fix broken urls on datagov export
Former-commit-id: 3c41d2694ab3235f5b6e99681b28dc21dda4e617
--- a/documents/datagov-export-groups.py
+++ b/documents/datagov-export-groups.py
@@ -9,7 +9,7 @@
# Instantiate the CKAN client.
#ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b')
-api_key = 'b3ab75e4-afbb-465b-a09d-8171c8c69a7a'
+api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api',
api_key=api_key)
couch = couchdb.Server('http://127.0.0.1:5984/')
@@ -39,41 +39,43 @@
groups = {}
for doc in docsdb.view('app/datasetGroups'):
group_name = doc.key
- pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
- doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
- if group_name in groups.keys():
- groups[group_name] = list(set(groups[group_name] + [pkg_name]))
- else:
- groups[group_name] = [pkg_name]
+ if group_name != "Not specified":
+ pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
+ doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
+ if group_name in groups.keys():
+ groups[group_name] = list(set(groups[group_name] + [pkg_name]))
+ else:
+ groups[group_name] = [pkg_name]
# add dataset to group(s)
for group_name in groups.keys():
- group_url = name_munge(group_name[:100])
- print group_name
- print groups[group_name]
- try:
- # Update the group details
- group_entity = ckan.group_entity_get(group_url)
- print "group "+group_name+" exists"
- if 'packages' in group_entity.keys():
- group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name]))
- else:
- group_entity['packages'] = groups[group_name]
- ckan.group_entity_put(group_entity)
- except CkanApiError, e:
- if ckan.last_status == 404:
- print "group "+group_name+" does not exist, creating"
- group_entity = {
- 'name': group_url,
- 'title': group_name,
- 'description': group_name,
- 'packages': groups[group_name]
- }
- #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))
+ if group_name != "Not specified":
+ group_url = name_munge(group_name[:100])
+ print group_name
+ print groups[group_name]
+ try:
+ # Update the group details
+ group_entity = ckan.group_entity_get(group_url)
+ print "group "+group_name+" exists"
+ if 'packages' in group_entity.keys():
+ group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name]))
+ else:
+ group_entity['packages'] = groups[group_name]
+ ckan.group_entity_put(group_entity)
+ except CkanApiError, e:
+ if ckan.last_status == 404:
+ print "group "+group_name+" does not exist, creating"
+ group_entity = {
+ 'name': group_url,
+ 'title': group_name,
+ 'description': group_name,
+ 'packages': groups[group_name]
+ }
+ #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/datagov-export.py
+++ b/documents/datagov-export.py
@@ -11,11 +11,37 @@
# Instantiate the CKAN client.
api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
-ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api',
+server = 'data.disclosurelo.gs'
+
+ckan = ckanclient.CkanClient(base_location='http://'+server+'api',
api_key=api_key)
-ckandirect = ckanapi.RemoteCKAN('http://data.disclosurelo.gs', api_key=api_key)
+ckandirect = ckanapi.RemoteCKAN('http://'+server, api_key=api_key)
couch = couchdb.Server('http://127.0.0.1:5984/')
#couch = couchdb.Server('http://192.168.1.113:5984/')
+
+import urllib
+import urlparse
+
+def url_fix(s, charset='utf-8'):
+ """Sometimes you get an URL by a user that just isn't a real
+ URL because it contains unsafe characters like ' ' and so on. This
+ function can fix some of the problems in a similar way browsers
+ handle data entered by the user:
+
+ >>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)')
+ 'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29'
+
+ :param charset: The target charset for the URL if the url was
+ given as unicode string.
+ """
+ if isinstance(s, unicode):
+ s = s.encode(charset, 'ignore')
+ if not urlparse.urlparse(s).scheme:
+ s = "http://"+s
+ scheme, netloc, path, qs, anchor = urlparse.urlsplit(s)
+ path = urllib.quote(path, '/%')
+ qs = urllib.quote_plus(qs, ':&=')
+ return urlparse.urlunsplit((scheme, netloc, path, qs, anchor))
# http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/
SYMBOLS = {
@@ -135,15 +161,26 @@
doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
print pkg_name
#add to or create organization using direct API
- org_name = name_munge(doc.value['metadata']["Agency"][:100])
+ agency = doc.value['metadata']["Agency"]
+ if agency == "APS":
+ agency = "Australian Public Service Commission"
+ if agency == "Shared Services, Treasury Directorate":
+ agency = "Shared Services Procurement, Treasury Directorate"
+ if agency == "Treasury - Shared Services":
+ agency = "Shared Services Procurement, Treasury Directorate"
+ if agency == "Territory and Municipal Services (TAMS)":
+ agency = "Territory and Municipal Services Directorate"
+ if agency == "State Library of NSW":
+ agency = "State Library of New South Wales"
+ org_name = name_munge(agency[:100])
if org_name not in orgs_list:
orgs_list = ckandirect.action.organization_list()['result']
#print orgs_list
if org_name not in orgs_list:
try:
print "org not found, creating " + org_name
- ckandirect.action.organization_create(name=org_name, title=doc.value['metadata']["Agency"],
- description=doc.value['metadata']["Agency"])
+ ckandirect.action.organization_create(name=org_name, title=agency,
+ description=agency)
orgs_list.append(org_name)
except ckanapi.ValidationError, e:
print e
@@ -158,6 +195,7 @@
org_id = orgs_ids[org_name]
print "org id is "+org_id
tags = []
+ creator = doc.value['metadata']["DCTERMS.Creator"]
if doc.value['agencyID'] == "AGIMO":
if len(doc.value['metadata']["Keywords / Tags"]) > 0:
if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
@@ -167,20 +205,26 @@
tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
#print tags
+ extras = []
+
+ for extra_key in doc.value['metadata'].keys():
+ if extra_key not in ["Description","Content-Language","DCTERMS.Description", "Keywords / Tags" ,"data.gov.au Category", "Download", "Permalink","DCTERMS.Identifier"]:
+ if doc.value['metadata'][extra_key] != None and doc.value['metadata'][extra_key] != "":
+ extras.append([extra_key, doc.value['metadata'][extra_key]])
+
package_entity = {
'name': pkg_name,
'title': doc.value['metadata']['DCTERMS.Title'],
'url': doc.value['metadata']['DCTERMS.Source.URI'],
'tags': tags, #tags are mandatory?
- 'author': doc.value['metadata']["DCTERMS.Creator"],
- 'maintainer': doc.value['metadata']["DCTERMS.Creator"],
+ 'author': creator,
+ 'maintainer': creator,
'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']),
'notes': html2text.html2text(doc.value['metadata']['Description']),
- 'owner_org': org_id
- #todo add missing key values like jurasdiction
+ 'owner_org': org_id,
+ 'extras': extras
}
- if doc.value['agencyID'] == "qld":
- package_entity = doc.value['metadata']
+
try:
#print package_entity
@@ -193,6 +237,7 @@
raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % (
ckan.last_status, pkg_name, e.args))
pkg = ckan.package_entity_get(pkg_name)
+
# add resources (downloadable data files)
if 'Download' in doc.value['metadata'].keys():
@@ -217,7 +262,7 @@
if 'name' in resource.keys():
name = resource['name']
print resource
- ckan.add_package_resource(pkg_name, resource['href'], name=name, resource_type='data',
+ ckan.add_package_resource(pkg_name, url_fix(resource['href']), name=name, resource_type='data',
format=format,
size=human2bytes(resource.get('size','0B')))
else: