diff options
Diffstat (limited to 'inc.com.txt')
| -rw-r--r-- | inc.com.txt | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/inc.com.txt b/inc.com.txt new file mode 100644 index 0000000..5410e64 --- /dev/null +++ b/inc.com.txt @@ -0,0 +1,21 @@ +author: substring-after(substring-before(//div[@id='byline'],'|'),'By') +author: //div[@class='byline']/a +date: //span[@class='pubdate'] +# print friendly page +body: //div[@id='text'] +# regular page +body: //div[@id= 'articlecontent'] + +strip: //div[@id= 'articlecontent']/h1 +strip: //div[@id='articlecontent']/p[@class='deck'] +strip: //div[@id='articlecontent']/div[@class='byline'] +strip: //div[@id='articlespacer'] +strip: //div[@id='incsharebox'] +strip: //div[@id='articlesidebar'] + +prune: no + +single_page_link: //a[contains(@href, 'Printer_Friendly.html')] +strip: //a[contains(., 'Dig Deeper')] +test_url: http://www.inc.com/guides/2010/11/seven-tips-for-lobbying-politicians.html +test_url: http://www.inc.com/eric-schurenberg/startups-are-we-geting-irrationally-exuberant.html
\ No newline at end of file |