X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fellentv.py;h=74bbc5c51c576880465e76453604891b6b5f48ca;hb=b92d3c5343536eb0a865afa79e3787fc384ec0ec;hp=93affaa8f880b19f5ac13af57f7be34ed0970ce6;hpb=2ad978532bd0a94fb7529f429a26e9b9966b2e1a;p=youtube-dl diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 93affaa8f..74bbc5c51 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -6,7 +6,7 @@ import json from .common import InfoExtractor from ..utils import ( ExtractorError, - parse_iso8601, + NO_DEFAULT, ) @@ -14,43 +14,56 @@ class EllenTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' _TESTS = [{ 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', - 'md5': '8e3c576bf2e9bfff4d76565f56f94c9c', + 'md5': '4294cf98bc165f218aaa0b89e0fd8042', 'info_dict': { - 'id': '0-ipq1gsai', - 'ext': 'mp4', + 'id': '0_ipq1gsai', + 'ext': 'mov', 'title': 'Fast Fingers of Fate', - 'description': 'md5:686114ced0a032926935e9015ee794ac', - 'timestamp': 1428033600, + 'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a', + 'timestamp': 1428035648, 'upload_date': '20150403', - } + 'uploader_id': 'batchUser', + }, }, { - 'url': 'http://ellentube.com/videos/0-dvzmabd5/', - 'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb', + # not available via http://widgets.ellentube.com/ + 'url': 'http://www.ellentv.com/videos/1-szkgu2m2/', 'info_dict': { - 'id': '0-dvzmabd5', - 'ext': 'mp4', - 'title': '1 year old twin sister makes her brother laugh', - 'description': '1 year old twin sister makes her brother laugh', - 'timestamp': 1419542075, - 'upload_date': '20141225', - } + 'id': '1_szkgu2m2', + 'ext': 'flv', + 'title': "Ellen's Amazingly Talented Audience", + 'description': 'md5:86ff1e376ff0d717d7171590e273f0a5', + 'timestamp': 1255140900, + 'upload_date': '20091010', + 'uploader_id': 'ellenkaltura@gmail.com', + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'http://widgets.ellentube.com/videos/%s' % video_id, - video_id) + URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url) + + for num, url_ in enumerate(URLS, 1): + webpage = self._download_webpage( + url_, video_id, fatal=num == len(URLS)) + + default = NO_DEFAULT if num == len(URLS) else None + + partner_id = self._search_regex( + r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id', + default=default) - 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', default=default) - kaltura_id = self._search_regex( - [r'id="kaltura_player_([^"]+)"', - r"_wb_entry_id\s*:\s*'([^']+)", - r'data-kaltura-entry-id="([^"]+)'], - webpage, 'kaltura id') + if partner_id and kaltura_id: + break return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura') @@ -64,7 +77,7 @@ class EllenTVClipsIE(InfoExtractor): 'id': 'meryl-streep-vanessa-hudgens', 'title': 'Meryl Streep, Vanessa Hudgens', }, - 'playlist_mincount': 9, + 'playlist_mincount': 7, } def _real_extract(self, url): @@ -83,9 +96,13 @@ class EllenTVClipsIE(InfoExtractor): def _extract_playlist(self, webpage): json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') try: - return json.loads("[{" + json_string + "}]") + return json.loads('[{' + json_string + '}]') except ValueError as ve: raise ExtractorError('Failed to download JSON', cause=ve) def _extract_entries(self, playlist): - return [self.url_result(item['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]