Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / tvigle.py

diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index 0921cc5f822f5bf0bcfefae8d6ef063e88f6e29d..dc3a8334a6b335143dff417d805a26df412d8783 100644 (file)
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -5,80 +5,105 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    unified_strdate,
-    clean_html,
+    ExtractorError,
+    float_or_none,

     int_or_none,
     int_or_none,

+    parse_age_limit,

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

 
     _TESTS = [
         {
 
     _TESTS = [
         {

-            'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081',
-            'md5': '09afba4616666249f087efc6dcf83cb3',
+            'url': 'http://www.tvigle.ru/video/sokrat/',
+            'md5': '36514aed3657d4f70b4b2cef8eb520cd',

             'info_dict': {
             'info_dict': {

-                'id': '503081',
+                'id': '1848932',
+                'display_id': 'sokrat',

                 'ext': 'flv',
                 'ext': 'flv',

-                'title': 'Брат 2 ',
-                'description': 'md5:f5a42970f50648cee3d7ad740f3ae769',
-                'upload_date': '20110919',
+                'title': 'Сократ',
+                'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
+                'duration': 6586,
+                'age_limit': 12,

             },
             },

+            'skip': 'georestricted',

         },
         {
         },
         {

-            'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433',
+            'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',

             'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
             'info_dict': {
             'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
             'info_dict': {

-                'id': '676433',
+                'id': '5142516',

                 'ext': 'flv',
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'ext': 'flv',
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',

-                'upload_date': '20121218',
+                'duration': 186.080,
+                'age_limit': 0,

             },
             },

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

     ]
 
     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')

+        display_id = mobj.group('display_id')

 
 

-        video_data = self._download_xml(
-            'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML')
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._html_search_regex(
+                r'class="video-preview current_playing" id="(\d+)">',
+                webpage, 'video id')

 
 

-        video = video_data.find('./video')
+        video_data = self._download_json(
+            'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)

 
 

-        title = video.get('name')
-        description = video.get('anons')
-        if description:
-            description = clean_html(description)
-        thumbnail = video_data.get('img')
-        upload_date = unified_strdate(video.get('date'))
-        like_count = int_or_none(video.get('vtp'))
+        item = video_data['playlist']['items'][0]

 
 

-        formats = []
-        for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]):
-            video_url = video.get(format_id)
-            if not video_url:
-                continue
-            formats.append({
-                'url': video_url,
-                'format_id': format_id,
-                'format_note': format_note,
-                'quality': num,
-            })
+        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']
+        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():
+            for format_id, video_url in fmts.items():
+                if format_id == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', m3u8_id=vcodec))
+                    continue
+                height = self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None)
+                formats.append({
+                    'url': video_url,
+                    'format_id': '%s-%s' % (vcodec, format_id),
+                    'vcodec': vcodec,
+                    'height': int_or_none(height),
+                    'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),
+                })

         self._sort_formats(formats)
 
         return {
             'id': video_id,
         self._sort_formats(formats)
 
         return {
             'id': video_id,

+            'display_id': display_id,

             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

-            'upload_date': upload_date,
-            'like_count': like_count,
-            'age_limit': 18,
+            'duration': duration,
+            'age_limit': age_limit,

             'formats': formats,
             'formats': formats,

-        }
\ No newline at end of file
+        }