more export fixes
more export fixes


Former-commit-id: 4ca7f1f81d51d7c094d904b6aa1e176cf5958630

<?php <?php
   
require_once '../include/common.inc.php'; require_once '../include/common.inc.php';
//function createFOIDocumentsDesignDoc() { //function createFOIDocumentsDesignDoc() {
   
$foidb = $server->get_db('disclosr-foidocuments'); $foidb = $server->get_db('disclosr-foidocuments');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };"; $obj->views->byDate->map = "function(doc) { if (doc.title != "Disclosure Log Updated") { emit(doc.date, doc); } };";
$obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };"; $obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };";
$obj->views->byDateMonthYear->reduce = "_count"; $obj->views->byDateMonthYear->reduce = "_count";
$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };"; $obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
$obj->views->byAgencyID->reduce = "_count"; $obj->views->byAgencyID->reduce = "_count";
$obj->views->fieldNames->map = ' $obj->views->fieldNames->map = '
function(doc) { function(doc) {
for(var propName in doc) { for(var propName in doc) {
emit(propName, doc._id); emit(propName, doc._id);
} }
   
}'; }';
$obj->views->fieldNames->reduce = 'function (key, values, rereduce) { $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
return values.length; return values.length;
}'; }';
// allow safe updates (even if slightly slower due to extra: rev-detection check). // allow safe updates (even if slightly slower due to extra: rev-detection check).
$foidb->save($obj, true); $foidb->save($obj, true);
   
   
//function createDocumentsDesignDoc() { //function createDocumentsDesignDoc() {
$docdb = $server->get_db('disclosr-documents'); $docdb = $server->get_db('disclosr-documents');
   
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}"; $obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}";
$obj->views->web_server->reduce = "_sum"; $obj->views->web_server->reduce = "_sum";
$obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}"; $obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}";
$obj->views->byAgency->reduce = "_sum"; $obj->views->byAgency->reduce = "_sum";
$obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}"; $obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}";
$obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}"; $obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}";
$obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}"; $obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}";
   
$obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n emit(doc._id, doc);\n}\n}"; $obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n emit(doc._id, doc);\n}\n}";
$obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n });\n}\n}"; $obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n });\n}\n}";
$obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"; $obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}";
$docdb->save($obj, true); $docdb->save($obj, true);
   
   
   
   
//function createAgencyDesignDoc() { //function createAgencyDesignDoc() {
$db = $server->get_db('disclosr-agencies'); $db = $server->get_db('disclosr-agencies');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
$obj->views->byCanonicalName->map = "function(doc) { $obj->views->byCanonicalName->map = "function(doc) {
if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') { if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc); emit(doc.name, doc);
} }
};"; };";
$obj->views->byDeptStateName->map = "function(doc) { $obj->views->byDeptStateName->map = "function(doc) {
if (doc.orgType == 'FMA-DepartmentOfState') { if (doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc._id); emit(doc.name, doc._id);
} }
};"; };";
$obj->views->parentOrgs->map = "function(doc) { $obj->views->parentOrgs->map = "function(doc) {
if (doc.parentOrg) { if (doc.parentOrg) {
emit(doc._id, doc.parentOrg); emit(doc._id, doc.parentOrg);
} }
};"; };";
$obj->views->byName->map = 'function(doc) { $obj->views->byName->map = 'function(doc) {
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
emit(doc.name, doc._id); emit(doc.name, doc._id);
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) { if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
emit(doc.shortName, doc._id); emit(doc.shortName, doc._id);
} }
for (name in doc.otherNames) { for (name in doc.otherNames) {
if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) { if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
emit(doc.otherNames[name], doc._id); emit(doc.otherNames[name], doc._id);
} }
} }
for (name in doc.foiBodies) { for (name in doc.foiBodies) {
if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) { if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
emit(doc.foiBodies[name], doc._id); emit(doc.foiBodies[name], doc._id);
} }
} }
for (name in doc.positions) { for (name in doc.positions) {
if (doc.positions[name] != "" && doc.positions[name] != doc.name) { if (doc.positions[name] != "" && doc.positions[name] != doc.name) {
emit(doc.positions[name], doc._id); emit(doc.positions[name], doc._id);
} }
} }
} }
};'; };';
   
$obj->views->foiEmails->map = "function(doc) { $obj->views->foiEmails->map = "function(doc) {
emit(doc._id, doc.foiEmail); emit(doc._id, doc.foiEmail);
};"; };";
   
$obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }"; $obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }";
$obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };'; $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };';
$obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };'; $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
$obj->views->getScrapeRequired->map = "function(doc) { $obj->views->getScrapeRequired->map = "function(doc) {
   
var lastScrape = Date.parse(doc.metadata.lastScraped); var lastScrape = Date.parse(doc.metadata.lastScraped);
   
var today = new Date(); var today = new Date();
   
if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) { if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
emit(doc._id, doc); emit(doc._id, doc);
} }
   
};"; };";
$obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };"; $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
$obj->views->getConflicts->map = "function(doc) { $obj->views->getConflicts->map = "function(doc) {
if (doc._conflicts) { if (doc._conflicts) {
emit(null, [doc._rev].concat(doc._conflicts)); emit(null, [doc._rev].concat(doc._conflicts));
} }
}"; }";
$obj->views->getStatistics->map = $obj->views->getStatistics->map =
"function(doc) { "function(doc) {
if (doc.statistics) { if (doc.statistics) {
for (var statisticSet in doc.statistics) { for (var statisticSet in doc.statistics) {
for (var statisticPeriod in doc.statistics[statisticSet]) { for (var statisticPeriod in doc.statistics[statisticSet]) {
emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']); emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']);
} }
} }
} }
}"; }";
$obj->views->getStatistics->reduce = '_sum'; $obj->views->getStatistics->reduce = '_sum';
// http://stackoverflow.com/questions/646628/javascript-startswith // http://stackoverflow.com/questions/646628/javascript-startswith
$obj->views->score->map = 'if(!String.prototype.startsWith){ $obj->views->score->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
} }
} }
   
function(doc) { function(doc) {
count = 0; count = 0;
if (doc["status"] != "suspended") { if (doc["status"] != "suspended") {
for(var propName in doc) { for(var propName in doc) {
if(typeof(doc[propName]) != "undefined" && doc[propName] != "") { if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
count++; count++;
} }
} }
portfolio = doc.parentOrg; portfolio = doc.parentOrg;
if (doc.orgType == "FMA-DepartmentOfState") { if (doc.orgType == "FMA-DepartmentOfState") {
portfolio = doc._id; portfolio = doc._id;
} }
if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") { if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
portfolio = doc.orgType; portfolio = doc.orgType;
} }
emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio}); emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
} }
}'; }';
$obj->views->scoreHas->map = 'if(!String.prototype.startsWith){ $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
} }
} }
if(!String.prototype.endsWith){ if(!String.prototype.endsWith){
String.prototype.endsWith = function(suffix) { String.prototype.endsWith = function(suffix) {
    return this.indexOf(suffix, this.length - suffix.length) !== -1;     return this.indexOf(suffix, this.length - suffix.length) !== -1;
}; };
} }
function(doc) { function(doc) {
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
for(var propName in doc) { for(var propName in doc) {
if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) { if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
emit(propName, 1); emit(propName, 1);
} }
} }
emit("total", 1); emit("total", 1);
} }
}'; }';
$obj->views->scoreHas->reduce = '_sum'; $obj->views->scoreHas->reduce = '_sum';
$obj->views->fieldNames->map = ' $obj->views->fieldNames->map = '
function(doc) { function(doc) {
for(var propName in doc) { for(var propName in doc) {
emit(propName, doc._id); emit(propName, doc._id);
} }
}'; }';
$obj->views->fieldNames->reduce = '_count'; $obj->views->fieldNames->reduce = '_count';
// allow safe updates (even if slightly slower due to extra: rev-detection check). // allow safe updates (even if slightly slower due to extra: rev-detection check).
$db->save($obj, true); $db->save($obj, true);
?> ?>
   
import ckanclient import ckanclient
import couchdb import couchdb
from ckanclient import CkanApiError from ckanclient import CkanApiError
import re import re
   
   
class LoaderError(Exception): class LoaderError(Exception):
pass pass
   
# Instantiate the CKAN client. # 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://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b')
api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api', server = 'data.disclosurelo.gs'
  api_key = 'c30eb6f5-0f90-47e0-bf05-9b1b4e3a461a'
  server = 'ckan.data.gov.au'
   
  ckan = ckanclient.CkanClient(base_location='http://' + server + '/api',
api_key=api_key) api_key=api_key)
couch = couchdb.Server('http://127.0.0.1:5984/') couch = couchdb.Server('http://127.0.0.1:5984/')
#couch = couchdb.Server('http://192.168.1.113:5984/') #couch = couchdb.Server('http://192.168.1.113:5984/')
   
