From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/falter.at.txt | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/falter.at.txt (limited to 'inc/3rdparty/site_config/standard/falter.at.txt') diff --git a/inc/3rdparty/site_config/standard/falter.at.txt b/inc/3rdparty/site_config/standard/falter.at.txt new file mode 100644 index 00000000..b941b740 --- /dev/null +++ b/inc/3rdparty/site_config/standard/falter.at.txt @@ -0,0 +1,18 @@ +title: //h2[@class='related relatedTitle'] +author: //a[contains(@href, 'liste.php?author_id')] + +# can't think of a better way unfortunately, really bad markup on this site +date: substring-after(//td[@style='width:85%;'], 'vom') + +# not sure why, but instapaper seems to suck up the teaser paragraph +# not solved! +body: //div[contains(@class, 'teaser')] +body: //div[@id='content'] + +# cleanup +strip: //img[@src='http://www.falter.at/web/_pics/falterlogo_dblau.gif'] +strip: //div[@class='servicebox'] +strip: //h1 +strip: //br +strip: //td[@id='adcol'] +test_url: http://www.falter.at/web/print/detail.php?id=1634 \ No newline at end of file -- cgit v1.2.3