diff options
Diffstat (limited to 'inc/3rdparty/site_config/standard/reuters.com.txt')
-rw-r--r-- | inc/3rdparty/site_config/standard/reuters.com.txt | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/reuters.com.txt b/inc/3rdparty/site_config/standard/reuters.com.txt new file mode 100644 index 00000000..c5c94a4f --- /dev/null +++ b/inc/3rdparty/site_config/standard/reuters.com.txt | |||
@@ -0,0 +1,10 @@ | |||
1 | title: //h1[@class='headline3'] | ||
2 | author: substring-after(//p[@class="byline"], 'By ') | ||
3 | date: //meta[@name="REVISION_DATE"]/@content | ||
4 | body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] | ||
5 | strip: //li[@class='next'] | ||
6 | strip: //span[@class='articleLocation'] | ||
7 | prune: no | ||
8 | tidy: no | ||
9 | |||
10 | test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408 \ No newline at end of file | ||