tempCodeRunnerFile.python

import fitz  # PyMuPDF
import requests
import os
from bs4 import BeautifulSoup

# Function to download a PDF file
def download_pdf(url, folder_path):
    response = requests.get(url)
    filename = os.path.join(folder_path, url.split("/")[-1])
    with open(filename, 'wb') as pdf_file:
        pdf_file.write(response.content)
    print(f"Downloaded: {filename}")

# Function to extract hyperlinks from a PDF
def extract_links_from_pdf(pdf_path):
    links = []
    with fitz.open(pdf_path) as pdf_document:
        for page_number in range(pdf_document.page_count):
            page = pdf_document[page_number]
            annotations = page.get_links()
            for annotation in annotations:
                links.append(annotation.get('uri'))
    return links

# Function to download PDFs from extracted hyperlinks
def download_pdfs_from_links(links, folder_path):
    for link in links:
        if link and link.endswith('.pdf'):
            download_pdf(link, folder_path)

# Specify the path to the PDF file you want to process
pdf_path = r"F:\UCSC\Second Year\First Sem\Group Project\Data Bases\Ticket Fare\main_line.pdf"

# Specify the folder where you want to save the downloaded PDFs
download_folder = r"F:\UCSC\Second Year\First Sem\Group Project\Data Bases\Ticket Fare\Main Line\All PDFs"

# Create the download folder if it doesn't exist
os.makedirs(download_folder, exist_ok=True)

# Extract hyperlinks from the PDF
pdf_links = extract_links_from_pdf(pdf_path)

# Download PDFs from the extracted hyperlinks
download_pdfs_from_links(pdf_links, download_folder)