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 --- .../standard/prospectmagazine.co.uk.txt | 50 +++++++++++----------- 1 file changed, 25 insertions(+), 25 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt b/inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt old mode 100644 new mode 100755 index 19059c4a..739d1b9e --- a/inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt +++ b/inc/3rdparty/site_config/standard/prospectmagazine.co.uk.txt @@ -1,26 +1,26 @@ -#basics -author: (//div[contains(@class,'author')])[1] -date: substring-before(//a[@class='issue'], '—') -#body://div[@class = 'entry'] -# use this until move_into support is ready -body: //div[@class = 'entry' or @class='standfirst' or @class='lead_image'] - -#moves header image and tagline into body -move_into(//div[@class='entry']/div)://div[@class = 'lead_image'] -move_into(//div[@class='entry']/div)://div[@class = 'standfirst'] - - -# moves author info to end of text -move_into(//p[strong[string(.) = 'Follow Prospect on Twitter']])://div[@id='sidebar_content']/p/em - -prune: no - -# strips social links -strip_id_or_class:login-status -strip_id_or_class:shareinpost -strip_id_or_class:content_subscribe -strip_id_or_class:postinfo -strip_id_or_class:postutils -strip_id_or_class:comments -strip://strong[string(.) = 'Follow Prospect on Twitter'] +#basics +author: (//div[contains(@class,'author')])[1] +date: substring-before(//a[@class='issue'], '—') +#body://div[@class = 'entry'] +# use this until move_into support is ready +body: //div[@class = 'entry' or @class='standfirst' or @class='lead_image'] + +#moves header image and tagline into body +move_into(//div[@class='entry']/div)://div[@class = 'lead_image'] +move_into(//div[@class='entry']/div)://div[@class = 'standfirst'] + + +# moves author info to end of text +move_into(//p[strong[string(.) = 'Follow Prospect on Twitter']])://div[@id='sidebar_content']/p/em + +prune: no + +# strips social links +strip_id_or_class:login-status +strip_id_or_class:shareinpost +strip_id_or_class:content_subscribe +strip_id_or_class:postinfo +strip_id_or_class:postutils +strip_id_or_class:comments +strip://strong[string(.) = 'Follow Prospect on Twitter'] test_url: http://www.prospectmagazine.co.uk/2011/07/postmodernism-is-dead-va-exhibition-age-of-authenticism/ \ No newline at end of file -- cgit v1.2.3