Use html5lib instead of html.parser.

6 files changed, 9 insertions, 9 deletions

diff --git a/sec_certs/dataset/common_criteria.py b/sec_certs/dataset/common_criteria.py
index 378bca61..d53f1e35 100644
--- a/sec_certs/dataset/common_criteria.py
+++ b/sec_certs/dataset/common_criteria.py
@@ -603,7 +603,7 @@ class CCDataset(Dataset[CommonCriteriaCert], ComplexSerializableType):
         cat_dict = {x: y for (x, y) in zip(cc_table_ids, cc_categories)}
 
         with file.open("r") as handle:
-            soup = BeautifulSoup(handle, "html.parser")
+            soup = BeautifulSoup(handle, "html5lib")
 
         certs = {}
         for key, val in cat_dict.items():
@@ -1006,7 +1006,7 @@ class CCSchemeDataset:
         resp = conn.get(url, headers={"User-Agent": "seccerts.org"})
         if resp.status_code != requests.codes.ok:
             raise ValueError(f"Unable to download: status={resp.status_code}")
-        return BeautifulSoup(resp.content, "html.parser")
+        return BeautifulSoup(resp.content, "html5lib")
 
     @staticmethod
     def get_australia_in_evaluation():
@@ -1500,7 +1500,7 @@ class CCSchemeDataset:
             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, "html.parser")
+            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")
diff --git a/sec_certs/dataset/fips.py b/sec_certs/dataset/fips.py
index 64fd636e..1cb67480 100644
--- a/sec_certs/dataset/fips.py
+++ b/sec_certs/dataset/fips.py
@@ -164,7 +164,7 @@ class FIPSDataset(Dataset[FIPSCertificate], ComplexSerializableType):
     def _get_certificates_from_html(self, html_file: Path, update: bool = False) -> Set[str]:
         logger.info(f"Getting certificate ids from {html_file}")
         with open(html_file, "r", encoding="utf-8") as handle:
-            html = BeautifulSoup(handle.read(), "html.parser")
+            html = BeautifulSoup(handle.read(), "html5lib")
 
         table = [x for x in html.find(id="searchResultsTable").tbody.contents if x != "\n"]
         entries: Set[str] = set()
diff --git a/sec_certs/dataset/fips_algorithm.py b/sec_certs/dataset/fips_algorithm.py
index caaa5a7b..e9e3680c 100644
--- a/sec_certs/dataset/fips_algorithm.py
+++ b/sec_certs/dataset/fips_algorithm.py
@@ -40,7 +40,7 @@ class FIPSAlgorithmDataset(Dataset, ComplexSerializableType):
             logger.error("Couldn't download first page of algo dataset")
 
         with open(self.root_dir / "page1.html", "r") as alg_file:
-            soup = BeautifulSoup(alg_file.read(), "html.parser")
+            soup = BeautifulSoup(alg_file.read(), "html5lib")
             num_pages_elem = soup.select("span[data-total-pages]")[0].attrs
 
         num_pages = int(num_pages_elem["data-total-pages"])
@@ -89,7 +89,7 @@ class FIPSAlgorithmDataset(Dataset, ComplexSerializableType):
                 continue
 
             with open(f, "r", encoding="utf-8") as handle:
-                html_soup = BeautifulSoup(handle.read(), "html.parser")
+                html_soup = BeautifulSoup(handle.read(), "html5lib")
 
             table = html_soup.find("table", class_="table table-condensed publications-table table-bordered")
             tbody_contents = table.find("tbody").find_all("tr")
diff --git a/sec_certs/sample/fips.py b/sec_certs/sample/fips.py
index ed9a90f8..723bc332 100644
--- a/sec_certs/sample/fips.py
+++ b/sec_certs/sample/fips.py
@@ -426,7 +426,7 @@ class FIPSCertificate(Certificate["FIPSCertificate", "FIPSCertificate.Heuristics
             items_found["cert_id"] = int(file.stem)
 
         text = sec_certs.utils.extract.load_cert_html_file(str(file))
-        soup = BeautifulSoup(text, "html.parser")
+        soup = BeautifulSoup(text, "html5lib")
         for div in soup.find_all("div", class_="row padrow"):
             _FIPSHTMLParser.parse_html_main(div, items_found)
 
diff --git a/sec_certs/sample/fips_iut.py b/sec_certs/sample/fips_iut.py
index 2fab9a56..6cdc5900 100644
--- a/sec_certs/sample/fips_iut.py
+++ b/sec_certs/sample/fips_iut.py
@@ -71,7 +71,7 @@ class IUTSnapshot(ComplexSerializableType):
     def from_page(cls, content: bytes, snapshot_date: datetime) -> "IUTSnapshot":
         if not content:
             raise ValueError("Empty content in IUT.")
-        soup = BeautifulSoup(content, "html.parser")
+        soup = BeautifulSoup(content, "html5lib")
         tables = soup.find_all("table")
         if len(tables) != 1:
             raise ValueError("Not only a single table in IUT.")
diff --git a/sec_certs/sample/fips_mip.py b/sec_certs/sample/fips_mip.py
index 4bb33904..71c2d9d2 100644
--- a/sec_certs/sample/fips_mip.py
+++ b/sec_certs/sample/fips_mip.py
@@ -159,7 +159,7 @@ class MIPSnapshot(ComplexSerializableType):
     def from_page(cls, content: bytes, snapshot_date: datetime) -> "MIPSnapshot":
         if not content:
             raise ValueError("Empty content in MIP.")
-        soup = BeautifulSoup(content, "html.parser")
+        soup = BeautifulSoup(content, "html5lib")
         tables = soup.find_all("table")
         if len(tables) != 1:
             raise ValueError("Not only a single table in MIP data.")