From 906420cae37ee3c2f48d23c3a4fa0543a66947d5 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Mon, 16 Jan 2017 21:54:47 +0700 Subject: [limelight] Improve and make more robust (closes #11737) + Add support for direct http for videos hosted on video.llnw.net * Check handmade http URLs --- youtube_dl/extractor/limelight.py | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 905a0e85f..e635f3c4d 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -59,14 +59,26 @@ class LimelightBaseIE(InfoExtractor): format_id = 'rtmp' if stream.get('videoBitRate'): format_id += '-%d' % int_or_none(stream['videoBitRate']) - http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:] - urls.append(http_url) - http_fmt = fmt.copy() - http_fmt.update({ - 'url': http_url, - 'format_id': format_id.replace('rtmp', 'http'), - }) - formats.append(http_fmt) + http_format_id = format_id.replace('rtmp', 'http') + + CDN_HOSTS = ( + ('delvenetworks.com', 'cpl.delvenetworks.com'), + ('video.llnw.net', 's2.content.video.llnw.net'), + ) + for cdn_host, http_host in CDN_HOSTS: + if cdn_host not in rtmp.group('host').lower(): + continue + http_url = 'http://%s/%s' % (http_host, rtmp.group('playpath')[4:]) + urls.append(http_url) + if self._is_valid_url(http_url, video_id, http_format_id): + http_fmt = fmt.copy() + http_fmt.update({ + 'url': http_url, + 'format_id': http_format_id, + }) + formats.append(http_fmt) + break + fmt.update({ 'url': rtmp.group('url'), 'play_path': rtmp.group('playpath'), -- cgit 1.4.1 From 454e5cdb17dd4e77f3d387045b083f3d3ed61ae0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 13 Feb 2017 14:28:30 +0100 Subject: [limelight] add support referer protected videos --- youtube_dl/extractor/generic.py | 9 ++++++--- youtube_dl/extractor/limelight.py | 23 ++++++++++++++++------- 2 files changed, 22 insertions(+), 10 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 494cc3c84..a2b0298ec 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2337,8 +2337,9 @@ class GenericIE(InfoExtractor): 'Channel': 'channel', 'ChannelList': 'channel_list', } - return self.url_result('limelight:%s:%s' % ( - lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + return self.url_result(smuggle_url('limelight:%s:%s' % ( + lm[mobj.group(1)], mobj.group(2)), {'source_url': url}), + 'Limelight%s' % mobj.group(1), mobj.group(2)) mobj = re.search( r'''(?sx) @@ -2348,7 +2349,9 @@ class GenericIE(InfoExtractor): value=(["\'])(?:(?!\3).)*mediaId=(?P[a-z0-9]{32}) ''', webpage) if mobj: - return self.url_result('limelight:media:%s' % mobj.group('id')) + return self.url_result(smuggle_url( + 'limelight:media:%s' % mobj.group('id'), + {'source_url': url}), 'LimelightMedia', mobj.group('id')) # Look for AdobeTVVideo embeds mobj = re.search( diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index e635f3c4d..a3712665b 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -8,6 +8,7 @@ from ..utils import ( determine_ext, float_or_none, int_or_none, + unsmuggle_url, ) @@ -15,20 +16,23 @@ class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' - def _call_playlist_service(self, item_id, method, fatal=True): + def _call_playlist_service(self, item_id, method, fatal=True, referer=None): + headers = {} + if referer: + headers['Referer'] = referer return self._download_json( self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal) + item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) def _call_api(self, organization_id, item_id, method): return self._download_json( self._API_URL % (organization_id, self._API_PATH, item_id, method), item_id, 'Downloading API %s JSON' % method) - def _extract(self, item_id, pc_method, mobile_method, meta_method): - pc = self._call_playlist_service(item_id, pc_method) + def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None): + pc = self._call_playlist_service(item_id, pc_method, referer=referer) metadata = self._call_api(pc['orgId'], item_id, meta_method) - mobile = self._call_playlist_service(item_id, mobile_method, fatal=False) + mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) return pc, mobile, metadata def _extract_info(self, streams, mobile_urls, properties): @@ -207,10 +211,13 @@ class LimelightMediaIE(LimelightBaseIE): _API_PATH = 'media' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) pc, mobile, metadata = self._extract( - video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties') + video_id, 'getPlaylistByMediaId', + 'getMobilePlaylistByMediaId', 'properties', + smuggled_data.get('source_url')) return