From bf267bd848cdd6df92ecbecf15fc25db46952ad7 Mon Sep 17 00:00:00 2001 From: Lukas Anzinger Date: Thu, 28 Jul 2016 18:43:24 +0200 Subject: thegap.at: Add site config. (#190) thegap.at uses relative URLs and a base tag in the HTML code. Handling of such URLs (i.e. making them absolute) is not supported by Full-Text RSS as of 3.6 so only the first page is extracted for these versions. --- thegap.at.txt | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 thegap.at.txt diff --git a/thegap.at.txt b/thegap.at.txt new file mode 100644 index 0000000..5bf8ce5 --- /dev/null +++ b/thegap.at.txt @@ -0,0 +1,41 @@ +prune: no +tidy: no + +title: //h1 +strip: //h1 + +date: //span[contains(concat(' ', normalize-space(@class), ' '), ' date ')] +strip: //span[contains(concat(' ', normalize-space(@class), ' '), ' date ')] + +# Article + +author: normalize-space(substring-after(//div[@class='artikel']/p[1], 'von ')) +strip: //div[@class='artikel']/p[1] + +next_page_link: //a[@class='but weiter']/@href +strip: //div[@class='browsetext'] + +body: //div[@class='artikel'] +strip: //h5 +strip: //div[@class='copyrights'] +strip: //div[@class='textbox'] +strip: (//div[@class='artikel']//br)[1] +strip: //div[@class='clear'] +strip: //p[starts-with(., 'Weiter zu:')] +strip: //a[@name='minislide'] +strip: //div[@class='kommentare'] + +# Slideshows + +author: normalize-space(substring-after(//div[@id='normal']/p[1], 'von ')) +strip: //div[@id='normal']/p[1] + +body: //div[@id='normal'] +next_page_link: //a[@class='next']/@href +strip: //a[@class='next'] +strip: //a[@class='prev'] +strip: (//div[@id='normal']//br)[1] + +test_url: http://www.thegap.at/rubriken/stories/artikel/lecko-mio/ +test_url: http://www.thegap.at/rubriken/stories/artikel/die-frauen-im-arkadenhof/ +test_url: http://www.thegap.at/rubriken/stories/artikel/nothilfe-im-wandel/ -- cgit v1.3.1