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 --- inc/3rdparty/site_config/standard/salon.com.txt | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/salon.com.txt (limited to 'inc/3rdparty/site_config/standard/salon.com.txt') diff --git a/inc/3rdparty/site_config/standard/salon.com.txt b/inc/3rdparty/site_config/standard/salon.com.txt old mode 100644 new mode 100755 index 04f8afd5..2b47f744 --- a/inc/3rdparty/site_config/standard/salon.com.txt +++ b/inc/3rdparty/site_config/standard/salon.com.txt @@ -1,11 +1,11 @@ -title: //meta[@property='og:title']/@content -author: (//span[@class="byline"]/a)[1] -date: //span[contains(@class, "toLocalTime")] -body: (//div[contains(@class, "articleInner")]//img[contains(@src, 'media.salon.com') and contains(@src, '460x')])[1] | //div[contains(@class, "articleContent") or contains(@class, "writerMeta")] - -prune: no - -# deal with singleton links -single_page_link: (//h1/a[contains(@href, '/singleton')])[1] - +title: //meta[@property='og:title']/@content +author: (//span[@class="byline"]/a)[1] +date: //span[contains(@class, "toLocalTime")] +body: (//div[contains(@class, "articleInner")]//img[contains(@src, 'media.salon.com') and contains(@src, '460x')])[1] | //div[contains(@class, "articleContent") or contains(@class, "writerMeta")] + +prune: no + +# deal with singleton links +single_page_link: (//h1/a[contains(@href, '/singleton')])[1] + test_url: http://www.salon.com/2011/10/25/occupying_the_rust_belt/singleton/ \ No newline at end of file -- cgit v1.2.3