A python3 run to run on MacOS to extract links from a PDF document

extract-links.py

# Requirements
# pip3 install fitz
# pip3 install xlsxwriter
# pip3 install urllib
#
# Run the script
# python3 extract-links.py 

import fitz  # PyMuPDF
import urllib.parse
import re
import xlsxwriter
import requests

def check_link_status(link):
    try:
        response = requests.head(link)
        return response.status_code
    except:
        return 500

def extract_links(pdf_path):
    # Open the PDF file
    pdf = fitz.open(pdf_path)
    links = []

    # Iterate over each page
    for page_num in range(len(pdf)):
        # Get the page
        page = pdf[page_num]
        # Get the list of links in the page
        page_links = page.get_links()

        # Iterate over each link
        for link in page_links:
            # Check if the link is a URI
            if link['kind'] == fitz.LINK_URI:
                # Append the link and page number to the list
                links.append((link['uri'], page_num + 1))

    # Close the PDF file
    pdf.close()
    return links

def write_links_to_file(links, file_path):
    links.sort()
    with open(file_path, 'w') as f:
        for link,page_num in links:
            f.write(link + ' : page ' + str( page_num ) + '\n')

def get_subfolder_count(url):
    subfolder_pattern = r"/[^/]+"
    match = re.findall(subfolder_pattern, url)
    return len(match)

def write_to_excel(worksheet,links):
    row = 0 
    for link,page_num in links:
        worksheet.write(row, 0, link)
        worksheet.write(row, 1, page_num)
        row += 1
    return worksheet

def main():
    pdf_path = 'report.pdf'
    hsph_links_path = 'hsph.txt'
    hsph_top_level_path = 'hsph_top_level.txt'
    hsph_multi_level_path = 'hsph_multi_level.txt'
    other_links_path = 'others.txt'
    broken_path = 'broken.txt'
    redirecting_path = 'redirecting.txt'

    workbook = xlsxwriter.Workbook('links.xlsx')

    summary_worksheet = workbook.add_worksheet('Summary')
    raw_worksheet = workbook.add_worksheet('Raw links')
    hsph_worksheet = workbook.add_worksheet('All Unique HSPH links')
    hsph_top_worksheet = workbook.add_worksheet('Unique HSPH Top links')
    hsph_multi_worksheet = workbook.add_worksheet('Unique HSPH Deep links')
    other_worksheet = workbook.add_worksheet('External')
    redirecting_worksheet = workbook.add_worksheet('Redirections')
    broken_worksheet = workbook.add_worksheet('Broken')

    # Get all links
    links = extract_links(pdf_path)
    print(f"Total links extracted: {len(links)}")
    summary_row = 0
    summary_worksheet.write(summary_row, 0, f"Total links extracted: {len(links)}")
    summary_row+= 1
    write_to_excel(raw_worksheet,links)

    # Extract main website links

    hsph_links = list(set([(link,page_num) for link,page_num in links if 'www.hsph' in link]))
    hsph_top_level_links = []
    hsph_multi_level_links = []

    for link,page_num in hsph_links:
        if get_subfolder_count(link) > 2:
            hsph_multi_level_links.append((link,page_num))
        else:
            hsph_top_level_links.append((link,page_num))

    write_links_to_file(hsph_links, hsph_links_path)
    write_to_excel(hsph_worksheet,hsph_links)
    print(f"Unique HSPH links: {len(hsph_links)}")
    summary_worksheet.write(summary_row, 0, f"Unique HSPH links: {len(hsph_links)}")
    summary_row+= 1

    write_links_to_file(hsph_top_level_links, hsph_top_level_path)
    write_to_excel(hsph_top_worksheet,hsph_top_level_links)
    print(f"Unique HSPH top level links: {len(hsph_top_level_links)}")
    summary_worksheet.write(summary_row, 0, f"Unique HSPH top level links: {len(hsph_top_level_links)}")
    summary_row+= 1

    write_links_to_file(hsph_multi_level_links, hsph_multi_level_path)
    write_to_excel(hsph_multi_worksheet,hsph_multi_level_links)
    print(f"Unique HSPH deep links: {len(hsph_multi_level_links)}")
    summary_worksheet.write(summary_row, 0, f"Unique HSPH deep links: {len(hsph_multi_level_links)}")
    summary_row+= 1

    # Extract other domains links
    other_links = list(set([link for link in links if link not in hsph_links]))
    write_links_to_file(other_links, other_links_path)
    write_to_excel(other_worksheet,other_links)
    summary_worksheet.write(summary_row, 0, f"Unique external links: {len(other_links)}")
    summary_row+= 1
    print(f"Unique external links: {len(other_links)}")

    # Check links

    redirecting_links = []
    broken_links = []

    redirecting_row = 0
    broken_row = 0
    for link,page_num in links:
        code = check_link_status(link)
        if 300 <= code < 400:
            redirecting_links.append((link + ' code: ' +  str(code),page_num))
            redirecting_worksheet.write(redirecting_row, 0, link)
            redirecting_worksheet.write(redirecting_row, 1, str(code))
            redirecting_worksheet.write(redirecting_row, 2, str(page_num))
            redirecting_row+= 1
        if 400 <= code < 500:
            broken_links.append((link + ' code: ' +  str(code),page_num))
            broken_worksheet.write(broken_row, 0, link)
            broken_worksheet.write(broken_row, 1, str(code))
            broken_worksheet.write(broken_row, 2, str(page_num))
            broken_row+= 1
    write_links_to_file(redirecting_links, redirecting_path)
    print(f"Redirecting links: {len(redirecting_links)}")
    summary_worksheet.write(summary_row, 0, f"Redirecting links: {len(redirecting_links)}")
    summary_row+= 1

    write_links_to_file(broken_links, broken_path)
    print(f"Broken links: {len(broken_links)}")
    summary_worksheet.write(summary_row, 0, f"Broken links: {len(broken_links)}")
    summary_row+= 1

    workbook.close() 

if __name__ == "__main__":
    main()

This was mostly written using Claude AI, this is a "quick and dirty" document analysis and is not meant to be production code.