_ 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': 'mp4',
  18             'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
  19             'duration': 725.983,
  20         },
  21         'params': {
  22             # Requires ffmpeg (m3u8 manifest)
  23             'skip_download': True,
  24         },
  25     }, {
  26         'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
  27         'only_matching': True,
  28     }, {
  29         'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(url, video_id)
  39         try:
  40             embed_code = self._search_regex(
  41                 r'embedCode=([^&\'"]+)', webpage,
  42                 'ooyala embed code')
  43             ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
  44         except ExtractorError:
  45             raise ExtractorError('The page doesn\'t contain a video', expected=True)
  46         return self.url_result(ooyala_url, ie='Ooyala')
  47
  48
  49 class ViceShowIE(InfoExtractor):
  50     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
  51
  52     _TEST = {
  53         'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
  54         'info_dict': {
  55             'id': 'fuck-thats-delicious-2',
  56             'title': "Fuck, That's Delicious",
  57             'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
  58         },
  59         'playlist_count': 17,
  60     }
  61
  62     def _real_extract(self, url):
  63         show_id = self._match_id(url)
  64         webpage = self._download_webpage(url, show_id)
  65
  66         entries = [
  67             self.url_result(video_url, ViceIE.ie_key())
  68             for video_url, _ in re.findall(
  69                 r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
  70                 % ViceIE._VALID_URL, webpage)]
  71
  72         title = self._search_regex(
  73             r'<title>(.+?)</title>', webpage, 'title', default=None)
  74         if title:
  75             title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
  76         description = self._html_search_meta('description', webpage, 'description')
  77
  78         return self.playlist_result(entries, show_id, title, description)