self._extract_info( pc['playlistItems'][0].get('streams', []), @@ -247,11 +254,13 @@ class LimelightChannelIE(LimelightBaseIE): _API_PATH = 'channels' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) pc, mobile, medias = self._extract( channel_id, 'getPlaylistByChannelId', - 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media') + 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', + 'media', smuggled_data.get('source_url')) entries = [ self._extract_info( -- cgit 1.4.1 From 3444844b04ae482edc5a353d9125b45ba47cd8d8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 21 Feb 2017 17:47:14 +0100 Subject: [limelight] extract PlaylistService errors --- youtube_dl/extractor/limelight.py | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index a3712665b..422be2528 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, float_or_none, int_or_none, unsmuggle_url, + ExtractorError, ) @@ -20,9 +22,17 @@ class LimelightBaseIE(InfoExtractor): headers = {} if referer: headers['Referer'] = referer - return self._download_json( - self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + try: + return self._download_json( + self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), + item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] + if error == 'CountryDisabled': + self.raise_geo_restricted() + raise ExtractorError(error, expected=True) + raise def _call_api(self, organization_id, item_id, method): return self._download_json( @@ -213,6 +223,7 @@ class LimelightMediaIE(LimelightBaseIE): def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) pc, mobile, metadata = self._extract( video_id, 'getPlaylistByMediaId', -- cgit 1.4.1 From a6f3a162f35cc05ac5a34773b438dd4c5f0d164a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 1 Apr 2017 15:35:39 +0100 Subject: [limelight] improve extraction for audio only formats --- youtube_dl/extractor/limelight.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 422be2528..f52c2e169 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -62,13 +62,21 @@ class LimelightBaseIE(InfoExtractor): fmt = { 'url': stream_url, 'abr': float_or_none(stream.get('audioBitRate')), - 'vbr': float_or_none(stream.get('videoBitRate')), 'fps': float_or_none(stream.get('videoFrameRate')), - 'width': int_or_none(stream.get('videoWidthInPixels')), - 'height': int_or_none(stream.get('videoHeightInPixels')), 'ext': ext, } - rtmp = re.search(r'^(?Prtmpe?://(?P[^/]+)/(?P.+))/(?Pmp4:.+)$', stream_url) + width = int_or_none(stream.get('videoWidthInPixels')) + height = int_or_none(stream.get('videoHeightInPixels')) + vbr = float_or_none(stream.get('videoBitRate')) + if width or height or vbr: + fmt.update({ + 'width': width, + 'height': height, + 'vbr': vbr, + }) + else: + fmt['vcodec'] = 'none' + rtmp = re.search(r'^(?Prtmpe?://(?P[^/]+)/(?P.+))/(?Pmp[34]:.+)$', stream_url) if rtmp: format_id = 'rtmp' if stream.get('videoBitRate'): -- cgit 1.4.1 From e5d39886ec8e4e40b2b7257d16cc5d8505cc1f69 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Mon, 17 Apr 2017 00:23:16 +0700 Subject: [limelight] Improve embeds extraction (closes #12761) * Move extraction code to extractor * Add extraction for LimelightEmbeddedPlayerFlash embeds * Extract multiple video --- youtube_dl/extractor/generic.py | 6 ++++++ youtube_dl/extractor/limelight.py | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 6a34c2491..c523abb25 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -85,6 +85,7 @@ from .ustream import UstreamIE from .openload import OpenloadIE from .videopress import VideoPressIE from .rutube import RutubeIE +from .limelight import LimelightBaseIE class GenericIE(InfoExtractor): @@ -2483,6 +2484,11 @@ class GenericIE(InfoExtractor): return self.url_result(piksel_url, PikselIE.ie_key()) # Look for Limelight embeds + limelight_urls = LimelightBaseIE._extract_urls(webpage, url) + if limelight_urls: + return self.playlist_result( + limelight_urls, video_id, video_title, video_description) + mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P[a-z0-9]{32})', webpage) if mobj: lm = { diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index f52c2e169..0041453af 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -9,6 +9,7 @@ from ..utils import ( determine_ext, float_or_none, int_or_none, + smuggle_url, unsmuggle_url, ExtractorError, ) @@ -18,6 +19,42 @@ class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' + @classmethod + def _extract_urls(cls, webpage, source_url): + lm = { + 'Media': 'media', + 'Channel': 