youtube_dl/extractor/roosterteeth.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     urlencode_postdata,
   8 )
   9
  10
  11 class RoosterTeethIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
  13     _LOGIN_URL = 'https://roosterteeth.com/login'
  14     _NETRC_MACHINE = 'roosterteeth'
  15     _TESTS = [{
  16         'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  17         'info_dict': {
  18             'id': '26576',
  19             'ext': 'mp4',
  20             'title': 'Million Dollars, But... The Game Announcement',
  21             'thumbnail': 're:^https?://.*\.png$',
  22             'description': 'Introducing Million Dollars, But... The Game! Available for pre-order now at www.MDBGame.com ',
  23             'creator': 'Rooster Teeth',
  24             'series': 'Million Dollars, But...',
  25             'episode': 'Million Dollars, But... The Game Announcement',
  26             'episode_id': '26576',
  27         },
  28         'params': {
  29             'skip_download': True,  # m3u8 downloads
  30         },
  31     }, {
  32         'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
  33         'only_matching': True,
  34     }, {
  35         'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
  42         'only_matching': True,
  43     }]
  44
  45     def _login(self):
  46         (username, password) = self._get_login_info()
  47         if username is None or password is None:
  48             return False
  49
  50         # token is required to authenticate request
  51         login_page = self._download_webpage(self._LOGIN_URL, None, 'Getting login token', 'Unable to get login token')
  52
  53         login_form = self._hidden_inputs(login_page)
  54         login_form.update({
  55             'username': username,
  56             'password': password,
  57         })
  58         login_payload = urlencode_postdata(login_form)
  59
  60         # required for proper responses
  61         login_headers = {
  62             'Referer': self._LOGIN_URL,
  63         }
  64
  65         login_request = self._download_webpage(
  66             self._LOGIN_URL, None,
  67             note='Logging in as %s' % username,
  68             data=login_payload,
  69             headers=login_headers)
  70
  71         if 'Authentication failed' in login_request:
  72             raise ExtractorError(
  73                 'Login failed (invalid username/password)', expected=True)
  74
  75     def _real_initialize(self):
  76         self._login()
  77
  78     def _real_extract(self, url):
  79         match_id = self._match_id(url)
  80         webpage = self._download_webpage(url, match_id)
  81
  82         episode_id = self._html_search_regex(r"commentControls\('#comment-([0-9]+)'\)", webpage, 'episode id', match_id, False)
  83
  84         self.report_extraction(episode_id)
  85
  86         title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', self._og_search_title(webpage), False)
  87         thumbnail = self._og_search_thumbnail(webpage)
  88         description = self._og_search_description(webpage)
  89         creator = self._html_search_regex(r'<h3>Latest (.+) Gear</h3>', webpage, 'site', 'Rooster Teeth', False)
  90         series = self._html_search_regex(r'<h2>More ([^<]+)</h2>', webpage, 'series', fatal=False)
  91         episode = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', fatal=False)
  92
  93         if '<div class="non-sponsor">' in webpage:
  94             self.raise_login_required('%s is only available for FIRST members' % title)
  95
  96         if '<div class="golive-gate">' in webpage:
  97             self.raise_login_required('%s is not available yet' % title)
  98
  99         formats = self._extract_m3u8_formats(self._html_search_regex(r"file: '(.+?)m3u8'", webpage, 'm3u8 url') + 'm3u8', episode_id, ext='mp4')
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': episode_id,
 104             'title': title,
 105             'formats': formats,
 106             'thumbnail': thumbnail,
 107             'description': description,
 108             'creator': creator,
 109             'series': series,
 110             'episode': episode,
 111             'episode_id': episode_id,
 112         }