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
# install | |
sudo apt-get install proxychains | |
sudo apt-get install tor | |
# then update the files /etc/proxychains.conf and /etc/tor/torrc with the given config | |
# restart tor server | |
sudo service restart tor |
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 requests | |
import sys | |
import json | |
def waybackurls(host, with_subs): | |
if with_subs: | |
url = 'http://web.archive.org/cdx/search/cdx?url=*.%s/*&output=json&fl=original&collapse=urlkey' % host | |
else: | |
url = 'http://web.archive.org/cdx/search/cdx?url=%s/*&output=json&fl=original&collapse=urlkey' % host |
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 requests | |
import re | |
import sys | |
from multiprocessing.dummy import Pool | |
def robots(host): | |
r = requests.get( | |
'https://web.archive.org/cdx/search/cdx\ | |
?url=%s/robots.txt&output=json&fl=timestamp,original&filter=statuscode:200&collapse=digest' % host) |