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/stalbansreview.co.uk.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/stalbansreview.co.uk.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt b/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt index bde14217..a0f1587c 100644..100755 --- a/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt +++ b/inc/3rdparty/site_config/standard/stalbansreview.co.uk.txt | |||
@@ -1,14 +1,14 @@ | |||
1 | title: //div[@class='articleLeft']/h3 | 1 | title: //div[@class='articleLeft']/h3 |
2 | 2 | ||
3 | author: substring-after(//span[@class='articleAuthor']/a,'By ') | 3 | author: substring-after(//span[@class='articleAuthor']/a,'By ') |
4 | 4 | ||
5 | date: substring-before(//span[@class='articleDateTime'],'in ') | 5 | date: substring-before(//span[@class='articleDateTime'],'in ') |
6 | 6 | ||
7 | body: //div[@class='articleLeft'] | 7 | body: //div[@class='articleLeft'] |
8 | strip: //div[@class='articleMoreNews'] | 8 | strip: //div[@class='articleMoreNews'] |
9 | strip: //div[@class='articleLeft']/h3 | 9 | strip: //div[@class='articleLeft']/h3 |
10 | strip: //div[@class='articleLeft']/p[@class='articleInfo clearfix'] | 10 | strip: //div[@class='articleLeft']/p[@class='articleInfo clearfix'] |
11 | 11 | ||
12 | # Remove duplicate title from text | 12 | # Remove duplicate title from text |
13 | strip: //div[@id='site']/div[5][@class='holder']/div[1][@class='hBlock']/div[1][@class='sglCol article']/h3 | 13 | strip: //div[@id='site']/div[5][@class='holder']/div[1][@class='hBlock']/div[1][@class='sglCol article']/h3 |
14 | test_url: http://www.stalbansreview.co.uk/news/9581446.New_roundabout_in_King_Harry_Lane/r/?ref=rss \ No newline at end of file | 14 | test_url: http://www.stalbansreview.co.uk/news/9581446.New_roundabout_in_King_Harry_Lane/r/?ref=rss \ No newline at end of file |