[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py
index b1322f13f8b62a4618b1f857dadf0829b9752238..4aef186ea22b4dab1be50a0bdd6dbcbbcae1e2b1 100644 (file)
--- a/youtube_dl/extractor/playvid.py
+++ b/youtube_dl/extractor/playvid.py
@@ -3,31 +3,50 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
+)
 from ..utils import (
-    compat_urllib_parse,
+    clean_html,
+    ExtractorError,
 )
 
 
 class PlayvidIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
-    _TEST = {
-        'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
-        'md5': '44930f8afa616efdf9482daf4fe53e1e',
+    _VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
+    _TESTS = [{
+        'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
+        'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
         'info_dict': {
-            'id': 'agbDDi7WZTV',
+            'id': 'RnmBNgtrrJu',
             'ext': 'mp4',
-            'title': 'Michelle Lewin in Miami Beach',
-            'duration': 240,
+            'title': 'md5:9256d01c6317e3f703848b5906880dc8',
+            'duration': 82,
             'age_limit': 18,
-        }
-    }
+        },
+        'skip': 'Video removed due to ToS',
+    }, {
+        'url': 'http://www.playvid.com/watch/hwb0GpNkzgH',
+        'md5': '39d49df503ad7b8f23a4432cbf046477',
+        'info_dict': {
+            'id': 'hwb0GpNkzgH',
+            'ext': 'mp4',
+            'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park',
+            'age_limit': 18,
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        m_error = re.search(
+            r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
+        if m_error:
+            raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
+
         video_title = None
         duration = None
         video_thumbnail = None
@@ -37,7 +56,7 @@ class PlayvidIE(InfoExtractor):
         flashvars = self._html_search_regex(
             r'flashvars="(.+?)"', webpage, 'flashvars')
 
-        infos = compat_urllib_parse.unquote(flashvars).split(r'&')
+        infos = compat_urllib_parse_unquote(flashvars).split(r'&')
         for info in infos:
             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
             if videovars_match:
@@ -45,7 +64,7 @@ class PlayvidIE(InfoExtractor):
                 val = videovars_match.group(2)
 
                 if key == 'title':
-                    video_title = compat_urllib_parse.unquote_plus(val)
+                    video_title = compat_urllib_parse_unquote_plus(val)
                 if key == 'duration':
                     try:
                         duration = int(val)