youtube_dl/extractor/ellentv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     parse_iso8601,
  10 )
  11
  12
  13 class EllenTVIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
  15     _TEST = {
  16         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
  17         'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
  18         'info_dict': {
  19             'id': '0_ipq1gsai',
  20             'ext': 'mp4',
  21             'title': 'Fast Fingers of Fate',
  22             'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
  23             'timestamp': 1428035648,
  24             'upload_date': '20150403',
  25             'uploader_id': 'batchUser',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(
  33             'http://widgets.ellentube.com/videos/%s' % video_id,
  34             video_id)
  35
  36         partner_id = self._search_regex(
  37             r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
  38
  39         kaltura_id = self._search_regex(
  40             [r'id="kaltura_player_([^"]+)"',
  41              r"_wb_entry_id\s*:\s*'([^']+)",
  42              r'data-kaltura-entry-id="([^"]+)'],
  43             webpage, 'kaltura id')
  44
  45         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
  46
  47
  48 class EllenTVClipsIE(InfoExtractor):
  49     IE_NAME = 'EllenTV:clips'
  50     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  51     _TEST = {
  52         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  53         'info_dict': {
  54             'id': 'meryl-streep-vanessa-hudgens',
  55             'title': 'Meryl Streep, Vanessa Hudgens',
  56         },
  57         'playlist_mincount': 9,
  58     }
  59
  60     def _real_extract(self, url):
  61         playlist_id = self._match_id(url)
  62
  63         webpage = self._download_webpage(url, playlist_id)
  64         playlist = self._extract_playlist(webpage)
  65
  66         return {
  67             '_type': 'playlist',
  68             'id': playlist_id,
  69             'title': self._og_search_title(webpage),
  70             'entries': self._extract_entries(playlist)
  71         }
  72
  73     def _extract_playlist(self, webpage):
  74         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  75         try:
  76             return json.loads("[{" + json_string + "}]")
  77         except ValueError as ve:
  78             raise ExtractorError('Failed to download JSON', cause=ve)
  79
  80     def _extract_entries(self, playlist):
  81         return [self.url_result(item['url'], 'EllenTV') for item in playlist]