diff options
| author | Petter Reinholdtsen <pere@scraper.nuug.no> | 2014-12-07 23:04:54 +0100 |
|---|---|---|
| committer | Petter Reinholdtsen <pere@scraper.nuug.no> | 2014-12-07 23:05:34 +0100 |
| commit | 3ac6eb2db52f6423700ce59dd0e703c41ce71c3a (patch) | |
| tree | c1946d86af1ceb674ab6f63650b58b8f78aefa58 | |
| parent | 757e2de0aca1108cfa28fd532ebf9136e57e4ad7 (diff) | |
Adjust for new location.
| -rw-r--r-- | scrapersources/postliste-lier | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/scrapersources/postliste-lier b/scrapersources/postliste-lier index 5f39eb1..651cc52 100644 --- a/scrapersources/postliste-lier +++ b/scrapersources/postliste-lier @@ -18,7 +18,7 @@ import dateutil.parser import lxml.html import urlparse -scraperwiki.scrape("http://www.lier.kommune.no/no/Tjenesteomrader-/Oversikter/Postlister---Offentlig-journal/") +scraperwiki.scrape("http://www.lier.kommune.no/politikk-og-samfunnsutvikling/motekalender/") lazycache=scraperwiki.swimport('lazycache') postlistelib=scraperwiki.swimport('postliste-python-lib') @@ -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.fullwidth a"): + for ahref in root.cssselect("div.arrow-list-parent a"): href = ahref.attrib['href'] url = urlparse.urljoin(listurl, href) if -1 != href.find("file://") or -1 == href.find(".pdf"): @@ -85,7 +85,7 @@ parser = postlistelib.PDFJournalParser(agency=agency) #test_small_pdfs(parser) -process_journal_pdfs(parser, "http://www.lier.kommune.no/no/Tjenesteomrader-/Oversikter/Postlister---Offentlig-journal/", errors) +process_journal_pdfs(parser, "http://www.lier.kommune.no/politikk-og-samfunnsutvikling/motekalender/", errors) process_page_queue(parser, errors) report_errors(errors) |