["objects"]:
+            cert: dict[str, Any] = {
+                "level": obj["assuranceLevel"],
+                "product": obj["productName"],
+                "vendor": obj["productDeveloper"],
+                "url": urljoin(constants.CC_SINGAPORE_BASE_URL, obj["productUrl"]),
+                "certification_date": obj["dateOfIssuance"],
+                "expiration_date": obj["dateOfExpiry"],
+                "category": obj["productCategory"]["title"],
+                "cert_title": obj["certificate"]["title"],
+                "cert_link": urljoin(constants.CC_SINGAPORE_BASE_URL, obj["certificate"]["mediaUrl"]),
+                "report_title": obj["certificationReport"]["title"],
+                "report_link": urljoin(constants.CC_SINGAPORE_BASE_URL, obj["certificationReport"]["mediaUrl"]),
+                "target_title": obj["securityTarget"]["title"],
+                "target_link": urljoin(constants.CC_SINGAPORE_BASE_URL, obj["securityTarget"]["mediaUrl"]),
+            }
+            if artifacts:
+                cert["cert_hash"] = _get_hash(cert["cert_link"]).hex()
+                cert["report_hash"] = _get_hash(cert["report_link"]).hex()
+                cert["target_hash"] = _get_hash(cert["target_link"]).hex()
+            results.append(cert)
+        page += 1
+        api_call = requests.post(
+            constants.CC_SINGAPORE_API_URL,
+            data={
+                "PassSortFilter": False,
+                "currentPageId": page_id,
+                "page": page,
+                "limit": 15,
+                "ProductDeveloperName": "",
+            },
+        )
+        api_json = api_call.json()
+    return results
+
+
+def get_singapore_certified(artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Singaporean "certified product" entries.
+
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_singapore(constants.CC_SINGAPORE_CERTIFIED_URL, artifacts)
+
+
+def get_singapore_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get Singaporean "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_SINGAPORE_INEVAL_URL)
+    blocks = soup.find_all("div", class_="sfContentBlock")
+    for block in blocks:
+        table = block.find("table")
+        if table:
+            break
+    else:
+        raise ValueError("Cannot find table.")
+    results = []
+    for tr in table.find_all("tr")[1:]:
+        tds = tr.find_all("td")
+        cert = {
+            "name": sns(tds[0].text),
+            "vendor": sns(tds[1].text),
+            "level": sns(tds[2].text),
+        }
+        results.append(cert)
+    return results
+
+
+def get_singapore_archived(artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Singaporean "archived product" entries.
+
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_singapore(constants.CC_SINGAPORE_ARCHIVED_URL, artifacts)
+
+
+def get_spain_certified() -> list[dict[str, Any]]:
+    """
+    Get Spanish "certified product" entries.
+
+    :return: The entries.
+    """
+    soup = _get_page(constants.CC_SPAIN_CERTIFIED_URL)
+    tbody = soup.find("table", class_="djc_items_table").find("tbody")
+    results = []
+    for tr in tbody.find_all("tr", recursive=False):
+        tds = tr.find_all("td")
+        cert = {
+            "product": sns(tds[0].text),
+            "product_link": urljoin(constants.CC_SPAIN_BASE_URL, tds[0].find("a")["href"]),
+            "category": sns(tds[1].text),
+            "manufacturer": sns(tds[2].text),
+            "certification_date": sns(tds[3].find("td", class_="djc_value").text),
+        }
+        results.append(cert)
+    return results
+
+
+def _get_sweden(url: str, enhanced: bool, artifacts: bool) -> list[dict[str, Any]]:  # noqa: C901
+    soup = _get_page(url)
+    nav = soup.find("main").find("nav", class_="component-nav-box__list")
+    results = []
+    for link in nav.find_all("a"):
+        cert: dict[str, Any] = {
+            "product": sns(link.text),
+            "url": urljoin(constants.CC_SWEDEN_BASE_URL, link["href"]),
+        }
+        if enhanced:
+            e: dict[str, Any] = {}
+            if not cert["url"]:
+                continue
+            cert_page = _get_page(cert["url"])
+            content = cert_page.find("section", class_="container-article")
+            head = content.find("h1")
+            e["title"] = sns(head.text)
+            table = content.find("table")
+            if table:
+                for tr in table.find_all("tr"):
+                    tds = tr.find_all("td")
+                    if len(tds) != 2:
+                        continue
+                    title = sns(tds[0].text)
+                    value = sns(tds[1].text)
+                    a = tds[1].find("a")
+                    if not title:
+                        continue
+                    if "Certifierings ID" in title:
+                        e["cert_id"] = value
+                    elif "Giltighet" in title:
+                        e["mutual_recognition"] = value
+                    elif "Produktnamn" in title:
+                        e["product"] = value
+                    elif "Produktkategori" in title:
+                        e["category"] = value
+                    elif "Assuranspaket" in title:
+                        e["assurance_level"] = value
+                    elif "Certifieringsdatum" in title:
+                        e["certification_date"] = value
+                    elif "Sponsor" in title:
+                        e["sponsor"] = value
+                    elif "Utvecklare" in title:
+                        e["developer"] = value
+                    elif "Evalueringsföretag" in title:
+                        e["evaluation_facility"] = value
+                    elif "Security Target" in title and a:
+                        e["target_link"] = urljoin(constants.CC_SWEDEN_BASE_URL, a["href"])
+                        if artifacts:
+                            e["target_hash"] = _get_hash(e["target_link"]).hex()
+                    elif "Certifieringsrapport" in title and a:
+                        e["report_link"] = urljoin(constants.CC_SWEDEN_BASE_URL, a["href"])
+                        if artifacts:
+                            e["report_hash"] = _get_hash(e["report_hash"]).hex()
+                    elif "Certifikat" in title and a:
