Merge tag 'upstream/2016.08.17'

[youtubedl] / youtube_dl / extractor / tvigle.py

diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index ba65996dc01646e019cfd5820aa36c1934365d9b..ead4c00c79bb453585b4ba18c67f7535bcc69254 100644 (file)
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -1,9 +1,13 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
 # encoding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from ..utils import (
 from .common import InfoExtractor
 from ..utils import (

+    ExtractorError,

     float_or_none,
     float_or_none,

+    int_or_none,

     parse_age_limit,
 )
 
     parse_age_limit,
 )
 


@@ -11,7 +15,7 @@ from ..utils import (
 class TvigleIE(InfoExtractor):
     IE_NAME = 'tvigle'
     IE_DESC = 'Интернет-телевидение Tvigle.ru'
 class TvigleIE(InfoExtractor):
     IE_NAME = 'tvigle'
     IE_DESC = 'Интернет-телевидение Tvigle.ru'

-    _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$'
+    _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'

 
     _TESTS = [
         {
 
     _TESTS = [
         {


@@ -22,53 +26,76 @@ class TvigleIE(InfoExtractor):
                 'display_id': 'sokrat',
                 'ext': 'flv',
                 'title': 'Сократ',
                 'display_id': 'sokrat',
                 'ext': 'flv',
                 'title': 'Сократ',

-                'description': 'md5:a05bd01be310074d5833efc6743be95e',
+                'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',

                 'duration': 6586,
                 'duration': 6586,

-                'age_limit': 0,
+                'age_limit': 12,

             },
             },

+            'skip': 'georestricted',

         },
         {
             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
         },
         {
             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',

-            'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574',
+            'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',

             'info_dict': {
                 'id': '5142516',
             'info_dict': {
                 'id': '5142516',

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

                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'duration': 186.080,
                 'age_limit': 0,
             },
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'duration': 186.080,
                 'age_limit': 0,
             },

-        },
+            'skip': 'georestricted',
+        }, {
+            'url': 'https://cloud.tvigle.ru/video/5267604/',
+            'only_matching': True,
+        }

     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):

-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')

 
 

-        video_id = self._html_search_regex(
-            r'<li class="video-preview current_playing" id="(\d+)">', webpage, 'video id')
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._html_search_regex(
+                (r'<div[^>]+class=["\']player["\'][^>]+id=["\'](\d+)',
+                 r'var\s+cloudId\s*=\s*["\'](\d+)',
+                 r'class="video-preview current_playing" id="(\d+)"'),
+                webpage, 'video id')

 
         video_data = self._download_json(
             'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)
 
         item = video_data['playlist']['items'][0]
 
 
         video_data = self._download_json(
             'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)
 
         item = video_data['playlist']['items'][0]
 

+        videos = item.get('videos')
+
+        error_message = item.get('errorMessage')
+        if not videos and error_message:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+

         title = item['title']
         title = item['title']

-        description = item['description']
-        thumbnail = item['thumbnail']
+        description = item.get('description')
+        thumbnail = item.get('thumbnail')

         duration = float_or_none(item.get('durationMilliseconds'), 1000)
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []
         for vcodec, fmts in item['videos'].items():
         duration = float_or_none(item.get('durationMilliseconds'), 1000)
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []
         for vcodec, fmts in item['videos'].items():

-            for quality, video_url in fmts.items():
+            if vcodec == 'hls':
+                continue
+            for format_id, video_url in fmts.items():
+                if format_id == 'm3u8':
+                    continue
+                height = self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None)

                 formats.append({
                     'url': video_url,
                 formats.append({
                     'url': video_url,

-                    'format_id': '%s-%s' % (vcodec, quality),
+                    'format_id': '%s-%s' % (vcodec, format_id),

                     'vcodec': vcodec,
                     'vcodec': vcodec,

-                    'height': int(quality[:-1]),
-                    'filesize': item['video_files_size'][vcodec][quality],
+                    'height': int_or_none(height),
+                    'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),

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