From fd3e2d4ac37db716ed29211790ca44a4bcc95ff3 Mon Sep 17 00:00:00 2001 From: Strubbl Date: Sat, 4 Mar 2017 17:01:48 +0100 Subject: fixes next_page_link detection for heise-ct (#274) This commit fixes the next_page_link detection for heise.de/ct/ articles, where the next-link ( with class=next) refers to the next article and not to the next page. Therefore i added a check, that the link text does not contain the word "Artikel". Without that check all consecutive articles are fetched, altough they are new articles and not a follow-up page of the same article. e.g.: https://www.heise.de/ct/ausgabe/2017-6-DVB-T2-HD-startet-in-Deutschland-3636637.html --- heise.de.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/heise.de.txt b/heise.de.txt index 869cd9b..cc80203 100755 --- a/heise.de.txt +++ b/heise.de.txt @@ -49,7 +49,7 @@ replace_string(
):
single_page_link: //a[contains(@href, '?view=print')] single_page_link: //a[contains(@title, 'Druck')] -next_page_link: //a[@class='next'] +next_page_link: //a[@class='next' and not(contains(text(), 'Artikel'))] next_page_link: //a[@title='vor'] next_page_link: //a[@rel='next'] -- cgit v1.3.1