# 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'))
   
   
docsdb = couch['disclosr-documents'] docsdb = couch['disclosr-documents']
   
if __name__ == "__main__": if __name__ == "__main__":
groups = {} groups = {}
for doc in docsdb.view('app/datasetGroups'): for doc in docsdb.view('app/datasetGroups'):
group_name = doc.key group_name = doc.key
if group_name != "Not specified": if group_name != "Not specified":
pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
if group_name in groups.keys(): if group_name in groups.keys():
groups[group_name] = list(set(groups[group_name] + [pkg_name])) groups[group_name] = list(set(groups[group_name] + [pkg_name]))
else: else:
groups[group_name] = [pkg_name] groups[group_name] = [pkg_name]
   
# add dataset to group(s) # add dataset to group(s)
for group_name in groups.keys(): for group_name in groups.keys():
if group_name != "Not specified": if group_name != "Not specified":
group_url = name_munge(group_name[:100]) group_url = name_munge(group_name[:100])
print group_name print group_name
print groups[group_name] print groups[group_name]
try: try:
# Update the group details # Update the group details
group_entity = ckan.group_entity_get(group_url) group_entity = ckan.group_entity_get(group_url)
print "group "+group_name+" exists" print "group "+group_name+" exists"
if 'packages' in group_entity.keys(): if 'packages' in group_entity.keys():
group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name])) group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name]))
else: else:
group_entity['packages'] = groups[group_name] group_entity['packages'] = groups[group_name]
ckan.group_entity_put(group_entity) ckan.group_entity_put(group_entity)
except CkanApiError, e: except CkanApiError, e:
if ckan.last_status == 404: if ckan.last_status == 404:
print "group "+group_name+" does not exist, creating" print "group "+group_name+" does not exist, creating"
group_entity = { group_entity = {
'name': group_url, 'name': group_url,
'title': group_name, 'title': group_name,
'description': group_name, 'description': group_name,
'packages': groups[group_name] 'packages': groups[group_name]
} }
#print group_entity #print group_entity
ckan.group_register_post(group_entity) ckan.group_register_post(group_entity)
elif ckan.last_status == 409: elif ckan.last_status == 409:
print "group already exists" print "group already exists"
else: else:
raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % ( raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % (
ckan.last_status, pkg_name, e.args)) ckan.last_status, pkg_name, e.args))
   
# coding=utf-8 # 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 html2text # aaronsw :(
import ckanapi # https://github.com/open-data/ckanapi import ckanapi # https://github.com/open-data/ckanapi
import scrape import scrape
import datetime, os, hashlib import datetime, os, hashlib
import urllib2 import urllib2
   
class LoaderError(Exception): class LoaderError(Exception):
pass pass
   
import tempfile import tempfile
def add_package_resource_cachedurl(ckan, package_name, url, name, format, license_id, size,**kwargs): def add_package_resource_cachedurl(ckan, package_name, url, name, format, license_id, size,**kwargs):
  excluded_apis = "recent-earthquakes,sentinel-hotspots,abc-local-stations,action-bus-service-gtfs-feed-act,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,journey-planner-data-act,live-traffic-cameras-nsw,precis-forecast-national,precis-forecast-national,precis-forecast-new-south-wales,precis-forecast-new-south-wales,precis-forecast-northern-territory,precis-forecast-northern-territory,precis-forecast-queensland,precis-forecast-queensland,precis-forecast-south-australia,precis-forecast-south-australia,precis-forecast-tasmania,precis-forecast-tasmania,precis-forecast-victoria,precis-forecast-victoria,precis-forecast-western-australia,precis-forecast-western-australia,register-of-penalty-notices-nsw,sentinel-hotspots,trove-people-and-organisations-data,weather-data-services-radar,abc-local-stations,act-emergency-services-agency-esa-28093-current-incidents,act-emergency-services-agency-esa-news-alerts,act-government-news-and-events,act-government-summaries-of-cabinet-outcomes,act-magistrates-court-judgements,act-supreme-court-judgements,act-supreme-court-sentences,actpla-latest-news,all-vacant-act-government-jobs,community-engagement-current-engagements,community-engagement-news,edd-media-releases,edd-news-and-events,freedom-of-information-foi-summaries,libraries-act-announcements,nsw-rural-fire-service-current-incidents,nsw-rural-fire-service-major-updates,precis-forecast-new-south-wales,precis-forecast-south-australia,precis-forecast-tasmania,precis-forecast-victoria,sentinel-hotspots,south-australian-road-crash-statistics,trove-people-and-organisations-data,weather-warnings-for-new-south-wales-australian-capital-territory,weather-warnings-for-northern-territory,weather-warnings-for-queensland,weather-warnings-for-south-australia,weather-warnings-for-tasmania,weather-warnings-for-victoria,weather-warnings-for-western-australia".split(",")
if "xls" in url: if "xls" in url:
format = "xls" format = "xls"
if "pdf" in url: if "pdf" in url:
format = "pdf" format = "pdf"
if "xlsx" in url: if "xlsx" in url:
format = "xlsx" format = "xlsx"
(returned_url, mime_type, content) = scrape.fetchURL(scrape.docsdb, (returned_url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
url, "dataset_resource", "AGIMO", False) url, "dataset_resource", "AGIMO", False)
if mime_type in ["application/vnd.ms-excel","application/msexcel","application/x-msexcel","application/x-ms-excel","application/x-excel","application/x-dos_ms_excel","application/xls","application/x-xls"]: if mime_type in ["application/vnd.ms-excel","application/msexcel","application/x-msexcel","application/x-ms-excel","application/x-excel","application/x-dos_ms_excel","application/xls","application/x-xls"]:
format = "xls" format = "xls"
if mime_type in ["application/xlsx","application/x-xlsx","application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]: if mime_type in ["application/xlsx","application/x-xlsx","application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]:
format = "xlsx" format = "xlsx"
   
if content != None: #put file extensions on for windows users downloading files
tf = tempfile.NamedTemporaryFile(delete=False) suffix = name.encode("ascii","ignore").replace("/","")
  if len(suffix) < 5 or (suffix[-4] != "." and suffix[-5] != "."):
  suffix = suffix + "." + format
  if content != None and package_name not in excluded_apis:
  tf = tempfile.NamedTemporaryFile(suffix=suffix)
tfName = os.path.abspath(tf.name) tfName = os.path.abspath(tf.name)
print tfName print tfName
tf.seek(0) tf.seek(0)
tf.write(content) tf.write(content)
tf.flush() tf.flush()
ckan.add_package_resource (package_name, tfName, name=name, format=format, license_id=license_id) ckan.add_package_resource (package_name, tfName, name=name, format=format, license_id=license_id)
else: else:
print "fetch error" print "fetch error"
return ckan.add_package_resource(package_name, url, name=name, resource_type='data', return ckan.add_package_resource(package_name, url, name=name, resource_type='data',
format=format, format=format,
size=size, mimetype=mime_type, license_id=license_id) size=size, mimetype=mime_type, license_id=license_id)
   
# Instantiate the CKAN client. # Instantiate the CKAN client.
api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
server = 'data.disclosurelo.gs' server = 'data.disclosurelo.gs'
   
ckan = ckanclient.CkanClient(base_location='http://' + server + '/api', ckan = ckanclient.CkanClient(base_location='http://' + server + '/api',
api_key=api_key) api_key=api_key)
ckandirect = ckanapi.RemoteCKAN('http://' + server, 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://127.0.0.1:5984/')
#couch = couchdb.Server('http://192.168.1.113:5984/') #couch = couchdb.Server('http://192.168.1.113:5984/')
   
import urllib import urllib
import urlparse import urlparse
   
   
def url_fix(s, charset='utf-8'): def url_fix(s, charset='utf-8'):
"""Sometimes you get an URL by a user that just isn't a real """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 URL because it contains unsafe characters like ' ' and so on. This
function can fix some of the problems in a similar way browsers function can fix some of the problems in a similar way browsers
handle data entered by the user: handle data entered by the user:
   
>>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)') >>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)')
'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29' 'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29'
   
