New upstream version 2017.05.18.1

[youtubedl] / youtube_dl / extractor / odnoklassniki.py

diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
index 986708e75e45f7f24f656f319767e6adbd9504ea..854b6800c18bd47d2ed1b40cace0969a22eebc75 100644 (file)
--- a/youtube_dl/extractor/odnoklassniki.py
+++ b/youtube_dl/extractor/odnoklassniki.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import (
 
 from .common import InfoExtractor
 from ..compat import (

+    compat_etree_fromstring,

     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
     compat_parse_qs,
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,


@@ -37,7 +38,7 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         # metadataUrl
         'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
     }, {
         # metadataUrl
         'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',

-        'md5': '9676cf86eff5391d35dea675d224e131',
+        'md5': '6ff470ea2dd51d5d18c295a355b0b6bc',

         'info_dict': {
             'id': '63567059965189-0',
             'ext': 'mp4',
         'info_dict': {
             'id': '63567059965189-0',
             'ext': 'mp4',


@@ -53,7 +54,7 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
         'url': 'http://ok.ru/video/64211978996595-1',
     }, {
         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
         'url': 'http://ok.ru/video/64211978996595-1',

-        'md5': '5d7475d428845cd2e13bae6f1a992278',
+        'md5': '2f206894ffb5dbfcce2c5a14b909eea5',

         'info_dict': {
             'id': '64211978996595-1',
             'ext': 'mp4',
         'info_dict': {
             'id': '64211978996595-1',
             'ext': 'mp4',


@@ -61,8 +62,8 @@ class OdnoklassnikiIE(InfoExtractor):
             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
             'duration': 440,
             'upload_date': '20150826',
             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
             'duration': 440,
             'upload_date': '20150826',

-            'uploader_id': '750099571',
-            'uploader': 'Ð\90лина Ð\9f',
+            'uploader_id': 'tvroscosmos',
+            'uploader': 'ТелеÑ\81Ñ\82Ñ\83диÑ\8f РоÑ\81коÑ\81моÑ\81а',

             'age_limit': 0,
         },
     }, {
             'age_limit': 0,
         },
     }, {


@@ -81,6 +82,7 @@ class OdnoklassnikiIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,
         },

+        'skip': 'Video has not been found',

     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,
     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,


@@ -176,14 +178,32 @@ class OdnoklassnikiIE(InfoExtractor):
             })
             return info
 
             })
             return info
 

-        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
+        quality = qualities(('4', '0', '1', '2', '3', '5'))

 
         formats = [{
             'url': f['url'],
             'ext': 'mp4',
             'format_id': f['name'],
 
         formats = [{
             'url': f['url'],
             'ext': 'mp4',
             'format_id': f['name'],

-            'quality': quality(f['name']),

         } for f in metadata['videos']]
         } for f in metadata['videos']]

+
+        m3u8_url = metadata.get('hlsManifestUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        dash_manifest = metadata.get('metadataEmbedded')
+        if dash_manifest:
+            formats.extend(self._parse_mpd_formats(
+                compat_etree_fromstring(dash_manifest), 'mpd'))
+
+        for fmt in formats:
+            fmt_type = self._search_regex(
+                r'\btype[/=](\d)', fmt['url'],
+                'format type', default=None)
+            if fmt_type:
+                fmt['quality'] = quality(fmt_type)
+

         self._sort_formats(formats)
 
         info['formats'] = formats
         self._sort_formats(formats)
 
         info['formats'] = formats