From d8b7e80d29a67835555a6317b2c528b911077d47 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9my=20L=C3=A9one?= Date: Wed, 11 Nov 2015 12:00:31 +0100 Subject: [PATCH 1/5] Remove duplicate key --- youtube_dl/extractor/wsj.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/wsj.py b/youtube_dl/extractor/wsj.py index 2ddf29a69..5a897371d 100644 --- 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, } From 6abce58a1226a5c359e4eb0cb228353fa7cb2aaf Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Wed, 11 Nov 2015 20:16:18 +0800 Subject: [PATCH 2/5] Credit @sieben for fixing wsj extractor --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index cc552bcb2..4cdbf4a5f 100644 --- a/AUTHORS +++ b/AUTHORS @@ -144,3 +144,4 @@ Lee Jenkins Anssi Hannula Lukáš Lalinský Qijiang Fan +Rémy Léone From 2eb99a4b98ecece86a8d0c692066644a855f8524 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 11 Nov 2015 21:00:23 +0600 Subject: [PATCH 3/5] [nowvideo] Replace main host to resolvable one --- youtube_dl/extractor/nowvideo.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index 17baa9679..57ee3d366 100644 --- 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="([^"]+)";' From 82393e2bb2c499cad285beb07c222f501302d830 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 11 Nov 2015 21:02:05 +0600 Subject: [PATCH 4/5] [novamov] Follow continue-to-the-video button if any (Closes #7330) --- youtube_dl/extractor/novamov.py | 40 +++++++++++++++++++++++++++------ 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 04d779890..e0bf6d1bc 100644 --- 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']+action=(["\'])(?P.+?)\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, From 3d9c4bf09a57871f0030d6b6022b863d66616b8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 11 Nov 2015 21:21:21 +0600 Subject: [PATCH 5/5] [vimeo] Fix password protected videos (Closes #7451) --- youtube_dl/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ca716c8f5..9dc6247e8 100644 --- 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,