--- a/documents/datagov-export.py +++ b/documents/datagov-export.py @@ -2,14 +2,88 @@ import couchdb from ckanclient import CkanApiError import re +import html2text # aaronsw :( +import ckanapi # https://github.com/open-data/ckanapi + + class LoaderError(Exception): pass + +# Instantiate the CKAN client. +api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' +server = 'data.disclosurelo.gs' + +ckan = ckanclient.CkanClient(base_location='http://'+server+'api', + 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/') + +# http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/ +SYMBOLS = { + 'customary': ('B', 'KB', 'MB', 'GB', 'T', 'P', 'E', 'Z', 'Y'), + 'customary_ext': ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa', + 'zetta', 'iotta'), + 'iec': ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'), + 'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi', + 'zebi', 'yobi'), +} + + +def human2bytes(s): + """ + Attempts to guess the string format based on default symbols + set and return the corresponding bytes as an integer. + When unable to recognize the format ValueError is raised. + + >>> human2bytes('0 B') + 0 + >>> human2bytes('1 K') + 1024 + >>> human2bytes('1 M') + 1048576 + >>> human2bytes('1 Gi') + 1073741824 + >>> human2bytes('1 tera') + 1099511627776 + + >>> human2bytes('0.5kilo') + 512 + >>> human2bytes('0.1 byte') + 0 + >>> human2bytes('1 k') # k is an alias for K + 1024 + >>> human2bytes('12 foo') + Traceback (most recent call last): + ... + ValueError: can't interpret '12 foo' + """ + if s == None: + return 0 + s = s.replace(',', '') + init = s + num = "" + while s and s[0:1].isdigit() or s[0:1] == '.': + num += s[0] + s = s[1:] + num = float(num) + letter = s.strip() + for name, sset in SYMBOLS.items(): + if letter in sset: + break + else: + if letter == 'k': + # treat 'k' as an alias for 'K' as per: http://goo.gl/kTQMs + sset = SYMBOLS['customary'] + letter = letter.upper() + else: + raise ValueError("can't interpret %r" % init) + prefix = {sset[0]: 1} + for i, s in enumerate(sset[1:]): + prefix[s] = 1 << (i + 1) * 10 + return int(num * prefix[letter]) + # https://github.com/okfn/ckanext-importlib -# Instantiate the CKAN client. -ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', - api_key='b47b24cd-591d-40c1-8677-d73101d56d1b') -# (use your own api_key from http://thedatahub.org/user/me ) - def munge(name): # convert spaces to underscores name = re.sub(' ', '_', name).lower() @@ -21,38 +95,158 @@ # remove double underscores name = re.sub('__', '_', name).lower() return name + + def name_munge(input_name): return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) - #return input_name.replace(' ', '').replace('.', '_').replace('&', 'and') - -couch = couchdb.Server('http://127.0.0.1:5984/') + + +def get_licence_id(licencename): + map = { + "Creative Commons - Attribution-Share Alike 2.0 Australia (CC-SA)\nThe downloadable version of the database is licensed under CC-BY-SA Creative Commons Attribution Share Alike and contains only the database fields that are released under that license. These fields are object title, object number, object description as well as temporal, spatial and dimension details. It also contains a persistent URL for each record.": 'cc-by-sa', + "CreativeCommonsAttributionNonCommercial30AustraliaCCBYNC30": 'cc-nc', + 'Otherpleasespecify': 'notspecified', + '': 'notspecified', + "Publicly available data": 'notspecified', + "CreativeCommonsAttributionNoDerivativeWorks30AustraliaCCBYND30": "other-closed", + "CreativeCommonsAttributionNonCommercialNoDerivs30AustraliaCCBYNCND30": "other-closed", + 'CreativeCommonsAttribution30AustraliaCCBY30': 'cc-by', + "Creative Commons - Attribution 2.5 Australia (CC-BY)": 'cc-by', + 'CreativeCommonsAttributionCCBY25': 'cc-by', + "PublicDomain": 'other-pd', + } + if licencename not in map.keys(): + raise Exception(licencename + " not found"); + return map[licencename]; + + docsdb = couch['disclosr-documents'] if __name__ == "__main__": + orgs_list = [] + orgs_ids = {} for doc in docsdb.view('app/datasets'): + print " --- " 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 = name_munge(doc.value['metadata']['DCTERMS.Title'][:100]) - package_entity = { - 'name': pkg_name, - 'title': doc.value['metadata']['DCTERMS.Title'], - 'url': doc.value['metadata']['DCTERMS.Source.URI'], - 'tags': doc.value['metadata']["Keywords / Tags"], #todo must be alphanumeric characters or symbols - - 'author': doc.value['metadata']["DCTERMS.Creator"], - 'maintainer': doc.value['metadata']["DCTERMS.Creator"], - 'licence_id': doc.value['metadata']['DCTERMS.License'], - 'notes': doc.value['metadata']['Description'], + pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', + doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); + print pkg_name + #add to or create organization using direct API + 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=agency, + description=agency) + orgs_list.append(org_name) + except ckanapi.ValidationError, e: + print e + raise LoaderError('Unexpected status') + else: + print "org found, adding dataset to " + org_name + + # cache org names -> id mapping + if org_name not in orgs_ids: + org = ckandirect.action.organization_show(id=org_name) + orgs_ids[org_name] = org["result"]["id"] + 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__'): + tags = tags + doc.value['metadata']["Keywords / Tags"] + else: + tags = tags + [doc.value['metadata']["Keywords / Tags"]] + + 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': creator, + 'maintainer': creator, + 'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']), + 'notes': html2text.html2text(doc.value['metadata']['Description']), + 'owner_org': org_id, + 'extras': extras } + + try: + #print package_entity ckan.package_register_post(package_entity) except CkanApiError, e: - if ckan.last_status == 409: - print "already exists" + if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}": + print "package already exists" else: - raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % (ckan.last_status, doc.id, e.args)) - - print package_entity - ckan.add_package_resource(pkg_name, 'http://example.org/', name='Foo', resource_type='data', format='csv') - + print ckan.last_message + 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(): + try: + + resources = pkg.get('resources', []) + if len(resources) < len(doc.value['metadata']['Download']): + for resource in doc.value['metadata']['Download']: + + # http://docs.ckan.org/en/ckan-1.7/domain-model-resource.html + # (KML/KMZ) / (Shapefile) /(Other) + format = "plain" + if resource['format'] == '(XML)': + format = 'xml' + if resource['format'] == '(CSV/XLS)': + format = 'csv' + if resource['format'] == '(Shapefile)': + format = 'shp' + if resource['format'] == '(KML/KMZ)': + format = 'kml' + name = resource['href'] + if 'name' in resource.keys(): + name = resource['name'] + print resource + ckan.add_package_resource(pkg_name, resource['href'], name=name, resource_type='data', + format=format, + size=human2bytes(resource.get('size','0B'))) + else: + print "resources already exist" + except CkanApiError, e: + if ckan.last_status == 404: + print "parent dataset does not exist" + else: + raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % ( + ckan.last_status, pkg_name, e.args)) +