Imported Upstream version 2015.01.16

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 279f75e7a1f5b860e81d955c33bb58fcea092cbc..4527567f8fc26c45b091aa868dc77b159576b56c 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -1,111 +1,135 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 from ..utils import (
 import re
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_urllib_parse,
-    unescapeHTML,
-    determine_ext,

     ExtractorError,
     ExtractorError,

+    unified_strdate,
+    str_to_int,
+    int_or_none,
+    parse_duration,

 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""

-    _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
-    _TESTS = [{
-        u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        u'file': u'1509445.flv',
-        u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
-        u'info_dict': {
-            u"upload_date": u"20121014", 
-            u"uploader_id": u"Ruseful2011", 
-            u"title": u"FemaleAgent Shy beauty takes the bait",
-            u"age_limit": 18,
-        }
-    },
-    {
-        u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-        u'file': u'2221348.flv',
-        u'md5': u'970a94178ca4118c5aa3aaea21211b81',
-        u'info_dict': {
-            u"upload_date": u"20130914",
-            u"uploader_id": u"jojo747400",
-            u"title": u"Britney Spears  Sexy Booty",
-            u"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',
+            'info_dict': {
+                'id': '1509445',
+                'ext': 'mp4',
+                'title': 'FemaleAgent Shy beauty takes the bait',
+                'upload_date': '20121014',
+                'uploader_id': '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_id': 'jojo747400',
+                'duration': 200,
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+            'only_matching': True,
+        },
+    ]

 
 

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

         def extract_video_url(webpage):
         def extract_video_url(webpage):

-            mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
-            if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
-            if len(mobj.group('server')) == 0:
-                return compat_urllib_parse.unquote(mobj.group('file'))
+            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
+            if mp4 is None:
+                raise ExtractorError('Unable to extract media URL')

             else:
             else:

-                return mobj.group('server')+'/key='+mobj.group('file')
+                return mp4.group(1)

 
         def is_hd(webpage):
 
         def is_hd(webpage):

-            return webpage.find('<div class=\'icon iconHD\'>') != -1
+            return '<div class=\'icon iconHD\'' in webpage

 
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         seo = mobj.group('seo')
 
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         seo = mobj.group('seo')

-        mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
+        proto = mobj.group('proto')
+        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)

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

-        video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
-            webpage, u'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')

 
         # Only a few videos have an description
 
         # Only a few videos have an description

-        mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
-        if mobj:
-            video_description = unescapeHTML(mobj.group('description'))
-        else:
-            video_description = None
+        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)
+
+        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+                                              webpage, 'uploader id', default='anonymous')
+
+        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
+                                                          webpage, 'duration', fatal=False))

 
 

-        mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
-        if mobj:
-            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
-        else:
-            video_upload_date = None
-            self._downloader.report_warning(u'Unable to extract upload date')
+        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)

 
 

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

 
 

-        video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
-            webpage, u'thumbnail', fatal=False)
+        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+        comment_count = mobj.group('commentcount') if mobj else 0

 
         age_limit = self._rta_search(webpage)
 
 
         age_limit = self._rta_search(webpage)
 

-        video_url = extract_video_url(webpage)

         hd = is_hd(webpage)
         hd = is_hd(webpage)

+
+        video_url = extract_video_url(webpage)

         formats = [{
             'url': video_url,
         formats = [{
             'url': video_url,

-            'ext': determine_ext(video_url),
-            'format': 'hd' if hd else 'sd',

             'format_id': 'hd' if hd else 'sd',
             'format_id': 'hd' if hd else 'sd',

+            'preference': 1,

         }]
         }]

+

         if not hd:
         if not hd:

-            webpage = self._download_webpage(mrss_url+'?hd', video_id)
+            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)
                 formats.append({
                     'url': video_url,
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)
                 formats.append({
                     'url': video_url,

-                    'ext': determine_ext(video_url),
-                    'format': 'hd',

                     'format_id': 'hd',
                     'format_id': 'hd',

+                    'preference': 2,

                 })
 
                 })
 

+        self._sort_formats(formats)
+

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

-            'title': video_title,
-            'formats': formats,
-            'description': video_description,
-            'upload_date': video_upload_date,
-            'uploader_id': video_uploader_id,
-            'thumbnail': video_thumbnail,
+            'title': title,
+            'description': description,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+            'comment_count': int_or_none(comment_count),

             'age_limit': age_limit,
             'age_limit': age_limit,

+            'formats': formats,

         }
         }