AIL/ail-framework
7
0
Fork 0
mirror of https://github.com/ail-project/ail-framework.git synced 2024-11-26 07:47:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chg: [crawler] crawl list urls: filter duplicates
Some checks are pending
CI / ail_test (3.10) (push) Waiting to run
Details
CI / ail_test (3.7) (push) Waiting to run
Details
CI / ail_test (3.8) (push) Waiting to run
Details
CI / ail_test (3.9) (push) Waiting to run
Details

Browse source
This commit is contained in:
terrtia 2024-10-09 15:37:37 +02:00
parent 1505bf0157
commit 72f4733242
No known key found for this signature in database
GPG key ID: 1E1B1F50D84613D0
1 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
bin/lib/crawlers.py
View file

@ -187,12 +187,18 @@ def unpack_url(url):
# TODO options to only extract domains # TODO options to only extract domains
# TODO extract onions # TODO extract onions
def extract_url_from_text(content): def extract_url_from_text(content):
urls = [] urls = set()
r_url = r"(?:(?:https?|ftp):\/\/)?(?:\S+(?::\S*)?@)?(?:\[(?:(?:[A-Fa-f0-9]{1,4}:){7}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,4}:){1,7}:|(?:[A-Fa-f0-9]{1,4}:){1,6}:[A-Fa-f0-9]{1,4}|::(?:[A-Fa-f0-9]{1,4}:){0,5}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,4}:){1,5}::(?:[A-Fa-f0-9]{1,4})?|(?:[A-Fa-f0-9]{1,4}:){1,4}::(?:[A-Fa-f0-9]{1,4}:){0,1}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,3}:){1}::(?:[A-Fa-f0-9]{1,4}:){0,2}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,2}:){1}::(?:[A-Fa-f0-9]{1,4}:){0,3}[A-Fa-f0-9]{1,4}|[A-Fa-f0-9]{1,4}::(?:[A-Fa-f0-9]{1,4}:){0,4}[A-Fa-f0-9]{1,4}|::(?:[A-Fa-f0-9]{1,4}:){0,5}[A-Fa-f0-9]{1,4}|fe80:(?:[A-Fa-f0-9]{0,4}:){0,4}%[0-9a-zA-Z]{1,}|::(?:ffff(?::0{1,4}){0,1}:){0,1}(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9])?[0-9])\.){3}(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9])?[0-9]))\]|(?:(?:25[0-5]|2[0-4]\d|1\d\d|\d{1,2})\.){3}(?:25[0-5]|2[0-4]\d|1\d\d|\d{1,2})|(?:(?:[a-zA-Z0-9\-]+\.)+[a-zA-Z]{2,}))(?::\d{2,5})?(?:\/[^\s]*)?" r_url = r"(?:(?:https?|ftp):\/\/)?(?:\S+(?::\S*)?@)?(?:\[(?:(?:[A-Fa-f0-9]{1,4}:){7}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,4}:){1,7}:|(?:[A-Fa-f0-9]{1,4}:){1,6}:[A-Fa-f0-9]{1,4}|::(?:[A-Fa-f0-9]{1,4}:){0,5}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,4}:){1,5}::(?:[A-Fa-f0-9]{1,4})?|(?:[A-Fa-f0-9]{1,4}:){1,4}::(?:[A-Fa-f0-9]{1,4}:){0,1}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,3}:){1}::(?:[A-Fa-f0-9]{1,4}:){0,2}[A-Fa-f0-9]{1,4}|(?:[A-Fa-f0-9]{1,2}:){1}::(?:[A-Fa-f0-9]{1,4}:){0,3}[A-Fa-f0-9]{1,4}|[A-Fa-f0-9]{1,4}::(?:[A-Fa-f0-9]{1,4}:){0,4}[A-Fa-f0-9]{1,4}|::(?:[A-Fa-f0-9]{1,4}:){0,5}[A-Fa-f0-9]{1,4}|fe80:(?:[A-Fa-f0-9]{0,4}:){0,4}%[0-9a-zA-Z]{1,}|::(?:ffff(?::0{1,4}){0,1}:){0,1}(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9])?[0-9])\.){3}(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9])?[0-9]))\]|(?:(?:25[0-5]|2[0-4]\d|1\d\d|\d{1,2})\.){3}(?:25[0-5]|2[0-4]\d|1\d\d|\d{1,2})|(?:(?:[a-zA-Z0-9\-]+\.)+[a-zA-Z]{2,}))(?::\d{2,5})?(?:\/[^\s]*)?"
for url in regex_findall('extract_url_from_text', gen_uuid(), r_url, 'user_id', content, max_time=10): for url in regex_findall('extract_url_from_text', gen_uuid(), r_url, 'user_id', content, max_time=10):
urls.append(url) if url.startswith('http://'):
if url in urls:
continue
elif not url.startswith('https://'):
if f'http://{url}' in urls:
continue
urls.add(url)
# check if onions # check if onions
return urls return list(urls)
# extract onions # extract onions
# extract IP # extract IP