youtube_dl/extractor/ellentv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .kaltura import KalturaIE
   6 from ..utils import NO_DEFAULT
   7
   8
   9 class EllenTVIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
  11     _TESTS = [{
  12         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
  13         'md5': '4294cf98bc165f218aaa0b89e0fd8042',
  14         'info_dict': {
  15             'id': '0_ipq1gsai',
  16             'ext': 'mov',
  17             'title': 'Fast Fingers of Fate',
  18             'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',
  19             'timestamp': 1428035648,
  20             'upload_date': '20150403',
  21             'uploader_id': 'batchUser',
  22         },
  23     }, {
  24         # not available via http://widgets.ellentube.com/
  25         'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
  26         'info_dict': {
  27             'id': '1_szkgu2m2',
  28             'ext': 'flv',
  29             'title': "Ellen's Amazingly Talented Audience",
  30             'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
  31             'timestamp': 1255140900,
  32             'upload_date': '20091010',
  33             'uploader_id': 'ellenkaltura@gmail.com',
  34         },
  35         'params': {
  36             'skip_download': True,
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
  44
  45         for num, url_ in enumerate(URLS, 1):
  46             webpage = self._download_webpage(
  47                 url_, video_id, fatal=num == len(URLS))
  48
  49             default = NO_DEFAULT if num == len(URLS) else None
  50
  51             partner_id = self._search_regex(
  52                 r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
  53                 default=default)
  54
  55             kaltura_id = self._search_regex(
  56                 [r'id="kaltura_player_([^"]+)"',
  57                  r"_wb_entry_id\s*:\s*'([^']+)",
  58                  r'data-kaltura-entry-id="([^"]+)'],
  59                 webpage, 'kaltura id', default=default)
  60
  61             if partner_id and kaltura_id:
  62                 break
  63
  64         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())
  65
  66
  67 class EllenTVClipsIE(InfoExtractor):
  68     IE_NAME = 'EllenTV:clips'
  69     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  70     _TEST = {
  71         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  72         'info_dict': {
  73             'id': 'meryl-streep-vanessa-hudgens',
  74             'title': 'Meryl Streep, Vanessa Hudgens',
  75         },
  76         'playlist_mincount': 5,
  77     }
  78
  79     def _real_extract(self, url):
  80         playlist_id = self._match_id(url)
  81
  82         webpage = self._download_webpage(url, playlist_id)
  83         playlist = self._extract_playlist(webpage, playlist_id)
  84
  85         return {
  86             '_type': 'playlist',
  87             'id': playlist_id,
  88             'title': self._og_search_title(webpage),
  89             'entries': self._extract_entries(playlist)
  90         }
  91
  92     def _extract_playlist(self, webpage, playlist_id):
  93         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  94         return self._parse_json('[{' + json_string + '}]', playlist_id)
  95
  96     def _extract_entries(self, playlist):
  97         return [
  98             self.url_result(
  99                 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
 100                 KalturaIE.ie_key(), video_id=item['kaltura_entry_id'])
 101             for item in playlist]