Extract hyperlinks from document Leave feedback
On this page
GroupDocs.Parser provides functionality to extract hyperlinks from documents including their text, URL, and position information.
- GroupDocs.Parser for Python via .NET installed
- Sample documents containing hyperlinks
- Basic understanding of hyperlink structure
To extract all hyperlinks from a document:
from groupdocs.parser import Parser
# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
# Check if hyperlink extraction is supported
if not parser.features.hyperlinks:
print("Document doesn't support hyperlink extraction")
else:
# Extract hyperlinks from the document
hyperlinks = parser.get_hyperlinks()
if hyperlinks:
# Iterate over hyperlinks
for hyperlink in hyperlinks:
# Print the hyperlink text
print(f"Text: {hyperlink.text}")
# Print the hyperlink URL
print(f"URL: {hyperlink.url}")
# Print page number
print(f"Page: {hyperlink.page.index + 1}")
print()
else:
print("No hyperlinks found")
The following sample file is used in this example: sample.pdf
Text: harborlane.example
URL: https://harborlane.example/
Page: 1
Text: LinkedIn
URL: https://www.linkedin.com/company/harbor-lane-provisions-example
Page: 1
Text: Instagram
URL: https://www.instagram.com/harborlane.example/
[TRUNCATED]
Expected behavior: Returns a collection of PageHyperlinkArea objects representing all hyperlinks found in the document, or None if hyperlink extraction is not supported.
To extract hyperlinks with detailed position data:
from groupdocs.parser import Parser
# Create an instance of Parser class
with Parser("document.docx") as parser:
# Check if hyperlink extraction is supported
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
else:
# Extract hyperlinks
hyperlinks = parser.get_hyperlinks()
if hyperlinks:
for idx, hyperlink in enumerate(hyperlinks):
print(f"Hyperlink {idx + 1}:")
print(f" Text: {hyperlink.text}")
print(f" URL: {hyperlink.url}")
print(f" Page: {hyperlink.page.index + 1}")
print(f" Position: ({hyperlink.rectangle.left}, {hyperlink.rectangle.top})")
print(f" Size: {hyperlink.rectangle.size.width}x{hyperlink.rectangle.size.height}")
print()
else:
print("No hyperlinks found")
The following sample file is used in this example: document.docx
Hyperlink 1:
Text: supplier quality charter
URL: https://harborlane.example/suppliers/charter
Page: 2
Position: (201.3090057373047, 369.78399658203125)
Size: 100.60499572753906x11.49899959564209
Hyperlink 2:
Text: northwindroasters.example/quality
URL: https://northwindroasters.example/quality
[TRUNCATED]
Expected behavior: Displays comprehensive information about each hyperlink including text, URL, page number, and position coordinates.
To extract hyperlinks and validate URL formats:
from groupdocs.parser import Parser
import re
def is_valid_url(url):
"""
Basic URL validation.
"""
url_pattern = re.compile(
r'^(https?|ftp)://' # Protocol
r'([a-zA-Z0-9.-]+)' # Domain
r'(:[0-9]+)?' # Optional port
r'(/.*)?$' # Optional path
)
return url_pattern.match(url) is not None
# Create an instance of Parser class
with Parser("document.docx") as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
else:
# Extract hyperlinks
hyperlinks = parser.get_hyperlinks()
if hyperlinks:
valid_links = []
invalid_links = []
for hyperlink in hyperlinks:
if is_valid_url(hyperlink.url):
valid_links.append(hyperlink)
else:
invalid_links.append(hyperlink)
print(f"Valid hyperlinks: {len(valid_links)}")
print(f"Invalid hyperlinks: {len(invalid_links)}")
print("\nValid URLs:")
for link in valid_links[:10]: # Show first 10
print(f" {link.text} -> {link.url}")
print("\nOther links (mail addresses and the like):")
for link in invalid_links:
print(f" {link.text} -> {link.url}")
The following sample file is used in this example: document.docx
Valid hyperlinks: 3
Invalid hyperlinks: 1
Valid URLs:
supplier quality charter -> https://harborlane.example/suppliers/charter
northwindroasters.example/quality -> https://northwindroasters.example/quality
harborlane.example/terms -> https://harborlane.example/terms
Other links (mail addresses and the like):
lena.park@harborlane.example -> mailto:lena.park@harborlane.example
Expected behavior: Categorizes hyperlinks into valid and invalid based on URL format validation.
