Start new release.

[youtubedl] / youtube_dl / extractor / limelight.py

diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py
index 5d2c3e256740d865e1c0be2c8e2808a9ee97ee43..729d8de50fab70cd69bab41fae9db0cba4d7da9b 100644 (file)
--- a/youtube_dl/extractor/limelight.py
+++ b/youtube_dl/extractor/limelight.py
@@ -4,10 +4,15 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_HTTPError

 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,

+    smuggle_url,
+    try_get,
+    unsmuggle_url,
+    ExtractorError,

 )
 
 
 )
 
 


@@ -15,48 +20,132 @@ 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'
 
     _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):
-        return self._download_json(
-            self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
-            item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal)
+    @classmethod
+    def _extract_urls(cls, webpage, source_url):
+        lm = {
+            'Media': 'media',
+            '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<id>[a-z0-9]{32})',
+                webpage):
+            entries.append(cls.url_result(
+                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
+                # 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)
+                    <object[^>]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*?
+                        <param[^>]+
+                            name=(["\'])flashVars\2[^>]+
+                            value=(["\'])(?:(?!\3).)*(?P<kind>media|channel(?:List)?)Id=(?P<id>[a-z0-9]{32})
+                ''', webpage):
+            kind, video_id = mobj.group('kind'), mobj.group('id')
+            entries.append(cls.url_result(
+                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<id>[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):
+        headers = {}
+        if referer:
+            headers['Referer'] = referer
+        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(
             self._API_URL % (organization_id, self._API_PATH, item_id, method),
             item_id, 'Downloading API %s JSON' % method)
 
 
     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)
         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):
         video_id = properties['media_id']
         formats = []
         return pc, mobile, metadata
 
     def _extract_info(self, streams, mobile_urls, properties):
         video_id = properties['media_id']
         formats = []

-
+        urls = []

         for stream in streams:
             stream_url = stream.get('url')
         for stream in streams:
             stream_url = stream.get('url')

-            if not stream_url:
+            if not stream_url or stream.get('drmProtected') or stream_url in urls:

                 continue
                 continue

-            if '.f4m' in stream_url:
+            urls.append(stream_url)
+            ext = determine_ext(stream_url)
+            if ext == 'f4m':

                 formats.extend(self._extract_f4m_formats(
                 formats.extend(self._extract_f4m_formats(

-                    stream_url, video_id, fatal=False))
+                    stream_url, video_id, f4m_id='hds', fatal=False))

             else:
                 fmt = {
                     'url': stream_url,
                     'abr': float_or_none(stream.get('audioBitRate')),
             else:
                 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')),
                     'fps': float_or_none(stream.get('videoFrameRate')),

-                    'width': int_or_none(stream.get('videoWidthInPixels')),
-                    'height': int_or_none(stream.get('videoHeightInPixels')),
-                    'ext': determine_ext(stream_url)
+                    'ext': ext,

                 }
                 }

-                rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
+                width = int_or_none(stream.get('videoWidthInPixels'))
+                height = int_or_none(stream.get('videoHeightInPixels'))
+                vbr = float_or_none(stream.get('videoBitRate'))
+                if width or height or vbr:
+                    fmt.update({
+                        'width': width,
+                        'height': height,
+                        'vbr': vbr,
+                    })
+                else:
+                    fmt['vcodec'] = 'none'
+                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', stream_url)

                 if rtmp:
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
                 if rtmp:
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])

+                    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'),
                     fmt.update({
                         'url': rtmp.group('url'),
                         'play_path': rtmp.group('playpath'),


@@ -68,18 +157,24 @@ class LimelightBaseIE(InfoExtractor):
 
         for mobile_url in mobile_urls:
             media_url = mobile_url.get('mobileUrl')
 
         for mobile_url in mobile_urls:
             media_url = mobile_url.get('mobileUrl')

-            if not media_url:
-                continue

             format_id = mobile_url.get('targetMediaPlatform')
             format_id = mobile_url.get('targetMediaPlatform')

-            if determine_ext(media_url) == 'm3u8':
+            if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
+                continue
+            urls.append(media_url)
+            ext = determine_ext(media_url)
+            if ext == 'm3u8':

                 formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id=format_id, fatal=False))
                 formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id=format_id, fatal=False))

