[xhamster] Fix duration extraction (closes #11549)

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 314e5020de0ec83e0bf20c72772f843dca71e45f..36a8c98407bcaf8466660279f2e444df48083a3a 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -5,56 +5,59 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     dict_get,
-    float_or_none,
     int_or_none,
+    parse_duration,
     unified_strdate,
 )
 
 
 class XHamsterIE(InfoExtractor):
     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
-    _TESTS = [
-        {
-            'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-            'info_dict': {
-                'id': '1509445',
-                'ext': 'mp4',
-                'title': 'FemaleAgent Shy beauty takes the bait',
-                'upload_date': '20121014',
-                'uploader': 'Ruseful2011',
-                'duration': 893.52,
-                'age_limit': 18,
-            }
+    _TESTS = [{
+        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'info_dict': {
+            'id': '1509445',
+            'ext': 'mp4',
+            'title': 'FemaleAgent Shy beauty takes the bait',
+            'upload_date': '20121014',
+            'uploader': 'Ruseful2011',
+            'duration': 893,
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'info_dict': {
+            'id': '2221348',
+            'ext': 'mp4',
+            'title': 'Britney Spears  Sexy Booty',
+            'upload_date': '20130914',
+            'uploader': 'jojo747400',
+            'duration': 200,
+            'age_limit': 18,
         },
-        {
-            'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-            'info_dict': {
-                'id': '2221348',
-                'ext': 'mp4',
-                'title': 'Britney Spears  Sexy Booty',
-                'upload_date': '20130914',
-                'uploader': 'jojo747400',
-                'duration': 200.48,
-                'age_limit': 18,
-            }
+        'params': {
+            'skip_download': True,
         },
-        {
-            'url': 'http://xhamster.com/movies/5667973/.html',
-            'info_dict': {
-                'id': '5667973',
-                'ext': 'mp4',
-                'title': '....',
-                'upload_date': '20160208',
-                'uploader': 'parejafree',
-                'duration': 72.0,
-                'age_limit': 18,
-            }
+    }, {
+        # empty seo
+        'url': 'http://xhamster.com/movies/5667973/.html',
+        'info_dict': {
+            'id': '5667973',
+            'ext': 'mp4',
+            'title': '....',
+            'upload_date': '20160208',
+            'uploader': 'parejafree',
+            'duration': 72,
+            'age_limit': 18,
         },
-        {
-            'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
-            'only_matching': True,
+        'params': {
+            'skip_download': True,
         },
-    ]
+    }, {
+        'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         def extract_video_url(webpage, name):
@@ -98,9 +101,9 @@ class XHamsterIE(InfoExtractor):
              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        duration = float_or_none(self._search_regex(
-            r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
-            webpage, 'duration', fatal=False, group='duration'))
+        duration = parse_duration(self._search_regex(
+            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+            'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',