To export hyperlinks to a CSV file:
from groupdocs.parser import Parser
import csv
def export_hyperlinks_to_csv(file_path, output_csv):
"""
Extract hyperlinks and save to CSV file.
"""
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return False
hyperlinks = parser.get_hyperlinks()
if not hyperlinks:
print("No hyperlinks found")
return False
# Write to CSV
with open(output_csv, 'w', newline='', encoding='utf-8') as csvfile:
fieldnames = ['Text', 'URL', 'Page', 'X', 'Y', 'Width', 'Height']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for hyperlink in hyperlinks:
writer.writerow({
'Text': hyperlink.text or '',
'URL': hyperlink.url or '',
'Page': hyperlink.page.index + 1,
'X': hyperlink.rectangle.left,
'Y': hyperlink.rectangle.top,
'Width': hyperlink.rectangle.size.width,
'Height': hyperlink.rectangle.size.height
})
print(f"Hyperlinks exported to {output_csv}")
return True
# Usage
export_hyperlinks_to_csv("document.pdf", "hyperlinks.csv")
The following sample file is used in this example: document.pdf
Text,URL,Page,X,Y,Width,Height
harborlane.example,https://harborlane.example/,1,267.14501953,801.7009887700001,74.71099853999999,11.19900131
LinkedIn,https://www.linkedin.com/company/harbor-lane-provisions-example,1,348.82400513,801.7009887700001,34.24600219000001,11.19900131
Instagram,https://www.instagram.com/harborlane.example/,1,390.03799438,801.7009887700001,39.57000733000001,11.19900131
YouTube,https://www.youtube.com/@harborlane-example,1,436.57598877,801.7009887700001,36.46899414000001,1
[TRUNCATED]
Expected behavior: Creates a CSV file containing all hyperlinks with their properties.
To analyze hyperlink distribution by domain:
from groupdocs.parser import Parser
from urllib.parse import urlparse
from collections import defaultdict
def analyze_hyperlinks_by_domain(file_path):
"""
Group hyperlinks by domain and show statistics.
"""
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return
hyperlinks = parser.get_hyperlinks()
if not hyperlinks:
print("No hyperlinks found")
return
# Group by domain
by_domain = defaultdict(list)
for hyperlink in hyperlinks:
try:
parsed_url = urlparse(hyperlink.url)
domain = parsed_url.netloc or "internal"
by_domain[domain].append(hyperlink)
except:
by_domain["invalid"].append(hyperlink)
# Print statistics
print(f"Total hyperlinks: {sum(len(links) for links in by_domain.values())}")
print(f"Unique domains: {len(by_domain)}\n")
# Sort by count
sorted_domains = sorted(by_domain.items(), key=lambda x: len(x[1]), reverse=True)
print(f"{'Domain':<40} {'Count':<10}")
print("-" * 50)
for domain, links in sorted_domains[:20]: # Top 20
print(f"{domain:<40} {len(links):<10}")
# Usage
analyze_hyperlinks_by_domain("document.docx")
The following sample file is used in this example: document.docx
Total hyperlinks: 4
Unique domains: 3
Domain Count
--------------------------------------------------
harborlane.example 2
northwindroasters.example 1
internal 1
Expected behavior: Provides statistical analysis of hyperlinks grouped by domain.