+                        e["cert_link"] = urljoin(constants.CC_SWEDEN_BASE_URL, a["href"])
+                        if artifacts:
+                            e["cert_hash"] = _get_hash(e["cert_link"]).hex()
+            cert["enhanced"] = e
+        results.append(cert)
+    return results
+
+
+def get_sweden_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Swedish "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_sweden(constants.CC_SWEDEN_CERTIFIED_URL, enhanced, artifacts)
+
+
+def get_sweden_in_evaluation(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Swedish "product in evaluation" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_sweden(constants.CC_SWEDEN_INEVAL_URL, enhanced, artifacts)
+
+
+def get_sweden_archived(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:
+    """
+    Get Swedish "archived product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    return _get_sweden(constants.CC_SWEDEN_ARCHIVED_URL, enhanced, artifacts)
+
+
+def get_turkey_certified() -> list[dict[str, Any]]:
+    """
+    Get Turkish "certified product" entries.
+
+    :return: The entries.
+    """
+    results = []
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pdf_path = Path(tmpdir) / "turkey.pdf"
+        resp = requests.get(constants.CC_TURKEY_ARCHIVED_URL)
+        if resp.status_code != requests.codes.ok:
+            raise ValueError(f"Unable to download: status={resp.status_code}")
+        with pdf_path.open("wb") as f:
+            f.write(resp.content)
+        dfs = tabula.read_pdf(str(pdf_path), pages="all")
+        for df in dfs:
+            for line in df.values:  # type: ignore
+                cert = {
+                    # TODO: Split item number and generate several dicts for a range they include.
+                    "item_no": line[0],
+                    "developer": line[1],
+                    "product": line[2],
+                    "cc_version": line[3],
+                    "level": line[4],
+                    "cert_lab": line[5],
+                    "certification_date": line[6],
+                    "expiration_date": line[7],
+                    # TODO: Parse "Ongoing Evaluation" out of this field as well.
+                    "archived": isinstance(line[9], str) and "Archived" in line[9],
+                }
+                results.append(cert)
+    return results
+
+
+def get_usa_certified(enhanced: bool = True, artifacts: bool = False) -> list[dict[str, Any]]:  # noqa: C901
+    """
+    Get American "certified product" entries.
+
+    :param enhanced: Whether to enhance the results by following links (slower, more data).
+    :param artifacts: Whether to download and compute artifact hashes (way slower, even more data).
+    :return: The entries.
+    """
+    # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
+    soup = _get_page(constants.CC_USA_CERTIFIED_URL)
+    tbody = soup.find("table", class_="tablesorter").find("tbody")
+    results = []
+    for tr in tbody.find_all("tr"):
+        tds = tr.find_all("td")
+        vendor_span = tds[0].find("span", class_="b u")
+        product_link = tds[0].find("a")
+        scheme_img = tds[6].find("img")
+        # Only return the US certifications.
+        if scheme_img["title"] != "USA":
+            continue
+        cert: dict[str, Any] = {
+            "product": sns(product_link.text),
+            "vendor": sns(vendor_span.text),
+            "product_link": urljoin(constants.CC_USA_PRODUCT_URL, product_link["href"]),
+            "id": sns(tds[1].text),
+            "cc_claim": sns(tds[2].text),
+            "cert_lab": sns(tds[3].text),
+            "certification_date": sns(tds[4].text),
+            "assurance_maintenance_date": sns(tds[5].text),
+        }
+        if enhanced:
+            e: dict[str, Any] = {}
+            if not cert["product_link"]:
+                continue
+            cert_page = _get_page(cert["product_link"])
+            details = cert_page.find("div", class_="txt2 lma")
+            for span in details.find_all("span"):
+                title = sns(span.text)
+                if not title:
+                    continue
+                sibling = span.next_sibling
+                value = sns(sibling.text)
+                if "Certificate Date" in title:
+                    e["certification_date"] = value
+                elif "Product Type" in title:
+                    e["product_type"] = value
+                elif "Conformance Claim" in title:
+                    e["cc_claim"] = value
+                elif "Validation Report Number" in title:
+                    e["cert_id"] = value
+                elif "PP Identifier" in title:
+                    e["protection_profile"] = sns(span.find_next_sibling("a").text)
+                elif "CC Testing Lab" in title:
+                    e["evaluation_facility"] = sns(span.find_next_sibling("a").text)
+            links = cert_page.find_all("a", class_="pseudobtn1")
+            for link in links:
+                name = sns(link.text)
+                href = urljoin(constants.CC_USA_BASE_URL, sns(link["href"]))
+                if not name:
+                    continue
+                if "CC Certificate" in name:
+                    e["cert_link"] = href
+                    if artifacts:
+                        e["cert_hash"] = _get_hash(href).hex()
+                elif "Security Target" in name:
+                    e["target_link"] = href
+                    if artifacts:
+                        e["target_hash"] = _get_hash(href).hex()
+                elif "Validation Report" in name:
+                    e["report_link"] = href
+                    if artifacts:
+                        e["report_hash"] = _get_hash(href).hex()
+                elif "Assurance Activity" in name:
+                    e["assurance_activity_link"] = href
+                    if artifacts:
+                        e["assurance_activity_hash"] = _get_hash(href).hex()
+                elif "Administrative Guide" in name:
+                    guides = e.setdefault("administrative_guides", [])
+                    guide = {"link": href}
+                    guides.append(guide)
+                    if artifacts:
+                        guide["hash"] = _get_hash(href).hex()
+            cert["enhanced"] = e
+        results.append(cert)
+    return results
+
+
+def get_usa_in_evaluation() -> list[dict[str, Any]]:
