Created
October 1, 2023 16:47
-
-
Save raisinbl/90e5ad1674af7817e3b68ee902d3a5da to your computer and use it in GitHub Desktop.
This file contains hidden or 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
#! /opt/miniconda3/bin/python | |
import requests | |
from bs4 import BeautifulSoup | |
tiengruoi = requests.get('https://bit.ly/tiengruoi') | |
soup = BeautifulSoup(tiengruoi.text, 'html.parser') | |
# Find all elements with class "cl_item" | |
cl_items = soup.find_all(class_="cl_item") | |
urls = [cl_item.find('a').get('href') for cl_item in cl_items][:-2] | |
# extract domain name | |
domains = [url.split('/')[2] for url in urls] | |
domain1 = "" | |
for domain in domains: | |
domain1 += '.'.join(domain.split('.')[1:])+',' | |
# load video | |
domain1 += "player.4shares.live" | |
# filter elements | |
elements = [".box-host.box", | |
".vebo-sp.container", | |
".mc_padding", | |
".to-left",".to-right", | |
".for-desktop.ft-box", | |
".jw-icon.jw-button-image.jw-button-color.jw-reset"] | |
filter_elements = [domain1 + "##" + element for element in elements] | |
# filter gif banner | |
domain2 = domain1.replace(",","|") | |
filter_gif_banner = "i.imgur.com/*.gif$image,domain="+domain2 | |
# filter | |
filter = ["! [SYNTAX] https://help.adblockplus.org/hc/en-us/articles/360062733293", | |
"||photo2.tinhte.vn/data/attachment-files/$image", | |
"no-large-media: behind-the-scene false"] +\ | |
filter_elements + [filter_gif_banner] | |
filter = "\n".join(filter) | |
# write to file | |
with open('tiengruoi-filter.txt', 'w') as f: | |
f.write(filter) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment