diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/reuters.com.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/reuters.com.txt | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/inc/3rdparty/site_config/standard/reuters.com.txt b/inc/3rdparty/site_config/standard/reuters.com.txt index c5c94a4f..7411e62b 100644..100755 --- a/inc/3rdparty/site_config/standard/reuters.com.txt +++ b/inc/3rdparty/site_config/standard/reuters.com.txt | |||
@@ -1,10 +1,10 @@ | |||
1 | title: //h1[@class='headline3'] | 1 | title: //h1[@class='headline3'] |
2 | author: substring-after(//p[@class="byline"], 'By ') | 2 | author: substring-after(//p[@class="byline"], 'By ') |
3 | date: //meta[@name="REVISION_DATE"]/@content | 3 | date: //meta[@name="REVISION_DATE"]/@content |
4 | body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] | 4 | body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] |
5 | strip: //li[@class='next'] | 5 | strip: //li[@class='next'] |
6 | strip: //span[@class='articleLocation'] | 6 | strip: //span[@class='articleLocation'] |
7 | prune: no | 7 | prune: no |
8 | tidy: no | 8 | tidy: no |
9 | 9 | ||
10 | test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408 \ No newline at end of file | 10 | test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408 \ No newline at end of file |