| # coding=utf-8 | |
| import ckanclient | import ckanclient |
| import couchdb | import couchdb |
| from ckanclient import CkanApiError | from ckanclient import CkanApiError |
| import re | import re |
| import html2text # aaronsw :( | |
| import ckanapi # https://github.com/open-data/ckanapi | |
| import scrape | |
| import datetime, os, hashlib | |
| class LoaderError(Exception): | class LoaderError(Exception): |
| pass | pass |
| def add_package_resource_cachedurl(ckan, package_name, url, name, format, size, **kwargs): | |
| # fileupload | |
| ts = datetime.datetime.isoformat(datetime.datetime.now()).replace(':', '').split('.')[0] | |
| file_key = os.path.join(ts, name) | |
| auth_dict = ckan.storage_auth_get('/form/' + file_key, {}) | |
| fields = [(kv['name'].encode('ascii'), kv['value'].encode('ascii')) | |
| for kv in auth_dict['fields']] | |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
| url, "dataset_resource", "AGIMO", False) | |
| files = [('file', os.path.basename(file_key), content)] | |
| errcode, body = ckan._post_multipart(auth_dict['action'].encode('ascii'), fields, files) | |
| if errcode == 200: | |
| file_metadata = ckan.storage_metadata_get(file_key) | |
| (url, msg) = file_metadata['_location'], '' | |
| else: | |
| (url, msg) = '', body | |
| # fileupload done | |
| if url == '': | |
| raise CkanApiError(msg) | |
| m = hashlib.sha1(msg) | |
| #todo mime-type dectection based on content | |
| r = dict(name=name, | |
| mimetype=mime_type, | |
| hash=m.hexdigest(), size=size, url=url) | |
| r.update(kwargs) | |
| if not r.has_key('name'): r['name'] = url | |
| p = ckan.package_entity_get(package_name) | |
| p['resources'].append(r) | |
| return ckan.package_entity_put(p) | |
| # Instantiate the CKAN client. | # Instantiate the CKAN client. |
| #ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b') | api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' |
| ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api', api_key='72f90359-0396-438c-804f-a26a24336747') | server = 'data.disclosurelo.gs' |
| #couch = couchdb.Server('http://127.0.0.1:5984/') | |
| couch = couchdb.Server('http://192.168.1.113:5984/') | ckan = ckanclient.CkanClient(base_location='http://' + server + '/api', |
| api_key=api_key) | |
| # http://stackoverflow.com/a/7778368/684978 | ckandirect = ckanapi.RemoteCKAN('http://' + server, api_key=api_key) |
| from HTMLParser import HTMLParser | couch = couchdb.Server('http://127.0.0.1:5984/') |
| import htmlentitydefs | #couch = couchdb.Server('http://192.168.1.113:5984/') |
| class HTMLTextExtractor(HTMLParser): | import urllib |
| def __init__(self): | import urlparse |
| HTMLParser.__init__(self) | |
| self.result = [ ] | |
| def url_fix(s, charset='utf-8'): | |
| def handle_data(self, d): | """Sometimes you get an URL by a user that just isn't a real |
| self.result.append(d) | URL because it contains unsafe characters like ' ' and so on. This |
| function can fix some of the problems in a similar way browsers | |
| def handle_charref(self, number): | handle data entered by the user: |
| codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number) | |
| self.result.append(unichr(codepoint)) | >>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)') |
| 'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29' | |
| def handle_entityref(self, name): | |
| codepoint = htmlentitydefs.name2codepoint[name] | :param charset: The target charset for the URL if the url was |
| self.result.append(unichr(codepoint)) | given as unicode string. |
| """ | |
| def get_text(self): | if isinstance(s, unicode): |
| return u''.join(self.result) | s = s.encode(charset, 'ignore') |
