Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / smotri.py

diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py
index 0751efc6111c96ca1c089c66183429f9bde6147c..24746a09a0c2183e8a0bd8e239cb59291b41f19a 100644 (file)
--- a/youtube_dl/extractor/smotri.py
+++ b/youtube_dl/extractor/smotri.py
@@ -7,9 +7,11 @@ import hashlib
 import uuid
 
 from .common import InfoExtractor
 import uuid
 
 from .common import InfoExtractor

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

     compat_urllib_parse,
     compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_request,

+)
+from ..utils import (

     ExtractorError,
     int_or_none,
     unified_strdate,
     ExtractorError,
     int_or_none,
     unified_strdate,


@@ -67,6 +69,7 @@ class SmotriIE(InfoExtractor):
             'params': {
                 'videopassword': 'qwerty',
             },
             'params': {
                 'videopassword': 'qwerty',
             },

+            'skip': 'Video is not approved by moderator',

         },
         # age limit + video-password
         {
         },
         # age limit + video-password
         {


@@ -84,12 +87,28 @@ class SmotriIE(InfoExtractor):
             },
             'params': {
                 'videopassword': '333'
             },
             'params': {
                 'videopassword': '333'

-            }
+            },
+            'skip': 'Video is not approved by moderator',
+        },
+        # not approved by moderator, but available
+        {
+            'url': 'http://smotri.com/video/view/?id=v28888533b73',
+            'md5': 'f44bc7adac90af518ef1ecf04893bb34',
+            'info_dict': {
+                'id': 'v28888533b73',
+                'ext': 'mp4',
+                'title': 'Russian Spies Killed By ISIL Child Soldier',
+                'uploader': 'Mopeder',
+                'uploader_id': 'mopeder',
+                'duration': 71,
+                'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
+                'upload_date': '20150114',
+            },

         },
         # swf player
         {
             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
         },
         # swf player
         {
             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',

-            'md5': '4d47034979d9390d14acdf59c4935bc2',
+            'md5': '31099eeb4bc906712c5f40092045108d',

             'info_dict': {
                 'id': 'v9188090500',
                 'ext': 'mp4',
             'info_dict': {
                 'id': 'v9188090500',
                 'ext': 'mp4',


@@ -120,9 +139,6 @@ class SmotriIE(InfoExtractor):
     def _search_meta(self, name, html, display_name=None):
         if display_name is None:
             display_name = name
     def _search_meta(self, name, html, display_name=None):
         if display_name is None:
             display_name = name

-        return self._html_search_regex(
-            r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
-            html, display_name, fatal=False)

         return self._html_search_meta(name, html, display_name)
 
     def _real_extract(self, url):
         return self._html_search_meta(name, html, display_name)
 
     def _real_extract(self, url):


@@ -142,13 +158,16 @@ class SmotriIE(InfoExtractor):
 
         video = self._download_json(request, video_id, 'Downloading video JSON')
 
 
         video = self._download_json(request, video_id, 'Downloading video JSON')
 

-        if video.get('_moderate_no') or not video.get('moderated'):
-            raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
+        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')

 
 

-        if video.get('error'):
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        if not video_url:
+            if video.get('_moderate_no') or not video.get('moderated'):
+                raise ExtractorError(
+                    'Video %s has not been approved by moderator' % video_id, expected=True)
+
+            if video.get('error'):
+                raise ExtractorError('Video %s does not exist' % video_id, expected=True)

 
 

-        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')

         title = video['title']
         thumbnail = video['_imgURL']
         upload_date = unified_strdate(video['added'])
         title = video['title']
         thumbnail = video['_imgURL']
         upload_date = unified_strdate(video['added'])


@@ -274,15 +293,18 @@ class SmotriBroadcastIE(InfoExtractor):
         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 
         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 
         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:

-            raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
+            raise ExtractorError(
+                'Broadcast %s does not exist' % broadcast_id, expected=True)

 
         # Adult content
         if re.search('EroConfirmText">', broadcast_page) is not None:
 
             (username, password) = self._get_login_info()
             if username is None:
 
