Update app.py

app.py

@@ -3,6 +3,7 @@ import tsadropboxretrieval
 import json
 import Find_Hyperlinking_text
 import findspecsv1
+import InitialMarkups
 import requests
 from io import BytesIO
 import urllib
@@ -11,7 +12,7 @@ app = Flask(__name__)
 
 pdf_content = None
 pageNumTextFound = 0
-BASE_URL = "https://marthee-nbslink.hf.space"  # Hugging Face Spaces base URL
+BASE_URL = "https://find-initialmarkups.hf.space"  # Hugging Face Spaces base URL
 
 @app.route("/", methods=["GET", "POST"])
 def thismain():
@@ -27,26 +28,17 @@ def download_pdf():
 
     # 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:
+    if not pdf_link :
         return "Missing required parameters.", 400
 
     # 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
 
     print("Extracted PDF Link:", pdf_link)
-    print("Extracted Keywords:", keyword)
+    # print("Extracted Keywords:", keyword)
     createDF=False
 
-    pdf_content = findspecsv1.extract_section_under_header(pdf_link, keyword)[0]
+    pdf_content = InitialMarkups.extract_section_under_header(pdf_link)[0]
     if pdf_content is None:
         return "PDF content not found.", 404
 
@@ -63,16 +55,16 @@ def receive_pdf_data():
     global pdf_content, pageNumTextFound
 
     # Get PDF link and keyword from finddata()
-    pdfLink, keyword = finddata()
+    pdfLink = finddata()
 
-    if not pdfLink or not keyword:
-        return jsonify({"error": "Both 'pdfLink' and 'keyword' must be provided."}), 400
+    if not pdfLink :
+        return jsonify({"error": "'pdfLink' must be provided."}), 400
 
     try:
-        print(pdfLink, keyword)
+        print(pdfLink)
 
 
-        pdfbytes, pdf_document , df ,tablepdfoutput= findspecsv1.extract_section_under_header(pdfLink, keyword)
+        pdfbytes, pdf_document,tablepdfoutput= InitialMarkups.extract_section_under_header(pdfLink)
         dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
 
         # Get metadata using the shared link
@@ -99,44 +91,44 @@ def finddata():
     keyword = ['115 INTEGRATED MRI ROOM LININGS', '310 ACCURACY']
     return pdfLink, keyword
 
-@app.route('/apiNBSData', methods=['POST'])
-def NBSData():
+# @app.route('/apiNBSData', methods=['POST'])
+# def NBSData():
 
 
-    try:
-        print('In process [Try]')
-        data = request.get_json()
-        # Extracting values
-        pdfLink = data.get('filePath')
-        keyword = data.get('NBS_List')
-
-        # Checking if both values are provided
-        if not pdfLink or not keyword:
-            return jsonify({"error": "Both 'pdfLink' and 'keyword' must be provided."}), 400
+#     try:
+#         print('In process [Try]')
+#         data = request.get_json()
+#         # Extracting values
+#         pdfLink = data.get('filePath')
+#         keyword = data.get('NBS_List')
+
+#         # Checking if both values are provided
+#         if not pdfLink or not keyword:
+#             return jsonify({"error": "Both 'pdfLink' and 'keyword' must be provided."}), 400
         
-        keyword = eval(keyword)  # Convert the string representation of the list to an actual list
+#         keyword = eval(keyword)  # Convert the string representation of the list to an actual list
         
-        # Now you can use the extracted pdfLink and keyword
-        print(pdfLink, keyword)
-        pdfbytes, pdf_document , df ,tablepdfoutput= findspecsv1.extract_section_under_header(pdfLink, keyword)
-        dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
-
-        # Get metadata using the shared link
-        metadata = dbxTeam.sharing_get_shared_link_metadata(pdfLink)
-        dbPath='/TSA JOBS/ADR Test/FIND/'
-        pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=metadata.name) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
-        print('LINKS0',pdflink)
+#         # Now you can use the extracted pdfLink and keyword
+#         print(pdfLink, keyword)
+#         pdfbytes, pdf_document , df ,tablepdfoutput= findspecsv1.extract_section_under_header(pdfLink, keyword)
+#         dbxTeam= tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+
+#         # Get metadata using the shared link
+#         metadata = dbxTeam.sharing_get_shared_link_metadata(pdfLink)
+#         dbPath='/TSA JOBS/ADR Test/FIND/'
+#         pdflink= tsadropboxretrieval.uploadanyFile(doc=pdf_document,path=dbPath,pdfname=metadata.name) #doc=doc,pdfname=path,pdfpath=pdfpath+'Measured Plan/
+#         print('LINKS0',pdflink)
      
-        dbPath='/TSA JOBS/ADR Test/FIND/'
-        tablepdfLink=tsadropboxretrieval.uploadanyFile(doc=tablepdfoutput,path=dbPath,pdfname=metadata.name.rsplit(".pdf", 1)[0] +' Markup Summary'+'.pdf')
-        print(f"PDF successfully uploaded to Dropbox at")
-        print('LINKS1',tablepdfLink)
-        return jsonify(tablepdfoutput)
+#         dbPath='/TSA JOBS/ADR Test/FIND/'
+#         tablepdfLink=tsadropboxretrieval.uploadanyFile(doc=tablepdfoutput,path=dbPath,pdfname=metadata.name.rsplit(".pdf", 1)[0] +' Markup Summary'+'.pdf')
+#         print(f"PDF successfully uploaded to Dropbox at")
+#         print('LINKS1',tablepdfLink)
+#         return jsonify(tablepdfoutput)
 
     
-    except Exception as e:
-        print(f"Error: {e}")
-        return jsonify({"error": str(e)}), 500
-
+#     except Exception as e:
+#         print(f"Error: {e}")
+#         return jsonify({"error": str(e)}), 500
+ 
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=7860)