| if not urlparse.urlparse(s).scheme: | |
| def html_to_text(html): | s = "http://" + s |
| s = HTMLTextExtractor() | scheme, netloc, path, qs, anchor = urlparse.urlsplit(s) |
| s.feed(html) | path = urllib.quote(path, '/%') |
| return s.get_text() | 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/ | # http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/ |
| SYMBOLS = { | SYMBOLS = { |
| 'customary': ('B', 'KB', 'MB', 'GB', 'T', 'P', 'E', 'Z', 'Y'), | 'customary': ('B', 'KB', 'MB', 'GB', 'T', 'P', 'E', 'Z', 'Y'), |
| 'customary_ext': ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa', | 'customary_ext': ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa', |
| 'zetta', 'iotta'), | 'zetta', 'iotta'), |
| 'iec': ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'), | 'iec': ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'), |
| 'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi', | 'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi', |
| 'zebi', 'yobi'), | 'zebi', 'yobi'), |
| } | } |
| def human2bytes(s): | def human2bytes(s): |
| """ | """ |
| Attempts to guess the string format based on default symbols | Attempts to guess the string format based on default symbols |
| set and return the corresponding bytes as an integer. | set and return the corresponding bytes as an integer. |
| When unable to recognize the format ValueError is raised. | When unable to recognize the format ValueError is raised. |
| >>> human2bytes('0 B') | >>> human2bytes('0 B') |
| 0 | 0 |
| >>> human2bytes('1 K') | >>> human2bytes('1 K') |
| 1024 | 1024 |
| >>> human2bytes('1 M') | >>> human2bytes('1 M') |
| 1048576 | 1048576 |
| >>> human2bytes('1 Gi') | >>> human2bytes('1 Gi') |
| 1073741824 | 1073741824 |
| >>> human2bytes('1 tera') | >>> human2bytes('1 tera') |
| 1099511627776 | 1099511627776 |
| >>> human2bytes('0.5kilo') | >>> human2bytes('0.5kilo') |
| 512 | 512 |
| >>> human2bytes('0.1 byte') | >>> human2bytes('0.1 byte') |
| 0 | 0 |
| >>> human2bytes('1 k') # k is an alias for K | >>> human2bytes('1 k') # k is an alias for K |
| 1024 | 1024 |
| >>> human2bytes('12 foo') | >>> human2bytes('12 foo') |
| Traceback (most recent call last): | Traceback (most recent call last): |
| ... | ... |
| ValueError: can't interpret '12 foo' | ValueError: can't interpret '12 foo' |
| """ | """ |
| if s == None: | |
| return 0 | |
| s = s.replace(',', '') | |
| init = s | init = s |
| num = "" | num = "" |
| while s and s[0:1].isdigit() or s[0:1] == '.': | while s and s[0:1].isdigit() or s[0:1] == '.': |
| num += s[0] | num += s[0] |
| s = s[1:] | s = s[1:] |
| num = float(num) | num = float(num) |
| letter = s.strip() | letter = s.strip() |
| for name, sset in SYMBOLS.items(): | for name, sset in SYMBOLS.items(): |
| if letter in sset: | if letter in sset: |
| break | break |
| else: | else: |
| if letter == 'k': | if letter == 'k': |
| # treat 'k' as an alias for 'K' as per: http://goo.gl/kTQMs | # treat 'k' as an alias for 'K' as per: http://goo.gl/kTQMs |
| sset = SYMBOLS['customary'] | sset = SYMBOLS['customary'] |
| letter = letter.upper() | letter = letter.upper() |
| else: | else: |
| raise ValueError("can't interpret %r" % init) | raise ValueError("can't interpret %r" % init) |
| prefix = {sset[0]: 1} | prefix = {sset[0]: 1} |
| for i, s in enumerate(sset[1:]): | for i, s in enumerate(sset[1:]): |
| prefix[s] = 1 << (i + 1) * 10 | prefix[s] = 1 << (i + 1) * 10 |
| return int(num * prefix[letter]) | return int(num * prefix[letter]) |
| # https://github.com/okfn/ckanext-importlib | # https://github.com/okfn/ckanext-importlib |
| def munge(name): | def munge(name): |
| # convert spaces to underscores | # convert spaces to underscores |
