yt-dlp/youtube_dl/extractor/criterion.py

41 lines
1.5 KiB
Python
Raw Normal View History

2013-07-13 00:17:48 -04:00
# -*- coding: utf-8 -*-
import re
from .common import InfoExtractor
from ..utils import determine_ext
2013-07-13 00:17:48 -04:00
class CriterionIE(InfoExtractor):
_VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
2013-07-13 00:18:03 -04:00
_TEST = {
u'url': u'http://www.criterion.com/films/184-le-samourai',
u'file': u'184.mp4',
u'md5': u'bc51beba55685509883a9a7830919ec3',
u'info_dict': {
u"title": u"Le Samouraï",
u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
2013-07-13 00:18:03 -04:00
}
}
2013-07-13 00:17:48 -04:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
2013-07-13 00:17:48 -04:00
webpage = self._download_webpage(url, video_id)
final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
webpage, 'video url')
title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
2013-07-13 00:17:48 -04:00
webpage, 'video title')
description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
2013-07-13 00:17:48 -04:00
webpage, 'video description')
thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
return {'id': video_id,
'url' : final_url,
'title': title,
'ext': determine_ext(final_url),
2013-07-13 00:17:48 -04:00
'description': description,
'thumbnail': thumbnail,
}