diff options
| -rw-r--r-- | truthdig.com.txt | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/truthdig.com.txt b/truthdig.com.txt index e2a0280..0b34ec4 100644 --- a/truthdig.com.txt +++ b/truthdig.com.txt @@ -1,12 +1,16 @@ title: //div[@class='printbody']/h1 body: //div[@class='printbody'] -date: //meta[@property="article:published_time"]/@content +# date: //meta[@property="article:published_time"]/@content prune: no -strip: //div[@class='printbody']/a[@href='http://www.truthdig.com/'] +strip: //div[@class='printbody']//a[@href='http://www.truthdig.com/'] strip: //table[@class='footer'] strip: //h6[contains(., 'http://')] +strip_id_or_class: masthead +strip_id_or_class: addthis +strip_id_or_class: article_tools + single_page_link: //a[contains(@href, '/print/')] test_url: http://www.truthdig.com/report/item/the_election_march_of_the_trolls_20110829/ |