:param charset: The target charset for the URL if the url was :param charset: The target charset for the URL if the url was
given as unicode string. given as unicode string.
""" """
if isinstance(s, unicode): if isinstance(s, unicode):
s = s.encode(charset, 'ignore') s = s.encode(charset, 'ignore')
if not urlparse.urlparse(s).scheme: if not urlparse.urlparse(s).scheme:
s = "http://" + s s = "http://" + s
scheme, netloc, path, qs, anchor = urlparse.urlsplit(s) scheme, netloc, path, qs, anchor = urlparse.urlsplit(s)
path = urllib.quote(path, '/%') path = urllib.quote(path, '/%')
qs = urllib.quote_plus(qs, ':&=') qs = urllib.quote_plus(qs, ':&=')
return urlparse.urlunsplit((scheme, netloc, path, qs, anchor)) 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: if s == None:
return 0 return 0
s = s.replace(',', '') 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'))
   
   
def get_license_id(licencename): def get_license_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": "cc-by-nd", "CreativeCommonsAttributionNoDerivativeWorks30AustraliaCCBYND30": "cc-by-nd",
"CreativeCommonsAttributionNonCommercialNoDerivs30AustraliaCCBYNCND30": "cc-nc-nd", "CreativeCommonsAttributionNonCommercialNoDerivs30AustraliaCCBYNCND30": "cc-nc-nd",
'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];
   
