Update app.py

app.py

@@ -8,30 +8,47 @@ import urllib
 
 app = Flask(__name__)
 
-@app.route("/",methods=["GET", "POST"])
-def thismain():
-    print('ayhaga')
-    return render_template("gui.html")
+from flask import Flask, request, jsonify, send_file, render_template
+import urllib.parse
+import json
+from io import BytesIO
+
+app = Flask(__name__)
 
 pdf_content = None
 pageNumTextFound = 0
-BASE_URL = "https://marthee-nbslink.hf.space"  # Localhost URL for testing
+BASE_URL = "https://marthee-nbslink.hf.space"  # Hugging Face Spaces base URL
+
+@app.route("/", methods=["GET", "POST"])
+def thismain():
+    print('ayhaga')
+    return render_template("gui.html")
 
 @app.route('/view-pdf', methods=['GET'])
 def download_pdf():
     global pdf_content, pageNumTextFound
-    pdf_link = request.args.get('pdfLink')
-    keyword = request.args.get('keyword')
 
-    # Check if parameters exist
+    # 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]
+
     if not pdf_link or not keyword:
         return "Missing required parameters.", 400
 
-    # Decode URL-encoded parameters
-    pdf_link = urllib.parse.unquote(pdf_link)  # Decode URL encoding
-    keyword = json.loads(urllib.parse.unquote(keyword))  # Decode and convert back to a list
+    # Decode the extracted values
+    pdf_link = urllib.parse.unquote(pdf_link)
+    keyword = urllib.parse.unquote(keyword)
+
+    # If the keyword is a JSON string, convert it back to a list
+    try:
+        keyword = json.loads(keyword)
+    except json.JSONDecodeError:
+        keyword = [keyword]  # Treat it as a single keyword if not JSON
 
-    # Debugging output
     print("Extracted PDF Link:", pdf_link)
     print("Extracted Keywords:", keyword)
 
@@ -49,38 +66,38 @@ def download_pdf():
 @app.route('/api/process-data', methods=['POST'])
 def receive_pdf_data():
     global pdf_content, pageNumTextFound
-    pdfLink,keyword=finddata()
-    # Get PDF link and keyword from the request body
-    # pdfLink = request.form.get('pdfLink')
-    # keyword = request.form.get('keyword')
+
+    # Get PDF link and keyword from finddata()
+    pdfLink, keyword = finddata()
 
     if not pdfLink or not keyword:
         return jsonify({"error": "Both 'pdfLink' and 'keyword' must be provided."}), 400
 
     try:
-        # # Call the function to process the PDF
-        # keyword = json.loads(keyword)
-        print(pdfLink,keyword)
-        global pdf_content
-        pdf_content, pageNumTextFound,highlight_rect  = Find_Hyperlinking_text.annotate_text_from_pdf([pdfLink], keyword)
+        print(pdfLink, keyword)
+
+        # Call function to process the PDF
+        pdf_content, pageNumTextFound, highlight_rect = Find_Hyperlinking_text.annotate_text_from_pdf([pdfLink], keyword)
 
         if pdf_content is None:
             return jsonify({"error": "No valid PDF content found."}), 404
 
-        # Construct the URL in the desired format with the rectangle coordinates
+        # Construct the URL with the rectangle coordinates
         download_link = f"{BASE_URL}/view-pdf#page={pageNumTextFound}&zoom={highlight_rect}"
-        print('download_link',download_link)
+        print('Download Link:', download_link)
+
         return jsonify({
             "message": "PDF processed successfully.",
-            "download_link": download_link  # Return the formatted URL
+            "download_link": download_link
         })
 
     except Exception as e:
         return jsonify({"error": str(e)}), 500
-    
+
 def finddata():
-    pdfLink = 'https://www.dropbox.com/scl/fi/hnp4mqigb51a5kp89kgfa/00801-ARC-20-ZZ-S-A-0002.pdf?rlkey=45abeoebzqw4qwnslnei6dkd6&st=m4yrcjm2&dl=1'; # Dropbox link
-    keyword = ['115 INTEGRATED MRI ROOM LININGS','710 TRANSPORTATION'] ;  # Example keyword
-    return pdfLink,keyword
+    pdfLink = 'https://www.dropbox.com/scl/fi/hnp4mqigb51a5kp89kgfa/00801-ARC-20-ZZ-S-A-0002.pdf?rlkey=45abeoebzqw4qwnslnei6dkd6&st=m4yrcjm2&dl=1'
+    keyword = ['115 INTEGRATED MRI ROOM LININGS', '710 TRANSPORTATION']
+    return pdfLink, keyword
+
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=7860)