diff options
| -rw-r--r-- | wired.com.txt | 29 |
1 files changed, 14 insertions, 15 deletions
diff --git a/wired.com.txt b/wired.com.txt index 43e2b9c..e06ad0e 100644 --- a/wired.com.txt +++ b/wired.com.txt @@ -1,22 +1,21 @@ -title: //meta[@property="og:title"]/@content -title: //h1 -title: //*[@class='posttitle'] -author: //*[@class='entryAuthor']/a[1] -author://*[@class='member-title'] -author://li[@class='author']/a[contains(@href, '/author/')] -date: substring-after(//div[@class='entryAuthor'], '·') -date: substring-before(//*[@class='entryDate'], '|') +title: //meta[@name='Title']/@content +author: //meta[@name='Author']/@content +date: //meta[@name='DisplayDate']/@content body: //div[@class='entry'] -strip: //span[contains(@class, 'nextprev')] -#strip_id_or_class: ngg-galleryoverview -# ngg-galleryoverview is the whole content sometimes, e.g. http://www.wired.com/underwire/2011/12/best-mixtapes-of-2011/?pid=5736&viewall=true +strip: //p[contains(., 'Pages:') and contains(., 'View All')] -strip: //p[span[contains(@class, 'contentjump')]] -strip: //text()[contains(., 'nextpage')] +strip_id_or_class: pullquote +strip_id_or_class: left_rail + +# Remove gallery? +strip_id_or_class: wpgallery + +#strip: //text()[contains(., 'nextpage')] prune: no -single_page_link: //a[contains(@href, '/all/1') and contains(@class, 'contentjumpall')] +single_page_link: //a[.='View All' and contains(@href, '/all/')] test_url: http://www.wired.com/cloudline/2011/10/meet-arms-cortex-a15-the-future-of-the-ipad-and-possibly-the-macbook-air/ -test_url: http://www.wired.com/threatlevel/2012/05/ff_counterfeiter/all/1
\ No newline at end of file +test_url: http://www.wired.com/wiredenterprise/2013/09/docker/ +test_url: http://www.wired.com/threatlevel/2012/05/ff_counterfeiter/all/
\ No newline at end of file |