yt-dlp/youtube_dl/extractor/criterion.py

42 lines
1.2 KiB
Python
Raw Normal View History

2013-07-13 00:17:48 -04:00
# -*- coding: utf-8 -*-
2014-07-11 07:21:32 -04:00
from __future__ import unicode_literals
2013-07-13 00:17:48 -04:00
import re
from .common import InfoExtractor
2014-07-11 07:21:32 -04:00
2013-07-13 00:17:48 -04:00
class CriterionIE(InfoExtractor):
2014-07-11 07:21:32 -04:00
_VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
2013-07-13 00:18:03 -04:00
_TEST = {
2014-07-11 07:21:32 -04:00
'url': 'http://www.criterion.com/films/184-le-samourai',
'md5': 'bc51beba55685509883a9a7830919ec3',
'info_dict': {
'id': '184',
'ext': 'mp4',
'title': 'Le Samouraï',
'description': '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)
2014-07-11 07:21:32 -04:00
video_id = mobj.group('id')
2013-07-13 00:17:48 -04:00
webpage = self._download_webpage(url, video_id)
2014-07-11 07:21:32 -04:00
final_url = self._search_regex(
r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage)
2015-10-14 09:13:53 -04:00
description = self._html_search_meta('description', webpage)
2014-07-11 07:21:32 -04:00
thumbnail = self._search_regex(
r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
2013-07-13 00:17:48 -04:00
2014-07-11 07:21:32 -04:00
return {
'id': video_id,
'url': final_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}