From 06cf4fa373ce5dfbc009306b79ae5bd127312bcc Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Tue, 1 Jul 2014 20:36:40 +0100 Subject: Remove m.guardian.co.uk. All the links now redirect to theguardian.com. --- m.guardian.co.uk.txt | 12 ------------ 1 file changed, 12 deletions(-) delete mode 100644 m.guardian.co.uk.txt diff --git a/m.guardian.co.uk.txt b/m.guardian.co.uk.txt deleted file mode 100644 index cce0271..0000000 --- a/m.guardian.co.uk.txt +++ /dev/null @@ -1,12 +0,0 @@ -title: //p[@class="txhead"] -author: //div[@class='txb'] -wrap_in(p): //div[@class='para'] -date: //div[@class='txb']/following-sibling::p/text()[substring(., 14)] -strip: //table[@class="tlogo"] -strip: //div[@class="cookieText"] -strip: //*[@class="sltb"] -strip: //*[@class="ijobs-x-link"] -strip: //*[@class="sponscolour"] -strip: //*[@class="sponsouter"] -strip: //div[@id="bottom-nav-block"]/following::* -test_url: http://m.guardian.co.uk/ms/p/gnm/op/s3OOwgO3yIhGuj41C1_S3Xg/view.m?id=15&gid=world/2012/jul/26/arctic-climate-change&cat=top-stories \ No newline at end of file -- cgit v1.3.1 From 4265f5b7772e694a8fa0729377e52c0d9df022cd Mon Sep 17 00:00:00 2001 From: Tom Taylor Date: Thu, 3 Jul 2014 09:17:49 +0100 Subject: Fix lareviewofbooks.org. --- lareviewofbooks.org.txt | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/lareviewofbooks.org.txt b/lareviewofbooks.org.txt index 9f86452..25e3654 100644 --- a/lareviewofbooks.org.txt +++ b/lareviewofbooks.org.txt @@ -1,12 +1,12 @@ -#meta data -title:substring-after(title,'|') - -author:substring-before( substring-after(//meta[@name = 'description']/@content, normalize-space(substring-after(//title,'|'))),' respond ') -date://h5[@class = 'postDate'] +#metadata +title: substring-before(//title,' |') +author: //a[contains(@class,'person') and starts-with(@href, '/contributor')] #text -body://div[@class = 'articleBody'] +body: //div[contains(@class, 'article_body')] #clean up -strip://center -test_url: http://lareviewofbooks.org/post/14066007115/literary-transactions-and-their-vicissitudes \ No newline at end of file +strip_id_or_class: recommended_section + +test_url: http://lareviewofbooks.org/review/american-politics-redeembale-robert-gates-hillary-clinton-two-memoirs-washington-dc +test_url: http://lareviewofbooks.org/interview/souvenirs-future -- cgit v1.3.1