| name = re.sub(' ', '_', name).lower() | name = re.sub(' ', '_', name).lower() |
| # convert symbols to dashes | # convert symbols to dashes |
| name = re.sub('[:]', '_-', name).lower() | name = re.sub('[:]', '_-', name).lower() |
| name = re.sub('[/]', '-', name).lower() | name = re.sub('[/]', '-', name).lower() |
| # take out not-allowed characters | # take out not-allowed characters |
| name = re.sub('[^a-zA-Z0-9-_]', '', name).lower() | name = re.sub('[^a-zA-Z0-9-_]', '', name).lower() |
| # remove double underscores | # remove double underscores |
| name = re.sub('__', '_', name).lower() | name = re.sub('__', '_', name).lower() |
| return name | return name |
| def name_munge(input_name): | def name_munge(input_name): |
| return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) | return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) |
| #return input_name.replace(' ', '').replace('.', '_').replace('&', 'and') | |
| def get_licence_id(licencename): | def get_licence_id(licencename): |
| map = { | 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', | "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', | "CreativeCommonsAttributionNonCommercial30AustraliaCCBYNC30": 'cc-nc', |
| 'Otherpleasespecify': 'notspecified', | 'Otherpleasespecify': 'notspecified', |
| '': 'notspecified', | '': 'notspecified', |
| "Publicly available data": 'notspecified', | "Publicly available data": 'notspecified', |
| "CreativeCommonsAttributionNoDerivativeWorks30AustraliaCCBYND30": "other-closed", | "CreativeCommonsAttributionNoDerivativeWorks30AustraliaCCBYND30": "other-closed", |
| "CreativeCommonsAttributionNonCommercialNoDerivs30AustraliaCCBYNCND30": "other-closed", | "CreativeCommonsAttributionNonCommercialNoDerivs30AustraliaCCBYNCND30": "other-closed", |
| 'CreativeCommonsAttribution30AustraliaCCBY30': 'cc-by', | 'CreativeCommonsAttribution30AustraliaCCBY30': 'cc-by', |
| "Creative Commons - Attribution 2.5 Australia (CC-BY)": 'cc-by', | "Creative Commons - Attribution 2.5 Australia (CC-BY)": 'cc-by', |
| 'CreativeCommonsAttributionCCBY25': 'cc-by', | 'CreativeCommonsAttributionCCBY25': 'cc-by', |
| "PublicDomain": 'other-pd', | "PublicDomain": 'other-pd', |
| } | } |
| if licencename not in map.keys(): | if licencename not in map.keys(): |
| raise Exception(licencename + " not found"); | raise Exception(licencename + " not found"); |
| return map[licencename]; | return map[licencename]; |
| gooddata = ["afl-in-victoria", "annual-budget-initiatives-by-suburb-brisbane-city-council"] | |
| #athletics-in-victoria-gfyl,bicycle-racks-mosman-municipal-council,boat-ramps-brisbane-city-council,brisbane-access-ratings-database,bus-stops-brisbane-city-council,cemeteries-brisbane-city-council,cfa-locations,citycycle-stations-brisbane-city-council,community-gardens-brisbane-city-council,community-halls-brisbane-city-council,cooking-classes-gfyl,court-locations-victoria,customer-service-centres-brisbane-city-council,dance-in-victoria-gfyl,disability-activity-gfyl,dog-parks-brisbane-city-council,ferry-terminals-brisbane-city-council,fishing-club-in-victoria-gfyl,fitness-centres-in-victoria-gfyl,gardens-reserves-gfyl,golf-courses-brisbane-city-council,gymnastics-in-victoria-gfyl,historic-cemeteries-brisbane-city-council,ice-skating-centres-gfyl,immunisation-clinics-brisbane-city-council,libraries-brisbane-city-council,licenced-venues-victoria,lifesaving-locations-victoria,loading-zones-brisbane-city-council,major-projects-victoria,markets-in-victoria,martial-arts-in-victoria-gfyl,melbourne-water-use-by-postcode,members-of-parliament-both-houses-nsw,members-of-the-legislative-assembly-nsw,members-of-the-legislative-council-nsw,mfb-locations-vic,ministers