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/blog.instapaper.com.txt | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/blog.instapaper.com.txt (limited to 'inc/3rdparty/site_config/standard/blog.instapaper.com.txt') diff --git a/inc/3rdparty/site_config/standard/blog.instapaper.com.txt b/inc/3rdparty/site_config/standard/blog.instapaper.com.txt new file mode 100755 index 00000000..fda01b15 --- /dev/null +++ b/inc/3rdparty/site_config/standard/blog.instapaper.com.txt @@ -0,0 +1,9 @@ +author: //a[@href="http://www.marco.org/about"] +date: //span[@class="date"] + +# Remove the date from article body. +strip: //span[@class="date"] + +# Remove pagination links from article body. +strip: //div[@id="pagination"] +test_url: http://blog.instapaper.com/post/31303984531 \ No newline at end of file -- cgit v1.2.3