From 665e9452461abaff7127653265c78bd585acea6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Jul 2017 15:57:33 +0700 Subject: [PATCH] [eagleplatform] Add support for referrer protected videos (closes #13557) --- youtube_dl/extractor/eagleplatform.py | 25 ++++++++++++++++++++++--- youtube_dl/extractor/generic.py | 10 +++++----- 2 files changed, 27 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index 5e1de04a1..34891a362 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -11,6 +11,7 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, + unsmuggle_url, ) @@ -50,6 +51,10 @@ class EaglePlatformIE(InfoExtractor): 'view_count': int, }, 'skip': 'Georestricted', + }, { + # referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/) + 'url': 'tvrainru.media.eagleplatform.com:582306', + 'only_matching': True, }] @staticmethod @@ -103,9 +108,10 @@ class EaglePlatformIE(InfoExtractor): if status != 200: raise ExtractorError(' '.join(response['errors']), expected=True) - def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs): + def _download_json(self, url_or_request, video_id, *args, **kwargs): try: - response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note) + response = super(EaglePlatformIE, self)._download_json( + url_or_request, video_id, *args, **kwargs) except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError): response = self._parse_json(ee.cause.read().decode('utf-8'), video_id) @@ -117,11 +123,24 @@ class EaglePlatformIE(InfoExtractor): return self._download_json(url_or_request, video_id, note)['data'][0] def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + mobj = re.match(self._VALID_URL, url) host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id') + headers = {} + query = { + 'id': video_id, + } + + referrer = smuggled_data.get('referrer') + if referrer: + headers['Referer'] = referrer + query['referrer'] = referrer + player_data = self._download_json( - 'http://%s/api/player_data?id=%s' % (host, video_id), video_id) + 'http://%s/api/player_data' % host, video_id, + headers=headers, query=query) media = player_data['data']['playlist']['viewports'][0]['medialist'][0] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f9bff433c..7232f39db 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1185,7 +1185,7 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Kaltura'], }, - # Eagle.Platform embed (generic URL) + # EaglePlatform embed (generic URL) { 'url': 'http://lenta.ru/news/2015/03/06/navalny/', # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used @@ -1200,7 +1200,7 @@ class GenericIE(InfoExtractor): 'age_limit': 0, }, }, - # ClipYou (Eagle.Platform) embed (custom URL) + # ClipYou (EaglePlatform) embed (custom URL) { 'url': 'http://muz-tv.ru/play/7129/', # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used @@ -2443,12 +2443,12 @@ class GenericIE(InfoExtractor): if kaltura_url: return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key()) - # Look for Eagle.Platform embeds + # Look for EaglePlatform embeds eagleplatform_url = EaglePlatformIE._extract_url(webpage) if eagleplatform_url: - return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key()) + return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key()) - # Look for ClipYou (uses Eagle.Platform) embeds + # Look for ClipYou (uses EaglePlatform) embeds mobj = re.search( r']+src="https?://(?Pmedia\.clipyou\.ru)/index/player\?.*\brecord_id=(?P\d+).*"', webpage) if mobj is not None: