diff options
Diffstat (limited to 'reuters.com.txt')
| -rw-r--r-- | reuters.com.txt | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/reuters.com.txt b/reuters.com.txt new file mode 100644 index 0000000..7411e62 --- /dev/null +++ b/reuters.com.txt @@ -0,0 +1,10 @@ +title: //h1[@class='headline3'] +author: substring-after(//p[@class="byline"], 'By ') +date: //meta[@name="REVISION_DATE"]/@content +body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] +strip: //li[@class='next'] +strip: //span[@class='articleLocation'] +prune: no +tidy: no + +test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408
\ No newline at end of file |