+    """
+    Get American "product in evaluation" entries.
+
+    :return: The entries.
+    """
+    # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
+    soup = _get_page(constants.CC_USA_INEVAL_URL)
+    tbody = soup.find("table", class_="tablesorter").find("tbody")
+    results = []
+    for tr in tbody.find_all("tr"):
+        tds = tr.find_all("td")
+        vendor_span = tds[0].find("span", class_="b u")
+        product_name = None
+        for child in tds[0].children:
+            if isinstance(child, NavigableString):
+                product_name = sns(child)
+                break
+        cert = {
+            "vendor": sns(vendor_span.text),
+            "id": sns(tds[1].text),
+            "cc_claim": sns(tds[2].text),
+            "cert_lab": sns(tds[3].text),
+            "kickoff_date": sns(tds[4].text),
+        }
+        if product_name:
+            cert["product"] = product_name
+        results.append(cert)
+    return results
+
+
+def get_usa_archived() -> list[dict[str, Any]]:
+    """
+    Get American "archived product" entries.
+
+    :return: The entries.
+    """
+    # TODO: Information could be expanded by following the cc_claims (has links to protection profiles).
+    soup = _get_page(constants.CC_USA_ARCHIVED_URL)
+    tbody = soup.find("table", class_="tablesorter").find("tbody")
+    results = []
+    for tr in tbody.find_all("tr"):
+        tds = tr.find_all("td")
+        scheme_img = tds[5].find("img")
+        # Only return the US certifications.
+        if scheme_img["title"] != "USA":
+            continue
+        vendor_span = tds[0].find("span", class_="b u")
+        product_name = None
+        for child in tds[0].children:
+            if isinstance(child, NavigableString):
+                product_name = sns(child)
+                break
+        cert = {
+            "vendor": sns(vendor_span.text),
+            "id": sns(tds[1].text),
+            "cc_claim": sns(tds[2].text),
+            "cert_lab": sns(tds[3].text),
+            "certification_date": sns(tds[4].text),
+        }
+        if product_name:
+            cert["product"] = product_name
+        results.append(cert)
+    return results
+
+
+class EntryType(Enum):
+    Certified = "CERTIFIED"
+    InEvaluation = "INEVALUATION"
+    Archived = "ARCHIVED"
+
+
+@dataclass
+class CCScheme(ComplexSerializableType):
+    """
+    Dataclass for data extracted from a CCScheme website, so more like a
+    "CCSchemeWebDump" but that classname is not so nice.
+
+    Contains the country (scheme) code a timestamp of extraction and
+    several lists of entries: certified, in-evaluation and archived.
+    It may only contain some lists of entries as the scheme might only publish
+    them.
+    """
+
+    country: str
+    timestamp: datetime
+    lists: dict[EntryType, Any]
+
+    methods: ClassVar[dict[str, dict[EntryType, Callable]]] = {
+        "AU": {EntryType.InEvaluation: get_australia_in_evaluation},
+        "CA": {EntryType.InEvaluation: get_canada_in_evaluation, EntryType.Certified: get_canada_certified},
+        "FR": {EntryType.Certified: get_france_certified},
+        "DE": {EntryType.Certified: get_germany_certified},
+        "IN": {EntryType.Certified: get_india_certified, EntryType.Archived: get_india_archived},
+        "IT": {EntryType.Certified: get_italy_certified, EntryType.InEvaluation: get_italy_in_evaluation},
+        "JP": {
+            EntryType.InEvaluation: get_japan_in_evaluation,
+            EntryType.Certified: get_japan_certified,
+            EntryType.Archived: get_japan_archived,
+        },
+        "MY": {EntryType.Certified: get_malaysia_certified, EntryType.InEvaluation: get_malaysia_in_evaluation},
+        "NL": {EntryType.Certified: get_netherlands_certified, EntryType.InEvaluation: get_netherlands_in_evaluation},
+        "NO": {EntryType.Certified: get_norway_certified, EntryType.Archived: get_norway_archived},
+        "KO": {EntryType.Certified: get_korea_certified, EntryType.Archived: get_korea_archived},
+        "SG": {
+            EntryType.InEvaluation: get_singapore_in_evaluation,
+            EntryType.Certified: get_singapore_certified,
+            EntryType.Archived: get_singapore_archived,
+        },
+        "ES": {EntryType.Certified: get_spain_certified},
+        "SE": {
+            EntryType.InEvaluation: get_sweden_in_evaluation,
+            EntryType.Certified: get_sweden_certified,
+            EntryType.Archived: get_sweden_archived,
+        },
+        "TR": {EntryType.Certified: get_turkey_certified},
+        "US": {
+            EntryType.InEvaluation: get_usa_in_evaluation,
+            EntryType.Certified: get_usa_certified,
+            EntryType.Archived: get_usa_archived,
+        },
+    }
+
+    @classmethod
+    def from_dict(cls, dct):
+        return cls(
+            dct["country"],
+            datetime.fromisoformat(dct["timestamp"]),
+            {EntryType(entry_type): entries for entry_type, entries in dct["lists"].items()},
+        )
+
+    def to_dict(self):
+        return {
+            "country": self.country,
+            "timestamp": self.timestamp.isoformat(),
+            "lists": {entry_type.value: entries for entry_type, entries in self.lists.items()},
+        }
+
+    @classmethod
+    def from_web(cls, scheme: str, entry_types: Iterable[EntryType]) -> CCScheme:
+        if not (scheme_lists := cls.methods.get(scheme)):
+            raise ValueError("Unknown scheme.")
+        entries = {}
+        timestamp = datetime.now()
+        for each_type in entry_types:
+            if not (method := scheme_lists.get(each_type)):
+                raise ValueError("Wrong entry_type for scheme.")
+            entries[each_type] = method()
+        return cls(scheme, timestamp, entries)
diff --git a/src/sec_certs/sample/fips_mip.py b/src/sec_certs/sample/fips_mip.py
index f1ef05c8..89c46d01 100644
--- a/src/sec_certs/sample/fips_mip.py
+++ b/src/sec_certs/sample/fips_mip.py
@@ -4,6 +4,7 @@ import logging
 from dataclasses import dataclass
 from datetime import date, datetime
 from enum import Enum
+from functools import total_ordering
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 from typing import Iterator, Mapping
@@ -20,25 +21,32 @@ from sec_certs.utils.helpers import to_utc
 logger = logging.getLogger(__name__)
 
