diff options
| -rw-r--r-- | foreignpolicy.com.txt | 21 |
1 files changed, 8 insertions, 13 deletions
diff --git a/foreignpolicy.com.txt b/foreignpolicy.com.txt index 853a5b7..749ad37 100644 --- a/foreignpolicy.com.txt +++ b/foreignpolicy.com.txt @@ -1,19 +1,14 @@ -title: //div[@class='translateHead']//h1 | //div[@id='art-mast']//h1 -author: substring-after(//span[@id='by-line'], 'BY ') -date: //span[@id='pub-date'] -body: (//article//img[contains(@class, 'main_photo')])[1] | (//article//div[contains(@class, 'full_post_content')])[1] -#body: //div[@id='art-mast']/h2 | //div[@class='translateBody'] | //div[@id='art-body'] -#Strip inside article content -strip: //div[@id='share-box'] -strip: //div[@id='special-box +title: //h1[contains(concat(' ',normalize-space(@class),' '),' feature-hed ')] +author: substring-after(//p[contains(concat(' ',normalize-space(@class),' '),' feature-byline ')], 'BY ') +date: //div[contains(concat(' ',normalize-space(@class),' '),' timestamp ')]//time +body: //div[contains(concat(' ',normalize-space(@class),' '),' feature-body ')] +body: //div[contains(concat(' ',normalize-space(@class),' '),' post-inner ')] -strip_id_or_class: side_panel +strip_id_or_class: share-links prune: no -single_page_link: //span[@id='controls']/a[contains(@href, 'print=yes')] -single_page_link: //a[text()='SINGLE PAGE'] - test_url: http://www.foreignpolicy.com/articles/2014/07/22/the_end_game_in_gaza_netanyahu_hamas test_url: http://www.foreignpolicy.com/articles/2011/08/01/a_murderers_manifesto_and_me -test_url: http://www.foreignpolicy.com/articles/2012/02/29/five_years_in_damascus
\ No newline at end of file +test_url: http://www.foreignpolicy.com/articles/2012/02/29/five_years_in_damascus +test_url: http://foreignpolicy.com/2016/04/26/fear-this-man-cyber-warfare-hacking-team-david-vincenzetti/ |
