X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9a117f94b4bfe84cfe1d904d5132aefcf41511c9..f8eb4d6a400267895af2f217c36101294f8a94d2:/youtube_dl/extractor/xnxx.py

diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py
index 40d8489..ac1ccc4 100644
--- a/youtube_dl/extractor/xnxx.py
+++ b/youtube_dl/extractor/xnxx.py
@@ -1,53 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
-
-    ExtractorError,
+    determine_ext,
+    int_or_none,
+    NO_DEFAULT,
+    str_to_int,
 )
 
 
 class XNXXIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
-    VIDEO_URL_RE = r'flv_url=(.*?)&'
-    VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
-    VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
-    _TEST = {
-        u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
-        u'file': u'1135332.flv',
-        u'md5': u'0831677e2b4761795f68d417e0b7b445',
-        u'info_dict': {
-            u"title": u"lida \u00bb Naked Funny Actress  (5)"
-        }
-    }
+    _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/'
+    _TESTS = [{
+        'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
+        'md5': '7583e96c15c0f21e9da3453d9920fbba',
+        'info_dict': {
+            'id': '55awb78',
+            'ext': 'mp4',
+            'title': 'Skyrim Test Video',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 469,
+            'view_count': int,
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.xnxx.com/video-55awb78/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
-        # Get webpage content
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(self.VIDEO_URL_RE,
-            webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        def get(meta, default=NO_DEFAULT, fatal=True):
+            return self._search_regex(
+                r'set%s\s*\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % meta,
+                webpage, meta, default=default, fatal=fatal, group='value')
 
-        video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
-            webpage, u'title')
+        title = self._og_search_title(
+            webpage, default=None) or get('VideoTitle')
 
-        video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
-            webpage, u'thumbnail', fatal=False)
+        formats = []
+        for mobj in re.finditer(
+                r'setVideo(?:Url(?P<id>Low|High)|HLS)\s*\(\s*(?P<q>["\'])(?P<url>(?:https?:)?//.+?)(?P=q)', webpage):
+            format_url = mobj.group('url')
+            if determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    preference=1, m3u8_id='hls', fatal=False))
+            else:
+                format_id = mobj.group('id')
+                if format_id:
+                    format_id = format_id.lower()
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'quality': -1 if format_id == 'low' else 0,
+                })
+        self._sort_formats(formats)
 
-        return [{
+        thumbnail = self._og_search_thumbnail(webpage, default=None) or get(
+            'ThumbUrl', fatal=False) or get('ThumbUrl169', fatal=False)
+        duration = int_or_none(self._og_search_property('duration', webpage))
+        view_count = str_to_int(self._search_regex(
+            r'id=["\']nb-views-number[^>]+>([\d,.]+)', webpage, 'view count',
+            default=None))
+
+        return {
             'id': video_id,
-            'url': video_url,
-            'uploader': None,
-            'upload_date': None,
-            'title': video_title,
-            'ext': 'flv',
-            'thumbnail': video_thumbnail,
-            'description': None,
-        }]
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': 18,
+            'formats': formats,
+        }