Revert "debian/watch: Add back pgpsigurlmangle."

[youtubedl] / youtube_dl / extractor / xvideos.py

diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py
index 7e00448246beb9ab9b7c25f33b05e6f4f1bb8283..1dfe031cab8e9ccf4fa6fb23fbd90d40759ac930 100644 (file)
--- a/youtube_dl/extractor/xvideos.py
+++ b/youtube_dl/extractor/xvideos.py
@@ -3,15 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_urllib_parse_unquote

 from ..utils import (
 from ..utils import (

-    compat_urllib_parse,
-    ExtractorError,

     clean_html,
     clean_html,

+    ExtractorError,
+    determine_ext,

 )
 
 
 class XVideosIE(InfoExtractor):
 )
 
 
 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',
     _TEST = {
         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
         'md5': '4b46ae6ea5e6e9086e714d883313c0c9',


@@ -24,37 +25,48 @@ class XVideosIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
 
         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)
 
         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, 'video URL'))
-
-        # Extract title

         video_title = self._html_search_regex(
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
         video_title = self._html_search_regex(
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')

-
-        # Extract video thumbnail

         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 

+        formats = []
+
+        video_url = compat_urllib_parse_unquote(self._search_regex(
+            r'flv_url=(.+?)&', webpage, 'video URL', default=''))
+        if video_url:
+            formats.append({'url': video_url})
+
+        player_args = self._search_regex(
+            r'(?s)new\s+HTML5Player\((.+?)\)', webpage, ' html5 player', default=None)
+        if player_args:
+            for arg in player_args.split(','):
+                format_url = self._search_regex(
+                    r'(["\'])(?P<url>https?://.+?)\1', arg, 'url',
+                    default=None, group='url')
+                if not format_url:
+                    continue
+                ext = determine_ext(format_url)
+                if ext == 'mp4':
+                    formats.append({'url': format_url})
+                elif ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+        self._sort_formats(formats)
+

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

-            'url': video_url,
-            'uploader': None,
-            'upload_date': None,
+            'formats': formats,

             'title': video_title,
             'title': video_title,

-            'ext': 'flv',

             'thumbnail': video_thumbnail,
             'thumbnail': video_thumbnail,

-            'description': None,

             'age_limit': 18,
         }
             'age_limit': 18,
         }