1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-12-21 06:48:56 -05:00
wallabag/vendor/full-text-rss/site_config/standard/blog.sina.com.cn.txt
2013-12-10 16:19:15 +01:00

26 lines
773 B
Plaintext

# Sina blog, the most popular blog host in China.
# Its source code is horrible.
#
# Issue:
# Only the first image in the article is displayed.
# The rest images are replace by a 1x1 transparent gif by sina blog host.
#
title://*[contains(@class,'titName SG_txta')]
author://*[contains(@id,'ownernick')]
date://*[contains(@class,'time SG_txtc')]
body://div[contains(@class,'articalContent')]
# Remove redundant content which has span class start with "MASS"
# Example <span class="MASSf21674ffeef7"></span>
strip://span[contains(@class,'MASS')]
# Remove comment
strip://div[contains(@class,'allComm')]
# Remove hiden text and link
strip://ins
tidy:no
convert_double_br_tags:yes
test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html