X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxvideos.py;h=eca603028d9ac91cf98e3da6c3651444f1653730;hb=1c9c8de29e83bbfc38027dabcd9642f1c41a64b0;hp=710ad5041988b0e1c932b135af91a27036dfd664;hpb=b19ad2fb53c43c573d22663a739d192509bd8097;p=youtube-dl

diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py
index 710ad5041..eca603028 100644
--- a/youtube_dl/extractor/xvideos.py
+++ b/youtube_dl/extractor/xvideos.py
@@ -6,9 +6,10 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     clean_html,
-    ExtractorError,
     determine_ext,
-    sanitized_Request,
+    ExtractorError,
+    int_or_none,
+    parse_duration,
 )
 
 
@@ -16,17 +17,16 @@ class XVideosIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
     _TEST = {
         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
-        'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
+        'md5': '14cea69fcb84db54293b1e971466c2e1',
         'info_dict': {
             'id': '4588838',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Biker Takes his Girl',
+            'duration': 108,
             'age_limit': 18,
         }
     }
 
-    _ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -35,31 +35,39 @@ class XVideosIE(InfoExtractor):
         if mobj:
             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
 
-        video_url = compat_urllib_parse_unquote(
-            self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
         video_title = self._html_search_regex(
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
+        video_duration = int_or_none(self._og_search_property(
+            'duration', webpage, default=None)) or parse_duration(
+            self._search_regex(
+                r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
+                webpage, 'duration', fatal=False))
 
-        formats = [{
-            'url': video_url,
-        }]
+        formats = []
 
-        android_req = sanitized_Request(url)
-        android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
-        android_webpage = self._download_webpage(android_req, video_id, fatal=False)
+        video_url = compat_urllib_parse_unquote(self._search_regex(
+            r'flv_url=(.+?)&', webpage, 'video URL', default=''))
+        if video_url:
+            formats.append({
+                'url': video_url,
+                'format_id': 'flv',
+            })
 
-        if android_webpage is not None:
-            player_params_str = self._search_regex(
-                'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
-                android_webpage, 'player parameters', default='')
-            player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
-            if player_params:
-                formats.extend([{
-                    'url': param,
-                    'preference': -10,
-                } for param in player_params if determine_ext(param) == 'mp4'])
+        for kind, _, format_url in re.findall(
+                r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
+            format_id = kind.lower()
+            if format_id == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+            elif format_id in ('urllow', 'urlhigh'):
+                formats.append({
+                    'url': format_url,
+                    'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
+                    'quality': -2 if format_id.endswith('low') else None,
+                })
 
         self._sort_formats(formats)
 
@@ -67,7 +75,7 @@ class XVideosIE(InfoExtractor):
             'id': video_id,
             'formats': formats,
             'title': video_title,
-            'ext': 'flv',
+            'duration': video_duration,
             'thumbnail': video_thumbnail,
             'age_limit': 18,
         }