 
+@total_ordering
 class MIPStatus(Enum):
     IN_REVIEW = "In Review"
     REVIEW_PENDING = "Review Pending"
     COORDINATION = "Coordination"
     FINALIZATION = "Finalization"
 
+    def __lt__(self, other):
+        if self.__class__ == other.__class__:
+            mb = list(MIPStatus.__members__.keys())
+            return mb.index(self.name) < mb.index(other.name)
+        raise NotImplementedError
 
-@dataclass(frozen=True)
+
+@dataclass(frozen=True, order=True)
 class MIPEntry(ComplexSerializableType):
     module_name: str
     vendor_name: str
     standard: str
-    status: MIPStatus | None
+    status: MIPStatus
     status_since: date | None
 
-    def to_dict(self) -> dict[str, str | MIPStatus | None | date | None]:
+    def to_dict(self) -> dict[str, str | MIPStatus | date | None]:
         return {
             **self.__dict__,
-            "status": self.status.value if self.status else None,
+            "status": self.status.value,
             "status_since": self.status_since.isoformat() if self.status_since else None,
         }
 
@@ -48,12 +56,32 @@ class MIPEntry(ComplexSerializableType):
             dct["module_name"],
             dct["vendor_name"],
             dct["standard"],
-            MIPStatus(dct["status"]) if dct["status"] else None,
+            MIPStatus(dct["status"]),
             date.fromisoformat(dct["status_since"]) if dct.get("status_since") else None,
         )
 
 
 @dataclass
+class MIPFlow(ComplexSerializableType):
+    module_name: str
+    vendor_name: str
+    standard: str
+    state_changes: list[tuple[date, MIPStatus]]
+
+    def to_dict(self) -> dict[str, str | list]:
+        return {**self.__dict__, "state_changes": [(dt.isoformat(), status.value) for dt, status in self.state_changes]}
+
+    @classmethod
+    def from_dict(cls, dct: Mapping) -> MIPFlow:
+        return cls(
+            dct["module_name"],
+            dct["vendor_name"],
+            dct["standard"],
+            [(date.fromisoformat(dt), MIPStatus(status)) for dt, status in dct["state_changes"]],
+        )
+
+
+@dataclass
 class MIPSnapshot(ComplexSerializableType):
     entries: set[MIPEntry]
     timestamp: datetime
@@ -95,7 +123,6 @@ class MIPSnapshot(ComplexSerializableType):
         entries = set()
         for tr in lines:
             tds = tr.find_all("td")
-            status = None
             if "mip-highlight" in tds[-1]["class"]:
                 status = MIPStatus.FINALIZATION
             elif "mip-highlight" in tds[-2]["class"]:
@@ -104,6 +131,8 @@ class MIPSnapshot(ComplexSerializableType):
                 status = MIPStatus.REVIEW_PENDING
             elif "mip-highlight" in tds[-4]["class"]:
                 status = MIPStatus.IN_REVIEW
+            else:
+                raise ValueError("Cannot parse MIP status line.")
             entries.add(MIPEntry(str(tds[0].string), str(tds[1].string), str(tds[2].string), status, None))
         return entries
 
