Imported Upstream version 2015.11.10

[youtubedl] / youtube_dl / extractor / livestream.py

diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py
index 363a12ad0ab53a53892b59623fbd92d1cbf98358..6d7733e4111355a5011765336333f229596b8356 100644 (file)
--- a/youtube_dl/extractor/livestream.py
+++ b/youtube_dl/extractor/livestream.py
@@ -2,12 +2,15 @@ from __future__ import unicode_literals
 
 import re
 import json
 
 import re
 import json

+import itertools

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_str,
     compat_urllib_parse_urlparse,
     compat_urlparse,

+)
+from ..utils import (

     ExtractorError,
     find_xpath_attr,
     int_or_none,
     ExtractorError,
     find_xpath_attr,
     int_or_none,


@@ -18,7 +21,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'

-    _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _VALID_URL = r'https?://(?:new\.)?livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'

     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',


@@ -35,8 +38,22 @@ class LivestreamIE(InfoExtractor):
         'url': 'http://new.livestream.com/tedx/cityenglish',
         'info_dict': {
             'title': 'TEDCity2.0 (English)',
         'url': 'http://new.livestream.com/tedx/cityenglish',
         'info_dict': {
             'title': 'TEDCity2.0 (English)',

+            'id': '2245590',

         },
         'playlist_mincount': 4,
         },
         'playlist_mincount': 4,

+    }, {
+        'url': 'http://new.livestream.com/chess24/tatasteelchess',
+        'info_dict': {
+            'title': 'Tata Steel Chess',
+            'id': '3705884',
+        },
+        'playlist_mincount': 60,
+    }, {
+        'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
+        'only_matching': True,
+    }, {
+        'url': 'http://livestream.com/bsww/concacafbeachsoccercampeonato2015',
+        'only_matching': True,

     }]
 
     def _parse_smil(self, video_id, smil_url):
     }]
 
     def _parse_smil(self, video_id, smil_url):


@@ -111,6 +128,30 @@ class LivestreamIE(InfoExtractor):
             'view_count': video_data.get('views'),
         }
 
             'view_count': video_data.get('views'),
         }
 

+    def _extract_event(self, info):
+        event_id = compat_str(info['id'])
+        account = compat_str(info['owner_account_id'])
+        root_url = (
+            'https://new.livestream.com/api/accounts/{account}/events/{event}/'
+            'feed.json'.format(account=account, event=event_id))
+
+        def _extract_videos():
+            last_video = None
+            for i in itertools.count(1):
+                if last_video is None:
+                    info_url = root_url
+                else:
+                    info_url = '{root}?&id={id}&newer=-1&type=video'.format(
+                        root=root_url, id=last_video)
+                videos_info = self._download_json(info_url, event_id, 'Downloading page {0}'.format(i))['data']
+                videos_info = [v['data'] for v in videos_info if v['type'] == 'video']
+                if not videos_info:
+                    break
+                for v in videos_info:
+                    yield self._extract_video_info(v)
+                last_video = videos_info[-1]['id']
+        return self.playlist_result(_extract_videos(), event_id, info['full_name'])
+

     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')


@@ -138,13 +179,13 @@ class LivestreamIE(InfoExtractor):
                 result = result and compat_str(vdata['data']['id']) == vid
             return result
 
                 result = result and compat_str(vdata['data']['id']) == vid
             return result
 

-        videos = [self._extract_video_info(video_data['data'])
-                  for video_data in info['feed']['data']
-                  if is_relevant(video_data, video_id)]

         if video_id is None:
             # This is an event page:
         if video_id is None:
             # This is an event page:

-            return self.playlist_result(videos, info['id'], info['full_name'])
+            return self._extract_event(info)

         else:
         else:

+            videos = [self._extract_video_info(video_data['data'])
+                      for video_data in info['feed']['data']
+                      if is_relevant(video_data, video_id)]

             if not videos:
                 raise ExtractorError('Cannot find video %s' % video_id)
             return videos[0]
             if not videos:
                 raise ExtractorError('Cannot find video %s' % video_id)
             return videos[0]


@@ -153,23 +194,19 @@ class LivestreamIE(InfoExtractor):
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
     IE_NAME = 'livestream:original'
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
     IE_NAME = 'livestream:original'

-    _VALID_URL = r'''(?x)https?://www\.livestream\.com/
+    _VALID_URL = r'''(?x)https?://original\.livestream\.com/

         (?P<user>[^/]+)/(?P<type>video|folder)
         (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
         '''
     _TESTS = [{
         (?P<user>[^/]+)/(?P<type>video|folder)
         (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
         '''
     _TESTS = [{

-        'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+        'url': 'http://original.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',

         'info_dict': {
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
         'info_dict': {
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',

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

             'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
         },
             'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
         },

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

     }, {
     }, {

-        'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        'url': 'https://original.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',

         'info_dict': {
             'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
         },
         'info_dict': {
             'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
         },


@@ -180,19 +217,17 @@ class LivestreamOriginalIE(InfoExtractor):
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
 
         info = self._download_xml(api_url, video_id)
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
 
         info = self._download_xml(api_url, video_id)

+        # this url is used on mobile devices
+        stream_url = 'http://x{0}x.api.channel.livestream.com/3.0/getstream.json?id={1}'.format(user, video_id)
+        stream_info = self._download_json(stream_url, video_id)

         item = info.find('channel').find('item')
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
         item = info.find('channel').find('item')
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']

-        # Remove the extension and number from the path (like 1.jpg)
-        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')

 
         return {
             'id': video_id,
             'title': item.find('title').text,
 
         return {
             'id': video_id,
             'title': item.find('title').text,

-            'url': 'rtmp://extondemand.livestream.com/ondemand',
-            'play_path': 'trans/dv15/mogulus-{0}'.format(path),
-            'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque',
-            'ext': 'flv',
+            'url': stream_info['progressiveUrl'],

             'thumbnail': thumbnail_url,
         }
 
             'thumbnail': thumbnail_url,
         }