debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.

[youtubedl] / youtube_dl / extractor / tumblr.py

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index 2882c1809e0bd55c1e6c8b441c19293aeb64d301..2a1ae5a717cf7b2af16bf5a1ce3ef7494e28a7a6 100644 (file)
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -4,13 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
-    ExtractorError,
-)

 
 
 class TumblrIE(InfoExtractor):
 
 
 class TumblrIE(InfoExtractor):

-    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
+    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'

     _TESTS = [{
         'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
         'md5': '479bb068e5b16462f5176a6828829767',
     _TESTS = [{
         'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
         'md5': '479bb068e5b16462f5176a6828829767',


@@ -18,7 +15,7 @@ class TumblrIE(InfoExtractor):
             'id': '54196191430',
             'ext': 'mp4',
             'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
             'id': '54196191430',
             'ext': 'mp4',
             'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',

-            'description': 'md5:dfac39636969fe6bf1caa2d50405f069',
+            'description': 'md5:37db8211e40b50c7c44e95da14f630b7',

             'thumbnail': 're:http://.*\.jpg',
         }
     }, {
             'thumbnail': 're:http://.*\.jpg',
         }
     }, {


@@ -27,7 +24,7 @@ class TumblrIE(InfoExtractor):
         'info_dict': {
             'id': '90208453769',
             'ext': 'mp4',
         'info_dict': {
             'id': '90208453769',
             'ext': 'mp4',

-            'title': '5SOS STRUM ;)',
+            'title': '5SOS STRUM ;]',

             'description': 'md5:dba62ac8639482759c8eb10ce474586a',
             'thumbnail': 're:http://.*\.jpg',
         }
             'description': 'md5:dba62ac8639482759c8eb10ce474586a',
             'thumbnail': 're:http://.*\.jpg',
         }


@@ -41,28 +38,24 @@ class TumblrIE(InfoExtractor):
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
         webpage = self._download_webpage(url, video_id)
 
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
         webpage = self._download_webpage(url, video_id)
 

-        re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
-        video = re.search(re_video, webpage)
-        if video is None:
-            raise ExtractorError('Unable to extract video')
-        video_url = video.group('video_url')
-        ext = video.group('ext')
-
-        video_thumbnail = self._search_regex(
-            r'posters.*?\[\\x22(.*?)\\x22',
-            webpage, 'thumbnail', fatal=False)  # We pick the first poster
-        if video_thumbnail:
-            video_thumbnail = video_thumbnail.replace('\\\\/', '/')
+        iframe_url = self._search_regex(
+            r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
+            webpage, 'iframe url')
+        iframe = self._download_webpage(iframe_url, video_id)
+        video_url = self._search_regex(r'<source src="([^"]+)"',
+                                       iframe, 'video url')

 
         # The only place where you can get a title, it's not complete,
         # but searching in other places doesn't work for all videos
 
         # The only place where you can get a title, it's not complete,
         # but searching in other places doesn't work for all videos

-        video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
-            webpage, 'title', flags=re.DOTALL)
+        video_title = self._html_search_regex(
+            r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
+            webpage, 'title')

 
 

-        return [{'id': video_id,
-                 'url': video_url,
-                 'title': video_title,
-                 'description': self._html_search_meta('description', webpage),
-                 'thumbnail': video_thumbnail,
-                 'ext': ext
-                 }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': video_title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }