Extract hyperlinks from document page area Leave feedback
On this page
GroupDocs.Parser allows extracting hyperlinks from specific rectangular areas of document pages, enabling precise link extraction from defined regions.
- GroupDocs.Parser for Python via .NET installed
- Sample documents with hyperlinks
- Understanding of coordinate systems
To extract hyperlinks from a specific rectangular area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
# Create an instance of Parser class
with Parser("./document.pdf") as parser:
# Check if hyperlink extraction is supported
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
else:
# Define the area (upper portion, 600x200 pixels)
area = Rectangle(Point(0, 0), Size(600, 200))
# Create options for the area
options = PageAreaOptions(area)
# Extract hyperlinks from the specified area
hyperlinks = parser.get_hyperlinks(options)
if hyperlinks:
print("Hyperlinks found in area:")
for link in hyperlinks:
print(f" {link.text} -> {link.url}")
else:
print("No hyperlinks found in the specified area")
The following sample file is used in this example: document.pdf
Hyperlinks found in area:
Investor relations -> https://harborlane.example/investors
Expected behavior: Returns only hyperlinks located within the specified rectangular area.
To extract hyperlinks from an area on a specific page:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
# Create an instance of Parser class
with Parser("document.pdf") as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
else:
# Define area (sidebar region)
area = Rectangle(Point(400, 0), Size(200, 800))
options = PageAreaOptions(area)
# Get document info
info = parser.get_document_info()
# Process first page
page_index = 0
if page_index < info.page_count:
# Extract hyperlinks from area on specific page
hyperlinks = parser.get_hyperlinks(page_index, options)
if hyperlinks:
print(f"Hyperlinks in sidebar (page {page_index + 1}):")
for link in hyperlinks:
print(f" {link.text}: {link.url}")
else:
print(f"No hyperlinks in sidebar (page {page_index + 1})")
The following sample file is used in this example: document.pdf
Hyperlinks in sidebar (page 1):
Investor relations: https://harborlane.example/investors
Expected behavior: Extracts hyperlinks from a specific area on a specific page.
To extract navigation links from the header area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
def extract_header_links(file_path):
"""
Extract navigation links from document header.
"""
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return []
# Define header area (top 100 pixels, full width)
header_area = Rectangle(Point(0, 0), Size(1000, 100))
options = PageAreaOptions(header_area)
# Extract hyperlinks from header
hyperlinks = parser.get_hyperlinks(options)
if hyperlinks:
links = []
for link in hyperlinks:
links.append({
'text': link.text or 'No text',
'url': link.url or ''
})
return links
return []
# Usage
nav_links = extract_header_links("document.pdf")
print(f"Navigation links ({len(nav_links)}):")
for link in nav_links:
print(f" {link['text']} -> {link['url']}")
The following sample file is used in this example: document.pdf
Navigation links (1):
Investor relations -> https://harborlane.example/investors
Expected behavior: Extracts navigation or menu links typically found in document headers.
To extract hyperlinks from several predefined areas:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
def extract_links_from_regions(file_path, regions):
"""
Extract hyperlinks from multiple regions.
Args:
file_path: Path to document
regions: Dict of region names to (x, y, width, height) tuples
"""
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return {}
results = {}
for region_name, (x, y, w, h) in regions.items():
# Create rectangle for this region
area = Rectangle(Point(x, y), Size(w, h))
options = PageAreaOptions(area)
# Extract hyperlinks from this region
hyperlinks = parser.get_hyperlinks(options)
if hyperlinks:
results[region_name] = [link.url for link in hyperlinks]
else:
results[region_name] = []
return results
# Define regions
regions = {
'header': (0, 0, 600, 100),
'body': (0, 100, 600, 650),
'footer': (0, 780, 600, 62)
}
# Extract links from regions
links_by_region = extract_links_from_regions("document.pdf", regions)
for region, urls in links_by_region.items():
print(f"{region.upper()}: {len(urls)} links")
for url in urls[:5]: # Show first 5
print(f" - {url}")
The following sample file is used in this example: document.pdf
HEADER: 1 links
- https://harborlane.example/investors
BODY: 3 links
- https://harborlane.example/investors/2025
- https://harborlane.example/suppliers/charter
- https://harborlane.example/catalog
FOOTER: 16 links
- https://harborlane.example/
- https://www.linkedin.com/company/harbor-lane-provisions-example
- https://www.instagram.com/harborlane.example/
[TRUNCATED]
Expected behavior: Extracts and categorizes hyperlinks by document region.
To extract links from the footer area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
def extract_footer_links(file_path, page_height=842):
"""
Extract links from document footer.
