Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / vidme.py

diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py
index 5c89824c164272358923e245e60a4f86466287c4..e0b55078b2c9af8bf654ee6cd6982305074cb39b 100644 (file)
--- a/youtube_dl/extractor/vidme.py
+++ b/youtube_dl/extractor/vidme.py
@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,


@@ -12,7 +10,7 @@ from ..utils import (
 
 class VidmeIE(InfoExtractor):
     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
 
 class VidmeIE(InfoExtractor):
     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'

-    _TEST = {
+    _TESTS = [{

         'url': 'https://vid.me/QNB',
         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
         'info_dict': {
         'url': 'https://vid.me/QNB',
         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
         'info_dict': {


@@ -25,15 +23,19 @@ class VidmeIE(InfoExtractor):
             'upload_date': '20140725',
             'thumbnail': 're:^https?://.*\.jpg',
         },
             'upload_date': '20140725',
             'thumbnail': 're:^https?://.*\.jpg',
         },

-    }
+    }, {
+        # From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
+        'url': 'https://vid.me/e/Wmur',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        url = url.replace('vid.me/e/', 'vid.me/')
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
 
         webpage = self._download_webpage(url, video_id)
 

-        video_url = self._html_search_regex(r'<source src="([^"]+)"', webpage, 'video URL')
+        video_url = self._html_search_regex(
+            r'<source src="([^"]+)"', webpage, 'video URL')

 
         title = self._og_search_title(webpage)
         description = self._og_search_description(webpage, default='')
 
         title = self._og_search_title(webpage)
         description = self._og_search_description(webpage, default='')


@@ -44,13 +46,10 @@ class VidmeIE(InfoExtractor):
         duration = float_or_none(self._html_search_regex(
             r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
         view_count = str_to_int(self._html_search_regex(
         duration = float_or_none(self._html_search_regex(
             r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
         view_count = str_to_int(self._html_search_regex(

-            r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False))
+            r'<(?:li|span) class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False))

         like_count = str_to_int(self._html_search_regex(
             r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
             webpage, 'like count', fatal=False))
         like_count = str_to_int(self._html_search_regex(
             r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
             webpage, 'like count', fatal=False))

-        comment_count = str_to_int(self._html_search_regex(
-            r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">',
-            webpage, 'comment count', fatal=False))

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,


@@ -64,5 +63,4 @@ class VidmeIE(InfoExtractor):
             'duration': duration,
             'view_count': view_count,
             'like_count': like_count,
             'duration': duration,
             'view_count': view_count,
             'like_count': like_count,

-            'comment_count': comment_count,

         }
         }