_ Git - youtube-dl/blob - youtube_dl/extractor/vice.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .ooyala import OoyalaIE
   7 from ..utils import ExtractorError
   8
   9
  10 class ViceIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
  12
  13     _TESTS = [{
  14         'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
  15         'info_dict': {
  16             'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
  17             'ext': 'flv',
  18             'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
  19             'duration': 725.983,
  20         },
  21     }, {
  22         'url': 'http://www.vice.com/video/how-to-hack-a-car',
  23         'md5': '6fb2989a3fed069fb8eab3401fc2d3c9',
  24         'info_dict': {
  25             'id': '3jstaBeXgAs',
  26             'ext': 'mp4',
  27             'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
  28             'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
  29             'uploader_id': 'MotherboardTV',
  30             'uploader': 'Motherboard',
  31             'upload_date': '20140529',
  32         },
  33     }, {
  34         'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         webpage = self._download_webpage(url, video_id)
  47         try:
  48             embed_code = self._search_regex(
  49                 r'embedCode=([^&\'"]+)', webpage,
  50                 'ooyala embed code', default=None)
  51             if embed_code:
  52                 ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
  53                 return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
  54             youtube_id = self._search_regex(
  55                 r'data-youtube-id="([^"]+)"', webpage, 'youtube id')
  56             return self.url_result(youtube_id, 'Youtube')
  57         except ExtractorError:
  58             raise ExtractorError('The page doesn\'t contain a video', expected=True)
  59
  60
  61 class ViceShowIE(InfoExtractor):
  62     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
  63
  64     _TEST = {
  65         'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
  66         'info_dict': {
  67             'id': 'fuck-thats-delicious-2',
  68             'title': "Fuck, That's Delicious",
  69             'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
  70         },
  71         'playlist_count': 17,
  72     }
  73
  74     def _real_extract(self, url):
  75         show_id = self._match_id(url)
  76         webpage = self._download_webpage(url, show_id)
  77
  78         entries = [
  79             self.url_result(video_url, ViceIE.ie_key())
  80             for video_url, _ in re.findall(
  81                 r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
  82                 % ViceIE._VALID_URL, webpage)]
  83
  84         title = self._search_regex(
  85             r'<title>(.+?)</title>', webpage, 'title', default=None)
  86         if title:
  87             title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
  88         description = self._html_search_meta('description', webpage, 'description')
  89
  90         return self.playlist_result(entries, show_id, title, description)