1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | import ckanclient import couchdb from ckanclient import CkanApiError import re class LoaderError(Exception): pass # Instantiate the CKAN client. #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='72f90359-0396-438c-804f-a26a24336747') #couch = couchdb.Server('http://127.0.0.1:5984/') couch = couchdb.Server('http://192.168.1.113:5984/') # http://stackoverflow.com/a/7778368/684978 from HTMLParser import HTMLParser import htmlentitydefs class HTMLTextExtractor(HTMLParser): def __init__(self): HTMLParser.__init__(self) self.result = [ ] def handle_data(self, d): self.result.append(d) def handle_charref(self, number): codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number) self.result.append(unichr(codepoint)) def handle_entityref(self, name): codepoint = htmlentitydefs.name2codepoint[name] self.result.append(unichr(codepoint)) def get_text(self): return u''.join(self.result) def html_to_text(html): s = HTMLTextExtractor() s.feed(html) return s.get_text() # 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' """ 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 def munge(name): # convert spaces to underscores name = re.sub(' ', '_', name).lower() # convert symbols to dashes name = re.sub('[:]', '_-', name).lower() name = re.sub('[/]', '-', name).lower() # take out not-allowed characters name = re.sub('[^a-zA-Z0-9-_]', '', name).lower() # 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') 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__": for doc in docsdb.view('app/datasets'): print doc.id if doc.value['url'] != "http://data.gov.au/data/": # Collect the package metadata. pkg_name = name_munge(doc.value['metadata']['DCTERMS.Title'][:100]) tags = doc.value['metadata']["Keywords / Tags"] if not hasattr(tags, '__iter__'): tags = [tags] [re.sub('[^a-zA-Z0-9-_()]', '', tag).replace('&', 'and').lower() for tag in tags] package_entity = { 'name': pkg_name, 'title': doc.value['metadata']['DCTERMS.Title'], 'url': doc.value['metadata']['DCTERMS.Source.URI'], 'author': doc.value['metadata']["DCTERMS.Creator"], 'maintainer': doc.value['metadata']["DCTERMS.Creator"], 'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']), 'notes': html_to_text(doc.value['metadata']['Description']), } if len(tags) > 0: package_entity['tags'] = tags print tags try: #print doc.id ckan.package_register_post(package_entity) except CkanApiError, e: if ckan.last_status == 409: print "already exists" else: raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % ( ckan.last_status, pkg_name, e.args)) print package_entity #todo add to organisation (author/creator/maintainer) http://docs.ckan.org/en/latest/apiv3.html#examples ckan.logic.action.update.package_owner_org_update #if 'data.gov.au Category' in doc.value['metadata'].keys(): #todo add to group if 'Download' in doc.value['metadata'].keys(): try: pkg = ckan.package_entity_get(pkg_name) resources = pkg.get('resources', []) if len(resources) < len(doc.value['metadata']['Download']): for resource in doc.value['metadata']['Download']: print resource # 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: 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)) |