-of-the-nsw-parliament,mosman-local-government-area,mosman-rider-route,mosman-wwii-honour-roll,neighbourhood-houses-gfyl,news-feeds-mosman-municipal-council,off-street-car-parks-mosman-municipal-council,orienteering-clubs-gfyl,parking-meter-areas-brisbane-city-council,parks-and-reserves-mosman-municipal-council,parks-brisbane-city-council,personal-training-gfyl,picnic-areas-brisbane-city-council,playgrounds-brisbane-city-council,playgrounds-mosman-municipal-council,police-region-crime-statistics-victoria,police-service-area-crime-statistics-victoria,pony-clubs-in-victoria-gfyl,prison-locations-victoria,public-amenities-maintained-by-mosman-council,public-art-brisbane-city-council,public-internet-locations-vic,public-toilets-brisbane-city-council,racecourse-locations-victoria,recent-development-applications-mosman-municipal-council,recreation-groups-gfyl,recreational-fishing-spots,regional-business-centres-brisbane-city-council,reports-of-swooping-birds-mosman-municipal-council,restricted-parking-areas-brisbane-city-council,rollerskating-centres-in-victoria-gfyl,sailing-clubs-gfyl,school-locations-victoria,shadow-ministers-of-the-nsw-parliament,skate-parks-gfyl,sporting-clubs-and-organisations-gfyl,stakeboard-parks-brisbane-city-council,state-bodies-gfyl,street-names-brisbane-city-council,suburbs-and-adjoining-suburbs-brisbane-city-council,swimming-pools-brisbane-city-council,swimming-pools-gfyl,tennis-courts-brisbane-city-council,top-40-book-club-reads-brisbane-city-council,tracks-and-trails-gfyl,triathlon-clubs-gfyl,urban-water-restrictions-victoria,veterinary-services-in-mosman,victorian-microbreweries,volunteering-centres-services-and-groups-victoria,walking-groups-gfyl,ward-offices-brisbane-city-council,waste-collection-days-brisbane-city-council,waste-transfer-stations-brisbane-city-council,water-consumption-in-melbourne,water-sports-in-victoria-gfyl,wifi-hot-spots-brisbane-city-council,yoga-pilates-and-tai-chi-in-victoria-gfyl,2809cycling-in-new-south-wales-what-the-data-tells-us2809-and-related-data,act-barbecue-bbq-locations,act-tafe-locations,ausindustry-locations,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,australian-gas-light-company-maps,australian-gas-light-company-maps,australian-ports,australian-public-service-statistical-bulletin-2011-12,australian-public-service-statistical-bulletin-snapshot-at-december-31-2011,australian-public-service-statistical-bulletin-tables-0910,austrics-timetable-set,capital-works-call-tender-schedule,collection-item-usage-state-library-of-victoria,country-and-commodity-trade-data-spreadsheet,country-and-commodity-trade-data-spreadsheet-2,country-by-level-of-processing-trade-data-spreadsheet,crime-incident-type-and-frequency-by-capital-city-and-nationally,csiro-locations,data-from-the-oaic-public-sector-information-survey-2012,data-from-the-oaic-public-sector-information-survey-2012,data-from-the-oaic-public-sector-information-survey-2012,department-of-finance-and-deregulation-office-locations,digitised-maps,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-locations,diisr-portfolio-agency-locations-excluding-csiro,distance-to-legal-service-providers-from-disadvantaged-suburbs,enterprise-connect-locations,fire-insurance-maps-sydney-block-plans-1919-1940,fire-insurance-maps-sydney-block-plans-1919-1940,first-fleet-collection,first-fleet-collection,first-fleet-maps,first-fleet-maps,freedom-of-information-annual-estimated-costs-and-staff-time-statistical-data-2011-12,freedom-of-information-quarterly-request-and-review-statistical-data-2011-12,freedom-of-information-requests-estimated-costs-and-charges-collected-1982-83-to-2011-12,higher-education-course-completions,higher-education-enrolments,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,journey-planner-data-nt,library-catalogue-search-terms-state-library-of-victoria,location-of-act-schools,location-of-centrelink-offices,location-of-european-wasps-nests,location-of-lawyers-and-legal-service-providers-by-town,location-of-legal-assistance-service-providers,location-of-medicare-offices,location-of-medicare-offices,maps-of-the-southern-hemisphere-16th-18th-centuries,maps-of-the-southern-hemisphere-16th-18th-centuries,music-queensland,national-measurement-institute-locations,new-south-wales-officers-and-men-of-the-australian-imperial-force-a-i-f-and-the-australian-naval-for,new-south-wales-officers-and-men-of-the-australian-imperial-force-a-i-f-and-the-australian-naval-for,photographs-of-nsw-life-pre-1955,photographs-of-nsw-life-pre-1955,photographs-of-sydney-before-1885,photographs-of-sydney-before-1885,picture-queensland,plgr-28093-playgrounds-act,police-station-locations,queensland-public-libraries,rare-printed-books,rare-printed-books,real-estate-maps,regional-australia-funding-projects,sa-memory-state-library-of-south-australia,search-engine-terms-state-library-of-victoria,south-australian-photographs-state-library-of-south-australia,south-australian-sheet-music-state-library-of-south-australia,sydney-bond-store-maps-1894,sydney-bond-store-maps-1894,sydney-maps-1917,sydney-maps-1917,tafe-institute-locations-victoria,tafe-sa-campus-locations,tolt-public-toilets-act,victorian-public-library-branches-state-library-of-victoria,western-australia-public-library-network,world-war-one-photographs-by-frank-hurley,world-war-one-photographs-by-frank-hurley,citycat-timetables-brisbane-city-council,cityferry-timetables-brisbane-city-council,cost-of-salinity-to-local-infrastructure-1996-97-summary-of-component-costs-of-salinity-by-reporting,cost-of-salinity-to-local-infrastructure-1996-97-summary-of-component-costs-of-salinity-by-reporting,downstream-cost-calculator-model-and-data-for-199697-or-2001-prices,economics-of-australian-soil-conditions-199697-limiting-factor-or-relative-yield-min-of-ry_salt2000-,geographical-names-register-gnr-of-nsw,victorian-dryland-salinity-assessment-2000-d01cac_ramsar_final-xls,victorian-dryland-salinity-assessment-2000-d02cac_fauna_final-xls,victorian-dryland-salinity-assessment-2000-d03cac_fauna_dist_final-xls,victorian-dryland-salinity-assessment-2000-dc04cac_hydrol_final-xls,victorian-dryland-salinity-assessment-2000-dc05cac_wetland_final-xls,victorian-dryland-salinity-assessment-2000-dc06cac_util_final-xls,victorian-dryland-salinity-assessment-2000-dc07cac_road_final-xls,victorian-dryland-salinity-assessment-2000-dc08cac_towns_final-xls,victorian-dryland-salinity-assessment-2000-dc09cac_flora_final-xls,victorian-dryland-salinity-assessment-2000-dc10cac_flora_dist_final-xls,victorian-dryland-salinity-assessment-2000-dc12cac_infrastructure-xls,victorian-dryland-salinity-assessment-2000-dc13cac_natural_envt-xls,victorian-dryland-salinity-assessment-2000-dc14cac_agriculture-xls,victorian-dryland-salinity-assessment-2000-dc16cac_agric_cost-xls,victorian-dryland-salinity-assessment-2000-dc17cac_shallow_wt-xls,victorian-dryland-salinity-assessment-2000-dc18cac_agric_cost_time-xls,victorian-dryland-salinity-assessment-2000-dc21cac_water_resources_new-xls,victorian-dryland-salinity-assessment-2000-dc22cac_risk-xls,licensed-broadcasting-transmitter-data,nsw-crime-data,recorded-crime-dataset-nsw,crime-statistics-in-nsw-by-month,2001-02-to-2007-08-local-government-survey-victoria,2009-green-light-report,annual-statistical-reports-fire-brigades-nsw-200304,annual-statistical-reports-fire-brigades-nsw-200405,annual-statistical-reports-fire-brigades