diff options
author | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
commit | 4e067ceabd705201a16b4c92cf4b23f3b990326c (patch) | |
tree | 939f3a8e5ff3ab9ee414a57a895d3e78e1d46ce3 /inc/3rdparty/site_config/standard/businessinsider.com.txt | |
parent | 58dbe103889148def78b0fc8744d3f94c56a1561 (diff) | |
download | wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.gz wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.zst wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.zip |
updated specific configuration for parsing
Diffstat (limited to 'inc/3rdparty/site_config/standard/businessinsider.com.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/businessinsider.com.txt | 28 |
1 files changed, 16 insertions, 12 deletions
diff --git a/inc/3rdparty/site_config/standard/businessinsider.com.txt b/inc/3rdparty/site_config/standard/businessinsider.com.txt index c773db8b..39eb7426 100644..100755 --- a/inc/3rdparty/site_config/standard/businessinsider.com.txt +++ b/inc/3rdparty/site_config/standard/businessinsider.com.txt | |||
@@ -1,12 +1,16 @@ | |||
1 | title://div[@class="sl-layout-post"]/h1 | 1 | title://div[@class="sl-layout-post"]/h1 |
2 | body: //div[contains(@class, 'post-content') or contains(@class, 'KonaBody')] | 2 | body: //div[contains(@class, 'post-content') or contains(@class, 'slide-module') or contains(@class, 'KonaBody')] |
3 | strip: //div[contains(@class, "post-sidebar")] | 3 | strip: //div[contains(@class, "post-sidebar")] |
4 | strip: //div[@id='related-links'] | 4 | strip: //div[@id='related-links'] |
5 | author://div[@class="byline"]/a | 5 | strip: //div[@class='related-links-container'] |
6 | date://div[@class="byline"]/span[@class="date"] | 6 | strip: //p[@class='source'] |
7 | prune: no | 7 | author://div[@class="byline"]/a |
8 | 8 | date://div[@class="byline"]/span[@class="date"] | |
9 | strip://*[contains(@class,'sponsored-text')] | 9 | prune: no |
10 | strip: //div[@id='post_footer'] | 10 | |
11 | 11 | single_page_link: //a[contains(text(), 'View as one page')] | |
12 | test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1 \ No newline at end of file | 12 | |
13 | strip://*[contains(@class,'sponsored-text')] | ||
14 | strip: //div[@id='post_footer'] | ||
15 | |||
16 | test_url: http://www.businessinsider.com/microsoft-just-put-one-of-its-hardcore-technical-geniuses-on-xbox-2012-1 | ||