+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id=format_id, fatal=False))

             else:
                 formats.append({
                     'url': media_url,
                     'format_id': format_id,
                     'preference': -1,
             else:
                 formats.append({
                     'url': media_url,
                     'format_id': format_id,
                     'preference': -1,

+                    'ext': ext,

                 })
 
         self._sort_formats(formats)
                 })
 
         self._sort_formats(formats)


@@ -126,6 +221,12 @@ class LimelightBaseIE(InfoExtractor):
             'subtitles': subtitles,
         }
 
             'subtitles': subtitles,
         }
 

+    def _extract_info_helper(self, pc, mobile, i, metadata):
+        return self._extract_info(
+            try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
+            try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
+            metadata)
+

 
 class LimelightMediaIE(LimelightBaseIE):
     IE_NAME = 'limelight'
 
 class LimelightMediaIE(LimelightBaseIE):
     IE_NAME = 'limelight'


@@ -145,36 +246,32 @@ class LimelightMediaIE(LimelightBaseIE):
         'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
         'info_dict': {
             'id': '3ffd040b522b4485b6d84effc750cd86',
         'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
         'info_dict': {
             'id': '3ffd040b522b4485b6d84effc750cd86',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'HaP and the HB Prince Trailer',
             'description': 'md5:8005b944181778e313d95c1237ddb640',
             'title': 'HaP and the HB Prince Trailer',
             'description': 'md5:8005b944181778e313d95c1237ddb640',

-            'thumbnail': 're:^https?://.*\.jpeg$',
+            'thumbnail': r're:^https?://.*\.jpeg$',

             'duration': 144.23,
             'timestamp': 1244136834,
             'upload_date': '20090604',
         },
         'params': {
             'duration': 144.23,
             'timestamp': 1244136834,
             'upload_date': '20090604',
         },
         'params': {

-            # rtmp download
+            # m3u8 download

             'skip_download': True,
         },
     }, {
         # video with subtitles
         'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',
             'skip_download': True,
         },
     }, {
         # video with subtitles
         'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',

+        'md5': '2fa3bad9ac321e23860ca23bc2c69e3d',

         'info_dict': {
             'id': 'a3e00274d4564ec4a9b29b9466432335',
         'info_dict': {
             'id': 'a3e00274d4564ec4a9b29b9466432335',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': '3Play Media Overview Video',
             'title': '3Play Media Overview Video',

-            'description': '',
-            'thumbnail': 're:^https?://.*\.jpeg$',
+            'thumbnail': r're:^https?://.*\.jpeg$',

             'duration': 78.101,
             'timestamp': 1338929955,
             'upload_date': '20120605',
             'subtitles': 'mincount:9',
         },
             'duration': 78.101,
             'timestamp': 1338929955,
             'upload_date': '20120605',
             'subtitles': 'mincount:9',
         },

-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },

     }, {
         'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
         'only_matching': True,
     }, {
         'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
         'only_matching': True,


@@ -183,15 +280,18 @@ class LimelightMediaIE(LimelightBaseIE):
     _API_PATH = 'media'
 
     def _real_extract(self, url):
     _API_PATH = 'media'
 
     def _real_extract(self, url):

+        url, smuggled_data = unsmuggle_url(url, {})

         video_id = self._match_id(url)
         video_id = self._match_id(url)

+        self._initialize_geo_bypass({
+            'countries': smuggled_data.get('geo_countries'),
+        })

 
         pc, mobile, metadata = self._extract(
 
         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', []),
-            mobile['mediaList'][0].get('mobileUrls', []) if mobile else [],
-            metadata)
+        return self._extract_info_helper(pc, mobile, 0, metadata)

 
 
 class LimelightChannelIE(LimelightBaseIE):
 
 
 class LimelightChannelIE(LimelightBaseIE):


@@ -223,17 +323,16 @@ class LimelightChannelIE(LimelightBaseIE):
     _API_PATH = 'channels'
 
     def _real_extract(self, url):
     _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',
         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 = [
 
         entries = [

-            self._extract_info(
-                pc['playlistItems'][i].get('streams', []),
-                mobile['mediaList'][i].get('mobileUrls', []) if mobile else [],
-                medias['media_list'][i])
+            self._extract_info_helper(pc, mobile, i, medias['media_list'][i])

             for i in range(len(medias['media_list']))]
 
         return self.playlist_result(entries, channel_id, pc['title'])
             for i in range(len(medias['media_list']))]
 
         return self.playlist_result(entries, channel_id, pc['title'])