diff options
Diffstat (limited to 'mainpost.de.txt')
| -rw-r--r-- | mainpost.de.txt | 28 |
1 files changed, 28 insertions, 0 deletions
diff --git a/mainpost.de.txt b/mainpost.de.txt new file mode 100644 index 0000000..2136de3 --- /dev/null +++ b/mainpost.de.txt @@ -0,0 +1,28 @@ +title: substring-before(//title, '|') +body: //*[@id='content-left'] + +# Why is this not working here? +# body: //*[@id='content-left']/div[@class='content-container'][2]/div[@class='content-body']/div[@class='inner-container']/div[@class='detail'] + + +#Header +strip_id_or_class: 'subHead' +strip_id_or_class: 'fl_right' +strip_id_or_class: 'infolink' +strip_id_or_class: 'content-head' +strip_id_or_class: 'tab' +strip_id_or_class: 'tab-active' +strip: //*[contains(@class,'trenner')] + +# Headline +strip: //h1/* +strip_id_or_class: 'font16' + +#Images +strip_id_or_class: 'leftimage' +strip_id_or_class: 'rightimage' + +#Comments +strip: //table +strip: //p/following-sibling::*[0] +test_url: http://www.mainpost.de/ueberregional/meinung/Dioxin-Skandal-bringt-Agrarministerin-in-Bedraengnis;art9517,5920211
\ No newline at end of file |
