Open SC files and parse tables

requirements.txt

@@ -1,7 +1,13 @@
 certifi==2024.8.30
+cffi==1.17.1
 charset-normalizer==3.4.0
+cryptography==44.0.0
 idna==3.10
+pdfminer.six==20231228
+pdfplumber==0.11.4
+pillow==11.0.0
+pycparser==2.22
 pyOwlBoard==0.0.2
-PyPDF2==3.0.1
+pypdfium2==4.30.0
 requests==2.32.3
 urllib3==2.2.3

src/parse_pdf.py

@@ -1,4 +1,4 @@
-import PyPDF2
+import pdfplumber
 import re
 
 ## re Patterns
@@ -11,19 +11,18 @@ train_pis_line_pattern = r"\(PIS Code\s*:\s*(?P<pis_code>\d+|____)\s*\)" # Extra
 # Extract Schedule Cards to list of strings
 
 def extract_pdf_text(file_path):
-    with open(file_path, 'rb') as file:
-        pdf_reader = PyPDF2.PdfReader(file)
+    tables = []
+    try:
+        with pdfplumber.open(file_path) as file:
+            for page_number, page in enumerate(file.pages, start=1):
+                page_tables = page.extract_tables()
+                if page_tables:
+                    tables.extend(page_tables)
+    except Exception as e:
+        print(f"Error processing PDF: {e}")
+    return tables
 
-        page_texts = []
-        for page in pdf_reader.pages:
-            text = page.extract_text()
-            if text:
-                page_texts.append(text)
-
-        full_text = " ".join(page_texts)
-        return full_text
-
-# Does everything - should be split in to functional functions
+# Does everything - NEEDS REWRITE TO HANDLE EXTRACTED TABLES FROM ABOVE FN
 def parse_pdf_file(filename):
     pdf_text = extract_pdf_text(filename)
     schedule_cards = re.findall(schedule_pattern, pdf_text, re.DOTALL)

src/tables.py

@@ -0,0 +1,9 @@
+import pdfplumber
+
+with pdfplumber.open("./../1031 THO SC CNDR.pdf") as pdf:
+    for page_number, page in enumerate(pdf.pages, start=1):
+        tables = page.extract_tables()
+        for table in tables:
+            print(f"Table on page {page_number}: ")
+            for row in table:
+                print(row[0])