@@ -123,7 +152,7 @@ class MIPSnapshot(ComplexSerializableType):
         return {
             MIPEntry(
                 str(line[0].string),
-                str(" ".join(line[1].find_all(text=True, recursive=False)).strip()),
+                str(" ".join(line[1].find_all(string=True, recursive=False)).strip()),
                 str(line[2].string),
                 MIPStatus(str(line[3].string)),
                 None,
@@ -137,7 +166,7 @@ class MIPSnapshot(ComplexSerializableType):
         entries = set()
         for line in (tr.find_all("td") for tr in lines):
             module_name = str(line[0].string)
-            vendor_name = str(" ".join(line[1].find_all(text=True, recursive=False)).strip())
+            vendor_name = str(" ".join(line[1].find_all(string=True, recursive=False)).strip())
             standard = str(line[2].string)
             status_line = FIPS_MIP_STATUS_RE.match(str(line[3].string))
             if status_line is None:
diff --git a/src/sec_certs/serialization/__init__.py b/src/sec_certs/serialization/__init__.py
index e69de29b..faa56704 100644
--- a/src/sec_certs/serialization/__init__.py
+++ b/src/sec_certs/serialization/__init__.py
@@ -0,0 +1 @@
+"""This package provides tols for serialization of datasets and certificates."""
diff --git a/src/sec_certs/utils/__init__.py b/src/sec_certs/utils/__init__.py
index e69de29b..45b35aea 100644
--- a/src/sec_certs/utils/__init__.py
+++ b/src/sec_certs/utils/__init__.py
@@ -0,0 +1 @@
+"""This package provides utilities used throught the framework."""
diff --git a/src/sec_certs/utils/strings.py b/src/sec_certs/utils/strings.py
new file mode 100644
index 00000000..785b1026
--- /dev/null
+++ b/src/sec_certs/utils/strings.py
@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import re
+from functools import lru_cache
+
+import spacy
+
+
+@lru_cache
+def load_spacy_model(spacy_model_to_load: str = "en_core_web_sm"):
+    return spacy.load(spacy_model_to_load, disable=["parser", "ner"])
+
+
+def fully_sanitize_string(string: str) -> str:
+    return replace_special_chars_with_space(discard_trademark_symbols(string.lower())).strip()
+
+
+def replace_special_chars_with_space(string: str) -> str:
+    return re.sub(r"[^a-zA-Z0-9 \n\.]", " ", string)
+
+
+def discard_trademark_symbols(string: str) -> str:
+    return string.replace("®", "").replace("™", "")
+
+
+def strip_manufacturer_and_version(string: str, manufacturers: set[str] | None, versions: set[str]) -> str:
+    to_strip = versions | manufacturers if manufacturers else versions
+    for x in to_strip:
+        string = string.lower().replace(replace_special_chars_with_space(x.lower()), " ").strip()
+    return string
+
+
+def standardize_version_in_cert_name(string: str, detected_versions: set[str]) -> str:
+    for ver in detected_versions:
+        version_regex = r"(" + r"(\bversion)\s*" + ver + r"+) | (\bv\s*" + ver + r"+)"
+        string = re.sub(version_regex, " " + ver + " ", string, flags=re.IGNORECASE)
+    return string
+
+
+def lemmatize_product_name(nlp, product_name: str) -> str:
+    if not product_name:
+        return product_name
+    return " ".join([token.lemma_ for token in nlp(fully_sanitize_string(product_name))])
diff --git a/tests/cc/test_cc_analysis.py b/tests/cc/test_cc_analysis.py
index fb2633d9..d0618266 100644
--- a/tests/cc/test_cc_analysis.py
+++ b/tests/cc/test_cc_analysis.py
@@ -9,7 +9,7 @@ import tests.data.cc.analysis
 import tests.data.common
 
 from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL
-from sec_certs.dataset import CCDataset
+from sec_certs.dataset.cc import CCDataset
 from sec_certs.dataset.cpe import CPEDataset
 from sec_certs.dataset.cve import CVEDataset
 from sec_certs.sample.cc import CCCertificate
diff --git a/tests/cc/test_cc_dataset.py b/tests/cc/test_cc_dataset.py
index d9fe79e3..bbfea14b 100644
--- a/tests/cc/test_cc_dataset.py
+++ b/tests/cc/test_cc_dataset.py
@@ -8,7 +8,7 @@ import pytest
 import tests.data.cc.dataset
 
 from sec_certs import constants
-from sec_certs.dataset import CCDataset
+from sec_certs.dataset.cc import CCDataset
 from sec_certs.sample.cc import CCCertificate
 
 
diff --git a/tests/cc/test_cc_schemes.py b/tests/cc/test_cc_schemes.py
index 078a3190..24467709 100644
--- a/tests/cc/test_cc_schemes.py
+++ b/tests/cc/test_cc_schemes.py
@@ -1,99 +1,217 @@
+from urllib.parse import urlparse
+
 import pytest
+from requests import RequestException
+
+import sec_certs.sample.cc_scheme as CCSchemes
+from sec_certs.dataset.cc import CCDataset
+from sec_certs.model.cc_matching import CCSchemeMatcher
+from sec_certs.sample.cc import CCCertificate
+
 
