youtube-dl

commit a4c2ab35c1c1cc7385b21b15e5c082313236048c
parent 8b8a39e279b02926197230024e64a50d7995b95d
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Thu, 12 Nov 2015 00:08:42 +0800

Merge remote-tracking branch 'upstream/master'

Diffstat:
M
AUTHORS
 | 
1
+
M
youtube_dl/extractor/novamov.py
 | 
40
+++++++++++++++++++++++++++++++++-------
M
youtube_dl/extractor/nowvideo.py
 | 
4
++--
M
youtube_dl/extractor/vimeo.py
 | 
2
+-
M
youtube_dl/extractor/wsj.py
 | 
1
-

5 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/AUTHORS b/AUTHORS
@@ -144,3 +144,4 @@ Lee Jenkins
 Anssi Hannula
 Lukáš Lalinský
 Qijiang Fan
+Rémy Léone
diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py
@@ -4,10 +4,14 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
+    NO_DEFAULT,
+    encode_dict,
+    urlencode_postdata,
 )
 
 
@@ -41,16 +45,38 @@ class NovaMovIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        page = self._download_webpage(
-            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
+        url = 'http://%s/video/%s' % (self._HOST, video_id)
 
-        if re.search(self._FILE_DELETED_REGEX, page) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        webpage = self._download_webpage(
+            url, video_id, 'Downloading video page')
 
-        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
-        description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
+        def extract_filekey(default=NO_DEFAULT):
+            return self._search_regex(
+                self._FILEKEY_REGEX, webpage, 'filekey', default=default)
+
+        filekey = extract_filekey(default=None)
+
+        if not filekey:
+            fields = self._hidden_inputs(webpage)
+            post_url = self._search_regex(
+                r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
+                'post url', default=url, group='url')
+            if not post_url.startswith('http'):
+                post_url = compat_urlparse.urljoin(url, post_url)
+            request = compat_urllib_request.Request(
+                post_url, urlencode_postdata(encode_dict(fields)))
+            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            request.add_header('Referer', post_url)
+            webpage = self._download_webpage(
+                request, video_id, 'Downloading continue to the video page')
+
+        filekey = extract_filekey()
+
+        title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
+        description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py
@@ -7,9 +7,9 @@ class NowVideoIE(NovaMovIE):
     IE_NAME = 'nowvideo'
     IE_DESC = 'NowVideo'
 
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
 
-    _HOST = 'www.nowvideo.ch'
+    _HOST = 'www.nowvideo.to'
 
     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
     _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
@@ -217,7 +217,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             url = url.replace('http://', 'https://')
         password_request = compat_urllib_request.Request(url + '/password', data)
         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
+        password_request.add_header('Cookie', 'clip_test_v2=0; vuid=%s' % vuid)
         password_request.add_header('Referer', url)
         return self._download_webpage(
             password_request, video_id,
diff --git a/youtube_dl/extractor/wsj.py b/youtube_dl/extractor/wsj.py
@@ -84,6 +84,5 @@ class WSJIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
             'title': title,
-            'formats': formats,
             'categories': categories,
         }