diff options
Diffstat (limited to 'bt.no.txt')
| -rw-r--r-- | bt.no.txt | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/bt.no.txt b/bt.no.txt new file mode 100644 index 0000000..200c2e4 --- /dev/null +++ b/bt.no.txt @@ -0,0 +1,12 @@ +title: //h1[contains(@class,'articleTitle')] +author: //span[@itemprop='name'] +date: //time[@class='published'] +body: //div[contains(@class,'bodyText')] + +strip_id_or_class: 'pull1' +strip_id_or_class: 'relationArticle' +strip: //span[@class='quote'] + +# strip h2 if at end of article (typically a request for comments) +strip: //div[contains(@class,'bodyText')]/node()[last()-1]/self::h2 +test_url: http://www.bt.no/meninger/debatt/Typisk-norsk-a-vare-god-nok-2884108.html
\ No newline at end of file |