'channel', + 'ChannelList': 'channel_list', + } + entries = [] + for kind, video_id in re.findall( + r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P[a-z0-9]{32})', + webpage): + print('video_id', video_id) + entries.append(cls.url_result( + smuggle_url( + 'limelight:%s:%s' % (lm[kind], video_id), + {'source_url': source_url}), + 'Limelight%s' % kind, video_id)) + for mobj in re.finditer( + # As per [1] class attribute should be exactly equal to + # LimelightEmbeddedPlayerFlash but numerous examples seen + # that don't exactly match it (e.g. [2]). + # 1. http://support.3playmedia.com/hc/en-us/articles/227732408-Limelight-Embedding-the-Captions-Plugin-with-the-Limelight-Player-on-Your-Webpage + # 2. http://www.sedona.com/FacilitatorTraining2017 + r'''(?sx) + ]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*? + ]+ + name=(["\'])flashVars\2[^>]+ + value=(["\'])(?:(?!\3).)*mediaId=(?P[a-z0-9]{32}) + ''', webpage): + entries.append(cls.url_result( + smuggle_url( + 'limelight:media:%s' % mobj.group('id'), + {'source_url': source_url}), + 'LimelightMedia', mobj.group('id'))) + return entries + def _call_playlist_service(self, item_id, method, fatal=True, referer=None): headers = {} if referer: -- cgit 1.4.1 From 91bc57e4c527f918c7735d67f4bceb3cf1e2332c Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Mon, 17 Apr 2017 00:33:47 +0700 Subject: [limelight] Add support for channels and channels lists embedded using LimelightEmbeddedPlayerFlash (#12761) --- youtube_dl/extractor/limelight.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 0041453af..0a5a3956c 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -30,7 +30,6 @@ class LimelightBaseIE(InfoExtractor): for kind, video_id in re.findall( r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P[a-z0-9]{32})', webpage): - print('video_id', video_id) entries.append(cls.url_result( smuggle_url( 'limelight:%s:%s' % (lm[kind], video_id), @@ -46,13 +45,14 @@ class LimelightBaseIE(InfoExtractor): ]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*? ]+ name=(["\'])flashVars\2[^>]+ - value=(["\'])(?:(?!\3).)*mediaId=(?P[a-z0-9]{32}) + value=(["\'])(?:(?!\3).)*(?Pmedia|channel(?:List)?)Id=(?P[a-z0-9]{32}) ''', webpage): + kind, video_id = mobj.group('kind'), mobj.group('id') entries.append(cls.url_result( smuggle_url( - 'limelight:media:%s' % mobj.group('id'), + 'limelight:%s:%s' % (kind, video_id), {'source_url': source_url}), - 'LimelightMedia', mobj.group('id'))) + 'Limelight%s' % kind.capitalize(), video_id)) return entries def _call_playlist_service(self, item_id, method, fatal=True, referer=None): -- cgit 1.4.1 From 4ef9152428c4a000cb5fc76732fc579f1f4c1d69 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 13 Aug 2017 00:58:39 +0700 Subject: [limelight] Improve embeds detection (closes #13895) --- youtube_dl/extractor/limelight.py | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'youtube_dl/extractor/limelight.py') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 0a5a3956c..ad65b2759 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -26,14 +26,16 @@ class LimelightBaseIE(InfoExtractor): 'Channel': 'channel', 'ChannelList': 'channel_list', } + + def smuggle(url): + return smuggle_url(url, {'source_url': source_url}) + entries = [] for kind, video_id in re.findall( r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P[a-z0-9]{32})', webpage): entries.append(cls.url_result( - smuggle_url( - 'limelight:%s:%s' % (lm[kind], video_id), - {'source_url': source_url}), + smuggle('limelight:%s:%s' % (lm[kind], video_id)), 'Limelight%s' % kind, video_id)) for mobj in re.finditer( # As per [1] class attribute should be exactly equal to @@ -49,10 +51,15 @@ class LimelightBaseIE(InfoExtractor): ''', webpage): kind, video_id = mobj.group('kind'), mobj.group('id') entries.append(cls.url_result( - smuggle_url( - 'limelight:%s:%s' % (kind, video_id), - {'source_url': source_url}), + smuggle('limelight:%s:%s' % (kind, video_id)), 'Limelight%s' % kind.capitalize(), video_id)) + # http://support.3playmedia.com/hc/en-us/articles/115009517327-Limelight-Embedding-the-Audio-Description-Plugin-with-the-Limelight-Player-on-Your-Web-Page) + for video_id in re.findall( + r'(?s)LimelightPlayerUtil\.embed\s*\(\s*{.*?\bmediaId["\']\s*:\s*["\'](?P[a-z0-9]{32})', + webpage): + entries.append(cls.url_result( + smuggle('limelight:media:%s' % video_id), + LimelightMediaIE.ie_key(), video_id)) return entries def _call_playlist_service(self, item_id, method, fatal=True, referer=None): -- cgit 1.4.1