Update README.md

[youtubedl] / youtube_dl / extractor / sunporno.py

diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py
index 8a333f1d24d6be3bd5160d843c3cd6451ef83178..68051169b974d7bc748238566be1c31734eb8ed7 100644 (file)
--- a/youtube_dl/extractor/sunporno.py
+++ b/youtube_dl/extractor/sunporno.py
@@ -12,25 +12,29 @@ from ..utils import (
 
 
 class SunPornoIE(InfoExtractor):
 
 
 class SunPornoIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www\.)?sunporno\.com/videos|embeds\.sunporno\.com/embed)/(?P<id>\d+)'
+    _TESTS = [{

         'url': 'http://www.sunporno.com/videos/807778/',
         'url': 'http://www.sunporno.com/videos/807778/',

-        'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
+        'md5': '507887e29033502f29dba69affeebfc9',

         'info_dict': {
             'id': '807778',
         'info_dict': {
             'id': '807778',

-            'ext': 'flv',
+            'ext': 'mp4',

             'title': 'md5:0a400058e8105d39e35c35e7c5184164',
             'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
             'title': 'md5:0a400058e8105d39e35c35e7c5184164',
             'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'duration': 302,
             'age_limit': 18,
         }
             'duration': 302,
             'age_limit': 18,
         }

-    }
+    }, {
+        'url': 'http://embeds.sunporno.com/embed/807778',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.sunporno.com/videos/%s' % video_id, video_id)

 
         title = self._html_search_regex(
             r'<title>([^<]+)</title>', webpage, 'title')
 
         title = self._html_search_regex(
             r'<title>([^<]+)</title>', webpage, 'title')


@@ -40,19 +44,20 @@ class SunPornoIE(InfoExtractor):
             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         duration = parse_duration(self._search_regex(
             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         duration = parse_duration(self._search_regex(

-            r'itemprop="duration">\s*(\d+:\d+)\s*<',
+            (r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<',
+             r'>Duration:\s*<span[^>]+>\s*(\d+:\d+)\s*<'),

             webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(
             webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(

-            r'class="views">\s*(\d+)\s*<',
+            r'class="views">(?:<noscript>)?\s*(\d+)\s*<',

             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'(\d+)</b> Comments?',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'(\d+)</b> Comments?',

-            webpage, 'comment count', fatal=False))
+            webpage, 'comment count', fatal=False, default=None))

 
         formats = []
         quality = qualities(['mp4', 'flv'])
 
         formats = []
         quality = qualities(['mp4', 'flv'])

-        for video_url in re.findall(r'<source src="([^"]+)"', webpage):
+        for video_url in re.findall(r'<(?:source|video) src="([^"]+)"', webpage):

             video_ext = determine_ext(video_url)
             formats.append({
                 'url': video_url,
             video_ext = determine_ext(video_url)
             formats.append({
                 'url': video_url,