Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vice.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class ViceIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
  11
  12     _TESTS = [{
  13         'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
  14         'md5': 'e9d77741f9e42ba583e683cd170660f7',
  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         'add_ie': ['Ooyala'],
  22     }, {
  23         'url': 'http://www.vice.com/video/how-to-hack-a-car',
  24         'md5': '6fb2989a3fed069fb8eab3401fc2d3c9',
  25         'info_dict': {
  26             'id': '3jstaBeXgAs',
  27             'ext': 'mp4',
  28             'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
  29             'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
  30             'uploader_id': 'MotherboardTV',
  31             'uploader': 'Motherboard',
  32             'upload_date': '20140529',
  33         },
  34         'add_ie': ['Youtube'],
  35     }, {
  36         'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
  40         'only_matching': True,
  41     }, {
  42         'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48         webpage = self._download_webpage(url, video_id)
  49         try:
  50             embed_code = self._search_regex(
  51                 r'embedCode=([^&\'"]+)', webpage,
  52                 'ooyala embed code', default=None)
  53             if embed_code:
  54                 return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
  55             youtube_id = self._search_regex(
  56                 r'data-youtube-id="([^"]+)"', webpage, 'youtube id')
  57             return self.url_result(youtube_id, 'Youtube')
  58         except ExtractorError:
  59             raise ExtractorError('The page doesn\'t contain a video', expected=True)
  60
  61
  62 class ViceShowIE(InfoExtractor):
  63     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
  64
  65     _TEST = {
  66         'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2',
  67         'info_dict': {
  68             'id': 'fuck-thats-delicious-2',
  69             'title': "Fuck, That's Delicious",
  70             'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.',
  71         },
  72         'playlist_count': 17,
  73     }
  74
  75     def _real_extract(self, url):
  76         show_id = self._match_id(url)
  77         webpage = self._download_webpage(url, show_id)
  78
  79         entries = [
  80             self.url_result(video_url, ViceIE.ie_key())
  81             for video_url, _ in re.findall(
  82                 r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"'
  83                 % ViceIE._VALID_URL, webpage)]
  84
  85         title = self._search_regex(
  86             r'<title>(.+?)</title>', webpage, 'title', default=None)
  87         if title:
  88             title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
  89         description = self._html_search_meta('description', webpage, 'description')
  90
  91         return self.playlist_result(entries, show_id, title, description)