[tudou] Merge into youku extractor (fixes #12214)

Also, there are no tudou playlists anymore. All playlist URLs points to youku
playlists.

ChangeLog

@@ -5,6 +5,7 @@ Core
 * [postprocessor/ffmpeg] Fix metadata filename handling on Python 2 (#13182)
 
 Extractors
+* [tudou] Merge into youku extractor (#12214)
 * [youku:show] Fix extraction
 * [youku] Fix extraction (#13191)
 

youtube_dl/extractor/extractors.py

@@ -1019,11 +1019,6 @@
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
-from .tudou import (
-    TudouIE,
-    TudouPlaylistIE,
-    TudouAlbumIE,
-)
 from .tumblr import TumblrIE
 from .tunein import (
     TuneInClipIE,

youtube_dl/extractor/tudou.py

@@ -3,138 +3,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    InAdvancePagedList,
-    float_or_none,
-    unescapeHTML,
-)
-
-
-class TudouIE(InfoExtractor):
-    IE_NAME = 'tudou'
-    _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P<id>[\w-]{11})'
-    _TESTS = [{
-        'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
-        'md5': '140a49ed444bd22f93330985d8475fcb',
-        'info_dict': {
-            'id': '159448201',
-            'ext': 'f4v',
-            'title': '卡马乔国足开大脚长传冲吊集锦',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1372113489000,
-            'description': '卡马乔卡家军，开大脚先进战术不完全集锦！',
-            'duration': 289.04,
-            'view_count': int,
-            'filesize': int,
-        }
-    }, {
-        'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
-        'info_dict': {
-            'id': '117049447',
-            'ext': 'f4v',
-            'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1349207518000,
-            'description': 'md5:294612423894260f2dcd5c6c04fe248b',
-            'duration': 5478.33,
-            'view_count': int,
-            'filesize': int,
-        }
-    }]
-
-    _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
-
-    # Translated from tudou/tools/TVCHelper.as in PortalPlayer_193.swf
-    # 0001, 0002 and 4001 are not included as they indicate temporary issues
-    TVC_ERRORS = {
-        '0003': 'The video is deleted or does not exist',
-        '1001': 'This video is unavailable due to licensing issues',
-        '1002': 'This video is unavailable as it\'s under review',
-        '1003': 'This video is unavailable as it\'s under review',
-        '3001': 'Password required',
-        '5001': 'This video is available in Mainland China only due to licensing issues',
-        '7001': 'This video is unavailable',
-        '8001': 'This video is unavailable due to licensing issues',
-    }
-
-    def _url_for_id(self, video_id, quality=None):
-        info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
-        if quality:
-            info_url += '&hd' + quality
-        xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page')
-        error = xml_data.attrib.get('error')
-        if error is not None:
-            raise ExtractorError('Tudou said: %s' % error, expected=True)
-        final_url = xml_data.text
-        return final_url
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        item_data = self._download_json(
-            'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id)
-
-        youku_vcode = item_data.get('vcode')
-        if youku_vcode:
-            return self.url_result('youku:' + youku_vcode, ie='Youku')
-
-        if not item_data.get('itemSegs'):
-            tvc_code = item_data.get('tvcCode')
-            if tvc_code:
-                err_msg = self.TVC_ERRORS.get(tvc_code)
-                if err_msg:
-                    raise ExtractorError('Tudou said: %s' % err_msg, expected=True)
-                raise ExtractorError('Unexpected error %s returned from Tudou' % tvc_code)
-            raise ExtractorError('Unxpected error returned from Tudou')
-
-        title = unescapeHTML(item_data['kw'])
-        description = item_data.get('desc')
-        thumbnail_url = item_data.get('pic')
-        view_count = int_or_none(item_data.get('playTimes'))
-        timestamp = int_or_none(item_data.get('pt'))
-
-        segments = self._parse_json(item_data['itemSegs'], video_id)
-        # It looks like the keys are the arguments that have to be passed as
-        # the hd field in the request url, we pick the higher
-        # Also, filter non-number qualities (see issue #3643).
-        quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
-                         key=lambda k: int(k))[-1]
-        parts = segments[quality]
-        len_parts = len(parts)
-        if len_parts > 1:
-            self.to_screen('%s: found %s parts' % (video_id, len_parts))
-
-        def part_func(partnum):
-            part = parts[partnum]
-            part_id = part['k']
-            final_url = self._url_for_id(part_id, quality)
-            ext = (final_url.split('?')[0]).split('.')[-1]
-            return [{
-                'id': '%s' % part_id,
-                'url': final_url,
-                'ext': ext,
-                'title': title,
-                'thumbnail': thumbnail_url,
-                'description': description,
-                'view_count': view_count,
-                'timestamp': timestamp,
-                'duration': float_or_none(part.get('seconds'), 1000),
-                'filesize': int_or_none(part.get('size')),
-                'http_headers': {
-                    'Referer': self._PLAYER_URL,
-                },
-            }]
-
-        entries = InAdvancePagedList(part_func, len_parts, 1)
-
-        return {
-            '_type': 'multi_video',
-            'entries': entries,
-            'id': video_id,
-            'title': title,
-        }
 
 
 class TudouPlaylistIE(InfoExtractor):

youtube_dl/extractor/youku.py

@@ -22,7 +22,9 @@ class YoukuIE(InfoExtractor):
     IE_DESC = '优酷'
     _VALID_URL = r'''(?x)
         (?:
-            http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+            https?://(
+                (?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+                video\.tudou\.com/v/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
     '''
@@ -71,6 +73,16 @@ class YoukuIE(InfoExtractor):
             'ext': 'mp4',
             'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
         },
+    }, {
+        'url': 'http://video.tudou.com/v/XMjIyNzAzMTQ4NA==.html?f=46177805',
+        'info_dict': {
+            'id': 'XMjIyNzAzMTQ4NA',
+            'ext': 'mp4',
+            'title': '卡马乔国足开大脚长传冲吊集锦',
+        },
+    }, {
+        'url': 'http://video.tudou.com/v/XMjE4ODI3OTg2MA==.html',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -107,7 +119,7 @@ def _real_extract(self, url):
         # request basic data
         basic_data_params = {
             'vid': video_id,
-            'ccode': '0401',
+            'ccode': '0402' if 'tudou.com' in url else '0401',
             'client_ip': '192.168.1.1',
             'utid': cna,
             'client_ts': time.time() / 1000,