Use canonical URL in Vcs-Git.

[youtubedl] / youtube_dl / extractor / thisav.py

diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py
index 7f323c938762f6ec1337b6dbf6b9c64ec2993dd8..dc3dd03c823d7ec7878943b5f99bc14d266a6257 100644 (file)
--- a/youtube_dl/extractor/thisav.py
+++ b/youtube_dl/extractor/thisav.py
@@ -4,12 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import remove_end
 
 
 class ThisAVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
-    _TEST = {
+    _TESTS = [{
+        # jwplayer
         'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
         'md5': '0480f1ef3932d901f0e0e719f188f19b',
         'info_dict': {
@@ -19,29 +20,54 @@ class ThisAVIE(InfoExtractor):
             'uploader': 'dj7970',
             'uploader_id': 'dj7970'
         }
-    }
+    }, {
+        # html5 media
+        'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
+        'md5': 'ba90c076bd0f80203679e5b60bf523ee',
+        'info_dict': {
+            'id': '242352',
+            'ext': 'mp4',
+            'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
+            'uploader': 'cybersluts',
+            'uploader_id': 'cybersluts',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'),
+            ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
         video_url = self._html_search_regex(
-            r"addVariable\('file','([^']+)'\);", webpage, 'video url')
+            r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
+        if video_url:
+            info_dict = {
+                'formats': [{
+                    'url': video_url,
+                }],
+            }
+        else:
+            entries = self._parse_html5_media_entries(url, webpage, video_id)
+            if entries:
+                info_dict = entries[0]
+            else:
+                info_dict = self._extract_jwplayer_data(
+                    webpage, video_id, require_title=False)
         uploader = self._html_search_regex(
-            r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
+            r': <a href="http://www\.thisav\.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
             webpage, 'uploader name', fatal=False)
         uploader_id = self._html_search_regex(
-            r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
+            r': <a href="http://www\.thisav\.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
             webpage, 'uploader id', fatal=False)
-        ext = determine_ext(video_url)
 
-        return {
+        info_dict.update({
             'id': video_id,
-            'url': video_url,
             'uploader': uploader,
             'uploader_id': uploader_id,
             'title': title,
-            'ext': ext,
-        }
+        })
+
+        return info_dict