diff options
| author | FiveFilters.org <fivefilters@fivefilters.org> | 2016-02-17 00:30:36 +0100 |
|---|---|---|
| committer | FiveFilters.org <fivefilters@fivefilters.org> | 2016-02-17 00:30:36 +0100 |
| commit | 32e430a7cb5f509a77806293cba3078aa2459811 (patch) | |
| tree | 80ffb372fc823c498cbcec4658c7989754315140 | |
| parent | d4a5c0864884a455bc81fd90f237cde7374e3083 (diff) | |
| download | ftr-site-config-32e430a7cb5f509a77806293cba3078aa2459811.tar.gz ftr-site-config-32e430a7cb5f509a77806293cba3078aa2459811.zip | |
Update vanityfair.com.txt
| -rw-r--r-- | vanityfair.com.txt | 33 |
1 files changed, 5 insertions, 28 deletions
diff --git a/vanityfair.com.txt b/vanityfair.com.txt index f52339c..9851e72 100644 --- a/vanityfair.com.txt +++ b/vanityfair.com.txt @@ -1,33 +1,10 @@ -title: //meta[@property="og:title"]/@content -author: //div[contains(@class, 'byline')]//span[contains(@class, 'name')] -date: //div[contains(@class, 'cn_date_time')] -body: //div[contains(@class, 'pageContainers')] -body: //div[@id='main'] -body: //article[@id='items-container'] -#body: //h2[@class='sub-header'] | //div[contains(@class, 'contributor-type') or @class='display-date' or @class='content-container'] +body: //div[contains(concat(' ',normalize-space(@class),' '),' first-row ')]//div[contains(concat(' ',normalize-space(@class),' '),' article-row ') and (contains(concat(' ',normalize-space(@class),' '),' row-md '))]//div[contains(concat(' ',normalize-space(@class),' '),' article-main ') and (contains(concat(' ',normalize-space(@class),' '),' col-auto ')) and (contains(concat(' ',normalize-space(@class),' '),' article-content-body '))] -strip_id_or_class: bc -strip_id_or_class: utilities -strip_id_or_class: list-supporting -strip_id_or_class: yrail -strip_id_or_class: urail +// we can't load this (JS load) so may as well strip it to remove byline +strip: //figure[contains(@class, 'main-image')] -prune: no -#tidy: no - -strip_id_or_class: super-rubric-section -strip_id_or_class: cn_date_time -strip_id_or_class: cn_contributors -strip_id_or_class: cn_pagination_controls -strip_id_or_class: cn_features_container -strip_id_or_class: global-footer -strip_id_or_class: cn_ecom_placement -strip: //li[@class='blogNavPrev'] - -single_page_link: //a[@title='Print this page'] - -test_url: http://www.vanityfair.com/politics/features/2011/05/egypt-revolutionaries-201105 -test_contains: nothing can take away from the miracle of Tahrir Square +test_url: http://www.vanityfair.com/news/2016/02/george-w-bush-donald-trump-iraq +test_contains: riding high off a fourth-place finish in New Hampshire test_url: http://www.vanityfair.com/politics/features/2008/08/hitchens200808 test_url: http://www.vanityfair.com/style/2012/01/prisoners-of-style-201201 |