To extract only specific types of hyperlinks:
from groupdocs.parser import Parser
def extract_filtered_hyperlinks(file_path, url_pattern=None, text_pattern=None):
"""
Extract hyperlinks with optional filtering by URL or text pattern.
"""
import re
with Parser(file_path) as parser:
if not parser.features.hyperlinks:
print("Hyperlink extraction not supported")
return []
hyperlinks = parser.get_hyperlinks()
if not hyperlinks:
return []
filtered_links = []
for hyperlink in hyperlinks:
# Apply URL pattern filter
if url_pattern and not re.search(url_pattern, hyperlink.url, re.IGNORECASE):
continue
# Apply text pattern filter
if text_pattern and hyperlink.text and not re.search(text_pattern, hyperlink.text, re.IGNORECASE):
continue
filtered_links.append(hyperlink)
return filtered_links
# Usage examples
# Extract only the links to one site
site_links = extract_filtered_hyperlinks("document.docx", url_pattern=r'^https://harborlane\.example/')
print(f"Found {len(site_links)} links to harborlane.example")
for link in site_links:
print(f" {link.text} -> {link.url}")
# Extract links whose text mentions "charter"
charter_links = extract_filtered_hyperlinks("document.docx", text_pattern=r'charter')
print(f"Found {len(charter_links)} links about the charter")
# Extract web links (http/https), leaving out mail addresses
web_links = extract_filtered_hyperlinks("document.docx", url_pattern=r'^https?://')
print(f"Found {len(web_links)} web links")
The following sample file is used in this example: document.docx
Found 2 links to harborlane.example
supplier quality charter -> https://harborlane.example/suppliers/charter
harborlane.example/terms -> https://harborlane.example/terms
Found 1 links about the charter
Found 3 web links
Expected behavior: Returns only hyperlinks matching the specified criteria.
To extract hyperlinks from multiple documents:
from groupdocs.parser import Parser
from pathlib import Path
import json
def batch_extract_hyperlinks(input_dir, output_json):
"""
Extract hyperlinks from all documents in a directory.
"""
extensions = ['.pdf', '.docx', '.doc', '.html', '.htm']
all_hyperlinks = {}
for file_path in sorted(Path(input_dir).rglob('*')):
if file_path.suffix.lower() in extensions:
print(f"Processing: {file_path.name}")
try:
with Parser(str(file_path)) as parser:
if not parser.features.hyperlinks:
continue
hyperlinks = parser.get_hyperlinks()
if hyperlinks:
link_list = []
for link in hyperlinks:
link_list.append({
'text': link.text or '',
'url': link.url or '',
'page': link.page.index + 1
})
all_hyperlinks[file_path.name] = {
'count': len(link_list),
'links': link_list
}
except Exception as e:
print(f" Error: {e}")
# Save to JSON
with open(output_json, 'w', encoding='utf-8') as f:
json.dump(all_hyperlinks, f, indent=2, ensure_ascii=False)
total_links = sum(doc['count'] for doc in all_hyperlinks.values())
print(f"\nTotal documents: {len(all_hyperlinks)}")
print(f"Total hyperlinks: {total_links}")
print(f"Saved to {output_json}")
# Usage
batch_extract_hyperlinks("documents", "all_hyperlinks.json")
The following sample files are used in this example: annual-report.pdf, service-agreement.docx
{
"annual-report.pdf": {
"count": 20,
"links": [
{
"text": "harborlane.example",
"url": "https://harborlane.example/",
"page": 1
},
{
[TRUNCATED]
Expected behavior: Processes multiple documents and generates a comprehensive JSON report of all hyperlinks.
- The
get_hyperlinks()method returnsNoneif hyperlink extraction is not supported - Always check
parser.features.hyperlinksbefore extracting hyperlinks - Hyperlinks include both internal (anchors) and external (URLs) links
- The
textproperty contains the visible link text - The
urlproperty contains the actual hyperlink target - Position coordinates are in document-specific units
- Some documents may have hyperlinks without visible text
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.
