Update app.py

app.py

@@ -64,6 +64,48 @@ def download_pdf():
         download_name=f"annotated_page_{pageNumTextFound}.pdf"
     )
 
+
+@app.route('/view-highlight', methods=['GET','POST'])
+def download_pdfHighlight():
+
+    # Manually parse the query parameters
+    full_query_string = request.query_string.decode()  # Get raw query string
+    parsed_params = urllib.parse.parse_qs(full_query_string)  # Parse it
+    # Extract pdfLink and keyword manually
+    pdf_link = parsed_params.get('pdfLink', [None])[0]
+    keyword = parsed_params.get('keyword', [None])[0]
+#     linktoreplace = [listofheadingsfromrawan["Link"]]
+    if not pdf_link :
+        return "Missing required parameters.", 400
+
+    # Decode the extracted values
+    pdf_link = urllib.parse.unquote(pdf_link)
+
+    print("Extracted PDF Link:", pdf_link)
+    print("Extracted Keywords:", keyword)
+    createDF=False
+    global jsonoutput
+    matching_item = next((item for item in jsonoutput if item.get("Subject") == keyword), None)
+
+    if matching_item:
+        page_number = int(matching_item.get("Page"))-1
+        stringtowrite = matching_item.get("head above 1")
+        print(f"Page number for '{keyword}': {page_number}")
+    else:
+        page_number=0
+        print("No match found.")
+    pdf_content = InitialMarkups.extract_section_under_headerRawan(pdf_link,keyword,page_number,stringtowrite)[0]
+    if pdf_content is None:
+        return "PDF content not found.", 404
+
+    pdf_bytes = BytesIO(pdf_content)
+    return send_file(
+        pdf_bytes,
+        mimetype='application/pdf',
+        as_attachment=False,
+        download_name=f"annotated_page_{pageNumTextFound}.pdf"
+    )
+    
 @app.route('/api/process-data', methods=['POST'])
 def receive_pdf_data():
     global pdf_content, pageNumTextFound
@@ -115,15 +157,19 @@ def findapi():
     except Exception as e:
         return jsonify({"error": str(e)}), 500
         
-@app.route('/findapiFilteredHeadings', methods=['GET'])
+@app.route('/findapiFilteredHeadings', methods=['GET','POST'])
 def findapiFilteredHeadings():
     try:
         print('In process [Try]')
         data = request.get_json()
         # Extracting values
         pdfLink = data.get('filePath')
+        print(pdfLink)
         listofheadings = data.get('listofheadings') #in json format 
-        pdfbytes, pdf_document,tablepdfoutput= InitialMarkups.extract_section_under_header(pdfLink,listofheadings)
+        print(listofheadings)
+        pdfbytes, pdf_document,tablepdfoutput= InitialMarkups.extract_section_under_headerRawan(pdfLink,listofheadings)
+        global jsonoutput
+        jsonoutput=tablepdfoutput
         return jsonify(tablepdfoutput)
     except Exception as e:
         return jsonify({"error": str(e)}), 500