youtube-dl

commit ab19b46b88bb54971b973176976d8d189222a6d3
parent 8804f10e6b580db38df7301a174cb48ea374f9eb
Author: Sergey M․ <dstftw@gmail.com>
Date:   Wed, 17 Aug 2016 06:02:12 +0700

[extremetube] Modernize

Diffstat:
M
youtube_dl/extractor/extremetube.py
 | 
73
++++++++++++++++---------------------------------------------------------

1 file changed, 16 insertions(+), 57 deletions(-)
diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
@@ -1,22 +1,17 @@
 from __future__ import unicode_literals
 
-import re
+from ..utils import str_to_int
+from .keezmovies import KeezMoviesIE
 
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    sanitized_Request,
-    str_to_int,
-)
 
-
-class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
+class ExtremeTubeIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?:(?P<display_id>[^/]+)-)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
         'info_dict': {
-            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+            'id': '652431',
+            'display_id': 'music-video-14-british-euro-brit-european-cumshots-swallow',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
@@ -35,58 +30,22 @@ class ExtremeTubeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        webpage, info = self._extract_info(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        if not info['title']:
+            info['title'] = self._search_regex(
+                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
 
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
             webpage, 'uploader', fatal=False)
-        view_count = str_to_int(self._html_search_regex(
+        view_count = str_to_int(self._search_regex(
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        flash_vars = self._parse_json(
-            self._search_regex(
-                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
-            video_id)
-
-        formats = []
-        for quality_key, video_url in flash_vars.items():
-            height = int_or_none(self._search_regex(
-                r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
-            if not height:
-                continue
-            f = {
-                'url': video_url,
-            }
-            mobj = re.search(
-                r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
-            if mobj:
-                height = int(mobj.group('height'))
-                bitrate = int(mobj.group('bitrate'))
-                f.update({
-                    'format_id': '%dp-%dk' % (height, bitrate),
-                    'height': height,
-                    'tbr': bitrate,
-                })
-            else:
-                f.update({
-                    'format_id': '%dp' % height,
-                    'height': height,
-                })
-            formats.append(f)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'formats': formats,
+        info.update({
             'uploader': uploader,
             'view_count': view_count,
-            'age_limit': 18,
-        }
+        })
+
+        return info