Merge tag 'upstream/2015.11.27.1'

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index b4ad513a0d18ecbae558deceb6234efaa5ce5415..8938c0e4561d2c6163158e409106dd2e928e85bf 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,7 +4,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    ExtractorError,

     unified_strdate,
     str_to_int,
     int_or_none,
     unified_strdate,
     str_to_int,
     int_or_none,


@@ -22,7 +21,7 @@ class XHamsterIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'FemaleAgent Shy beauty takes the bait',
                 'upload_date': '20121014',
                 'ext': 'mp4',
                 'title': 'FemaleAgent Shy beauty takes the bait',
                 'upload_date': '20121014',

-                'uploader_id': 'Ruseful2011',
+                'uploader': 'Ruseful2011',

                 'duration': 893,
                 'age_limit': 18,
             }
                 'duration': 893,
                 'age_limit': 18,
             }


@@ -34,7 +33,7 @@ class XHamsterIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Britney Spears  Sexy Booty',
                 'upload_date': '20130914',
                 'ext': 'mp4',
                 'title': 'Britney Spears  Sexy Booty',
                 'upload_date': '20130914',

-                'uploader_id': 'jojo747400',
+                'uploader': 'jojo747400',

                 'duration': 200,
                 'age_limit': 18,
             }
                 'duration': 200,
                 'age_limit': 18,
             }


@@ -46,12 +45,12 @@ class XHamsterIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):

-        def extract_video_url(webpage):
-            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
-            if mp4 is None:
-                raise ExtractorError('Unable to extract media URL')
-            else:
-                return mp4.group(1)
+        def extract_video_url(webpage, name):
+            return self._search_regex(
+                [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
+                 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
+                 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
+                webpage, name, group='mp4')

 
         def is_hd(webpage):
             return '<div class=\'icon iconHD\'' in webpage
 
         def is_hd(webpage):
             return '<div class=\'icon iconHD\'' in webpage


@@ -64,7 +63,9 @@ class XHamsterIE(InfoExtractor):
         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 

-        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
+        title = self._html_search_regex(
+            [r'<title>(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)</title>',
+             r'<h1>([^<]+)</h1>'], webpage, 'title')

 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)


@@ -75,10 +76,14 @@ class XHamsterIE(InfoExtractor):
         if upload_date:
             upload_date = unified_strdate(upload_date)
 
         if upload_date:
             upload_date = unified_strdate(upload_date)
 

-        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-                                              webpage, 'uploader id', default='anonymous')
+        uploader = self._html_search_regex(
+            r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+            webpage, 'uploader', default='anonymous')

 
 

-        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+        thumbnail = self._search_regex(
+            [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+             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 = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
                                                           webpage, 'duration', fatal=False))


@@ -97,7 +102,9 @@ class XHamsterIE(InfoExtractor):
 
         hd = is_hd(webpage)
 
 
         hd = is_hd(webpage)
 

-        video_url = extract_video_url(webpage)
+        format_id = 'hd' if hd else 'sd'
+
+        video_url = extract_video_url(webpage, format_id)

         formats = [{
             'url': video_url,
             'format_id': 'hd' if hd else 'sd',
         formats = [{
             'url': video_url,
             'format_id': 'hd' if hd else 'sd',


@@ -108,7 +115,7 @@ class XHamsterIE(InfoExtractor):
             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):

-                video_url = extract_video_url(webpage)
+                video_url = extract_video_url(webpage, 'hd')

                 formats.append({
                     'url': video_url,
                     'format_id': 'hd',
                 formats.append({
                     'url': video_url,
                     'format_id': 'hd',


@@ -122,7 +129,7 @@ class XHamsterIE(InfoExtractor):
             'title': title,
             'description': description,
             'upload_date': upload_date,
             'title': title,
             'description': description,
             'upload_date': upload_date,

-            'uploader_id': uploader_id,
+            'uploader': uploader,

             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,
             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,