youtube-dl

commit 23e7f53bd3c75ead7d2e474adff9df47b5e1c34a
parent 5d8df28d2728299d5550355f929e1282c0301464
Author: Sergey M․ <dstftw@gmail.com>
Date:   Wed, 29 Jul 2015 03:43:55 +0600

Merge branch 'purdeaandrei-save_tags_simpler_only_saves_tags_to_info_json'

Diffstat:
M
youtube_dl/extractor/common.py
 | 
11
++++++++---
M
youtube_dl/extractor/youtube.py
 | 
11
++++++++++-

2 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -181,6 +181,7 @@ class InfoExtractor(object):
                     by YoutubeDL if it's missing)
     categories:     A list of categories that the video falls in, for example
                     ["Sports", "Berlin"]
+    tags:           A list of tags assigned to the video, e.g. ["sweden", "pop music"]
     is_live:        True, False, or None (=unknown). Whether this video is a
                     live stream that goes on instead of a fixed-length video.
     start_time:     Time in seconds where the reproduction should start, as
@@ -630,6 +631,12 @@ class InfoExtractor(object):
             template % (content_re, property_re),
         ]
 
+    @staticmethod
+    def _meta_regex(prop):
+        return r'''(?isx)<meta
+                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
+
     def _og_search_property(self, prop, html, name=None, **kargs):
         if name is None:
             name = 'OpenGraph %s' % prop
@@ -660,9 +667,7 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?isx)<meta
-                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
+            self._meta_regex(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
@@ -329,6 +329,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'upload_date': '20121002',
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
+                'tags': ['youtube-dl'],
                 'like_count': int,
                 'dislike_count': int,
                 'start_time': 1,
@@ -343,7 +344,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'upload_date': '20120506',
                 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
-                'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f',
+                'description': 'md5:782e8651347686cba06e58f71ab51773',
+                'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
+                         'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
+                         'iconic ep', 'iconic', 'love', 'it'],
                 'uploader': 'Icona Pop',
                 'uploader_id': 'IconaPop',
             }
@@ -1072,6 +1076,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             video_categories = None
 
+        video_tags = [
+            unescapeHTML(m.group('content'))
+            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
+
         # description
         video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:
@@ -1260,6 +1268,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'thumbnail': video_thumbnail,
             'description': video_description,
             'categories': video_categories,
+            'tags': video_tags,
             'subtitles': video_subtitles,
             'automatic_captions': automatic_captions,
             'duration': video_duration,