1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-02 06:57:44 +00:00
youtube-dl/youtube_dl/extractor/tasvideos.py
2020-12-29 21:28:35 -05:00

40 lines
1.1 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
import re
class TASVideosIE(InfoExtractor):
_VALID_URL = r'http://tasvideos.org/(?P<id>\d+M)\.html'
_TEST = {
'url': 'http://tasvideos.org/4352M.html',
'md5': '8dced25a575e853cec5533a887a8dcfc',
'info_dict': {
'id': '4352M',
'ext': 'mkv',
'title': 'C64 L\'Abbaye des Morts',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_urls = re.findall(
r'<a [^>]+(?P<URL>archive\.org\/download[^<]+\.(?:mkv|mp4|avi))[^<]+<\/a>',
webpage)
title = self._search_regex(
r'<span title="Movie[^"]+">(?P<TITLE>[^<]+)<\/span>', webpage,
'title')
formats = []
for url in video_urls:
format_entry = {'url': "http://www." + url}
formats.append(format_entry)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
}