From: Alex Sadleir Date: Thu, 11 Apr 2013 12:22:35 +0000 Subject: datagov fixes X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=c64b3fe20debb60737f29c859d2bcf41ef0f70a7 --- datagov fixes Former-commit-id: ed3ba96db4beeb126f802a3168476e27f298aeb8 --- --- a/documents/datagov-export.py +++ b/documents/datagov-export.py @@ -12,8 +12,8 @@ #ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b') ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api', api_key='482a9dd2-a976-4adf-ac77-d71d92a98a52') -#couch = couchdb.Server('http://127.0.0.1:5984/') -couch = couchdb.Server('http://192.168.1.113:5984/') +couch = couchdb.Server('http://127.0.0.1:5984/') +#couch = couchdb.Server('http://192.168.1.113:5984/') # http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/ SYMBOLS = { @@ -91,6 +91,7 @@ def name_munge(input_name): return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) + #[:100] #return input_name.replace(' ', '').replace('.', '_').replace('&', 'and') @@ -117,9 +118,9 @@ if __name__ == "__main__": for doc in docsdb.view('app/datasets'): print doc.id - if doc.value['url'] != "http://data.gov.au/data/": + if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld": # Collect the package metadata. - pkg_name = doc.value['url'].replace("http://data.gov.au/dataset/",'').replace('/',''); _ + pkg_name = doc.value['url'].replace("http://data.gov.au/dataset/",'').replace('/',''); tags = [] if doc.value['agencyID'] == "AGIMO": if len(doc.value['metadata']["Keywords / Tags"]) > 0: @@ -185,6 +186,8 @@ } print group_entity ckan.group_register_post(group_entity) + elif ckan.last_status == 409: + print "group already exists" else: raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % ( ckan.last_status, pkg_name, e.args)) --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -201,7 +201,7 @@ def getDate(self, content, entry, doc): date = ''.join(content.stripped_strings).strip() (a, b, c) = date.partition("(") - date = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012")) + date = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012").replace("Janurary","January")) print date edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") print edate --- a/documents/runScrapers.sh +++ b/documents/runScrapers.sh @@ -1,10 +1,14 @@ -for f in scrapers/*.py; - do echo "Processing $f file.."; - python $f; +rm /tmp/disclosr-error +for f in scrapers/*.py; do + echo "Processing $f file.."; + python $f 2>/tmp/disclosr-error; if [ "$?" -ne "0" ]; then echo "error"; - sleep 2; + sleep 2; fi done +if [ -s /tmp/disclosr-error ] ; then + mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ; +fi --- a/documents/scrape.py +++ b/documents/scrape.py @@ -13,8 +13,8 @@ import socket #couch = couchdb.Server('http://192.168.1.148:5984/') -couch = couchdb.Server('http://192.168.1.113:5984/') -#couch = couchdb.Server('http://127.0.0.1:5984/') +#couch = couchdb.Server('http://192.168.1.113:5984/') +couch = couchdb.Server('http://127.0.0.1:5984/') def mkhash(input):