Merge pull request #1622 from rbrito/fix-extension

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index b02ae25727f2843be3952670e8eba617ff23b749..7a7bbe26511436e8fae54f6f07ed5a3f741d48ba 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -236,11 +236,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '136': 'mp4',
         '137': 'mp4',
         '138': 'mp4',
-        '139': 'mp4',
-        '140': 'mp4',
-        '141': 'mp4',
         '160': 'mp4',
 
+        # Dash mp4 audio
+        '139': 'm4a',
+        '140': 'm4a',
+        '141': 'm4a',
+
         # Dash webm
         '171': 'webm',
         '172': 'webm',
@@ -1116,6 +1118,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'lang': lang,
                 'v': video_id,
                 'fmt': self._downloader.params.get('subtitlesformat'),
+                'name': l[0],
             })
             url = u'http://www.youtube.com/api/timedtext?' + params
             sub_lang_list[lang] = url
@@ -1149,7 +1152,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             list_page = self._download_webpage(list_url, video_id)
             caption_list = xml.etree.ElementTree.fromstring(list_page.encode('utf-8'))
             original_lang_node = caption_list.find('track')
-            if original_lang_node.attrib.get('kind') != 'asr' :
+            if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' :
                 self._downloader.report_warning(u'Video doesn\'t have automatic captions')
                 return {}
             original_lang = original_lang_node.attrib['lang_code']
@@ -1249,10 +1252,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             url_map[itag] = format_url
         return url_map
 
-    def _real_extract(self, url):
-        if re.match(r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$', url):
-            self._downloader.report_warning(u'Did you forget to quote the URL? Remember that & is a meta-character in most shells, so you want to put the URL in quotes, like  youtube-dl \'http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc\' (or simply  youtube-dl BaW_jenozKc  ).')
+    def _extract_annotations(self, video_id):
+        url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
+        return self._download_webpage(url, video_id, note=u'Searching for annotations.', errnote=u'Unable to download video annotations.')
 
+    def _real_extract(self, url):
         # Extract original video URL from URL with redirection, like age verification, using next_url parameter
         mobj = re.search(self._NEXT_URL_RE, url)
         if mobj:
@@ -1384,6 +1388,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         else:
             video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
 
+        # annotations
+        video_annotations = None
+        if self._downloader.params.get('writeannotations', False):
+                video_annotations = self._extract_annotations(video_id)
+
         # Decide which formats to download
 
         try:
@@ -1497,6 +1506,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'subtitles':    video_subtitles,
                 'duration':     video_duration,
                 'age_limit':    18 if age_gate else 0,
+                'annotations':  video_annotations
             })
         return results
 
@@ -1637,7 +1647,7 @@ class YoutubeChannelIE(InfoExtractor):
 
 class YoutubeUserIE(InfoExtractor):
     IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
-    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
+    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
     _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
     _GDATA_PAGE_SIZE = 50
     _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
@@ -1830,3 +1840,18 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
         webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
         playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, u'favourites playlist id')
         return self.url_result(playlist_id, 'YoutubePlaylist')
+
+
+class YoutubeTruncatedURLIE(InfoExtractor):
+    IE_NAME = 'youtube:truncated_url'
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$'
+
+    def _real_extract(self, url):
+        raise ExtractorError(
+            u'Did you forget to quote the URL? Remember that & is a meta '
+            u'character in most shells, so you want to put the URL in quotes, '
+            u'like  youtube-dl '
+            u'\'http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc\''
+            u' (or simply  youtube-dl BaW_jenozKc  ).',
+            expected=True)