diff options
| author | Petter Reinholdtsen <pere@hungry.com> | 2014-12-10 21:49:20 +0100 |
|---|---|---|
| committer | Petter Reinholdtsen <pere@hungry.com> | 2014-12-10 21:49:20 +0100 |
| commit | 64889b7d3bd8573fec7d8e0bd730c02c9e554ce2 (patch) | |
| tree | a84efa3d7ef41745b6ab2f97cc16ae903ed814a6 | |
| parent | 9b2909a8de0f5f1e9e5df7e1b13d6fccd4eaba32 (diff) | |
Quiet down URL extracter.
| -rw-r--r-- | scrapersources/postliste-universitetssykehuset-nord-norge | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/scrapersources/postliste-universitetssykehuset-nord-norge b/scrapersources/postliste-universitetssykehuset-nord-norge index faf1dce..0445436 100644 --- a/scrapersources/postliste-universitetssykehuset-nord-norge +++ b/scrapersources/postliste-universitetssykehuset-nord-norge @@ -62,7 +62,7 @@ def process_journal_pdfs(parser, listurl, errors): for ahref in root.cssselect("div.month-entry-title a"): href = ahref.attrib['href'] url = urlparse.urljoin(listurl, href) - print url +# print url if -1 != href.find("file://"): # print "Skipping non-http URL " + url continue @@ -96,7 +96,7 @@ parser = postlistelib.PDFJournalParser(agency=agency) process_page_queue(parser, errors) process_journal_pdfs(parser, "http://www.unn.no/offentlig-postjournal/category8944.html", errors) -for year in range(2011, 2007, -1): +for year in range(2013, 2007, -1): process_journal_pdfs(parser, "http://www.unn.no/offentlig-postjournal/category8944.html?year=" + str(year), errors) process_page_queue(parser, errors) report_errors(errors) |