goodcsvdata = "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".split(",") goodcsvdata = "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".split(",")
goodotherdata = "abc-local-stations,abc-local-stations,abc-local-stations,act-emergency-services-agency-esa-28093-current-incidents,act-government-news-and-events,act-government-summaries-of-cabinet-outcomes,act-magistrates-court-judgements,act-supreme-court-judgements,act-supreme-court-sentences,action-bus-service-gtfs-feed-act,actpla-latest-news,agricultural-commodities-for-199697-linked-to-profit-function-surfaces,agricultural-structure-classification,agricultural-structure-classification,all-vacant-act-government-jobs,annual-family-income-1996-1997-to-1998-1999-three-year-average,apvma-pubcris-dataset-for-registered-agricultural-and-veterinary-chemical-products-and-approved-acti,argus-newspaper-collection-of-photographs-state-library-of-victoria,assessment-of-terrestrial-biodiversity-2002-biodiversity-audit-data-entry-system-bades,assessment-of-terrestrial-biodiversity-2002-database,assisted-immigration-1848-1912-index,ausgrid-average-electricity-use,ausgrid-average-electricity-use-2011,ausindustry-locations,ausindustry-locations,austender-contract-notice-export,australian-broadband-guarantee,australian-broadband-guarantee,australian-data-access,australian-dryland-salinity-assessment-spatial-data-12500000-nlwra-2001,australian-dryland-salinity-assessment-spatial-data-12500000-nlwra-2001,australian-groundwater-flow-systems-national-land-and-water-resources-audit-january-2000,australian-groundwater-flow-systems-national-land-and-water-resources-audit-january-2000,australian-irrigation-areas-raster-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-raster-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-vector-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-vector-version-1a-national-land-and-water-resources-audit,australian-public-service-statistical-bulletin-2010-11,australian-water-resources-assessment-2000-database,australiana-index-state-library-of-victoria,available-water-capacity-for-australian-areas-of-intensive-agriculture-of-layer-1-a-horizon-top-soil,bicycle-racks-mosman-municipal-council,bikeways-briisbane-city-council,bikeways-briisbane-city-council,boreholes-in-the-murray-basin-southeastern-australia,boreholes-in-the-murray-basin-southeastern-australia,british-convict-transportation-registers,calculated-annual-and-monthly-potential-evaporation-mm,calculated-annual-and-monthly-potential-evaporation-mm,canberra-suburb-boundaries,catchment-and-subcatchments-grid,cemeteries-brisbane-city-council,cemeteries-brisbane-city-council,coal-fields-in-the-murray-basin-southeastern-australia,coal-fields-in-the-murray-basin-southeastern-australia,commonwealth-agencies,commonwealth-electoral-boundaries-archive-2009,commonwealth-electoral-boundaries-archive-2009,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-all-infrastructure-buildings-road-rail-a,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-all-infrastructure-buildings-road-rail-a,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-increase-to-local-infrastructure-based-o,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-general-infrastructure-component-,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-rail-component-of-infrastructure-,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-general-infrastructure-component-bui,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-road-component-of-infrastructure-bas,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-road-component-of-infrastructure-bas,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-to-the-bridge-component-of-infrastructur,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-to-the-bridge-component-of-infrastructur,country-by-level-of-processing-trade-data-spreadsheet-2,country-by-level-of-processing-trade-data-spreadsheet-2011-12,crime-incidents-data-2004-international-crime-victimisation-survey-icvs-australian-component,cropping-management-practices-1998-1999,csiro-locations,csiro-locations,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,cybersafety-outreach-program,cybersafety-outreach-program,data-source-for-polygonal-data-used-by-the-asris-project-in-generation-of-modelled-surfaces,department-of-finance-and-deregulation-office-locations,department-of-finance-and-deregulation-office-locations,depositional-path-length,digital-enterprise,digital-hubs,digitised-maps,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-locations,diisr-portfolio-agency-locations-excluding-csiro,diisr-portfolio-agency-locations-excluding-csiro,directory-gov-au-full-data-export,distance-to-ridges,economics-of-australian-soil-conditions-199697-factor-most-limiting-yield-aciditysodicitysalinity,economics-of-australian-soil-conditions-199697-gross-benefit-acidity-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-of-the-limiting-factor-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-salinity-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-sodicity-hayr,economics-of-australian-soil-conditions-199697-impact-cost-of-salinity-2000-2020-hayr,economics-of-australian-soil-conditions-199697-relative-yield-from-acidity,economics-of-australian-soil-conditions-199697-relative-yield-from-salinity-in-2000,economics-of-australian-soil-conditions-199697-relative-yield-from-salinity-in-2020,economics-of-australian-soil-conditions-199697-relative-yield-from-sodicity,edd-media-releases,edd-news-and-events,egovernment-resource-centre-website-analytics,elevation-of-the-pre-tertiary-basement-in-the-murray-basin,elevation-of-the-pre-tertiary-basement-in-the-murray-basin,enterprise-connect-locations,enterprise-connect-locations,equivalent-fresh-water-head-difference-between-the-shallowest-and-deepest-aquifers,equivalent-fresh-water-head-difference-between-the-shallowest-and-deepest-aquifers,erosion-gully-density,erosion-path-length,estimated-proportion-of-farms-carrying-out-landcare-related-work-1998-1999,estimated-value-of-agricultural-operations-evao-1996-1997,farm-equity-ratio-1996-1997-to-1998-1999-three-year-average,farm-family-cash-income-1196-1997-to-1998-1999-three-year-average,farmer-population-1996,farms-with-significant-degradation-problems-irrigation-salinity-1998-1999,farms-with-significant-degradation-problems-irrigation-salinity-1998-1999-2,farms-with-significant-degradation-problems-soil-acidity-1998-1999,forests-of-australia-2003,freedom-of-information-foi-summaries,geology-lithology-12-500-000-scale,glenorchy-city-council-building-footprints,glenorchy-city-council-building-footprints,glenorchy-city-council-building-footprints,glenorchy-city-council-kerbs,glenorchy-city-council-kerbs,glenorchy-city-council-kerbs,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pits,glenorchy-city-council-stormwater-pits,glenorchy-city-council-stormwater-pits,groundwater-sdl-resource-units,groundwater-sdl-resource-units,groundwater-sdl-resource-units,higher-qualifications-of-farmers-and-farm-managers-1996,historical-australian-government-contract-data,historical-australian-government-contract-data,hydrologic-indicator-sites,hydrologic-indicator-sites,immigration-land-orders-1861-1874,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-biota-condition-sub-in,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-catchment-condition-in,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-feral-animal-density,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-human-population-densi,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-impoundment-density,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-industrial-point-sourc,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-intensive-agricultural,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-land-condition-sub-ind,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-native-vegetation-frag,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-nutrient-point-source-,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-pesticide-hazard,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-predicted-2050-salinit,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-protected-areas,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-in-acidificatio,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-in-salt-hazard,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-through-forests,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-soil-acidification-haz,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-soil-degradation-hazar,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-suspended-sediment-loa,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-weed-density,integrated-vegetation-cover-2003-version-1,john-t-collins-collection-state-library-of-victoria,journal-of-the-h-m-s-endeavour-1768-1771,journey-planner-data-act,krantz-sheldon-architectural-images,land-use-of-australia-version-3-28093-20012002,lands-surveys-historic-map-series-western-australia,latest-coastal-weather-observations-for-coolangatta-qld,launceston-city-council-addresses,launceston-city-council-building-footprints,launceston-city-council-contours,launceston-city-council-detail-survey-drawing-file,launceston-city-council-drainage,launceston-city-council-fences,launceston-city-council-pavement,launceston-city-council-railway,launceston-city-council-roads,libraries-act-announcements,licensed-broadcasting-transmitter-data,linc-tasmania,look-up-table-of-auslig-river-basins-of-australia-1997,major-water-resources-infrastructure-part-of-the-australian-water-resources-assessment-2000-database,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-pre-1788-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-pre-1788-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-present-day-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-present-day-scenario,mean-annual-deep-drainage-mm-y-in-the-pre-1788-scenario,mean-annual-deep-drainage-mm-y-in-the-pre-1788-scenario,mean-annual-deep-drainage-mm-y-in-the-present-day-scenario,mean-annual-deep-drainage-mm-y-in-the-present-day-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-pre-1788-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-pre-1788-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-present-day-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-april-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-april-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-february-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-february-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario-2,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario-2,mean-transpiration-in-may-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-present-day-scenario,mildenhall-photographs-of-early-canberra,mobility-map-brisbane-city,mobility-map-mt-coot-tha,mosman-local-government-area,mosman-rider-route,mosman-wwii-honour-roll,mosman-wwii-honour-roll,murray-darling-basin-water-resource-plan-areas-groundwater,murray-darling-basin-water-resource-plan-areas-groundwater,murray-darling-basin-water-resource-plan-areas-surface-water,murray-darling-basin-water-resource-plan-areas-surface-water,music-queensland,national-broadband-network,national-broadband-network,national-broadband-network-2011-10,national-broadband-network-2011-10,national-broadband-network-2011-12,national-broadband-network-2011-12,national-broadband-network-2012,national-broadband-network-28093-august-2011,national-broadband-network-28093-august-2011,national-broadband-network-28093-july-2011,national-broadband-network-28093-july-2011,national-broadband-network-february-2012,national-broadband-network-february-2012,national-broadband-network-september-2011,national-broadband-network-september-2011,national-library-of-australia-sheet-music-collection,national-measurement-institute-locations,national-parks-and-asset-locations-south-australia,national-public-toilet-map,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,nsw-newspapers-catalogue-data,nsw-rural-fire-service-current-incidents,nsw-rural-fire-service-major-updates,off-street-car-parks-mosman-municipal-council,open-database-brisbane-city-council,ost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-rail-component-of-infrastructure-b,parking-areas-brisbane-city-council,parking-areas-brisbane-city-council,parks-and-reserves-mosman-municipal-council,parks-brisbane-city-council,parks-brisbane-city-council,picture-australia-metadata,picture-queensland,picture-queensland,playgrounds-mosman-municipal-council,police-station-locations,police-station-locations,port-phillip-papers-state-library-of-victoria,precis-forecast-national,precis-forecast-national,precis-forecast-new-south-wales,precis-forecast-new-south-wales,precis-forecast-new-south-wales,precis-forecast-northern-territory,precis-forecast-northern-territory,precis-forecast-queensland,precis-forecast-queensland,precis-forecast-south-australia,precis-forecast-south-australia,precis-forecast-south-australia,precis-forecast-tasmania,precis-forecast-tasmania,precis-forecast-tasmania,precis-forecast-victoria,precis-forecast-victoria,precis-forecast-victoria,precis-forecast-western-australia,precis-forecast-western-australia,public-amenities-maintained-by-mosman-council,radio-and-television-broadcasting-stations-book-internet-edition,real-estate-maps,recent-earthquakes,regional-development-australia,regional-development-australia-2011-september-2011,regional-development-australia-may-2012,reports-of-swooping-birds-mosman-municipal-council,sentinel-hotspots,sentinel-hotspots,slq-catalogue-searches,slq-catalogue-searches,slv-rural-water,slv-shipping,slwa-digital-photographic-collection,south-australian-boat-ramp-locator,south-australian-road-crash-statistics,state-library-of-victoria-online-image-collection,state-library-of-victoria-online-image-collection-inc-high-res,state-of-the-service-report-2010-11-australian-public-service-employee-survey-results,state-of-the-service-report-2010-11-australian-public-service-employee-survey-results,statistical-local-areas-1996-for-agricultural-structure-classification,surface-water-gauging-stations-part-of-the-australian-water-resources-assessment-2000-database,surface-water-gauging-stations-part-of-the-australian-water-resources-assessment-2000-database,surface-water-sdl-resource-units,surface-water-sdl-resource-units,tasmanian-herbarium,tasmanian-museum-and-art-gallery-faunal-collection".split(",") goodotherdata = "abc-local-stations,abc-local-stations,abc-local-stations,act-emergency-services-agency-esa-28093-current-incidents,act-government-news-and-events,act-government-summaries-of-cabinet-outcomes,act-magistrates-court-judgements,act-supreme-court-judgements,act-supreme-court-sentences,action-bus-service-gtfs-feed-act,actpla-latest-news,agricultural-commodities-for-199697-linked-to-profit-function-surfaces,agricultural-structure-classification,agricultural-structure-classification,all-vacant-act-government-jobs,annual-family-income-1996-1997-to-1998-1999-three-year-average,apvma-pubcris-dataset-for-registered-agricultural-and-veterinary-chemical-products-and-approved-acti,argus-newspaper-collection-of-photographs-state-library-of-victoria,assessment-of-terrestrial-biodiversity-2002-biodiversity-audit-data-entry-system-bades,assessment-of-terrestrial-biodiversity-2002-database,assisted-immigration-1848-1912-index,ausgrid-average-electricity-use,ausgrid-average-electricity-use-2011,ausindustry-locations,ausindustry-locations,austender-contract-notice-export,australian-broadband-guarantee,australian-broadband-guarantee,australian-data-access,australian-dryland-salinity-assessment-spatial-data-12500000-nlwra-2001,australian-dryland-salinity-assessment-spatial-data-12500000-nlwra-2001,australian-groundwater-flow-systems-national-land-and-water-resources-audit-january-2000,australian-groundwater-flow-systems-national-land-and-water-resources-audit-january-2000,australian-irrigation-areas-raster-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-raster-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-vector-version-1a-national-land-and-water-resources-audit,australian-irrigation-areas-vector-version-1a-national-land-and-water-resources-audit,australian-public-service-statistical-bulletin-2010-11,australian-water-resources-assessment-2000-database,australiana-index-state-library-of-victoria,available-water-capacity-for-australian-areas-of-intensive-agriculture-of-layer-1-a-horizon-top-soil,bicycle-racks-mosman-municipal-council,bikeways-briisbane-city-council,bikeways-briisbane-city-council,boreholes-in-the-murray-basin-southeastern-australia,boreholes-in-the-murray-basin-southeastern-australia,british-convict-transportation-registers,calculated-annual-and-monthly-potential-evaporation-mm,calculated-annual-and-monthly-potential-evaporation-mm,canberra-suburb-boundaries,catchment-and-subcatchments-grid,cemeteries-brisbane-city-council,cemeteries-brisbane-city-council,coal-fields-in-the-murray-basin-southeastern-australia,coal-fields-in-the-murray-basin-southeastern-australia,commonwealth-agencies,commonwealth-electoral-boundaries-archive-2009,commonwealth-electoral-boundaries-archive-2009,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-all-infrastructure-buildings-road-rail-a,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-all-infrastructure-buildings-road-rail-a,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-increase-to-local-infrastructure-based-o,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-all-infrastructure-buildings-road-rai,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-general-infrastructure-component-,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-rail-component-of-infrastructure-,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-general-infrastructure-component-bui,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-road-component-of-infrastructure-bas,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-the-road-component-of-infrastructure-bas,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-to-the-bridge-component-of-infrastructur,cost-of-salinity-to-local-infrastructure-1996-97-total-cost-to-the-bridge-component-of-infrastructur,country-by-level-of-processing-trade-data-spreadsheet-2,country-by-level-of-processing-trade-data-spreadsheet-2011-12,crime-incidents-data-2004-international-crime-victimisation-survey-icvs-australian-component,cropping-management-practices-1998-1999,csiro-locations,csiro-locations,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,current-and-future-road-reports-traffic-restrictions-in-south-australia,cybersafety-outreach-program,cybersafety-outreach-program,data-source-for-polygonal-data-used-by-the-asris-project-in-generation-of-modelled-surfaces,department-of-finance-and-deregulation-office-locations,department-of-finance-and-deregulation-office-locations,depositional-path-length,digital-enterprise,digital-hubs,digitised-maps,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-locations,diisr-portfolio-agency-locations-excluding-csiro,diisr-portfolio-agency-locations-excluding-csiro,directory-gov-au-full-data-export,distance-to-ridges,economics-of-australian-soil-conditions-199697-factor-most-limiting-yield-aciditysodicitysalinity,economics-of-australian-soil-conditions-199697-gross-benefit-acidity-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-of-the-limiting-factor-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-salinity-hayr,economics-of-australian-soil-conditions-199697-gross-benefit-sodicity-hayr,economics-of-australian-soil-conditions-199697-impact-cost-of-salinity-2000-2020-hayr,economics-of-australian-soil-conditions-199697-relative-yield-from-acidity,economics-of-australian-soil-conditions-199697-relative-yield-from-salinity-in-2000,economics-of-australian-soil-conditions-199697-relative-yield-from-salinity-in-2020,economics-of-australian-soil-conditions-199697-relative-yield-from-sodicity,edd-media-releases,edd-news-and-events,egovernment-resource-centre-website-analytics,elevation-of-the-pre-tertiary-basement-in-the-murray-basin,elevation-of-the-pre-tertiary-basement-in-the-murray-basin,enterprise-connect-locations,enterprise-connect-locations,equivalent-fresh-water-head-difference-between-the-shallowest-and-deepest-aquifers,equivalent-fresh-water-head-difference-between-the-shallowest-and-deepest-aquifers,erosion-gully-density,erosion-path-length,estimated-proportion-of-farms-carrying-out-landcare-related-work-1998-1999,estimated-value-of-agricultural-operations-evao-1996-1997,farm-equity-ratio-1996-1997-to-1998-1999-three-year-average,farm-family-cash-income-1196-1997-to-1998-1999-three-year-average,farmer-population-1996,farms-with-significant-degradation-problems-irrigation-salinity-1998-1999,farms-with-significant-degradation-problems-irrigation-salinity-1998-1999-2,farms-with-significant-degradation-problems-soil-acidity-1998-1999,forests-of-australia-2003,freedom-of-information-foi-summaries,geology-lithology-12-500-000-scale,glenorchy-city-council-building-footprints,glenorchy-city-council-building-footprints,glenorchy-city-council-building-footprints,glenorchy-city-council-kerbs,glenorchy-city-council-kerbs,glenorchy-city-council-kerbs,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pipes,glenorchy-city-council-stormwater-pits,glenorchy-city-council-stormwater-pits,glenorchy-city-council-stormwater-pits,groundwater-sdl-resource-units,groundwater-sdl-resource-units,groundwater-sdl-resource-units,higher-qualifications-of-farmers-and-farm-managers-1996,historical-australian-government-contract-data,historical-australian-government-contract-data,hydrologic-indicator-sites,hydrologic-indicator-sites,immigration-land-orders-1861-1874,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-biota-condition-sub-in,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-catchment-condition-in,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-feral-animal-density,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-human-population-densi,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-impoundment-density,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-industrial-point-sourc,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-intensive-agricultural,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-land-condition-sub-ind,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-native-vegetation-frag,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-nutrient-point-source-,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-pesticide-hazard,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-predicted-2050-salinit,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-protected-areas,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-in-acidificatio,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-in-salt-hazard,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-rivers-through-forests,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-soil-acidification-haz,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-soil-degradation-hazar,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-suspended-sediment-loa,indicators-of-catchment-condition-in-the-intensive-land-use-zone-of-australia-weed-density,integrated-vegetation-cover-2003-version-1,john-t-collins-collection-state-library-of-victoria,journal-of-the-h-m-s-endeavour-1768-1771,journey-planner-data-act,krantz-sheldon-architectural-images,land-use-of-australia-version-3-28093-20012002,lands-surveys-historic-map-series-western-australia,latest-coastal-weather-observations-for-coolangatta-qld,launceston-city-council-addresses,launceston-city-council-building-footprints,launceston-city-council-contours,launceston-city-council-detail-survey-drawing-file,launceston-city-council-drainage,launceston-city-council-fences,launceston-city-council-pavement,launceston-city-council-railway,launceston-city-council-roads,libraries-act-announcements,licensed-broadcasting-transmitter-data,linc-tasmania,look-up-table-of-auslig-river-basins-of-australia-1997,major-water-resources-infrastructure-part-of-the-australian-water-resources-assessment-2000-database,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-pre-1788-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-pre-1788-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-present-day-scenario,mean-annual-concentration-of-mineral-nitrogen-in-soil-water-mgn-kgh20-in-the-present-day-scenario,mean-annual-deep-drainage-mm-y-in-the-pre-1788-scenario,mean-annual-deep-drainage-mm-y-in-the-pre-1788-scenario,mean-annual-deep-drainage-mm-y-in-the-present-day-scenario,mean-annual-deep-drainage-mm-y-in-the-present-day-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-pre-1788-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-pre-1788-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-present-day-scenario,mean-annual-transpiration-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-april-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-april-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-august-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-december-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-february-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-february-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-january-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-july-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-june-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario-2,mean-transpiration-in-march-from-the-plant-canopy-for-the-present-day-scenario-2,mean-transpiration-in-may-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-may-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-november-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-october-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-pre-1788-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-present-day-scenario,mean-transpiration-in-september-from-the-plant-canopy-for-the-present-day-scenario,mildenhall-photographs-of-early-canberra,mobility-map-brisbane-city,mobility-map-mt-coot-tha,mosman-local-government-area,mosman-rider-route,mosman-wwii-honour-roll,mosman-wwii-honour-roll,murray-darling-basin-water-resource-plan-areas-groundwater,murray-darling-basin-water-resource-plan-areas-groundwater,murray-darling-basin-water-resource-plan-areas-surface-water,murray-darling-basin-water-resource-plan-areas-surface-water,music-queensland,national-broadband-network,national-broadband-network,national-broadband-network-2011-10,national-broadband-network-2011-10,national-broadband-network-2011-12,national-broadband-network-2011-12,national-broadband-network-2012,national-broadband-network-28093-august-2011,national-broadband-network-28093-august-2011,national-broadband-network-28093-july-2011,national-broadband-network-28093-july-2011,national-broadband-network-february-2012,national-broadband-network-february-2012,national-broadband-network-september-2011,national-broadband-network-september-2011,national-library-of-australia-sheet-music-collection,national-measurement-institute-locations,national-parks-and-asset-locations-south-australia,national-public-toilet-map,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2000,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2020,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,new-south-wales-dryland-salinity-assessment-2000-assessmet-of-dryland-salinity-extent-2050,nsw-newspapers-catalogue-data,nsw-rural-fire-service-current-incidents,nsw-rural-fire-service-major-updates,off-street-car-parks-mosman-municipal-council,open-database-brisbane-city-council,ost-of-salinity-to-local-infrastructure-1996-97-total-cost-of-the-rail-component-of-infrastructure-b,parking-areas-brisbane-city-council,parking-areas-brisbane-city-council,parks-and-reserves-mosman-municipal-council,parks-brisbane-city-council,parks-brisbane-city-council,picture-australia-metadata,picture-queensland,picture-queensland,playgrounds-mosman-municipal-council,police-station-locations,police-station-locations,port-phillip-papers-state-library-of-victoria,precis-forecast-national,precis-forecast-national,precis-forecast-new-south-wales,precis-forecast-new-south-wales,precis-forecast-new-south-wales,precis-forecast-northern-territory,precis-forecast-northern-territory,precis-forecast-queensland,precis-forecast-queensland,precis-forecast-south-australia,precis-forecast-south-australia,precis-forecast-south-australia,precis-forecast-tasmania,precis-forecast-tasmania,precis-forecast-tasmania,precis-forecast-victoria,precis-forecast-victoria,precis-forecast-victoria,precis-forecast-western-australia,precis-forecast-western-australia,public-amenities-maintained-by-mosman-council,radio-and-television-broadcasting-stations-book-internet-edition,real-estate-maps,recent-earthquakes,regional-development-australia,regional-development-australia-2011-september-2011,regional-development-australia-may-2012,reports-of-swooping-birds-mosman-municipal-council,sentinel-hotspots,sentinel-hotspots,slq-catalogue-searches,slq-catalogue-searches,slv-rural-water,slv-shipping,slwa-digital-photographic-collection,south-australian-boat-ramp-locator,south-australian-road-crash-statistics,state-library-of-victoria-online-image-collection,state-library-of-victoria-online-image-collection-inc-high-res,state-of-the-service-report-2010-11-australian-public-service-employee-survey-results,state-of-the-service-report-2010-11-australian-public-service-employee-survey-results,statistical-local-areas-1996-for-agricultural-structure-classification,surface-water-gauging-stations-part-of-the-australian-water-resources-assessment-2000-database,surface-water-gauging-stations-part-of-the-australian-water-resources-assessment-2000-database,surface-water-sdl-resource-units,surface-water-sdl-resource-units,tasmanian-herbarium,tasmanian-museum-and-art-gallery-faunal-collection".split(",")
   
