_ Git - youtube-dl/blob - 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|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
  16     _TESTS = [{
  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         'url': 'http://ellentube.com/videos/0-dvzmabd5/',
  29         'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
  30         'info_dict': {
  31             'id': '0-dvzmabd5',
  32             'ext': 'mp4',
  33             'title': '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         mobj = re.match(self._VALID_URL, url)
  41         video_id = mobj.group('id')
  42
  43         webpage = self._download_webpage(url, video_id)
  44         timestamp = parse_iso8601(self._search_regex(
  45             r'<span class="publish-date"><time datetime="([^"]+)">',
  46             webpage, 'timestamp'))
  47         print "\n"
  48         print timestamp
  49         print "\n"
  50
  51         return {
  52             'id': video_id,
  53             'title': self._og_search_title(webpage),
  54             'url': self._html_search_meta('VideoURL', webpage, 'url'),
  55             'timestamp': timestamp,
  56         }
  57
  58
  59 class EllenTVClipsIE(InfoExtractor):
  60     IE_NAME = 'EllenTV:clips'
  61     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  62     _TEST = {
  63         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  64         'info_dict': {
  65             'id': 'meryl-streep-vanessa-hudgens',
  66             'title': 'Meryl Streep, Vanessa Hudgens',
  67         },
  68         'playlist_mincount': 9,
  69     }
  70
  71     def _real_extract(self, url):
  72         mobj = re.match(self._VALID_URL, url)
  73         playlist_id = mobj.group('id')
  74
  75         webpage = self._download_webpage(url, playlist_id)
  76         playlist = self._extract_playlist(webpage)
  77
  78         return {
  79             '_type': 'playlist',
  80             'id': playlist_id,
  81             'title': self._og_search_title(webpage),
  82             'entries': self._extract_entries(playlist)
  83         }
  84
  85     def _extract_playlist(self, webpage):
  86         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  87         try:
  88             return json.loads("[{" + json_string + "}]")
  89         except ValueError as ve:
  90             raise ExtractorError('Failed to download JSON', cause=ve)
  91
  92     def _extract_entries(self, playlist):
  93         return [self.url_result(item['url'], 'EllenTV') for item in playlist]