diff options
author | Petter Reinholdtsen <pere@hungry.com> | 2014-12-07 22:55:36 +0100 |
---|---|---|
committer | Petter Reinholdtsen <pere@hungry.com> | 2014-12-07 22:55:36 +0100 |
commit | 391bc7246af20b228e4f4eda36d4f0f5c350fe43 (patch) | |
tree | 7469d298b091c139a68566a1c77afe406d21ef05 | |
parent | 3fe8f4b6269ad94cf01dbd1c61e92c6568dea4ac (diff) |
New URL.
-rw-r--r-- | scrapersources/postliste-ruter | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/scrapersources/postliste-ruter b/scrapersources/postliste-ruter index 96818b4..43ea37f 100644 --- a/scrapersources/postliste-ruter +++ b/scrapersources/postliste-ruter @@ -7,6 +7,7 @@ # Datatype: ePhorte # Vendor: Ergo # Publish duration: 12 weeks +# Run: daily import scraperwiki import json @@ -18,7 +19,7 @@ import resource import sys import urlparse import re -scraperwiki.scrape('http://www2.ruter.no/verdt-a-vite/presse/offentlig-journal/') +scraperwiki.scrape('https://ruter.no/verdt-a-vite%2Fpresse%2Foffentlig-journal%2F') lazycache=scraperwiki.swimport('lazycache') postlistelib=scraperwiki.swimport('postliste-python-lib') @@ -84,7 +85,7 @@ parser = postlistelib.PDFJournalParser(agency=agency) #test_small_pdfs(parser) -process_journal_pdfs(parser, "http://www2.ruter.no/verdt-a-vite/presse/offentlig-journal/", errors) +process_journal_pdfs(parser, "https://ruter.no/verdt-a-vite%2Fpresse%2Foffentlig-journal%2F", errors) process_page_queue(parser, errors) report_errors(errors) |