Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,12 +5,18 @@ import fitz # PyMuPDF
|
|
| 5 |
|
| 6 |
app = Flask(__name__)
|
| 7 |
|
| 8 |
-
# Route to render the main page
|
| 9 |
@app.route("/", methods=["GET", "POST"])
|
| 10 |
-
def getInfotoMeasure(
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
# Function to highlight text in PDF
|
| 14 |
def highlight_text_from_pdf(pdfshareablelinks, keyword):
|
| 15 |
print('PDF Links:', pdfshareablelinks)
|
| 16 |
for link in pdfshareablelinks:
|
|
@@ -21,11 +27,11 @@ def highlight_text_from_pdf(pdfshareablelinks, keyword):
|
|
| 21 |
if 'dl=0' in link:
|
| 22 |
link = link.replace('dl=0', 'dl=1')
|
| 23 |
|
| 24 |
-
# Download
|
| 25 |
response = requests.get(link)
|
| 26 |
if response.status_code == 200:
|
| 27 |
pdf_content = BytesIO(response.content)
|
| 28 |
-
print('Downloaded
|
| 29 |
|
| 30 |
if pdf_content is None:
|
| 31 |
raise ValueError("No valid PDF content found.")
|
|
@@ -40,11 +46,11 @@ def highlight_text_from_pdf(pdfshareablelinks, keyword):
|
|
| 40 |
if matched:
|
| 41 |
for word in matched:
|
| 42 |
page.add_highlight_annot(word)
|
| 43 |
-
pageNumTextFound = page_num + 1 # 1-indexed
|
| 44 |
|
| 45 |
return pdf_document, pageNumTextFound
|
| 46 |
|
| 47 |
-
#
|
| 48 |
@app.route('/view-pdf', methods=['GET'])
|
| 49 |
def download_pdf():
|
| 50 |
pdf_link = [
|
|
@@ -55,9 +61,7 @@ def download_pdf():
|
|
| 55 |
# Call function to highlight text and get PDF page
|
| 56 |
pdf_content, pageNumTextFound = highlight_text_from_pdf(pdf_link, keyword)
|
| 57 |
|
| 58 |
-
#
|
| 59 |
-
getInfotoMeasure(pageNumTextFound)
|
| 60 |
-
|
| 61 |
pdf_bytes = BytesIO()
|
| 62 |
pdf_content.save(pdf_bytes)
|
| 63 |
pdf_bytes.seek(0)
|
|
|
|
| 5 |
|
| 6 |
app = Flask(__name__)
|
| 7 |
|
| 8 |
+
# Route to render the main page with page number
|
| 9 |
@app.route("/", methods=["GET", "POST"])
|
| 10 |
+
def getInfotoMeasure():
|
| 11 |
+
# Call the function to highlight text and get the page number
|
| 12 |
+
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']
|
| 13 |
+
keyword = "To be read with preliminaries/ general conditions"
|
| 14 |
+
pdf_content, pageNumTextFound = highlight_text_from_pdf(pdf_link, keyword)
|
| 15 |
+
|
| 16 |
+
# Pass pageNumTextFound to the template for rendering
|
| 17 |
+
return render_template("gui.html", page=pageNumTextFound)
|
| 18 |
|
| 19 |
+
# Function to highlight text in PDF and return the page number
|
| 20 |
def highlight_text_from_pdf(pdfshareablelinks, keyword):
|
| 21 |
print('PDF Links:', pdfshareablelinks)
|
| 22 |
for link in pdfshareablelinks:
|
|
|
|
| 27 |
if 'dl=0' in link:
|
| 28 |
link = link.replace('dl=0', 'dl=1')
|
| 29 |
|
| 30 |
+
# Download PDF content from the link
|
| 31 |
response = requests.get(link)
|
| 32 |
if response.status_code == 200:
|
| 33 |
pdf_content = BytesIO(response.content)
|
| 34 |
+
print('Downloaded PDF content.')
|
| 35 |
|
| 36 |
if pdf_content is None:
|
| 37 |
raise ValueError("No valid PDF content found.")
|
|
|
|
| 46 |
if matched:
|
| 47 |
for word in matched:
|
| 48 |
page.add_highlight_annot(word)
|
| 49 |
+
pageNumTextFound = page_num + 1 # 1-indexed
|
| 50 |
|
| 51 |
return pdf_document, pageNumTextFound
|
| 52 |
|
| 53 |
+
# Flask route to serve the highlighted PDF
|
| 54 |
@app.route('/view-pdf', methods=['GET'])
|
| 55 |
def download_pdf():
|
| 56 |
pdf_link = [
|
|
|
|
| 61 |
# Call function to highlight text and get PDF page
|
| 62 |
pdf_content, pageNumTextFound = highlight_text_from_pdf(pdf_link, keyword)
|
| 63 |
|
| 64 |
+
# Create a BytesIO object from the modified PDF content
|
|
|
|
|
|
|
| 65 |
pdf_bytes = BytesIO()
|
| 66 |
pdf_content.save(pdf_bytes)
|
| 67 |
pdf_bytes.seek(0)
|