Update app.py

app.py

@@ -1,71 +1,72 @@
 from flask import Flask, send_file, render_template, request
 import requests
 from io import BytesIO
+import fitz  # PyMuPDF
 
 app = Flask(__name__)
 
+# Route to render the main page
 @app.route("/", methods=["GET", "POST"])
 def getInfotoMeasure(pagenum):
-    # Set the page number internally in Flask (for example, page 2)
-    
-    # page = 2  
-
     return render_template("gui.html", page=pagenum)
 
-def highlight_text_from_pdf(pdfshareablelinks , keyword): 
-    print('intexts',pdfshareablelinks)
-    # pdfshareablelinks=split_links(pdfshareablelinks) #if array like in pdftotext
+# Function to highlight text in PDF
+def highlight_text_from_pdf(pdfshareablelinks, keyword): 
+    print('PDF Links:', pdfshareablelinks)
     for link in pdfshareablelinks:
-      pdf_content = None
-
-      if link and ('http' in link or 'dropbox' in link):
-        # Modify Dropbox link for direct download
-        if 'dl=0' in link:
-            link = link.replace('dl=0', 'dl=1')
-
-        # Download the PDF content from the shareable link
-        response = requests.get(link)
-        pdf_content = BytesIO(response.content)  # Store the content in memory
-        print('Downloaded from shareable link.')
-
-      if pdf_content is None:
-          raise ValueError("No valid PDF content found.")
-      pageNumTextFound=1
-      # Open the PDF using fitz (PyMuPDF) directly from memory
-      pdf_document = fitz.open(stream=pdf_content, filetype="pdf")
-      for page_num in range(pdf_document.page_count):
+        pdf_content = None
+
+        if link and ('http' in link or 'dropbox' in link):
+            # Modify Dropbox link for direct download
+            if 'dl=0' in link:
+                link = link.replace('dl=0', 'dl=1')
+
+            # Download the PDF content from the shareable link
+            response = requests.get(link)
+            if response.status_code == 200:
+                pdf_content = BytesIO(response.content)
+                print('Downloaded from shareable link.')
+
+        if pdf_content is None:
+            raise ValueError("No valid PDF content found.")
+
+        pageNumTextFound = 1
+        pdf_document = fitz.open(stream=pdf_content, filetype="pdf")
+
+        for page_num in range(pdf_document.page_count):
             page = pdf_document.load_page(page_num)
-            matched=page.search_for(keyword)
+            matched = page.search_for(keyword)
+
             if matched:
-                page.add_highlight_annot(word)
-                pageNumTextFound=page_num +1 # 1 indexed pdfs
-    return pdf_document, pageNumTextFound 
+                for word in matched:
+                    page.add_highlight_annot(word)
+                pageNumTextFound = page_num + 1  # 1-indexed pages
+
+        return pdf_document, pageNumTextFound
+
 # Route to serve PDF with a specified page
 @app.route('/view-pdf', methods=['GET'])
 def download_pdf():
-    # page = 3  # Get the page number (default is page 1)
-    # dropbox_link = 'https://www.dropbox.com/scl/fi/fjykwhhn9gu9t3kqrflxd/LA002-NOR-ZZ-ZZ-T-A-2403_Architectural-Specification-F10-Brick-and-Block-Walling_A4-_C01.pdf?rlkey=ek9i66i79m0hwp8z5yjs6rp5p&st=jh05a6qs&dl=0'
+    pdf_link = [
+        'https://www.dropbox.com/scl/fi/fjykwhhn9gu9t3kqrflxd/LA002-NOR-ZZ-ZZ-T-A-2403_Architectural-Specification-F10-Brick-and-Block-Walling_A4-_C01.pdf?rlkey=ek9i66i79m0hwp8z5yjs6rp5p&st=jh05a6qs&dl=0'
+    ]
+    keyword = "To be read with preliminaries/ general conditions"
 
-    # # Modify Dropbox link to enable direct download
-    # if 'dl=0' in dropbox_link:
-    #     dropbox_link = dropbox_link.replace('dl=0', 'dl=1')
+    # Call function to highlight text and get PDF page
+    pdf_content, pageNumTextFound = highlight_text_from_pdf(pdf_link, keyword)
 
-    # response = requests.get(dropbox_link)
-
-    # if response.status_code != 200:
-    #     return "Failed to download the PDF.", 500
-    pdflink='https://www.dropbox.com/scl/fi/fjykwhhn9gu9t3kqrflxd/LA002-NOR-ZZ-ZZ-T-A-2403_Architectural-Specification-F10-Brick-and-Block-Walling_A4-_C01.pdf?rlkey=ek9i66i79m0hwp8z5yjs6rp5p&st=jh05a6qs&dl=0'
-    keyword='To be read with preliminaries/ general conditions'
-
-    pdf_content, page_num = highlight_text_from_pdf(pdf_link, keyword)
+    # Render the main GUI with the detected page number
     getInfotoMeasure(pageNumTextFound)
-    pdf_content = BytesIO(response.content)
+
+    pdf_bytes = BytesIO()
+    pdf_content.save(pdf_bytes)
+    pdf_bytes.seek(0)
 
     return send_file(
-        pdf_content,
+        pdf_bytes,
         mimetype='application/pdf',
         as_attachment=False,
-        download_name=f"document_page_{page}.pdf"
+        download_name=f"highlighted_page_{pageNumTextFound}.pdf"
     )
 
 if __name__ == '__main__':