From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/vanityfair.com.txt | 58 +++++++++++----------- 1 file changed, 29 insertions(+), 29 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/vanityfair.com.txt (limited to 'inc/3rdparty/site_config/standard/vanityfair.com.txt') diff --git a/inc/3rdparty/site_config/standard/vanityfair.com.txt b/inc/3rdparty/site_config/standard/vanityfair.com.txt old mode 100644 new mode 100755 index bfc47d1f..efa38224 --- a/inc/3rdparty/site_config/standard/vanityfair.com.txt +++ b/inc/3rdparty/site_config/standard/vanityfair.com.txt @@ -1,30 +1,30 @@ -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: //article[@id='items-container'] -#body: //h2[@class='sub-header'] | //div[contains(@class, 'contributor-type') or @class='display-date' or @class='content-container'] - -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 - -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_url: http://www.vanityfair.com/politics/features/2008/08/hitchens200808 +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: //article[@id='items-container'] +#body: //h2[@class='sub-header'] | //div[contains(@class, 'contributor-type') or @class='display-date' or @class='content-container'] + +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 + +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_url: http://www.vanityfair.com/politics/features/2008/08/hitchens200808 test_url: http://www.vanityfair.com/style/2012/01/prisoners-of-style-201201 \ No newline at end of file -- cgit v1.2.3