From 0eaf610cfe6a0a36cfad2fa71b42d1f921b6e49b Mon Sep 17 00:00:00 2001
From: GeorgeFI
Date: Wed, 20 Sep 2023 20:53:19 +0200
Subject: feat: Added pytesseract wrapper

---
 src/sec_certs/utils/pdf.py | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'src')

diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index 749a8a5a..b4ec1e94 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -11,6 +11,7 @@ from typing import Any
 
 import pdftotext
 import pikepdf
+import pytesseract
 
 from sec_certs import constants
 from sec_certs.constants import (
@@ -51,13 +52,16 @@ def ocr_pdf_file(pdf_path: Path) -> str:
         )
         if ppm.returncode != 0:
             raise ValueError(f"pdftoppm failed: {ppm.returncode}")
+
         for ppm_path in map(Path, glob.glob(str(tmppath / "image*.ppm"))):
             base = ppm_path.with_suffix("")
-            tes = subprocess.run(
-                ["tesseract", "-l", "eng+deu+fra", ppm_path, base], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-            )
-            if tes.returncode != 0:
-                raise ValueError(f"tesseract failed: {tes.returncode}")
+            content = pytesseract.image_to_string(ppm_path, lang="eng+deu+fra")
+
+            if content:
+                with Path(base.with_suffix(".txt")).open("w") as file:
+                    file.write(content)
+            else:
+                raise ValueError(f"OCR failed for document {ppm_path}. Check document manually")
 
         contents = ""
 
-- 
cgit v1.3.1


From 498308a737943b87ecbf38a05404d4caa22fa726 Mon Sep 17 00:00:00 2001
From: GeorgeFI
Date: Mon, 25 Sep 2023 21:12:26 +0200
Subject: fix: OCR with Pytesseract fixed now

---
 src/sec_certs/utils/pdf.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'src')

diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index b4ec1e94..7736b5d0 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -12,6 +12,7 @@ from typing import Any
 import pdftotext
 import pikepdf
 import pytesseract
+from PIL import Image
 
 from sec_certs import constants
 from sec_certs.constants import (
@@ -55,7 +56,7 @@ def ocr_pdf_file(pdf_path: Path) -> str:
 
         for ppm_path in map(Path, glob.glob(str(tmppath / "image*.ppm"))):
             base = ppm_path.with_suffix("")
-            content = pytesseract.image_to_string(ppm_path, lang="eng+deu+fra")
+            content = pytesseract.image_to_string(Image.open(ppm_path), lang="eng+deu+fra")
 
             if content:
                 with Path(base.with_suffix(".txt")).open("w") as file:
-- 
cgit v1.3.1


From 779c19ecca9612861b8d5694c6d8a0c3e27036cb Mon Sep 17 00:00:00 2001
From: GeorgeFI
Date: Sun, 1 Oct 2023 14:26:05 +0200
Subject: fix: Fixed calling method on NoneType

---
 src/sec_certs/sample/cc_scheme.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'src')

diff --git a/src/sec_certs/sample/cc_scheme.py b/src/sec_certs/sample/cc_scheme.py
index 307dfb57..bc0c0792 100644
--- a/src/sec_certs/sample/cc_scheme.py
+++ b/src/sec_certs/sample/cc_scheme.py
@@ -107,7 +107,7 @@ def get_australia_in_evaluation(enhanced: bool = True) -> list[dict[str, Any]]:
         if enhanced:
             e: dict[str, Any] = {}
             cert_page = _get_page(cert["url"])
-            article = cert_page.find("article", attrs={"role": "article"})
+            article = cert_page.find("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)
-- 
cgit v1.3.1