Args:
file_path: Path to document
page_height: Approximate page height in points (default: A4 = 842)
"""
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return []
# Define footer area (bottom 100 pixels)
footer_y = page_height - 100
footer_area = Rectangle(Point(0, footer_y), Size(600, 100))
options = PageAreaOptions(footer_area)
# Extract hyperlinks from footer
hyperlinks = parser.get_hyperlinks(options)
if hyperlinks:
links = []
for link in hyperlinks:
links.append({
'text': link.text or '',
'url': link.url or '',
'position': (link.rectangle.left, link.rectangle.top)
})
return links
return []
# Usage
footer_links = extract_footer_links("document.pdf")
print(f"Footer links: {len(footer_links)}")
for link in footer_links:
print(f"{link['text']}: {link['url']}")
The following sample file is used in this example: document.pdf
Footer links: 16
harborlane.example: https://harborlane.example/
LinkedIn: https://www.linkedin.com/company/harbor-lane-provisions-example
Instagram: https://www.instagram.com/harborlane.example/
YouTube: https://www.youtube.com/@harborlane-example
harborlane.example: https://harborlane.example/
LinkedIn: https://www.linkedin.com/company/harbor-lane-provisions-example
Instagram: https://www.instagram.com/harborlane.example/
YouTube: https://www.youtube.com/@harborlane-example
harborlane.example:
[TRUNCATED]
Expected behavior: Extracts links commonly found in document footers (e.g., copyright, contact, social media).
To extract links from an area matching a URL pattern:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
import re
def extract_links_by_area_and_pattern(file_path, area_rect, url_pattern):
"""
Extract links from area matching URL pattern.
Args:
file_path: Path to document
area_rect: Tuple (x, y, width, height)
url_pattern: Regex pattern for URLs
"""
x, y, w, h = area_rect
area = Rectangle(Point(x, y), Size(w, h))
options = PageAreaOptions(area)
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return []
hyperlinks = parser.get_hyperlinks(options)
if not hyperlinks:
return []
# Filter by URL pattern
matching_links = []
pattern = re.compile(url_pattern, re.IGNORECASE)
for link in hyperlinks:
if link.url and pattern.search(link.url):
matching_links.append({
'text': link.text,
'url': link.url
})
return matching_links
# Usage - extract the investor and supplier links from the page body
body_area = (0, 100, 600, 650)
section_links = extract_links_by_area_and_pattern(
"document.pdf",
body_area,
r'/(investors|suppliers)/'
)
print(f"Investor and supplier links in the body: {len(section_links)}\n")
for link in section_links:
print(f" {link['text']}: {link['url']}")
The following sample file is used in this example: document.pdf
Investor and supplier links in the body: 2
harborlane.example/investors/2025: https://harborlane.example/investors/2025
harborlane.example/suppliers/charter: https://harborlane.example/suppliers/charter
Expected behavior: Extracts only links from the specified area that match the URL pattern.
To extract social media links from a defined region:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
def extract_social_media_links(file_path, area_rect):
"""
Extract social media links from a specific area.
"""
x, y, w, h = area_rect
area = Rectangle(Point(x, y), Size(w, h))
options = PageAreaOptions(area)
# Social media domains
social_domains = [
'facebook.com', 'twitter.com', 'linkedin.com',
'instagram.com', 'youtube.com', 'tiktok.com'
]
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return {}
hyperlinks = parser.get_hyperlinks(options)
if not hyperlinks:
return {}
# Categorize by platform
social_links = {}
for link in hyperlinks:
if link.url:
for domain in social_domains:
if domain in link.url:
platform = domain.split('.')[0].capitalize()
urls = social_links.setdefault(platform, [])
if link.url not in urls: # the footer repeats on every page
urls.append(link.url)
break
return social_links
# Usage - extract from the footer area of an A4 page
footer_area = (0, 780, 600, 62)
social_links = extract_social_media_links("document.pdf", footer_area)
print("Social Media Links:")
for platform, urls in social_links.items():
print(f" {platform}: {', '.join(urls)}")
if not social_links:
print(" none in this area")
The following sample file is used in this example: document.pdf
Social Media Links:
Linkedin: https://www.linkedin.com/company/harbor-lane-provisions-example
Instagram: https://www.instagram.com/harborlane.example/
Youtube: https://www.youtube.com/@harborlane-example
Expected behavior: Extracts and categorizes social media links from a specific area.
- Coordinates are in document-specific units (points or pixels)
- The origin (0, 0) is at the top-left corner
- Hyperlinks partially overlapping the area boundary are included
- Use
get_hyperlinks(page_index, options)for page-specific area extraction - Empty collections are returned if no hyperlinks are found (not
None) - Combine with page index for precise multi-page area extraction
Was this page helpful?
Any additional feedback you'd like to share with us?
Please tell us how we can improve this page.
Thank you for your feedback!
We value your opinion. Your feedback will help us improve our documentation.
