diff options
Diffstat (limited to 'blog.sina.com.cn.txt')
| -rw-r--r-- | blog.sina.com.cn.txt | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/blog.sina.com.cn.txt b/blog.sina.com.cn.txt new file mode 100644 index 0000000..4895272 --- /dev/null +++ b/blog.sina.com.cn.txt @@ -0,0 +1,26 @@ +# 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
\ No newline at end of file |