   
docsdb = couch['disclosr-documents'] docsdb = couch['disclosr-documents']
   
if __name__ == "__main__": if __name__ == "__main__":
orgs_list = [] orgs_list = []
orgs_ids = {} orgs_ids = {}
for doc in docsdb.view('app/datasets'): for doc in docsdb.view('app/datasets'):
print " --- " print " --- "
print doc.id print doc.id
   
if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld": if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld":
   
   
# Collect the package metadata. # Collect the package metadata.
pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
print pkg_name print pkg_name
if pkg_name != "": if pkg_name != "" :
   
#add to or create organization using direct API #add to or create organization using direct API
agency = doc.value['metadata']["Agency"] agency = doc.value['metadata']["Agency"]
if agency == "APS": if agency == "APS":
agency = "Australian Public Service Commission" agency = "Australian Public Service Commission"
if agency == "Department of Broadband, Communications and the Digital Ecomomy": if agency == "Department of Broadband, Communications and the Digital Ecomomy":
agency = "Department of Broadband, Communications and the Digital Economy" agency = "Department of Broadband, Communications and the Digital Economy"
if agency == "Shared Services, Treasury Directorate": if agency == "Shared Services, Treasury Directorate":
agency = "Shared Services Procurement, Treasury Directorate" agency = "Shared Services Procurement, Treasury Directorate"
if agency == "Treasury - Shared Services": if agency == "Treasury - Shared Services":
agency = "Shared Services Procurement, Treasury Directorate" agency = "Shared Services Procurement, Treasury Directorate"
if agency == "Territory and Municipal Services (TAMS)": if agency == "Territory and Municipal Services (TAMS)":
agency = "Territory and Municipal Services Directorate" agency = "Territory and Municipal Services Directorate"
if agency == "State Library of NSW": if agency == "State Library of NSW":
agency = "State Library of New South Wales" agency = "State Library of New South Wales"
org_name = name_munge(agency[:100]) org_name = name_munge(agency[:100])
if org_name not in orgs_list: if org_name not in orgs_list:
orgs_list = ckandirect.action.organization_list()['result'] orgs_list = ckandirect.action.organization_list()['result']
#print orgs_list #print orgs_list
if org_name not in orgs_list: if org_name not in orgs_list:
try: try:
print "org not found, creating " + org_name print "org not found, creating " + org_name
ckandirect.action.organization_create(name=org_name, title=agency, ckandirect.action.organization_create(name=org_name, title=agency,
description=agency) description=agency)
orgs_list.append(org_name) orgs_list.append(org_name)
except ckanapi.ValidationError, e: except ckanapi.ValidationError, e:
print e print e
raise LoaderError('Unexpected status') raise LoaderError('Unexpected status')
else: else:
print "org found, adding dataset to " + org_name print "org found, adding dataset to " + org_name
   
# cache org names -> id mapping # cache org names -> id mapping
if org_name not in orgs_ids: if org_name not in orgs_ids:
org = ckandirect.action.organization_show(id=org_name) org = ckandirect.action.organization_show(id=org_name)
orgs_ids[org_name] = org["result"]["id"] orgs_ids[org_name] = org["result"]["id"]
org_id = orgs_ids[org_name] org_id = orgs_ids[org_name]
print "org id is " + org_id print "org id is " + org_id
tags = [] tags = []
creator = doc.value['metadata']["DCTERMS.Creator"] creator = doc.value['metadata']["DCTERMS.Creator"]
if doc.value['agencyID'] == "AGIMO": if doc.value['agencyID'] == "AGIMO":
if len(doc.value['metadata']["Keywords / Tags"]) > 0: if len(doc.value['metadata']["Keywords / Tags"]) > 0:
if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'): if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
tags = tags + doc.value['metadata']["Keywords / Tags"] tags = tags + doc.value['metadata']["Keywords / Tags"]
else: else:
tags = tags + [doc.value['metadata']["Keywords / Tags"]] tags = tags + [doc.value['metadata']["Keywords / Tags"]]
   
tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag] tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
#print tags #print tags
extras = [] extras = []
   
for extra_key in doc.value['metadata'].keys(): for extra_key in doc.value['metadata'].keys():
if extra_key not in ["Description", "Content-Language", "DCTERMS.Description", if extra_key not in ["Description", "Content-Language", "DCTERMS.Description",
"Keywords / Tags", "Keywords / Tags",
"data.gov.au Category", "Download", "Permalink", "DCTERMS.Identifier"]: "data.gov.au Category", "Download", "Permalink", "DCTERMS.Identifier"]:
if doc.value['metadata'][extra_key] != None and doc.value['metadata'][extra_key] != "": if doc.value['metadata'][extra_key] != None and doc.value['metadata'][extra_key] != "":
extras.append([extra_key, doc.value['metadata'][extra_key]]) extras.append([extra_key, doc.value['metadata'][extra_key]])
   
package_entity = { package_entity = {
'name': pkg_name, 'name': pkg_name,
'title': doc.value['metadata']['DCTERMS.Title'], 'title': doc.value['metadata']['DCTERMS.Title'],
'url': doc.value['metadata']['DCTERMS.Source.URI'], 'url': doc.value['metadata']['DCTERMS.Source.URI'],
'tags': tags, #tags are mandatory? 'tags': tags, #tags are mandatory?
'author': creator, 'author': creator,
'maintainer': creator, 'maintainer': creator,
'license_id': get_license_id(doc.value['metadata']['DCTERMS.License']), 'license_id': get_license_id(doc.value['metadata']['DCTERMS.License']),
'notes': html2text.html2text(doc.value['metadata']['Description']).replace('AC/a!a','-').replace('AC/a!aC/',"'").replace("AC/a!E",":")replace("A "," "), 'notes': html2text.html2text(doc.value['metadata']['Description']).replace('AC/a!a','-').replace('AC/a!aC/',"'").replace("AC/a!E",":").replace("A "," "),
'owner_org': org_id, 'owner_org': org_id,
'extras': extras, 'extras': extras,
'private': (pkg_name not in goodcsvdata and pkg_name not in goodotherdata) 'private': (pkg_name not in goodcsvdata and pkg_name not in goodotherdata)
} }
   
try: try:
#print package_entity #print package_entity
ckan.package_register_post(package_entity) ckan.package_register_post(package_entity)
except CkanApiError, e: except CkanApiError, e:
if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}": if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}":
print "package already exists" print "package already exists"
else: else:
print ckan.last_message print ckan.last_message
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) pkg = ckan.package_entity_get(pkg_name)
   
   
# add resources (downloadable data files) # add resources (downloadable data files)
if 'Download' in doc.value['metadata'].keys(): if 'Download' in doc.value['metadata'].keys():
try: try:
   
resources = pkg.get('resources', []) resources = pkg.get('resources', [])
if len(resources) < len(doc.value['metadata']['Download']): if len(resources) < len(doc.value['metadata']['Download']):
for resource in doc.value['metadata']['Download']: for resource in doc.value['metadata']['Download']:
   
# http://docs.ckan.org/en/ckan-1.7/domain-model-resource.html # http://docs.ckan.org/en/ckan-1.7/domain-model-resource.html
# (KML/KMZ) / (Shapefile) /(Other) # (KML/KMZ) / (Shapefile) /(Other)
format = "plain" format = "plain"
if resource['format'] == '(XML)': if resource['format'] == '(XML)':
format = 'xml' format = 'xml'
if resource['format'] == '(CSV/XLS)': if resource['format'] == '(CSV/XLS)':
format = 'csv' format = 'csv'
if resource['format'] == '(Shapefile)': if resource['format'] == '(Shapefile)':
format = 'shp' format = 'shp'
if resource['format'] == '(KML/KMZ)': if resource['format'] == '(KML/KMZ)':
format = 'kml' format = 'kml'
name = resource['href'] name = resource['href']
if 'name' in resource.keys(): if 'name' in resource.keys():
name = resource['name'] name = resource['name']
print resource print resource
add_package_resource_cachedurl(ckan, pkg_name, url_fix(resource['href']), name, add_package_resource_cachedurl(ckan, pkg_name, url_fix(resource['href']), name,
format, get_license_id(doc.value['metadata']['DCTERMS.License']), format, get_license_id(doc.value['metadata']['DCTERMS.License']),
human2bytes(resource.get('size', '0B'))) human2bytes(resource.get('size', '0B')))
else: else:
print "resources already exist" print "resources already exist"
except CkanApiError, e: except CkanApiError, e:
if ckan.last_status == 404: if ckan.last_status == 404:
print "parent dataset does not exist" print "parent dataset does not exist"
else: 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))
   
import sys import sys
import os import os
   
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
import scrape import scrape
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from time import mktime from time import mktime
import feedparser import feedparser
import abc import abc
import unicodedata import unicodedata
import re import re
import dateutil import dateutil
from dateutil.parser import * from dateutil.parser import *
from datetime import * from datetime import *
import codecs import codecs
   
