Update app.py

app.py

@@ -31,21 +31,30 @@ os.environ['JAVA_HOME'] = '/usr/lib/jvm/java-11-openjdk-amd64'
 def extract_pdf_text(file) -> str:
     """Extracts full text from a PDF file using PyMuPDF."""
     try:
-        doc = fitz.open(stream=file.read(), filetype="pdf") if not isinstance(file, str) else fitz.open(file)
+        print(f"Opening PDF file: {file}")
+        if isinstance(file, str):
+            print(f"Opening file by path: {file}")
+            doc = fitz.open(file)
+        else:
+            print(f"Opening file from stream")
+            doc = fitz.open(stream=file.read(), filetype="pdf")
+            
+        print(f"PDF opened successfully with {len(doc)} pages")
         full_text = ""
         
         for page_number in range(len(doc)):
             page = doc[page_number]
-            words = page.get_text("word")
+            words = page.get_text("word")  # Change to "text" instead of "word"
             full_text += words
+            print(f"Extracted {len(words)} characters from page {page_number+1}")
 
-        # print(full_text)
         doc.close()
         print(f"Total extracted text length: {len(full_text)} characters.")
         return full_text
         
     except Exception as e:
-        print(f"Error extracting text from PDF: {e}")
+        print(f"Error extracting text from PDF: {str(e)}")
+        print(traceback.format_exc())
         return ""
 
 def check_text_presence(full_text: str, search_terms: List[str]) -> Dict[str, bool]:
@@ -472,4 +481,3 @@ if __name__ == "__main__":
         # server_name="0.0.0.0",
         server_port=None
     )
-