-from sec_certs.dataset import CCSchemeDataset
+def absolute_urls(results):
+    for result in results:
+        for key, value in result.items():
+            if "url" in key or "link" in key and value is not None:
+                parsed = urlparse(value)
+                assert bool(parsed.netloc)
+    return True
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_australia():
-    assert len(CCSchemeDataset.get_australia_in_evaluation()) != 0
+    ineval = CCSchemes.get_australia_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
-def test_canada():
-    assert len(CCSchemeDataset.get_canada_certified()) != 0
-    assert len(CCSchemeDataset.get_canada_in_evaluation()) != 0
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
+@pytest.fixture
+def canada_certified():
+    return CCSchemes.get_canada_certified()
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
+@pytest.mark.slow
+def test_canada(canada_certified):
+    assert len(canada_certified) != 0
+    assert absolute_urls(canada_certified)
+    ineval = CCSchemes.get_canada_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
+
+
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
+@pytest.mark.slow
 def test_anssi():
-    assert len(CCSchemeDataset.get_france_certified()) != 0
+    certified = CCSchemes.get_france_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
+@pytest.mark.slow
 def test_bsi():
-    assert len(CCSchemeDataset.get_germany_certified()) != 0
+    certified = CCSchemes.get_germany_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_india():
-    assert len(CCSchemeDataset.get_india_certified()) != 0
-    assert len(CCSchemeDataset.get_india_archived()) != 0
+    certified = CCSchemes.get_india_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_india_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_italy():
-    assert len(CCSchemeDataset.get_italy_certified()) != 0
-    assert len(CCSchemeDataset.get_italy_in_evaluation()) != 0
+    certified = CCSchemes.get_italy_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    ineval = CCSchemes.get_italy_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_japan():
-    assert len(CCSchemeDataset.get_japan_certified()) != 0
-    assert len(CCSchemeDataset.get_japan_archived()) != 0
-    assert len(CCSchemeDataset.get_japan_in_evaluation()) != 0
+    certified = CCSchemes.get_japan_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_japan_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
+    ineval = CCSchemes.get_japan_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_malaysia():
-    assert len(CCSchemeDataset.get_malaysia_certified()) != 0
-    assert len(CCSchemeDataset.get_malaysia_in_evaluation()) != 0
+    certified = CCSchemes.get_malaysia_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    ineval = CCSchemes.get_malaysia_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_netherlands():
-    assert len(CCSchemeDataset.get_netherlands_certified()) != 0
-    assert len(CCSchemeDataset.get_netherlands_in_evaluation()) != 0
+    certified = CCSchemes.get_netherlands_certified()
+    assert len(certified) != 0
+    # assert absolute_urls(certified)
+    ineval = CCSchemes.get_netherlands_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_norway():
-    assert len(CCSchemeDataset.get_norway_certified()) != 0
-    assert len(CCSchemeDataset.get_norway_archived()) != 0
+    certified = CCSchemes.get_norway_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_norway_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_korea():
-    assert len(CCSchemeDataset.get_korea_certified()) != 0
-    CCSchemeDataset.get_korea_suspended()
-    assert len(CCSchemeDataset.get_korea_archived()) != 0
+    certified = CCSchemes.get_korea_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_korea_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_singapore():
-    assert len(CCSchemeDataset.get_singapore_certified()) != 0
-    assert len(CCSchemeDataset.get_singapore_archived()) != 0
-    assert len(CCSchemeDataset.get_singapore_in_evaluation()) != 0
+    certified = CCSchemes.get_singapore_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_singapore_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
+    ineval = CCSchemes.get_singapore_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_spain():
-    assert len(CCSchemeDataset.get_spain_certified()) != 0
+    certified = CCSchemes.get_spain_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_sweden():
-    assert len(CCSchemeDataset.get_sweden_certified()) != 0
-    assert len(CCSchemeDataset.get_sweden_in_evaluation()) != 0
-    assert len(CCSchemeDataset.get_sweden_archived()) != 0
+    certified = CCSchemes.get_sweden_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_sweden_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
+    ineval = CCSchemes.get_sweden_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_turkey():
-    assert len(CCSchemeDataset.get_turkey_certified()) != 0
+    certified = CCSchemes.get_turkey_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
 