import difflib import difflib
   
from StringIO import StringIO from StringIO import StringIO
   
from pdfminer.pdfparser import PDFDocument, PDFParser from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
from pdfminer.pdfdevice import PDFDevice, TagExtractor from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.converter import TextConverter from pdfminer.converter import TextConverter
from pdfminer.cmapdb import CMapDB from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams from pdfminer.layout import LAParams
   
   
class GenericDisclogScraper(object): class GenericDisclogScraper(object):
__metaclass__ = abc.ABCMeta __metaclass__ = abc.ABCMeta
agencyID = None agencyID = None
disclogURL = None disclogURL = None
   
def remove_control_chars(self, input): def remove_control_chars(self, input):
return "".join([i for i in input if ord(i) in range(32, 127)]) return "".join([i for i in input if ord(i) in range(32, 127)])
   
def getAgencyID(self): def getAgencyID(self):
""" disclosr agency id """ """ disclosr agency id """
if self.agencyID is None: if self.agencyID is None:
self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "") self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "")
return self.agencyID return self.agencyID
   
def getURL(self): def getURL(self):
""" disclog URL""" """ disclog URL"""
if self.disclogURL is None: if self.disclogURL is None:
agency = scrape.agencydb.get(self.getAgencyID()) agency = scrape.agencydb.get(self.getAgencyID())
self.disclogURL = agency['FOIDocumentsURL'] self.disclogURL = agency['FOIDocumentsURL']
return self.disclogURL return self.disclogURL
   
@abc.abstractmethod @abc.abstractmethod
def doScrape(self): def doScrape(self):
""" do the scraping """ """ do the scraping """
return return
   
   
class GenericHTMLDisclogScraper(GenericDisclogScraper): class GenericHTMLDisclogScraper(GenericDisclogScraper):
def doScrape(self): def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments'] foidocsdb = scrape.couch['disclosr-foidocuments']
(url, mime_type, rcontent) = scrape.fetchURL(scrape.docsdb, (url, mime_type, rcontent) = scrape.fetchURL(scrape.docsdb,
self.getURL(), "foidocuments", self.getAgencyID()) self.getURL(), "foidocuments", self.getAgencyID())
content = rcontent content = rcontent
dochash = scrape.mkhash(content) dochash = scrape.mkhash(content)
doc = foidocsdb.get(dochash) doc = foidocsdb.get(dochash)
if doc is None: if doc is None:
print "saving " + dochash print "saving " + dochash
description = "This log may have updated but as it was not in a table last time we viewed it, we cannot extract what has changed. Please refer to the agency's website Disclosure Log to see the most recent entries" description = "This log may have updated but as it was not in a table last time we viewed it, we cannot extract what has changed. Please refer to the agency's website Disclosure Log to see the most recent entries"
last_attach = scrape.getLastAttachment(scrape.docsdb, self.getURL()) last_attach = scrape.getLastAttachment(scrape.docsdb, self.getURL())
if last_attach != None: if last_attach != None:
html_diff = difflib.HtmlDiff() html_diff = difflib.HtmlDiff()
diff = html_diff.make_table(last_attach.read().split('\n'), diff = html_diff.make_table(last_attach.read().split('\n'),
content.split('\n')) content.split('\n'))
edate = date.today().strftime("%Y-%m-%d") edate = date.today().strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID() doc = {'_id': dochash, 'agencyID': self.getAgencyID()
, 'url': self.getURL(), 'docID': dochash, , 'url': self.getURL(), 'docID': dochash,
"date": edate, "title": "Disclosure Log Updated", "date": edate, "title": "Disclosure Log Updated",
"description": self.remove_control_chars(description), "diff": self.remove_control_chars(diff)} "description": self.remove_control_chars(description), "diff": self.remove_control_chars(diff)}
foidocsdb.save(doc) foidocsdb.save(doc)
else: else:
print "already saved" print "already saved"
   
   
class GenericPDFDisclogScraper(GenericDisclogScraper): class GenericPDFDisclogScraper(GenericDisclogScraper):
def doScrape(self): def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments'] foidocsdb = scrape.couch['disclosr-foidocuments']
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
self.getURL(), "foidocuments", self.getAgencyID()) self.getURL(), "foidocuments", self.getAgencyID())
laparams = LAParams() laparams = LAParams()
rsrcmgr = PDFResourceManager(caching=True) rsrcmgr = PDFResourceManager(caching=True)
outfp = StringIO() outfp = StringIO()
device = TextConverter(rsrcmgr, outfp, codec='utf-8', device = TextConverter(rsrcmgr, outfp, codec='utf-8',
laparams=laparams) laparams=laparams)
fp = StringIO() fp = StringIO()
fp.write(content) fp.write(content)
   
process_pdf(rsrcmgr, device, fp, set(), caching=True, process_pdf(rsrcmgr, device, fp, set(), caching=True,
check_extractable=True) check_extractable=True)
description = outfp.getvalue() description = outfp.getvalue()
fp.close() fp.close()
device.close() device.close()
outfp.close() outfp.close()
dochash = scrape.mkhash(description) dochash = scrape.mkhash(description)
doc = foidocsdb.get(dochash) doc = foidocsdb.get(dochash)
if doc is None: if doc is None:
print "saving " + dochash print "saving " + dochash
edate = date.today().strftime("%Y-%m-%d") edate = date.today().strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID() doc = {'_id': dochash, 'agencyID': self.getAgencyID()
, 'url': self.getURL(), 'docID': dochash, , 'url': self.getURL(), 'docID': dochash,
"date": edate, "title": "Disclosure Log Updated", "description": self.remove_control_chars(description)} "date": edate, "title": "Disclosure Log Updated", "description": self.remove_control_chars(description)}
foidocsdb.save(doc) foidocsdb.save(doc)
else: else:
print "already saved" print "already saved"
   
   
class GenericDOCXDisclogScraper(GenericDisclogScraper): class GenericDOCXDisclogScraper(GenericDisclogScraper):
def doScrape(self): def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments'] foidocsdb = scrape.couch['disclosr-foidocuments']
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb (url, mime_type, content) = scrape.fetchURL(scrape.docsdb
, self.getURL(), "foidocuments", self.getAgencyID()) , self.getURL(), "foidocuments", self.getAgencyID())
mydoc = zipfile.ZipFile(file) mydoc = zipfile.ZipFile(file)
xmlcontent = mydoc.read('word/document.xml') xmlcontent = mydoc.read('word/document.xml')
document = etree.fromstring(xmlcontent) document = etree.fromstring(xmlcontent)
## Fetch all the text out of the document we just created ## Fetch all the text out of the document we just created
paratextlist = getdocumenttext(document) paratextlist = getdocumenttext(document)
# Make explicit unicode version # Make explicit unicode version
newparatextlist = [] newparatextlist = []
for paratext in paratextlist: for paratext in paratextlist:
newparatextlist.append(paratext.encode("utf-8")) newparatextlist.append(paratext.encode("utf-8"))
## Print our documnts test with two newlines under each paragraph ## Print our documnts test with two newlines under each paragraph
description = '\n\n'.join(newparatextlist).strip(' \t\n\r') description = '\n\n'.join(newparatextlist).strip(' \t\n\r')
dochash = scrape.mkhash(description) dochash = scrape.mkhash(description)
doc = foidocsdb.get(dochash) doc = foidocsdb.get(dochash)
   
if doc is None: if doc is None:
print "saving " + dochash print "saving " + dochash
edate = time().strftime("%Y-%m-%d") edate = time().strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID() doc = {'_id': dochash, 'agencyID': self.getAgencyID()
, 'url': self.getURL(), 'docID': dochash, , 'url': self.getURL(), 'docID': dochash,
"date": edate, "title": "Disclosure Log Updated", "description": description} "date": edate, "title": "Disclosure Log Updated", "description": description}
foidocsdb.save(doc) foidocsdb.save(doc)
else: else:
print "already saved" print "already saved"
   
   
class GenericRSSDisclogScraper(GenericDisclogScraper): class GenericRSSDisclogScraper(GenericDisclogScraper):
def doScrape(self): def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments'] foidocsdb = scrape.couch['disclosr-foidocuments']
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
self.getURL(), "foidocuments", self.getAgencyID()) self.getURL(), "foidocuments", self.getAgencyID())
feed = feedparser.parse(content) feed = feedparser.parse(content)
for entry in feed.entries: for entry in feed.entries:
#print entry #print entry
print entry.id print entry.id
dochash = scrape.mkhash(entry.id) dochash = scrape.mkhash(entry.id)
doc = foidocsdb.get(dochash) doc = foidocsdb.get(dochash)
#print doc #print doc
if doc is None: if doc is None:
print "saving " + dochash print "saving " + dochash
edate = datetime.fromtimestamp( edate = datetime.fromtimestamp(
mktime(entry.published_parsed)).strftime("%Y-%m-%d") mktime(entry.published_parsed)).strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID(), doc = {'_id': dochash, 'agencyID': self.getAgencyID(),
'url': entry.link, 'docID': entry.id, 'url': entry.link, 'docID': entry.id,
"date": edate, "title": entry.title} "date": edate, "title": entry.title}
self.getDescription(entry, entry, doc) self.getDescription(entry, entry, doc)
foidocsdb.save(doc) foidocsdb.save(doc)
else: else:
print "already saved" print "already saved"
   
def getDescription(self, content, entry, doc): def getDescription(self, content, entry, doc):
""" get description from rss entry""" """ get description from rss entry"""
doc.update({'description': content.summary}) doc.update({'description': content.summary})
   
return return
   
   
class GenericOAICDisclogScraper(GenericDisclogScraper): class GenericOAICDisclogScraper(GenericDisclogScraper):
__metaclass__ = abc.ABCMeta __metaclass__ = abc.ABCMeta
   
