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
# Before the first run, read the comments and change the script for your company | |
# Before anything, install ffuf with `go install github.com/ffuf/ffuf@latest` | |
# Change the WEBROOT variable below to the location of the webroot | |
WEBROOT=/var/www/html/CHANGE/ME | |
# This changes to the webroot directory | |
cd $WEBROOT | |
# This makes a directory for storing the files used for this script. Change it to be whatever path you want. | |
PROJPATH=/home/changeme/project | |
mkdir -p $PROJPATH |
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) |
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 |