 
-@pytest.mark.xfail(reason="May fail due to server errors.")
+@pytest.mark.xfail(reason="May fail due to server errors.", raises=RequestException)
 def test_usa():
-    assert len(CCSchemeDataset.get_usa_certified()) != 0
-    assert len(CCSchemeDataset.get_usa_in_evaluation()) != 0
-    assert len(CCSchemeDataset.get_usa_archived()) != 0
+    certified = CCSchemes.get_usa_certified()
+    assert len(certified) != 0
+    assert absolute_urls(certified)
+    archived = CCSchemes.get_usa_archived()
+    assert len(archived) != 0
+    assert absolute_urls(archived)
+    ineval = CCSchemes.get_usa_in_evaluation()
+    assert len(ineval) != 0
+    assert absolute_urls(ineval)
+
+
+def test_single_match(cert_one: CCCertificate):
+    entry = {
+        "product": "NetIQ Identity Manager 4.7",
+        "url": "https://www.fmv.se/verksamhet/ovrig-verksamhet/csec/certifikat-utgivna-av-csec/netiq-identity-manager-4.7/",
+        "enhanced": {
+            "title": "NetIQ Identity Manager 4.7",
+            "cert_id": "CSEC2018013",
+            "mutual_recognition": "CCRA, SOGIS-MRA, EA-MLA",
+            "product": "NetIQ Identity Manager 4.7Software Version: Identity Applications (RBPM) 4.7.3.0.1109, Identity Manager Engine 4.7.3.0.AE, Identity Reporting Module 6.5.0. F14508F, Sentinel Log Management for Identity Governance and Administration 8.2.2.0_5415, One SSO Provider (OSP) 6.3.3.0, Self Service Password Reset (SSPR) 4.4.0.2 B366 r39762",
+            "category": "Identity Manager",
+            "target_link": "https://www.fmv.se/globalassets/csec/netiq-identity-manager-4.7/st---netiq-identity-manager-4.7.pdf",
+            "assurance_level": "EAL3 + ALC_FLR.2",
+            "certification_date": "2020-06-15",
+            "report_link": "https://www.fmv.se/globalassets/csec/netiq-identity-manager-4.7/certification-report---netiq-identity-manager-4.7.pdf",
+            "cert_link": "https://www.fmv.se/globalassets/csec/netiq-identity-manager-4.7/certifikat-ccra---netiq-identity-manager-4.7.pdf",
+            "sponsor": "NetIQ Corporation",
+            "developer": "NetIQ Corporation",
+            "evaluation_facility": "Combitech AB and EWA-Canada",
+        },
+    }
+    matcher = CCSchemeMatcher(entry, "SE")
+    assert matcher.match(cert_one) > 95
+
+
+def test_matching(toy_dataset: CCDataset, canada_certified):
+    matches = CCSchemeMatcher.match_all(canada_certified, "CA", toy_dataset)
+    assert len(matches) == 1
+
+
+def test_process_dataset(toy_dataset: CCDataset):
+    toy_dataset.process_schemes(True, only_schemes={"CA"})
+    assert toy_dataset["8a5e6bcda602920c"].heuristics.scheme_data is not None
diff --git a/tests/data/cc/certificate/fictional_cert.json b/tests/data/cc/certificate/fictional_cert.json
index 5d5a0499..7cf04d2d 100644
--- a/tests/data/cc/certificate/fictional_cert.json
+++ b/tests/data/cc/certificate/fictional_cert.json
@@ -89,7 +89,8 @@
             "directly_referencing": null,
             "indirectly_referenced_by": null,
             "indirectly_referencing": null
-        }
+        },
+        "scheme_data": null
     },
     "report_link": "https://path.to/report/link",
     "st_link": "https://path.to/st/link",
diff --git a/tests/data/cc/dataset/auxiliary_datasets/maintenances/maintenance_updates.json b/tests/data/cc/dataset/auxiliary_datasets/maintenances/maintenance_updates.json
index fd21471b..8a087e2b 100644
--- a/tests/data/cc/dataset/auxiliary_datasets/maintenances/maintenance_updates.json
+++ b/tests/data/cc/dataset/auxiliary_datasets/maintenances/maintenance_updates.json
@@ -70,7 +70,8 @@
                 },
                 "extracted_sars": null,
                 "direct_transitive_cves": null,
-                "indirect_transitive_cves": null
+                "indirect_transitive_cves": null,
+                "scheme_data": null
             },
             "related_cert_digest": "8a5e6bcda602920c",
             "maintenance_date": "2019-08-26"
diff --git a/tests/data/cc/dataset/toy_dataset.json b/tests/data/cc/dataset/toy_dataset.json
index dec802f7..b425235e 100644
--- a/tests/data/cc/dataset/toy_dataset.json
+++ b/tests/data/cc/dataset/toy_dataset.json
@@ -93,7 +93,8 @@
                     "directly_referencing": null,
                     "indirectly_referenced_by": null,
                     "indirectly_referencing": null
-                }
+                },
+                "scheme_data": null
             }
         },
         {
@@ -180,7 +181,8 @@
                     "directly_referencing": null,
                     "indirectly_referenced_by": null,
                     "indirectly_referencing": null
-                }
+                },
+                "scheme_data": null
             }
         },
         {
@@ -275,7 +277,8 @@
                     "directly_referencing": null,
                     "indirectly_referenced_by": null,
                     "indirectly_referencing": null
-                }
+                },
+                "scheme_data": null
             }
         }
     ]
diff --git a/tests/fips/test_fips_certificate.py b/tests/fips/test_fips_certificate.py
index 207ae46d..99b1d9b7 100644
--- a/tests/fips/test_fips_certificate.py
+++ b/tests/fips/test_fips_certificate.py
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import json
 import shutil
 from importlib import resources
diff --git a/tests/fips/test_fips_dataset.py b/tests/fips/test_fips_dataset.py
index 7a4bc712..ed7808be 100644
--- a/tests/fips/test_fips_dataset.py
+++ b/tests/fips/test_fips_dataset.py
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import json
 import shutil
 from importlib import resources
diff --git a/tests/fips/test_fips_iut.py b/tests/fips/test_fips_iut.py
index 3412f6f2..cf1434b0 100644
--- a/tests/fips/test_fips_iut.py
+++ b/tests/fips/test_fips_iut.py
@@ -1,11 +1,16 @@
+from __future__ import annotations
+
+import datetime
 from importlib import resources
 from pathlib import Path
 
