Prepare to upload.

[youtubedl] / youtube_dl / extractor / extremetube.py

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index c826a5404a4f7da298927460f1f8e41dd013d3a7..3403581fddf08a0928a8e4c5b22e740117646bd2 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -3,23 +3,20 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_parse_qs,
-    compat_urllib_request,
-)

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

-    qualities,
+    int_or_none,
+    sanitized_Request,

     str_to_int,
 )
 
 
 class ExtremeTubeIE(InfoExtractor):
     str_to_int,
 )
 
 
 class ExtremeTubeIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'

     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {

-            'id': '652431',
+            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',

             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',


@@ -29,14 +26,18 @@ class ExtremeTubeIE(InfoExtractor):
     }, {
         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
         'only_matching': True,
     }, {
         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
         'only_matching': True,

+    }, {
+        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/652431',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)

 
 

-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request(url)

         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 


@@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor):
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 

-        flash_vars = compat_parse_qs(self._search_regex(
-            r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
+        flash_vars = self._parse_json(
+            self._search_regex(
+                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
+            video_id)

 
         formats = []
 
         formats = []

-        quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
-        for k, vals in flash_vars.items():
-            m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
-            if m is not None:
-                formats.append({
-                    'format_id': m.group('quality'),
-                    'quality': quality(m.group('quality')),
-                    'url': vals[0],
+        for quality_key, video_url in flash_vars.items():
+            height = int_or_none(self._search_regex(
+                r'quality_(\d+)[pP]$', 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 {
         self._sort_formats(formats)
 
         return {