A simple Tor-wrapped (onion) .pdf web extractor written in Python. Works on Python 2 and Python 3.

PDF_ExtractTor.py

#!/bin/python

import os
import sys
import urllib
import requests
from bs4 import BeautifulSoup

# A simple Tor-wrapped (onion) .pdf web extractor written in Python. Works on Python 2 and Python 3.

proxies = {
    'http': "socks5h://localhost:9050",
    'https': "socks5h://localhost:9050"
}

if __name__ == "__main__":
	if len(sys.argv) == 3:
		if os.path.exists(sys.argv[2]):
			resp = requests.get(sys.argv[1], proxies=proxies).content
			soup = BeautifulSoup(resp, 'html.parser')
			
			for link in soup.find_all('a', href=True):
				print(link['href'][-4:])
				if link['href'][-4:] == ".pdf":
					file_ = "".join([sys.argv[1], link['href']])
					
					try:
						file_ = urllib.parse.unquote(file_)
					except:
						file_ = urllib.unquote(file_)
					
					print("Downloading... ", file_)
					
					data = requests.get(file_, proxies=proxies).content
					
					filename = "{0}/{1}".format(sys.argv[2].replace(os.sep,""),file_.split("/")[-1])
					
					with open(filename, "wb") as f:
						f.write(data)
					
					print("Downloaded! ", file_)
	else:
		print("./{0} <oniondir> <path>".format(sys.argv[0]))