_ Git - youtube-dl/blob - 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     _TESTS = [{
  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': 'md5:686114ced0a032926935e9015ee794ac',
  23             'timestamp': 1428033600,
  24             'upload_date': '20150403',
  25         }
  26     }, {
  27         'url': 'http://ellentube.com/videos/0-dvzmabd5/',
  28         'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
  29         'info_dict': {
  30             'id': '0-dvzmabd5',
  31             'ext': 'mp4',
  32             'title': '1 year old twin sister makes her brother laugh',
  33             'description': '1 year old twin sister makes her brother laugh',
  34             'timestamp': 1419542075,
  35             'upload_date': '20141225',
  36         }
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(
  43             'http://widgets.ellentube.com/videos/%s' % video_id,
  44             video_id)
  45
  46         partner_id = self._search_regex(
  47             r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
  48
  49         kaltura_id = self._search_regex(
  50             [r'id="kaltura_player_([^"]+)"',
  51              r"_wb_entry_id\s*:\s*'([^']+)",
  52              r'data-kaltura-entry-id="([^"]+)'],
  53             webpage, 'kaltura id')
  54
  55         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
  56
  57
  58 class EllenTVClipsIE(InfoExtractor):
  59     IE_NAME = 'EllenTV:clips'
  60     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  61     _TEST = {
  62         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  63         'info_dict': {
  64             'id': 'meryl-streep-vanessa-hudgens',
  65             'title': 'Meryl Streep, Vanessa Hudgens',
  66         },
  67         'playlist_mincount': 9,
  68     }
  69
  70     def _real_extract(self, url):
  71         playlist_id = self._match_id(url)
  72
  73         webpage = self._download_webpage(url, playlist_id)
  74         playlist = self._extract_playlist(webpage)
  75
  76         return {
  77             '_type': 'playlist',
  78             'id': playlist_id,
  79             'title': self._og_search_title(webpage),
  80             'entries': self._extract_entries(playlist)
  81         }
  82
  83     def _extract_playlist(self, webpage):
  84         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  85         try:
  86             return json.loads("[{" + json_string + "}]")
  87         except ValueError as ve:
  88             raise ExtractorError('Failed to download JSON', cause=ve)
  89
  90     def _extract_entries(self, playlist):
  91         return [self.url_result(item['url'], 'EllenTV') for item in playlist]