]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/xhamster.py
Merge tag 'upstream/2016.06.25'
[youtubedl] / youtube_dl / extractor / xhamster.py
index 8938c0e4561d2c6163158e409106dd2e928e85bf..bd8e1af2e0f6c25fc44aea36c23b813b092b4438 100644 (file)
@@ -4,45 +4,60 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
-    str_to_int,
+    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,
-                'age_limit': 18,
-            }
+    _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',
+        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'info_dict': {
+            'id': '1509445',
+            'ext': 'mp4',
+            'title': 'FemaleAgent Shy beauty takes the bait',
+            'upload_date': '20121014',
+            'uploader': 'Ruseful2011',
+            'duration': 893.52,
+            '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,
+        },
+    }, {
+        # empty seo
+        '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,
         },
-        {
-            '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):
@@ -64,20 +79,21 @@ class XHamsterIE(InfoExtractor):
         webpage = self._download_webpage(mrss_url, video_id)
 
         title = self._html_search_regex(
-            [r'<title>(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)</title>',
-             r'<h1>([^<]+)</h1>'], webpage, 'title')
+            [r'<h1[^>]*>([^<]+)</h1>',
+             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+            webpage, 'title')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
         description = mobj.group(1) if mobj else None
 
-        upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
-                                              webpage, 'upload date', fatal=False)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
+        upload_date = unified_strdate(self._search_regex(
+            r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+            webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
-            r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(
@@ -85,12 +101,13 @@ class XHamsterIE(InfoExtractor):
              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
-                                                          webpage, 'duration', fatal=False))
+        duration = float_or_none(self._search_regex(
+            r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
+            webpage, 'duration', fatal=False, group='duration'))
 
-        view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
-        if view_count:
-            view_count = str_to_int(view_count)
+        view_count = int_or_none(self._search_regex(
+            r'content=["\']User(?:View|Play)s:(\d+)',
+            webpage, 'view count', fatal=False))
 
         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
@@ -168,7 +185,13 @@ class XHamsterEmbedIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(
-            r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
-            webpage, 'xhamster url')
+            r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
+            webpage, 'xhamster url', default=None)
+
+        if not video_url:
+            vars = self._parse_json(
+                self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+                video_id)
+            video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 
         return self.url_result(video_url, 'XHamster')