Update version in the changelog.

[youtubedl] / youtube_dl / extractor / mtv.py

diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index bc7f49ebbac86cda7aa1bb711076b783e24bfea8..302c9bf35bc6bb533c10f35ea11cd500012bba0a 100644 (file)
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -2,7 +2,7 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

-from .subtitles import SubtitlesInfoExtractor
+from .common import InfoExtractor

 from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,


@@ -23,8 +23,9 @@ def _media_xml_tag(tag):
     return '{http://search.yahoo.com/mrss/}%s' % tag
 
 
     return '{http://search.yahoo.com/mrss/}%s' % tag
 
 

-class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
+class MTVServicesInfoExtractor(InfoExtractor):

     _MOBILE_TEMPLATE = None
     _MOBILE_TEMPLATE = None

+    _LANG = None

 
     @staticmethod
     def _id_from_uri(uri):
 
     @staticmethod
     def _id_from_uri(uri):


@@ -66,7 +67,7 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
         return [{'url': url, 'ext': 'mp4'}]
 
     def _extract_video_formats(self, mdoc, mtvn_id):
         return [{'url': url, 'ext': 'mp4'}]
 
     def _extract_video_formats(self, mdoc, mtvn_id):

-        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
+        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:

             if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
                 self.to_screen('The normal version is not available from your '
                                'country, trying with the mobile version')
             if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
                 self.to_screen('The normal version is not available from your '
                                'country, trying with the mobile version')


@@ -95,25 +96,15 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
 
     def _extract_subtitles(self, mdoc, mtvn_id):
         subtitles = {}
 
     def _extract_subtitles(self, mdoc, mtvn_id):
         subtitles = {}

-        FORMATS = {
-            'scc': 'cea-608',
-            'eia-608': 'cea-608',
-            'xml': 'ttml',
-        }
-        subtitles_format = FORMATS.get(
-            self._downloader.params.get('subtitlesformat'), 'ttml')

         for transcript in mdoc.findall('.//transcript'):
             if transcript.get('kind') != 'captions':
                 continue
             lang = transcript.get('srclang')
         for transcript in mdoc.findall('.//transcript'):
             if transcript.get('kind') != 'captions':
                 continue
             lang = transcript.get('srclang')

-            for typographic in transcript.findall('./typographic'):
-                captions_format = typographic.get('format')
-                if captions_format == subtitles_format:
-                    subtitles[lang] = compat_str(typographic.get('src'))
-                    break
-        if self._downloader.params.get('listsubtitles', False):
-            self._list_available_subtitles(mtvn_id, subtitles)
-        return self.extract_subtitles(mtvn_id, subtitles)
+            subtitles[lang] = [{
+                'url': compat_str(typographic.get('src')),
+                'ext': typographic.get('format')
+            } for typographic in transcript.findall('./typographic')]
+        return subtitles

 
     def _get_video_info(self, itemdoc):
         uri = itemdoc.find('guid').text
 
     def _get_video_info(self, itemdoc):
         uri = itemdoc.find('guid').text


@@ -123,11 +114,20 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
         # Remove the templates, like &device={device}
         mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
         if 'acceptMethods' not in mediagen_url:
         # Remove the templates, like &device={device}
         mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
         if 'acceptMethods' not in mediagen_url:

-            mediagen_url += '&acceptMethods=fms'
+            mediagen_url += '&' if '?' in mediagen_url else '?'
+            mediagen_url += 'acceptMethods=fms'

 
         mediagen_doc = self._download_xml(mediagen_url, video_id,
                                           'Downloading video urls')
 
 
         mediagen_doc = self._download_xml(mediagen_url, video_id,
                                           'Downloading video urls')
 

+        item = mediagen_doc.find('./video/item')
+        if item is not None and item.get('type') == 'text':
+            message = '%s returned error: ' % self.IE_NAME
+            if item.get('code') is not None:
+                message += '%s - ' % item.get('code')
+            message += item.text
+            raise ExtractorError(message, expected=True)
+

         description_node = itemdoc.find('description')
         if description_node is not None:
             description = description_node.text.strip()
         description_node = itemdoc.find('description')
         if description_node is not None:
             description = description_node.text.strip()


@@ -142,7 +142,7 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
         if title_el is None:
             title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
         if title_el is None:
             title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:

-            title_el = itemdoc.find('.//title')
+            title_el = itemdoc.find('.//title') or itemdoc.find('./title')

             if title_el.text is None:
                 title_el = None
 
             if title_el.text is None:
                 title_el = None
 


@@ -171,8 +171,15 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})

+        info_url = feed_url + '?'
+        if self._LANG:
+            info_url += 'lang=%s&' % self._LANG
+        info_url += data
+        return self._get_videos_info_from_url(info_url, video_id)
+
+    def _get_videos_info_from_url(self, url, video_id):

         idoc = self._download_xml(
         idoc = self._download_xml(

-            feed_url + '?' + data, video_id,
+            url, video_id,

             'Downloading info', transform_source=fix_xml_ampersands)
         return self.playlist_result(
             [self._get_video_info(item) for item in idoc.findall('.//item')])
             'Downloading info', transform_source=fix_xml_ampersands)
         return self.playlist_result(
             [self._get_video_info(item) for item in idoc.findall('.//item')])


@@ -193,11 +200,15 @@ class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],

-                webpage, 'mgid')
+                webpage, 'mgid', default=None)
+
+        if not mgid:
+            sm4_embed = self._html_search_meta(
+                'sm4:video:embed', webpage, 'sm4 embed', default='')
+            mgid = self._search_regex(
+                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')

 
         videos_info = self._get_videos_info(mgid)
 
         videos_info = self._get_videos_info(mgid)

-        if self._downloader.params.get('listsubtitles', False):
-            return

         return videos_info
 
 
         return videos_info
 
 


@@ -217,6 +228,13 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
         },
     }
 
         },
     }
 

+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+

     def _get_feed_url(self, uri):
         video_id = self._id_from_uri(uri)
         site_id = uri.replace(video_id, '')
     def _get_feed_url(self, uri):
         video_id = self._id_from_uri(uri)
         site_id = uri.replace(video_id, '')


@@ -287,3 +305,65 @@ class MTVIggyIE(MTVServicesInfoExtractor):
         }
     }
     _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'
         }
     }
     _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'

+
+
+class MTVDEIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtv.de'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
+    _TESTS = [{
+        'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
+        'info_dict': {
+            'id': 'music_video-a50bc5f0b3aa4b3190aa',
+            'ext': 'mp4',
+            'title': 'MusicVideo_cro-traum',
+            'description': 'Cro - Traum',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
+        'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
+        'info_dict': {
+            'id': 'local_playlist-f5ae778b9832cc837189',
+            'ext': 'mp4',
+            'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        # single video in pagePlaylist with different id
+        'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
+        'info_dict': {
+            'id': 'local_playlist-4e760566473c4c8c5344',
+            'ext': 'mp4',
+            'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
+            'description': 'MTV Movies Supercut',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
+            video_id)
+
+        # news pages contain single video in playlist with different id
+        if len(playlist) == 1:
+            return self._get_videos_info_from_url(playlist[0]['mrss'], video_id)
+
+        for item in playlist:
+            item_id = item.get('id')
+            if item_id and compat_str(item_id) == video_id:
+                return self._get_videos_info_from_url(item['mrss'], video_id)