Merge tag 'upstream/2016.08.17'

[youtubedl] / youtube_dl / extractor / rutube.py

diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py
index e3e9bc07ffbf9cfbfb6a092f6f88583a31a012fb..9ca4ae147cb1e3c430de3abd9fd0927aaee2ed5a 100644 (file)
--- a/youtube_dl/extractor/rutube.py
+++ b/youtube_dl/extractor/rutube.py
@@ -1,58 +1,186 @@
 # encoding: utf-8
 # encoding: utf-8

+from __future__ import unicode_literals
+

 import re
 import re

-import json
+import itertools

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

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

     compat_str,
     compat_str,

-    ExtractorError,
+)
+from ..utils import (
+    determine_ext,
+    unified_strdate,

 )
 
 
 class RutubeIE(InfoExtractor):
 )
 
 
 class RutubeIE(InfoExtractor):

-    _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
-
-    _TEST = {
-        u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
-        u'info_dict': {
-            u'title': u'Раненный кенгуру забежал в аптеку',
-            u'uploader': u'NTDRussian',
-            u'uploader_id': u'29790',
+    IE_NAME = 'rutube'
+    IE_DESC = 'Rutube videos'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|play/embed)/(?P<id>[\da-z]{32})'
+
+    _TESTS = [{
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'info_dict': {
+            'id': '3eac3b4561676c17df9132a9a1e62e3e',
+            'ext': 'mp4',
+            'title': 'Раненный кенгуру забежал в аптеку',
+            'description': 'http://www.ntdtv.ru ',
+            'duration': 80,
+            'uploader': 'NTDRussian',
+            'uploader_id': '29790',
+            'upload_date': '20131016',
+            'age_limit': 0,

         },
         },

-        u'params': {
+        'params': {

             # It requires ffmpeg (m3u8 download)
             # It requires ffmpeg (m3u8 download)

-            u'skip_download': True,
+            'skip_download': True,

         },
         },

-    }
-
-    def _get_api_response(self, short_id, subpath):
-        api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id)
-        response_json = self._download_webpage(api_url, short_id,
-            u'Downloading %s json' % subpath)
-        return json.loads(response_json)
+    }, {
+        'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
+        'only_matching': True,
+    }]

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

-        mobj = re.match(self._VALID_URL, url)
-        long_id = mobj.group('long_id')
-        webpage = self._download_webpage(url, long_id)
-        og_video = self._og_search_video_url(webpage)
-        short_id = compat_urlparse.urlparse(og_video).path[1:]
-        options = self._get_api_response(short_id, 'options')
-        trackinfo = self._get_api_response(short_id, 'trackinfo')
+        video_id = self._match_id(url)
+        video = self._download_json(
+            'http://rutube.ru/api/video/%s/?format=json' % video_id,
+            video_id, 'Downloading video JSON')
+

         # Some videos don't have the author field
         # Some videos don't have the author field

-        author = trackinfo.get('author') or {}
-        m3u8_url = trackinfo['video_balancer'].get('m3u8')
-        if m3u8_url is None:
-            raise ExtractorError(u'Couldn\'t find m3u8 manifest url')
+        author = video.get('author') or {}
+
+        options = self._download_json(
+            'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
+            video_id, 'Downloading options JSON')
+
+        formats = []
+        for format_id, format_url in options['video_balancer'].items():
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id, fatal=False))
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)

 
         return {
 
         return {

-            'id': trackinfo['id'],
-            'title': trackinfo['title'],
-            'url': m3u8_url,
-            'ext': 'mp4',
-            'thumbnail': options['thumbnail_url'],
+            'id': video['id'],
+            'title': video['title'],
+            'description': video['description'],
+            'duration': video['duration'],
+            'view_count': video['hits'],
+            'formats': formats,
+            'thumbnail': video['thumbnail_url'],

             'uploader': author.get('name'),
             'uploader_id': compat_str(author['id']) if author else None,
             'uploader': author.get('name'),
             'uploader_id': compat_str(author['id']) if author else None,

+            'upload_date': unified_strdate(video['created_ts']),
+            'age_limit': 18 if video['is_adult'] else 0,

         }
         }

+
+
+class RutubeEmbedIE(InfoExtractor):
+    IE_NAME = 'rutube:embed'
+    IE_DESC = 'Rutube embedded videos'
+    _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
+        'info_dict': {
+            'id': 'a10e53b86e8f349080f718582ce4c661',
+            'ext': 'mp4',
+            'upload_date': '20131223',
+            'uploader_id': '297833',
+            'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
+            'uploader': 'subziro89 ILya',
+            'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
+        },
+        'params': {
+            'skip_download': 'Requires ffmpeg',
+        },
+    }, {
+        'url': 'http://rutube.ru/play/embed/8083783',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        embed_id = self._match_id(url)
+        webpage = self._download_webpage(url, embed_id)
+
+        canonical_url = self._html_search_regex(
+            r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
+            'Canonical URL')
+        return self.url_result(canonical_url, 'Rutube')
+
+
+class RutubeChannelIE(InfoExtractor):
+    IE_NAME = 'rutube:channel'
+    IE_DESC = 'Rutube channels'
+    _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/tags/video/1800/',
+        'info_dict': {
+            'id': '1800',
+        },
+        'playlist_mincount': 68,
+    }]
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
+
+    def _extract_videos(self, channel_id, channel_title=None):
+        entries = []
+        for pagenum in itertools.count(1):
+            page = self._download_json(
+                self._PAGE_TEMPLATE % (channel_id, pagenum),
+                channel_id, 'Downloading page %s' % pagenum)
+            results = page['results']
+            if not results:
+                break
+            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
+            if not page['has_next']:
+                break
+        return self.playlist_result(entries, channel_id, channel_title)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id = mobj.group('id')
+        return self._extract_videos(channel_id)
+
+
+class RutubeMovieIE(RutubeChannelIE):
+    IE_NAME = 'rutube:movie'
+    IE_DESC = 'Rutube movies'
+    _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+    _TESTS = []
+
+    _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
+
+    def _real_extract(self, url):
+        movie_id = self._match_id(url)
+        movie = self._download_json(
+            self._MOVIE_TEMPLATE % movie_id, movie_id,
+            'Downloading movie JSON')
+        movie_name = movie['name']
+        return self._extract_videos(movie_id, movie_name)
+
+
+class RutubePersonIE(RutubeChannelIE):
+    IE_NAME = 'rutube:person'
+    IE_DESC = 'Rutube person videos'
+    _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://rutube.ru/video/person/313878/',
+        'info_dict': {
+            'id': '313878',
+        },
+        'playlist_mincount': 37,
+    }]
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'