youtube_dl/extractor/roosterteeth.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     strip_or_none,
  11     unescapeHTML,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class RoosterTeethIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
  18     _LOGIN_URL = 'https://roosterteeth.com/login'
  19     _NETRC_MACHINE = 'roosterteeth'
  20     _TESTS = [{
  21         'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  22         'md5': 'e2bd7764732d785ef797700a2489f212',
  23         'info_dict': {
  24             'id': '26576',
  25             'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  26             'ext': 'mp4',
  27             'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
  28             'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
  29             'thumbnail': r're:^https?://.*\.png$',
  30             'series': 'Million Dollars, But...',
  31             'episode': 'Million Dollars, But... The Game Announcement',
  32             'comment_count': int,
  33         },
  34     }, {
  35         'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
  45         'only_matching': True,
  46     }, {
  47         # only available for FIRST members
  48         'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
  49         'only_matching': True,
  50     }]
  51
  52     def _login(self):
  53         (username, password) = self._get_login_info()
  54         if username is None:
  55             return
  56
  57         login_page = self._download_webpage(
  58             self._LOGIN_URL, None,
  59             note='Downloading login page',
  60             errnote='Unable to download login page')
  61
  62         login_form = self._hidden_inputs(login_page)
  63
  64         login_form.update({
  65             'username': username,
  66             'password': password,
  67         })
  68
  69         login_request = self._download_webpage(
  70             self._LOGIN_URL, None,
  71             note='Logging in',
  72             data=urlencode_postdata(login_form),
  73             headers={
  74                 'Referer': self._LOGIN_URL,
  75             })
  76
  77         if not any(re.search(p, login_request) for p in (
  78                 r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"',
  79                 r'>Sign Out<')):
  80             error = self._html_search_regex(
  81                 r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>',
  82                 login_request, 'alert', default=None, group='error')
  83             if error:
  84                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  85             raise ExtractorError('Unable to log in')
  86
  87     def _real_initialize(self):
  88         self._login()
  89
  90     def _real_extract(self, url):
  91         display_id = self._match_id(url)
  92
  93         webpage = self._download_webpage(url, display_id)
  94
  95         episode = strip_or_none(unescapeHTML(self._search_regex(
  96             (r'videoTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
  97              r'<title>(?P<title>[^<]+)</title>'), webpage, 'title',
  98             default=None, group='title')))
  99
 100         title = strip_or_none(self._og_search_title(
 101             webpage, default=None)) or episode
 102
 103         m3u8_url = self._search_regex(
 104             r'file\s*:\s*(["\'])(?P<url>http.+?\.m3u8.*?)\1',
 105             webpage, 'm3u8 url', default=None, group='url')
 106
 107         if not m3u8_url:
 108             if re.search(r'<div[^>]+class=["\']non-sponsor', webpage):
 109                 self.raise_login_required(
 110                     '%s is only available for FIRST members' % display_id)
 111
 112             if re.search(r'<div[^>]+class=["\']golive-gate', webpage):
 113                 self.raise_login_required('%s is not available yet' % display_id)
 114
 115             raise ExtractorError('Unable to extract m3u8 URL')
 116
 117         formats = self._extract_m3u8_formats(
 118             m3u8_url, display_id, ext='mp4',
 119             entry_protocol='m3u8_native', m3u8_id='hls')
 120         self._sort_formats(formats)
 121
 122         description = strip_or_none(self._og_search_description(webpage))
 123         thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
 124
 125         series = self._search_regex(
 126             (r'<h2>More ([^<]+)</h2>', r'<a[^>]+>See All ([^<]+) Videos<'),
 127             webpage, 'series', fatal=False)
 128
 129         comment_count = int_or_none(self._search_regex(
 130             r'>Comments \((\d+)\)<', webpage,
 131             'comment count', fatal=False))
 132
 133         video_id = self._search_regex(
 134             (r'containerId\s*=\s*["\']episode-(\d+)\1',
 135              r'<div[^<]+id=["\']episode-(\d+)'), webpage,
 136             'video id', default=display_id)
 137
 138         return {
 139             'id': video_id,
 140             'display_id': display_id,
 141             'title': title,
 142             'description': description,
 143             'thumbnail': thumbnail,
 144             'series': series,
 145             'episode': episode,
 146             'comment_count': comment_count,
 147             'formats': formats,
 148         }