Merge pull request #7045 from remitamine/ign

[youtube-dl] / youtube_dl / extractor / odnoklassniki.py

diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
index fbc521d1aae02077ae62c5cd0a6c5f9cdcff014a..184c7a323afad57f77e8d9b8c7402e68c721e705 100644 (file)
--- a/youtube_dl/extractor/odnoklassniki.py
+++ b/youtube_dl/extractor/odnoklassniki.py
@@ -2,7 +2,9 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
+    ExtractorError,
     unified_strdate,
     int_or_none,
     qualities,
@@ -11,10 +13,11 @@ from ..utils import (
 
 
 class OdnoklassnikiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
     _TESTS = [{
+        # metadata in JSON
         'url': 'http://ok.ru/video/20079905452',
-        'md5': '8e24ad2da6f387948e7a7d44eb8668fe',
+        'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
         'info_dict': {
             'id': '20079905452',
             'ext': 'mp4',
@@ -26,22 +29,75 @@ class OdnoklassnikiIE(InfoExtractor):
             'like_count': int,
             'age_limit': 0,
         },
+        'skip': 'Video has been blocked',
+    }, {
+        # metadataUrl
+        'url': 'http://ok.ru/video/63567059965189-0',
+        'md5': '9676cf86eff5391d35dea675d224e131',
+        'info_dict': {
+            'id': '63567059965189-0',
+            'ext': 'mp4',
+            'title': 'Девушка без комплексов ...',
+            'duration': 191,
+            'upload_date': '20150518',
+            'uploader_id': '534380003155',
+            'uploader': '☭ Андрей Мещанинов ☭',
+            'like_count': int,
+            'age_limit': 0,
+        },
+    }, {
+        # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
+        'url': 'http://ok.ru/video/64211978996595-1',
+        'md5': '5d7475d428845cd2e13bae6f1a992278',
+        'info_dict': {
+            'id': '64211978996595-1',
+            'ext': 'mp4',
+            'title': 'Космическая среда от 26 августа 2015',
+            'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
+            'duration': 440,
+            'upload_date': '20150826',
+            'uploader_id': '750099571',
+            'uploader': 'Алина П',
+            'age_limit': 0,
+        },
     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,
+    }, {
+        'url': 'http://www.ok.ru/video/20648036891',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.ok.ru/videoembed/20648036891',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://ok.ru/video/%s' % video_id, video_id)
+
+        error = self._search_regex(
+            r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
+            webpage, 'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
 
         player = self._parse_json(
             unescapeHTML(self._search_regex(
-                r'data-attributes="([^"]+)"', webpage, 'player')),
+                r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
+                webpage, 'player', group='player')),
             video_id)
 
-        metadata = self._parse_json(player['flashvars']['metadata'], video_id)
+        flashvars = player['flashvars']
+
+        metadata = flashvars.get('metadata')
+        if metadata:
+            metadata = self._parse_json(metadata, video_id)
+        else:
+            metadata = self._download_json(
+                compat_urllib_parse_unquote(flashvars['metadataUrl']),
+                video_id, 'Downloading metadata JSON')
 
         movie = metadata['movie']
         title = movie['title']
@@ -53,26 +109,17 @@ class OdnoklassnikiIE(InfoExtractor):
         uploader = author.get('name')
 
         upload_date = unified_strdate(self._html_search_meta(
-            'ya:ovs:upload_date', webpage, 'upload date'))
+            'ya:ovs:upload_date', webpage, 'upload date', default=None))
 
         age_limit = None
         adult = self._html_search_meta(
-            'ya:ovs:adult', webpage, 'age limit')
+            'ya:ovs:adult', webpage, 'age limit', default=None)
         if adult:
             age_limit = 18 if adult == 'true' else 0
 
         like_count = int_or_none(metadata.get('likeCount'))
 
-        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
-
-        formats = [{
-            'url': f['url'],
-            'ext': 'mp4',
-            'format_id': f['name'],
-            'quality': quality(f['name']),
-        } for f in metadata['videos']]
-
-        return {
+        info = {
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
@@ -82,5 +129,24 @@ class OdnoklassnikiIE(InfoExtractor):
             'uploader_id': uploader_id,
             'like_count': like_count,
             'age_limit': age_limit,
-            'formats': formats,
         }
+
+        if metadata.get('provider') == 'USER_YOUTUBE':
+            info.update({
+                '_type': 'url_transparent',
+                'url': movie['contentId'],
+            })
+            return info
+
+        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
+
+        formats = [{
+            'url': f['url'],
+            'ext': 'mp4',
+            'format_id': f['name'],
+            'quality': quality(f['name']),
+        } for f in metadata['videos']]
+        self._sort_formats(formats)
+
+        info['formats'] = formats
+        return info