From a668e1acbea28c0066136a700ab29079c763b524 Mon Sep 17 00:00:00 2001 From: Petter Reinholdtsen Date: Thu, 7 Apr 2016 10:11:41 +0200 Subject: Fix PDF locator code for Ruter scraper. --- scrapersources/postliste-ruter | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scrapersources/postliste-ruter b/scrapersources/postliste-ruter index 43ea37f..bae8042 100644 --- a/scrapersources/postliste-ruter +++ b/scrapersources/postliste-ruter @@ -59,7 +59,7 @@ def process_journal_pdfs(parser, listurl, errors): html = scraperwiki.scrape(listurl) root = lxml.html.fromstring(html) html = None - for ahref in root.cssselect("div.attachments a"): + for ahref in root.cssselect("div a"): href = ahref.attrib['href'] url = urlparse.urljoin(listurl, href) if -1 != href.find("file://") or -1 == url.find(".pdf"): -- cgit v1.2.3