2021-07-21 01:12:26 +00:00
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
from flask import *
|
|
|
|
from urllib.parse import urlparse
|
2021-08-04 15:35:10 +00:00
|
|
|
from files.classes import BannedDomain
|
2021-09-17 08:34:36 +00:00
|
|
|
from sqlalchemy.orm import lazyload
|
2021-07-21 01:12:26 +00:00
|
|
|
|
|
|
|
def filter_comment_html(html_text):
|
|
|
|
|
|
|
|
soup = BeautifulSoup(html_text, features="html.parser")
|
|
|
|
|
|
|
|
links = soup.find_all("a")
|
|
|
|
|
|
|
|
domain_list = set()
|
|
|
|
|
|
|
|
for link in links:
|
|
|
|
|
|
|
|
href=link.get("href", None)
|
|
|
|
if not href:
|
|
|
|
continue
|
|
|
|
|
|
|
|
domain = urlparse(href).netloc
|
|
|
|
|
|
|
|
# parse domain into all possible subdomains
|
|
|
|
parts = domain.split(".")
|
|
|
|
for i in range(len(parts)):
|
|
|
|
new_domain = parts[i]
|
|
|
|
for j in range(i + 1, len(parts)):
|
|
|
|
new_domain += "." + parts[j]
|
|
|
|
|
|
|
|
domain_list.add(new_domain)
|
|
|
|
|
|
|
|
# search db for domain rules that prohibit commenting
|
2021-09-17 12:22:10 +00:00
|
|
|
bans = [x for x in g.db.query(BannedDomain).options(lazyload('*')).filter(BannedDomain.domain.in_(list(domain_list))).all()]
|
2021-07-21 01:12:26 +00:00
|
|
|
|
|
|
|
if bans:
|
|
|
|
return bans
|
|
|
|
else:
|
|
|
|
return []
|