youtube_dl/extractor/ellentv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     parse_iso8601,
  11 )
  12
  13
  14 class EllenTVIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
  16     _TEST = {
  17         'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
  18         'md5': 'e4af06f3bf0d5f471921a18db5764642',
  19         'info_dict': {
  20             'id': '0-7jqrsr18',
  21             'ext': 'mp4',
  22             'title': 'What\'s Wrong with These Photos? A Whole Lot',
  23             'timestamp': 1406876400,
  24             'upload_date': '20140801',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         timestamp = parse_iso8601(self._search_regex(
  34             r'<span class="publish-date"><time datetime="([^"]+)">',
  35             webpage, 'timestamp'))
  36
  37         return {
  38             'id': video_id,
  39             'title': self._og_search_title(webpage),
  40             'url': self._html_search_meta('VideoURL', webpage, 'url'),
  41             'timestamp': timestamp,
  42         }
  43
  44
  45 class EllenTVClipsIE(InfoExtractor):
  46     IE_NAME = 'EllenTV:clips'
  47     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  48     _TEST = {
  49         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  50         'info_dict': {
  51             'id': 'meryl-streep-vanessa-hudgens',
  52             'title': 'Meryl Streep, Vanessa Hudgens',
  53         },
  54         'playlist_mincount': 9,
  55     }
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         playlist_id = mobj.group('id')
  60
  61         webpage = self._download_webpage(url, playlist_id)
  62         playlist = self._extract_playlist(webpage)
  63
  64         return {
  65             '_type': 'playlist',
  66             'id': playlist_id,
  67             'title': self._og_search_title(webpage),
  68             'entries': self._extract_entries(playlist)
  69         }
  70
  71     def _extract_playlist(self, webpage):
  72         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  73         try:
  74             return json.loads("[{" + json_string + "}]")
  75         except ValueError as ve:
  76             raise ExtractorError('Failed to download JSON', cause=ve)
  77
  78     def _extract_entries(self, playlist):
  79         return [self.url_result(item['url'], 'EllenTV') for item in playlist]