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 --- .../site_config/standard/tagesschau.de.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/tagesschau.de.txt (limited to 'inc/3rdparty/site_config/standard/tagesschau.de.txt') diff --git a/inc/3rdparty/site_config/standard/tagesschau.de.txt b/inc/3rdparty/site_config/standard/tagesschau.de.txt new file mode 100644 index 00000000..8ce8a90e --- /dev/null +++ b/inc/3rdparty/site_config/standard/tagesschau.de.txt @@ -0,0 +1,23 @@ +title://h1[1] + +author: substring-after(//em, 'Von ') +author:string('tagesschau.de') + +date:substring-after(//div[@class='standDatum'], 'Stand: ') + +body://div[contains(@class, 'article')] | //div[contains(@class, 'centerCol')] + +strip://h1[1] +strip: //div[contains(@class, 'directLinks')] +strip: //div[contains(@class, 'zitatBox')] +strip: //div[contains(@class, 'teaserBox metaBlock')] +strip: //*[contains(@class, 'inv')] +strip: //span[@class='imgSubline'] +strip: //*[contains(@class, 'topline')][1] +strip: //div[@id='rightCol'][1] +strip: //div[@id="footer"][1] +strip: //div[@class="fPlayer"] +strip: //div[@id='seitenanfang'] +strip: //div[@class='standDatum'] +strip: //em +test_url: http://www.tagesschau.de/ausland/wahlkampffrankreich102.html \ No newline at end of file -- cgit v1.2.3