Download multiple versions of Chrome extension source from crxcavator.io and run a string search on the files.

crxcagrepper.py

# Python 3
# Sometimes hunting for strings in a bunch of different browser extensions and their many versions can be a pain.
# This will call out to crxcavator.io, pull the versions and sources. Then just run a simple string match on it.
# Surprisingly, it works.
#
# sooshie@gmail.com


import requests
import json
import sys
import io
import zipfile


def parse_zip(r, extname, version, search_string):
    raw_data = b''
    for chunk in r.iter_content(chunk_size=128):
        raw_data += chunk
    zipfile_ob = zipfile.ZipFile(io.BytesIO(raw_data))
    for zipinfo in zipfile_ob.infolist():
        with zipfile_ob.open(zipinfo) as thefile:
            filecontent = thefile.read()
            offset = filecontent.find(search_string)
            if offset != -1:
                print('{} - {}'.format(version, zipinfo.filename))
                print('https://crxcavator.io/source/{}/{}?file={}'.format(extname, version, zipinfo.filename))
                print(str(filecontent[offset - 20: offset + len(search_string) + 20]))


def main():
    extension = ''
    versions = []
    report_url = 'https://api.crxcavator.io/v1/report/'
    search_string = None

    try:
        extension = sys.argv[1]
    except:
        print('Please provide an extension ID on the commandline')
        sys.exit(1)

    try:
        search_string = sys.argv[2].encode()
    except:
        print('Please provide a search string on the commandline')
        sys.exit(1)

    r = requests.get(report_url + extension)
    data = json.loads(r.text)
    
    for ext in data:
        versions.append(ext['version'])

    for version in versions:
        r = requests.get('https://extensions.crxcavator.io/{}_{}.zip'.format(extension, version))
        parse_zip(r, extension, version, search_string)


if __name__ == '__main__':
    main()