Fine tune the changelog.

[youtubedl] / youtube_dl / extractor / goshgay.py

diff --git a/youtube_dl/extractor/goshgay.py b/youtube_dl/extractor/goshgay.py
index 7bca21ad0fe81c71444bfe64fb23ea3ad62c6c5b..1d9166455aae935f1eb51777d170e0f6259ffd4e 100644 (file)
--- a/youtube_dl/extractor/goshgay.py
+++ b/youtube_dl/extractor/goshgay.py
@@ -1,73 +1,51 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import (
+    compat_parse_qs,
+)

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

-    compat_urlparse,
-    str_to_int,
-    ExtractorError,
+    parse_duration,

 )
 )

-import json

 
 
 class GoshgayIE(InfoExtractor):
 
 
 class GoshgayIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)'
+    _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'

     _TEST = {
     _TEST = {

-        'url': 'http://www.goshgay.com/video4116282',
-        'md5': '268b9f3c3229105c57859e166dd72b03',
+        'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
+        'md5': '027fcc54459dff0feb0bc06a7aeda680',

         'info_dict': {
         'info_dict': {

-            'id': '4116282',
+            'id': '299069',

             'ext': 'flv',
             'ext': 'flv',

-            'title': 'md5:089833a4790b5e103285a07337f245bf',
-            'thumbnail': 're:http://.*\.jpg',
+            'title': 'DIESEL SFW XXX Video',
+            'thumbnail': 're:^http://.*\.jpg$',
+            'duration': 79,

             'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
             'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):

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

         webpage = self._download_webpage(url, video_id)
         webpage = self._download_webpage(url, video_id)

-        title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')

 
 

-        player_config = self._search_regex(
-            r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings')
-        player_vars = json.loads(player_config.replace("'", '"'))
-        width = str_to_int(player_vars.get('width'))
-        height = str_to_int(player_vars.get('height'))
-        config_uri = player_vars.get('config')
+        title = self._html_search_regex(
+            r'<h2>(.*?)<', webpage, 'title')
+        duration = parse_duration(self._html_search_regex(
+            r'<span class="duration">\s*-?\s*(.*?)</span>',
+            webpage, 'duration', fatal=False))

 
 

-        if config_uri is None:
-            raise ExtractorError('Missing config URI')
-        node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
-                                  errnote='Unable to download XML')
-        if node is None:
-            raise ExtractorError('Missing config XML')
-        if node.tag != 'config':
-            raise ExtractorError('Missing config attribute')
-        fns = node.findall('file')
-        imgs = node.findall('image')
-        if len(fns) != 1:
-            raise ExtractorError('Missing media URI')
-        video_url = fns[0].text
-        if len(imgs) < 1:
-            thumbnail = None
-        else:
-            thumbnail = imgs[0].text
-
-        url_comp = compat_urlparse.urlparse(url)
-        ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
+        flashvars = compat_parse_qs(self._html_search_regex(
+            r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
+            webpage, 'flashvars'))
+        thumbnail = flashvars.get('url_bigthumb', [None])[0]
+        video_url = flashvars['flv_url'][0]

 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,

-            'width': width,
-            'height': height,

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

-            'http_referer': ref,
-            'age_limit': 18,
+            'duration': duration,
+            'age_limit': self._family_friendly_search(webpage),

         }
         }