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/thenation.com.txt | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/thenation.com.txt (limited to 'inc/3rdparty/site_config/standard/thenation.com.txt') diff --git a/inc/3rdparty/site_config/standard/thenation.com.txt b/inc/3rdparty/site_config/standard/thenation.com.txt old mode 100644 new mode 100755 index d88bcdd6..dab17f0b --- a/inc/3rdparty/site_config/standard/thenation.com.txt +++ b/inc/3rdparty/site_config/standard/thenation.com.txt @@ -1,11 +1,13 @@ -title: //h1[@class='print-title'] -body: //div[@class='print-content'] -author: //a[contains(@href, '/authors')] -author: substring-before(//div[@class='print-created'], '|') -date: //span[@class='article-date'] -date: substring-after(//div[@class='print-created'], '|') -prune: no - -single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '/print/article/')] - +title: //h2[@property='dc:title'] +#body: //div[@class='print-content'] +body: //div[@id='wysiwyg'] +author: //a[contains(@href, '/authors')] +author: substring-before(//div[@class='print-created'], '|') +date: //span[@class='article-date'] +date: substring-after(//div[@class='print-created'], '|') +prune: no + +#single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '/print/article/')] +single_page_link: //ul[contains(@class, 'article-actions-bar')]//a[contains(@href, '?page=full')] + test_url: http://www.thenation.com/article/162331/hard-against-time-roy-fisher \ No newline at end of file -- cgit v1.2.3