Last active
May 16, 2022 12:06
-
-
Save dannofx/561d304dceea33335a4ff4f7a3b53f90 to your computer and use it in GitHub Desktop.
Parse a list of links from eztv, extract the magnet links and format the output to use it with transmission-remote
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
#!/usr/bin/env python3 | |
from bs4 import BeautifulSoup | |
import requests | |
import sys | |
def scrap_magnet(url): | |
try: | |
html = requests.get(url) | |
soup = BeautifulSoup(html.text, 'html.parser') | |
tag = soup.find('a', 'downloadLink') | |
magnet_link = tag.get('href') | |
return magnet_link | |
except Exception as e: | |
print ('Error: ' + str(e)) | |
return None | |
if len(sys.argv) == 1: | |
print('Usage :', sys.argv[0], 'file_with_eztv_links additional_tranmission_args') | |
sys.exit(0) | |
content = None | |
with open(sys.argv[1]) as f: | |
content = f.readlines() | |
urls = content = [x.strip() for x in content] | |
magnet_links = [] | |
for url in urls: | |
magnet = scrap_magnet(url) | |
if not magnet is None: | |
magnet_links.append(magnet) | |
additional_transmission_args = '' | |
if len(sys.argv) > 2: | |
additional_transmission_args = sys.argv[2] | |
if len(magnet_links) > 0: | |
for magnet_link in magnet_links: | |
result = 'transmission-remote {0} --add "{1}"'.format(additional_transmission_args, magnet_link) | |
print(result) | |
else: | |
print('No links found') | |
sys.exit(1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
You can do
soup.find('a', href = re.compile(r'magnet.*'))
to extract magnet links only.