-nsw-200506,annual-statistical-reports-fire-brigades-nsw-200607,arts-on-the-map,assets-and-liabilities-of-australian-located-operations,assets-of-australian-located-operations,assets-of-australian-located-operations-by-country,assets-of-financial-institutions,back-issues-of-monthly-banking-statistics,banks-assets,banks-consolidated-group-capital,banks-consolidated-group-impaired-assets,banks-consolidated-group-off-balance-sheet-business,banks-liabilities,building-societies-selected-assets-and-liabilities,byteback2842-locations-vic,cash-management-trusts,city-of-melbourne-street-furniture-database,community-services-nsw,consolidated-exposures-immediate-and-ultimate-risk-basis,consolidated-exposures-immediate-risk-basis-foreign-claims-by-country,consolidated-exposures-immediate-risk-basis-international-claims-by-country,consolidated-exposures-ultimate-risk-basis,consolidated-exposures-ultimate-risk-basis-foreign-claims-by-country,cosolidated-exposures-immediate-risk-basis,credit-unions-selected-assets-and-liabilities,daily-net-foreign-exchange-transactions,detox-your-home,education-national-assessment-program-literacy-and-numeracy-nsw,employment-data-by-nsw-regions,excise-beer-clearance-data-updated-each-month-beer-clearance-summary-data,finance-companies-and-general-financiers-selected-assets-and-liabilities,foreign-exchange-transactions-and-holdings-of-official-reserve-assets,half-yearly-life-insurance-bulletin-december-2010,health-behaviours-in-nsw,international-liabilities-by-country-of-the-australian-located-operations-of-banks-and-rfcs,liabilities-and-assets-monthly,liabilities-and-assets-weekly,liabilities-of-australian-located-operations,life-insurance-offices-statutory-funds,managed-funds,monetary-policy-changes,money-market-corporations-selected-assets-and-liabilities,monthly-airport-traffic-data-for-top-ten-airports-january-1985-to-december-2008,monthly-banking-statistics-april-2011,monthly-banking-statistics-june-2011,monthly-banking-statistics-may-2011,open-market-operations-2009-to-current,projected-households-vic-rvic-msd-2006-2056,projected-population-by-age-and-sex-vic-rvic-msd-2006-2056,public-unit-trust,quarterly-bank-performance-statistics,quarterly-general-insurance-performance-statistics-march-2011,quarterly-superannuation-performance-march-2011,recorded-crime-dataset-nsw,residential-land-bulletin,resourcesmart-retailers,resourcesmart-retailers-vic,road-fatalities-nsw,securitisation-vehicles,selected-asset-and-liabilities-of-the-private-non-financial-sectors,seperannuation-funds-outside-life-offices,solar-report-vic,towns-in-time-victoria,vif2008-projected-population-by-5-year-age-groups-and-sex-sla-lga-ssd-sd-2006-2026,vif2008-projected-population-totals-and-components-vic-rvic-msd-2006-2056,vif2008-projected-population-totals-sla-lga-ssd-sd-2006-2026,arts-festivals-victoria,arts-organisations-victoria,arts-spaces-and-places-victoria,ausgrid-average-electricity-use,collecting-institutions-victoria,indigenous-arts-organisations-victoria,latest-coastal-weather-observations-for-coolangatta-qld,top-10-fiction-books-brisbane-city-council]; | |
| docsdb = couch['disclosr-documents'] | docsdb = couch['disclosr-documents'] |
| if __name__ == "__main__": | if __name__ == "__main__": |
| orgs_list = [] | |
| orgs_ids = {} | |
| for doc in docsdb.view('app/datasets'): | for doc in docsdb.view('app/datasets'): |
| print " --- " | |
| print doc.id | 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. | # Collect the package metadata. |
| pkg_name = name_munge(doc.value['metadata']['DCTERMS.Title'][:100]) | pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', |
| tags = doc.value['metadata']["Keywords / Tags"] | doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); |
