From: Yen Chi Hsuan Date: Sun, 13 Dec 2015 07:33:11 +0000 (+0800) Subject: [novamov] Fix filekey extraction (closes #7764) X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=47c7f3d99504325c43651b781376ea470e7e28bd;p=youtube-dl [novamov] Fix filekey extraction (closes #7764) --- diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 837c91559..0c4ff90f2 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -23,9 +23,10 @@ class NovaMovIE(InfoExtractor): _HOST = 'www.novamov.com' _FILE_DELETED_REGEX = r'This file no longer exists on our servers!' - _FILEKEY_REGEX = r'flashvars\.filekey="(?P[^"]+)";' + _FILEKEY_REGEX = r'flashvars\.filekey=(?P"?[^"]+"?);' _TITLE_REGEX = r'(?s)
\s*

([^<]+)

' _DESCRIPTION_REGEX = r'(?s)
\s*

[^<]+

([^<]+)

' + _URL_TEMPLATE = 'http://%s/video/%s' _TEST = { 'url': 'http://www.novamov.com/video/4rurhn9x446jj', @@ -42,7 +43,7 @@ class NovaMovIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - url = 'http://%s/video/%s' % (self._HOST, video_id) + url = self._URL_TEMPLATE % (self._HOST, video_id) webpage = self._download_webpage( url, video_id, 'Downloading video page') @@ -51,8 +52,13 @@ class NovaMovIE(InfoExtractor): raise ExtractorError('Video %s does not exist' % video_id, expected=True) def extract_filekey(default=NO_DEFAULT): - return self._search_regex( + filekey = self._search_regex( self._FILEKEY_REGEX, webpage, 'filekey', default=default) + if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'): + return self._search_regex( + r'var\s*%s\s*=\s*"([^"]+)"', webpage, 'filekey', default=default) + else: + return filekey filekey = extract_filekey(default=None) @@ -127,7 +133,6 @@ class NowVideoIE(NovaMovIE): _HOST = 'www.nowvideo.to' _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _FILEKEY_REGEX = r'var fkzd="([^"]+)";' _TITLE_REGEX = r'

([^<]+)

' _DESCRIPTION_REGEX = r'\s*

([^<]+)

' @@ -153,6 +158,7 @@ class VideoWeedIE(NovaMovIE): _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' _TITLE_REGEX = r'

([^<]+)

' + _URL_TEMPLATE = 'http://%s/file/%s' _TEST = { 'url': 'http://www.videoweed.es/file/b42178afbea14',