# coding: utf-8
from __future__ import unicode_literals
-import re
import json
-from .common import InfoExtractor, ExtractorError
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+)
+
class EllenTVIE(InfoExtractor):
- IE_NAME = u'ellentv'
- _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
_TEST = {
- 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
- 'md5': 'e4af06f3bf0d5f471921a18db5764642',
+ 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
+ 'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
'info_dict': {
- 'id': '0-7jqrsr18',
+ 'id': '0_ipq1gsai',
'ext': 'mp4',
- 'title': u'What\'s Wrong with These Photos? A Whole Lot',
- # TODO more properties, either as:
- # * A value
- # * MD5 checksum; start the string with md5:
- # * A regular expression; start the string with re:
- # * Any Python type (for example int or float)
+ 'title': 'Fast Fingers of Fate',
+ 'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
+ 'timestamp': 1428035648,
+ 'upload_date': '20150403',
+ 'uploader_id': 'batchUser',
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- id = mobj.group('id')
+ video_id = self._match_id(url)
- webpage = self._download_webpage(url, id)
+ webpage = self._download_webpage(
+ 'http://widgets.ellentube.com/videos/%s' % video_id,
+ video_id)
+
+ partner_id = self._search_regex(
+ r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
+
+ kaltura_id = self._search_regex(
+ [r'id="kaltura_player_([^"]+)"',
+ r"_wb_entry_id\s*:\s*'([^']+)",
+ r'data-kaltura-entry-id="([^"]+)'],
+ webpage, 'kaltura id')
+
+ return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
- return {
- 'id': id,
- 'title': self._og_search_title(webpage),
- 'url': self._html_search_meta('VideoURL', webpage, 'url')
- }
class EllenTVClipsIE(InfoExtractor):
- IE_NAME = u'ellentv:clips'
+ IE_NAME = 'EllenTV:clips'
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
_TEST = {
'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
- 'md5': 'TODO: md5 sum of the first 10KiB of the video file',
'info_dict': {
- 'id': '0_wf6pizq7',
- 'ext': 'mp4',
- 'title': 'Video title goes here',
- # TODO more properties, either as:
- # * A value
- # * MD5 checksum; start the string with md5:
- # * A regular expression; start the string with re:
- # * Any Python type (for example int or float)
- }
+ 'id': 'meryl-streep-vanessa-hudgens',
+ 'title': 'Meryl Streep, Vanessa Hudgens',
+ },
+ 'playlist_mincount': 7,
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- playlist_id = mobj.group('id')
+ playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
playlist = self._extract_playlist(webpage)
raise ExtractorError('Failed to download JSON', cause=ve)
def _extract_entries(self, playlist):
- return [self.url_result(item[u'url'], 'EllenTV') for item in playlist]
+ return [
+ self.url_result(
+ 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
+ 'Kaltura')
+ for item in playlist]