| if not hasattr(tags, '__iter__'): | print pkg_name |
| tags = [tags] | if pkg_name in gooddata: |
| [re.sub('[^a-zA-Z0-9-_()]', '', tag).replace('&', 'and').lower() for tag in tags] | |
| package_entity = { | #add to or create organization using direct API |
| 'name': pkg_name, | agency = doc.value['metadata']["Agency"] |
| 'title': doc.value['metadata']['DCTERMS.Title'], | if agency == "APS": |
| 'url': doc.value['metadata']['DCTERMS.Source.URI'], | agency = "Australian Public Service Commission" |
| if agency == "Shared Services, Treasury Directorate": | |
| 'author': doc.value['metadata']["DCTERMS.Creator"], | agency = "Shared Services Procurement, Treasury Directorate" |
| 'maintainer': doc.value['metadata']["DCTERMS.Creator"], | if agency == "Treasury - Shared Services": |
| 'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']), | agency = "Shared Services Procurement, Treasury Directorate" |
| 'notes': html_to_text(doc.value['metadata']['Description']), | if agency == "Territory and Municipal Services (TAMS)": |
| } | agency = "Territory and Municipal Services Directorate" |
| if len(tags) > 0: | if agency == "State Library of NSW": |
| package_entity['tags'] = tags | agency = "State Library of New South Wales" |
| print tags | org_name = name_munge(agency[:100]) |
| try: | if org_name not in orgs_list: |
| #print doc.id | orgs_list = ckandirect.action.organization_list()['result'] |
| ckan.package_register_post(package_entity) | #print orgs_list |
| except CkanApiError, e: | if org_name not in orgs_list: |
| if ckan.last_status == 409: | try: |
| print "already exists" | print "org not found, creating " + org_name |
| else: | ckandirect.action.organization_create(name=org_name, title=agency, |
| raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % ( | description=agency) |
| ckan.last_status, pkg_name, e.args)) | orgs_list.append(org_name) |
| except ckanapi.ValidationError, e: | |
| print package_entity | print e |
| #todo add to organisation (author/creator/maintainer) http://docs.ckan.org/en/latest/apiv3.html#examples ckan.logic.action.update.package_owner_org_update | raise LoaderError('Unexpected status') |
| #if 'data.gov.au Category' in doc.value['metadata'].keys(): #todo add to group | else: |
| if 'Download' in doc.value['metadata'].keys(): | 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: | try: |
| pkg = ckan.package_entity_get(pkg_name) | #print package_entity |
| resources = pkg.get('resources', []) | ckan.package_register_post(package_entity) |
| if len(resources) < len(doc.value['metadata']['Download']): | except CkanApiError, e: |
| for resource in doc.value['metadata']['Download']: | if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}": |
| print resource | print "package already exists" |
| # 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' | |
| name = resource['href'] | |
| if 'name' in resource.keys(): | |
| name = resource['name'] | |
| ckan.add_package_resource(pkg_name, resource['href'], name=name, resource_type='data', | |
| format=format, size=human2bytes(resource['size'].replace(',', ''))) | |
| else: | else: |
| print "resources already exist" | print ckan.last_message |
| 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' % ( | raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % ( |
| ckan.last_status, pkg_name, e.args)) | 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 | |
| add_package_resource_cachedurl(ckan, pkg_name, url_fix(resource['href']), name, | |
| format, | |
| human2bytes(resource.get('size', '0B')), | |
| resource_type='data') | |
| 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)) | |