 import pytest
 import tests.data.fips.iut
 
-from sec_certs.dataset import IUTDataset
-from sec_certs.sample import IUTSnapshot
+from sec_certs.dataset.fips import FIPSDataset
+from sec_certs.dataset.fips_iut import IUTDataset
+from sec_certs.model.fips_matching import FIPSProcessMatcher
+from sec_certs.sample.fips_iut import IUTEntry, IUTSnapshot
 
 
 @pytest.fixture(scope="module")
@@ -39,3 +44,23 @@ def test_iut_snapshot_from_web():
 
 def test_iut_snapshot_from_web_latest():
     assert IUTSnapshot.from_web_latest()
+
+
+def test_iut_matching(processed_dataset: FIPSDataset):
+    entry = IUTEntry(
+        module_name="Red Hat Enterprise Linux 7.1 OpenSSL Module",
+        vendor_name="Red Hat(R), Inc.",
+        standard="FIPS 140-2",
+        iut_date=datetime.date(2014, 1, 1),
+    )
+    matcher = FIPSProcessMatcher(entry)
+    scores = [matcher.match(cert) for cert in processed_dataset]
+    assert len(list(filter(lambda x: x > 90, scores))) == 1
+
+
+def test_iut_snapshot_match(processed_dataset: FIPSDataset, data_dump_path: Path):
+    snapshot = IUTSnapshot.from_dump(data_dump_path)
+    # Move snapshot date back so that there are matches
+    snapshot.timestamp = datetime.datetime(2014, 1, 2)
+    matches = FIPSProcessMatcher.match_snapshot(snapshot, processed_dataset)
+    assert matches
diff --git a/tests/fips/test_fips_mip.py b/tests/fips/test_fips_mip.py
index 807b83af..7fb473c2 100644
--- a/tests/fips/test_fips_mip.py
+++ b/tests/fips/test_fips_mip.py
@@ -1,11 +1,16 @@
+from __future__ import annotations
+
+import datetime
 from importlib import resources
 from pathlib import Path
 
 import pytest
 import tests.data.fips.mip
 
-from sec_certs.dataset import MIPDataset
-from sec_certs.sample import MIPSnapshot
+from sec_certs.dataset.fips import FIPSDataset
+from sec_certs.dataset.fips_mip import MIPDataset
+from sec_certs.model.fips_matching import FIPSProcessMatcher
+from sec_certs.sample.fips_mip import MIPEntry, MIPSnapshot, MIPStatus
 
 
 @pytest.fixture(scope="module")
@@ -25,8 +30,9 @@ def test_mip_dataset_from_dumps(data_dir: Path):
     assert len(dset) == 3
 
 
-def test_mip_dataset_from_dataset_latest():
-    assert MIPDataset.from_web_latest()
+def test_mip_flows():
+    dset = MIPDataset.from_web_latest()
+    assert dset.compute_flows()
 
 
 def test_mip_snapshot_from_dump(data_dump_path: Path):
@@ -39,3 +45,24 @@ def test_from_web():
 
 def test_from_web_latest():
     assert MIPSnapshot.from_web_latest()
+
+
+def test_mip_matching(processed_dataset: FIPSDataset):
+    entry = MIPEntry(
+        module_name="Red Hat Enterprise Linux 7.1 OpenSSL Module",
+        vendor_name="Red Hat(R), Inc.",
+        standard="FIPS 140-2",
+        status=MIPStatus.IN_REVIEW,
+        status_since=datetime.date(2014, 1, 1),
+    )
+    matcher = FIPSProcessMatcher(entry)
+    scores = [matcher.match(cert) for cert in processed_dataset]
+    assert len(list(filter(lambda x: x > 90, scores))) == 1
+
+
+def test_mip_snapshot_match(processed_dataset: FIPSDataset, data_dump_path: Path):
+    snapshot = MIPSnapshot.from_dump(data_dump_path)
+    # Move snapshot date back so that there are matches
+    snapshot.timestamp = datetime.datetime(2014, 1, 2)
+    matches = FIPSProcessMatcher.match_snapshot(snapshot, processed_dataset)
+    assert matches