X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bddc9fc577d16b1428924bf8a5c37ef1d9295f14..d317bf370d3cbd2231f3d6b1970e0a86fddc4e5b:/youtube_dl/extractor/xvideos.py?ds=sidebyside

diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py
index 8b3cb39..5dcf2fd 100644
--- a/youtube_dl/extractor/xvideos.py
+++ b/youtube_dl/extractor/xvideos.py
@@ -1,43 +1,75 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urllib_request,
+)
 from ..utils import (
-    compat_urllib_parse,
+    clean_html,
+    ExtractorError,
+    determine_ext,
 )
 
 
 class XVideosIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+    _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',
+        'info_dict': {
+            'id': '4588838',
+            'ext': 'flv',
+            'title': 'Biker Takes his Girl',
+            'age_limit': 18,
+        }
+    }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+    _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)
 
-        self.report_extraction(video_id)
+        mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
+        if mobj:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
 
-        # Extract video URL
-        video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
-            webpage, u'video URL'))
+        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)
 
-        # Extract title
-        video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
-            webpage, u'title')
+        formats = [{
+            'url': video_url,
+        }]
+
+        android_req = compat_urllib_request.Request(url)
+        android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
+        android_webpage = self._download_webpage(android_req, video_id, fatal=False)
+
+        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'])
 
-        # Extract video thumbnail
-        video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
-            webpage, u'thumbnail', fatal=False)
+        self._sort_formats(formats)
 
-        info = {
+        return {
             'id': video_id,
-            'url': video_url,
-            'uploader': None,
-            'upload_date': None,
+            'formats': formats,
             'title': video_title,
             'ext': 'flv',
             'thumbnail': video_thumbnail,
-            'description': None,
+            'age_limit': 18,
         }
-
-        return [info]