1 # Sina blog, the most popular blog host in China.
2 # Its source code is horrible.
5 # Only the first image in the article is displayed.
6 # The rest images are replace by a 1x1 transparent gif by sina blog host.
9 title://*[contains(@class,'titName SG_txta')]
10 author://*[contains(@id,'ownernick')]
11 date://*[contains(@class,'time SG_txtc')]
12 body://div[contains(@class,'articalContent')]
14 # Remove redundant content which has span class start with "MASS"
15 # Example <span class="MASSf21674ffeef7"></span>
16 strip://span[contains(@class,'MASS')]
19 strip://div[contains(@class,'allComm')]
21 # Remove hiden text and link
25 convert_double_br_tags:yes
26 test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html