         # Adult content
         if re.search('EroConfirmText">', broadcast_page) is not None:
 
             (username, password) = self._get_login_info()
             if username is None:

-                raise ExtractorError('Erotic broadcasts allowed only for registered users, '
-                                     'use --username and --password options to provide account credentials.', expected=True)
+                raise ExtractorError(
+                    'Erotic broadcasts allowed only for registered users, '
+                    'use --username and --password options to provide account credentials.',
+                    expected=True)

 
             login_form = {
                 'login-hint53': '1',
 
             login_form = {
                 'login-hint53': '1',


@@ -291,9 +313,11 @@ class SmotriBroadcastIE(InfoExtractor):
                 'password': password,
             }
 
                 'password': password,
             }
 

-            request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
+            request = compat_urllib_request.Request(
+                broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))

             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
             request.add_header('Content-Type', 'application/x-www-form-urlencoded')

-            broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
+            broadcast_page = self._download_webpage(
+                request, broadcast_id, 'Logging in and confirming age')

 
             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 
             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
                 raise ExtractorError('Unable to log in: bad username or password', expected=True)


@@ -303,7 +327,7 @@ class SmotriBroadcastIE(InfoExtractor):
             adult_content = False
 
         ticket = self._html_search_regex(
             adult_content = False
 
         ticket = self._html_search_regex(

-            'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+            r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",

             broadcast_page, 'broadcast ticket')
 
         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
             broadcast_page, 'broadcast ticket')
 
         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket


@@ -312,26 +336,31 @@ class SmotriBroadcastIE(InfoExtractor):
         if broadcast_password:
             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 
         if broadcast_password:
             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 

-        broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
+        broadcast_json_page = self._download_webpage(
+            url, broadcast_id, 'Downloading broadcast JSON')

 
         try:
             broadcast_json = json.loads(broadcast_json_page)
 
             protected_broadcast = broadcast_json['_pass_protected'] == 1
             if protected_broadcast and not broadcast_password:
 
         try:
             broadcast_json = json.loads(broadcast_json_page)
 
             protected_broadcast = broadcast_json['_pass_protected'] == 1
             if protected_broadcast and not broadcast_password:

-                raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
+                raise ExtractorError(
+                    'This broadcast is protected by a password, use the --video-password option',
+                    expected=True)

 
             broadcast_offline = broadcast_json['is_play'] == 0
             if broadcast_offline:
                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 
             rtmp_url = broadcast_json['_server']
 
             broadcast_offline = broadcast_json['is_play'] == 0
             if broadcast_offline:
                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 
             rtmp_url = broadcast_json['_server']

-            if not rtmp_url.startswith('rtmp://'):
+            mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
+            if not mobj:

                 raise ExtractorError('Unexpected broadcast rtmp URL')
 
             broadcast_playpath = broadcast_json['_streamName']
                 raise ExtractorError('Unexpected broadcast rtmp URL')
 
             broadcast_playpath = broadcast_json['_streamName']

+            broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])

             broadcast_thumbnail = broadcast_json['_imgURL']
             broadcast_thumbnail = broadcast_json['_imgURL']

-            broadcast_title = broadcast_json['title']
+            broadcast_title = self._live_title(broadcast_json['title'])

             broadcast_description = broadcast_json['description']
             broadcaster_nick = broadcast_json['nick']
             broadcaster_login = broadcast_json['login']
             broadcast_description = broadcast_json['description']
             broadcaster_nick = broadcast_json['nick']
             broadcaster_login = broadcast_json['login']


@@ -352,6 +381,9 @@ class SmotriBroadcastIE(InfoExtractor):
             'age_limit': 18 if adult_content else 0,
             'ext': 'flv',
             'play_path': broadcast_playpath,
             'age_limit': 18 if adult_content else 0,
             'ext': 'flv',
             'play_path': broadcast_playpath,

+            'player_url': 'http://pics.smotri.com/broadcast_play.swf',
+            'app': broadcast_app,

             'rtmp_live': True,
             'rtmp_live': True,

-            'rtmp_conn': rtmp_conn
+            'rtmp_conn': rtmp_conn,
+            'is_live': True,

         }
         }