[github/wallabag/wallabag.git] / inc / 3rdparty / site_config / standard / blog.sina.com.cn.txt

# Sina blog, the most popular blog host in China.\r
# Its source code is horrible.\r
#  \r
# Issue:\r
# Only the first image in the article is displayed.\r
# The rest images are replace by a 1x1 transparent gif by sina blog host.\r
# \r
\r
title://*[contains(@class,'titName SG_txta')]\r
author://*[contains(@id,'ownernick')]\r
date://*[contains(@class,'time SG_txtc')]\r
body://div[contains(@class,'articalContent')]\r
\r
# Remove redundant content which has span class start with "MASS"\r
# Example <span class="MASSf21674ffeef7"></span>\r
strip://span[contains(@class,'MASS')]\r
\r
# Remove comment\r
strip://div[contains(@class,'allComm')]\r
\r
# Remove hiden text and link\r
strip://ins\r
\r
tidy:no\r
convert_double_br_tags:yes\r
test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html
Commit	Line	Data
ac4d1142 NL	1	# Sina blog, the most popular blog host in China.\r
	2	# Its source code is horrible.\r
	3	# \r
	4	# Issue:\r
	5	# Only the first image in the article is displayed.\r
	6	# The rest images are replace by a 1x1 transparent gif by sina blog host.\r
	7	# \r
	8	\r
	9	title://*[contains(@class,'titName SG_txta')]\r
	10	author://*[contains(@id,'ownernick')]\r
	11	date://*[contains(@class,'time SG_txtc')]\r
	12	body://div[contains(@class,'articalContent')]\r
	13	\r
	14	# Remove redundant content which has span class start with "MASS"\r
	15	# Example <span class="MASSf21674ffeef7"></span>\r
	16	strip://span[contains(@class,'MASS')]\r
	17	\r
	18	# Remove comment\r
	19	strip://div[contains(@class,'allComm')]\r
	20	\r
	21	# Remove hiden text and link\r
	22	strip://ins\r
	23	\r
	24	tidy:no\r
	25	convert_double_br_tags:yes\r
	26	test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html