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/tagesschau.de.txt | 42 +++++++++++----------- 1 file changed, 21 insertions(+), 21 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 8ce8a90e..be76cd05 --- a/inc/3rdparty/site_config/standard/tagesschau.de.txt +++ b/inc/3rdparty/site_config/standard/tagesschau.de.txt @@ -1,23 +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'] +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