X-Git-Url: https://git.immae.eu/?a=blobdiff_plain;ds=sidebyside;f=inc%2F3rdparty%2Fsite_config%2Fstandard%2Fsmithsonianmag.com.txt;h=3e8fee9578a22dc79e16093274ec581b305ce20c;hb=8327f1c371ad1d930bf9c9a13e443f2aa29ecfe3;hp=10a3f7173a3d1347a37fde2fe027c08ec0eb4424;hpb=7f667839764621b5aa01c9db8ce5dde2a29ef18f;p=github%2Fwallabag%2Fwallabag.git diff --git a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt old mode 100644 new mode 100755 index 10a3f717..3e8fee95 --- a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt +++ b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt @@ -1,20 +1,20 @@ -# meta data -title://h1[@id = 'articleTitle'] -author:substring-after(//ul[@id = 'byLine']/li[1],'By ') -date:substring-before(substring-after(//ul[@id = 'byLine']/li[last()],','),',') -body://div[@id = 'article-body'] - -# full content -single_page_link://td/li[@class = 'article-singlepage']/a - -# caption clean up -wrap_in(i)://span[@class='articleImageCaptionwide'] -move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p - - -# clean up -strip://p[@id = 'articlePaginationWrapper'] -strip://ul[contains(@class, 'cat-breadcrumb')] -strip://div [@class= 'viewMorePhotos'] +# meta data +title://h1[@id = 'articleTitle'] +author:substring-after(//ul[@id = 'byLine']/li[1],'By ') +date:substring-before(substring-after(//ul[@id = 'byLine']/li[last()],','),',') +body://div[@id = 'article-body'] + +# full content +single_page_link://td/li[@class = 'article-singlepage']/a + +# caption clean up +wrap_in(i)://span[@class='articleImageCaptionwide'] +move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p + + +# clean up +strip://p[@id = 'articlePaginationWrapper'] +strip://ul[contains(@class, 'cat-breadcrumb')] +strip://div [@class= 'viewMorePhotos'] test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html \ No newline at end of file