Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -42,52 +42,95 @@ def home():
|
|
| 42 |
else:
|
| 43 |
# Redirect to your PDF viewer route when ready
|
| 44 |
return redirect(url_for("view_pdf", **request.args))
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
##################### Main console ###########################################################################################################
|
| 48 |
-
################################################################################################################################################################
|
| 49 |
-
################################################################################################################################################################
|
| 50 |
-
|
| 51 |
@app.route('/view-pdf', methods=['GET'])
|
| 52 |
-
def
|
| 53 |
-
|
| 54 |
-
# full_query_string = request.query_string.decode()
|
| 55 |
-
# parsed_params = urllib.parse.parse_qs(full_query_string)
|
| 56 |
-
# # print(parsed_params)
|
| 57 |
-
# encoded_pdf_link = parsed_params.get('pdfLink', [None])[0]
|
| 58 |
-
# # Get PDF link and keyword from finddata()
|
| 59 |
-
# # pdf_link = finddata()
|
| 60 |
encoded_pdf_link = request.args.get("pdfLink")
|
| 61 |
-
|
| 62 |
-
|
|
|
|
| 63 |
if not encoded_pdf_link:
|
| 64 |
return "Missing pdfLink parameter.", 400
|
| 65 |
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
#
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
pdf_content = InitialMarkups.extract_section_under_header(pdf_link)[0]
|
| 77 |
-
except Exception as e:
|
| 78 |
-
print("Error during PDF extraction:", e)
|
| 79 |
-
return "PDF could not be processed.", 500
|
| 80 |
|
| 81 |
-
if pdf_content is None or not pdf_content.startswith(b"%PDF"):
|
| 82 |
-
return "PDF content not found or broken.", 404
|
| 83 |
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
|
| 93 |
@app.route('/api/process-data', methods=['POST'])
|
|
|
|
| 42 |
else:
|
| 43 |
# Redirect to your PDF viewer route when ready
|
| 44 |
return redirect(url_for("view_pdf", **request.args))
|
| 45 |
+
PROCESSED_PDF_PATH = "static/processed.pdf" # cached processed PDF
|
| 46 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
@app.route('/view-pdf', methods=['GET'])
|
| 48 |
+
def view_pdf():
|
| 49 |
+
"""First entry point — process the PDF once, then show viewer at specific page/zoom."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
encoded_pdf_link = request.args.get("pdfLink")
|
| 51 |
+
page = request.args.get("page", default="1")
|
| 52 |
+
zoom = request.args.get("zoom", default="100")
|
| 53 |
+
|
| 54 |
if not encoded_pdf_link:
|
| 55 |
return "Missing pdfLink parameter.", 400
|
| 56 |
|
| 57 |
+
pdf_link = urllib.parse.unquote(encoded_pdf_link)
|
| 58 |
+
print(f"Requested PDF: {pdf_link} | Page: {page} | Zoom: {zoom}")
|
| 59 |
+
|
| 60 |
+
# Only process PDF if not already processed
|
| 61 |
+
if not os.path.exists(PROCESSED_PDF_PATH):
|
| 62 |
+
try:
|
| 63 |
+
from InitialMarkups import extract_section_under_header
|
| 64 |
+
pdf_content = extract_section_under_header(pdf_link)[0]
|
| 65 |
+
if not pdf_content.startswith(b"%PDF"):
|
| 66 |
+
return "Invalid PDF content.", 500
|
| 67 |
+
|
| 68 |
+
os.makedirs("static", exist_ok=True)
|
| 69 |
+
with open(PROCESSED_PDF_PATH, "wb") as f:
|
| 70 |
+
f.write(pdf_content)
|
| 71 |
+
print("✅ PDF processed and saved to:", PROCESSED_PDF_PATH)
|
| 72 |
+
except Exception as e:
|
| 73 |
+
print("❌ Error processing PDF:", e)
|
| 74 |
+
return "PDF could not be processed.", 500
|
| 75 |
+
else:
|
| 76 |
+
print("⚙️ Using cached PDF (already processed).")
|
| 77 |
|
| 78 |
+
# Render viewer and start at requested page/zoom
|
| 79 |
+
return render_template("viewer.html", start_page=page, start_zoom=zoom)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
|
|
|
|
|
|
| 81 |
|
| 82 |
+
@app.route('/get-pdf')
|
| 83 |
+
def get_pdf():
|
| 84 |
+
"""Serve the cached processed PDF."""
|
| 85 |
+
if not os.path.exists(PROCESSED_PDF_PATH):
|
| 86 |
+
return "PDF not processed yet.", 404
|
| 87 |
+
return send_file(PROCESSED_PDF_PATH, mimetype="application/pdf")
|
| 88 |
+
################################################################################################################################################################
|
| 89 |
+
################################################################################################################################################################
|
| 90 |
+
##################### Main console ###########################################################################################################
|
| 91 |
+
################################################################################################################################################################
|
| 92 |
+
################################################################################################################################################################
|
| 93 |
+
|
| 94 |
+
# @app.route('/view-pdf', methods=['GET'])
|
| 95 |
+
# def download_pdf():
|
| 96 |
+
# # Parse and decode pdfLink safely
|
| 97 |
+
# # full_query_string = request.query_string.decode()
|
| 98 |
+
# # parsed_params = urllib.parse.parse_qs(full_query_string)
|
| 99 |
+
# # # print(parsed_params)
|
| 100 |
+
# # encoded_pdf_link = parsed_params.get('pdfLink', [None])[0]
|
| 101 |
+
# # # Get PDF link and keyword from finddata()
|
| 102 |
+
# # # pdf_link = finddata()
|
| 103 |
+
# encoded_pdf_link = request.args.get("pdfLink")
|
| 104 |
+
# if encoded_pdf_link:
|
| 105 |
+
# pdf_link = urllib.parse.unquote(encoded_pdf_link)
|
| 106 |
+
# if not encoded_pdf_link:
|
| 107 |
+
# return "Missing pdfLink parameter.", 400
|
| 108 |
+
|
| 109 |
+
# # Decode the URL-encoded PDF link
|
| 110 |
+
# # pdf_link = urllib.parse.unquote(encoded_pdf_link)
|
| 111 |
+
# print("Extracted PDF Link:", pdf_link)
|
| 112 |
+
# # pdf_link = request.get_json()
|
| 113 |
+
# # if not pdf_link:
|
| 114 |
+
# # return "Missing pdfLink in request body.", 400
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
# try:
|
| 118 |
+
# # Use InitialMarkups to extract content
|
| 119 |
+
# pdf_content = InitialMarkups.extract_section_under_header(pdf_link)[0]
|
| 120 |
+
# except Exception as e:
|
| 121 |
+
# print("Error during PDF extraction:", e)
|
| 122 |
+
# return "PDF could not be processed.", 500
|
| 123 |
+
|
| 124 |
+
# if pdf_content is None or not pdf_content.startswith(b"%PDF"):
|
| 125 |
+
# return "PDF content not found or broken.", 404
|
| 126 |
+
|
| 127 |
+
# pdf_bytes = BytesIO(pdf_content)
|
| 128 |
+
# return send_file(
|
| 129 |
+
# pdf_bytes,
|
| 130 |
+
# mimetype='application/pdf',
|
| 131 |
+
# as_attachment=False,
|
| 132 |
+
# download_name=f"annotated_page_{pageNumTextFound}.pdf"
|
| 133 |
+
# )
|
| 134 |
|
| 135 |
|
| 136 |
@app.route('/api/process-data', methods=['POST'])
|