Last active
September 8, 2022 05:35
-
-
Save R0X4R/6e7204cd019145b7ac09b40512c3917b to your computer and use it in GitHub Desktop.
Fetch all the links of the stdin links
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Import modules that'll be needed to run this tool | |
import requests | |
from bs4 import BeautifulSoup | |
from re import search | |
from sys import stdin, exit, stdout | |
from time import sleep | |
# Hide insecure request warning error | |
from requests.packages.urllib3.exceptions import InsecureRequestWarning | |
requests.packages.urllib3.disable_warnings(InsecureRequestWarning) | |
# Declaring variable | |
host = stdin.readlines() | |
# Fetch all the urls from the page source-code | |
def pagelinks(): | |
for link in host: | |
try: | |
sleep(1) # Pause for one second | |
header = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"} | |
response = requests.get(str(link.strip()), headers=header, timeout=20, verify=False) | |
soup = BeautifulSoup(response.content, 'html.parser') | |
for line in soup.find_all('a'): | |
if search(str('http'), str(line.get('href'))): | |
stdout.write(str(line.get('href')) + '\n') | |
except requests.Timeout: | |
pass # Handle timeout error | |
except requests.ConnectionError: | |
pass # Handle connection error | |
# Fetch all the urls from the wayback archive | |
def waybacklinks(): | |
for link in host: | |
try: | |
sleep(1) # Pause for one second | |
header = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"} | |
location = 'http://web.archive.org/cdx/search/cdx?url=%s/*&output=txt&fl=original&collapse=urlkey' % link.strip() | |
request = requests.get(location, headers=header, verify=False, timeout=20) | |
response = request.text | |
stdout.write(str(response)) | |
except requests.Timeout: | |
pass # Handle timeout error | |
except requests.ConnectionError: | |
pass # Handle connection error | |
try: | |
pagelinks() # Run pagelinks function | |
waybacklinks() # Run waybacklinks function | |
except KeyboardInterrupt: | |
print("\n[!] CTRL+C, Pressed. Exiting the program") | |
exit(0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment