diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/blog.sina.com.cn.txt')
| -rw-r--r-- | inc/3rdparty/site_config/standard/blog.sina.com.cn.txt | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/blog.sina.com.cn.txt b/inc/3rdparty/site_config/standard/blog.sina.com.cn.txt new file mode 100644 index 00000000..acb9ce81 --- /dev/null +++ b/inc/3rdparty/site_config/standard/blog.sina.com.cn.txt | |||
| @@ -0,0 +1,26 @@ | |||
| 1 | # Sina blog, the most popular blog host in China. | ||
| 2 | # Its source code is horrible. | ||
| 3 | # | ||
| 4 | # Issue: | ||
| 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. | ||
| 7 | # | ||
| 8 | |||
| 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')] | ||
| 13 | |||
| 14 | # Remove redundant content which has span class start with "MASS" | ||
| 15 | # Example <span class="MASSf21674ffeef7"></span> | ||
| 16 | strip://span[contains(@class,'MASS')] | ||
| 17 | |||
| 18 | # Remove comment | ||
| 19 | strip://div[contains(@class,'allComm')] | ||
| 20 | |||
| 21 | # Remove hiden text and link | ||
| 22 | strip://ins | ||
| 23 | |||
| 24 | tidy:no | ||
| 25 | convert_double_br_tags:yes | ||
| 26 | test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html \ No newline at end of file | ||