@abc.abstractmethod @abc.abstractmethod
def getColumns(self, columns): def getColumns(self, columns):
""" rearranges columns if required """ """ rearranges columns if required """
return return
   
def getColumnCount(self): def getColumnCount(self):
return 5 return 5
   
def getDescription(self, content, entry, doc): def getDescription(self, content, entry, doc):
""" get description from rss entry""" """ get description from rss entry"""
descriptiontxt = "" descriptiontxt = ""
for string in content.stripped_strings: for string in content.stripped_strings:
descriptiontxt = descriptiontxt + " \n" + string descriptiontxt = descriptiontxt + " \n" + string
doc.update({'description': descriptiontxt}) doc.update({'description': descriptiontxt})
   
def getTitle(self, content, entry, doc): def getTitle(self, content, entry, doc):
doc.update({'title': (''.join(content.stripped_strings))}) doc.update({'title': (''.join(content.stripped_strings))})
   
def getTable(self, soup): def getTable(self, soup):
return soup.table return soup.table
   
def getRows(self, table): def getRows(self, table):
return table.find_all('tr') return table.find_all('tr')
   
def getDate(self, content, entry, doc): def getDate(self, content, entry, doc):
strdate = ''.join(content.stripped_strings).strip() strdate = ''.join(content.stripped_strings).strip()
(a, b, c) = strdate.partition("(") (a, b, c) = strdate.partition("(")
strdate = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012")replace("Janrurary", "January").replace("1012","2012")) strdate = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012").replace("Janrurary", "January").replace("1012","2012"))
print strdate print strdate
try: try:
edate = parse(strdate, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") edate = parse(strdate, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
except ValueError: except ValueError:
print >> sys.stderr, "ERROR date invalid %s " % strdate print >> sys.stderr, "ERROR date invalid %s " % strdate
print >> sys.stderr, "ERROR date originally %s " % ''.join(content.stripped_strings).strip() print >> sys.stderr, "ERROR date originally %s " % ''.join(content.stripped_strings).strip()
edate = date.today().strftime("%Y-%m-%d") edate = date.today().strftime("%Y-%m-%d")
print edate print edate
doc.update({'date': edate}) doc.update({'date': edate})
return return
   
def getLinks(self, content, entry, doc): def getLinks(self, content, entry, doc):
links = [] links = []
for atag in entry.find_all("a"): for atag in entry.find_all("a"):
if atag.has_key('href'): if atag.has_key('href'):
links.append(scrape.fullurl(content, atag['href'])) links.append(scrape.fullurl(content, atag['href']))
if links != []: if links != []:
doc.update({'links': links}) doc.update({'links': links})
return return
   
def doScrape(self): def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments'] foidocsdb = scrape.couch['disclosr-foidocuments']
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
self.getURL(), "foidocuments", self.getAgencyID()) self.getURL(), "foidocuments", self.getAgencyID())
if content is not None: if content is not None:
if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type == "application/xml": if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type == "application/xml":
# http://www.crummy.com/software/BeautifulSoup/documentation.html # http://www.crummy.com/software/BeautifulSoup/documentation.html
print "parsing" print "parsing"
soup = BeautifulSoup(content) soup = BeautifulSoup(content)
table = self.getTable(soup) table = self.getTable(soup)
for row in self.getRows(table): for row in self.getRows(table):
columns = row.find_all('td') columns = row.find_all('td')
if len(columns) is self.getColumnCount(): if len(columns) is self.getColumnCount():
(id, date, title, (id, date, title,
description, notes) = self.getColumns(columns) description, notes) = self.getColumns(columns)
print self.remove_control_chars( print self.remove_control_chars(
''.join(id.stripped_strings)) ''.join(id.stripped_strings))
if id.string is None: if id.string is None:
dochash = scrape.mkhash( dochash = scrape.mkhash(
self.remove_control_chars( self.remove_control_chars(
url + (''.join(date.stripped_strings)))) url + (''.join(date.stripped_strings))))
else: else:
dochash = scrape.mkhash( dochash = scrape.mkhash(
self.remove_control_chars( self.remove_control_chars(
url + (''.join(id.stripped_strings)))) url + (''.join(id.stripped_strings))))
doc = foidocsdb.get(dochash) doc = foidocsdb.get(dochash)
   
if doc is None: if doc is None:
print "saving " + dochash print "saving " + dochash
doc = {'_id': dochash, doc = {'_id': dochash,
'agencyID': self.getAgencyID(), 'agencyID': self.getAgencyID(),
'url': self.getURL(), 'url': self.getURL(),
'docID': (''.join(id.stripped_strings))} 'docID': (''.join(id.stripped_strings))}
self.getLinks(self.getURL(), row, doc) self.getLinks(self.getURL(), row, doc)
self.getTitle(title, row, doc) self.getTitle(title, row, doc)
self.getDate(date, row, doc) self.getDate(date, row, doc)
self.getDescription(description, row, doc) self.getDescription(description, row, doc)
if notes is not None: if notes is not None:
doc.update({'notes': ( doc.update({'notes': (
''.join(notes.stripped_strings))}) ''.join(notes.stripped_strings))})
badtitles = ['-', 'Summary of FOI Request' badtitles = ['-', 'Summary of FOI Request'
, 'FOI request(in summary form)' , 'FOI request(in summary form)'
, 'Summary of FOI request received by the ASC', , 'Summary of FOI request received by the ASC',
'Summary of FOI request received by agency/minister', 'Summary of FOI request received by agency/minister',
'Description of Documents Requested', 'FOI request', 'Description of Documents Requested', 'FOI request',
'Description of FOI Request', 'Summary of request', 'Description', 'Summary', 'Description of FOI Request', 'Summary of request', 'Description', 'Summary',
'Summary of FOIrequest received by agency/minister', 'Summary of FOIrequest received by agency/minister',
'Summary of FOI request received', 'Description of FOI Request', 'Summary of FOI request received', 'Description of FOI Request',
"FOI request", 'Results 1 to 67 of 67'] "FOI request", 'Results 1 to 67 of 67']
if doc['title'] not in badtitles and 'description' in doc.keys() and doc['description'] != '': if doc['title'] not in badtitles and 'description' in doc.keys() and doc['description'] != '':
print "saving" print "saving"
foidocsdb.save(doc) foidocsdb.save(doc)
else: else:
print "already saved " + dochash print "already saved " + dochash
   
elif len(row.find_all('th')) is self.getColumnCount(): elif len(row.find_all('th')) is self.getColumnCount():
print "header row" print "header row"
   
else: else:
print >> sys.stderr, "ERROR number of columns incorrect" print >> sys.stderr, "ERROR number of columns incorrect"
print row print row
   
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
  echo $DIR
cd $DIR cd $DIR
echo "" > /tmp/disclosr-error echo "" > /tmp/disclosr-error
for f in scrapers/*.py; do for f in $DIR/scrapers/*.py; do
echo "Processing $f file.."; echo "Processing $f file..";
md5=`md5sum /tmp/disclosr-error` md5=`md5sum /tmp/disclosr-error`
python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error; python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error;
md52=`md5sum /tmp/disclosr-error` md52=`md5sum /tmp/disclosr-error`
if [ "$md5" != "$md52" ]; then if [ "$md5" != "$md52" ]; then
echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error; echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error;
fi fi
if [ "$?" -ne "0" ]; then if [ "$?" -ne "0" ]; then
echo "error"; echo "error";
sleep 1; sleep 1;
fi fi
done done
if [ -s /tmp/disclosr-error ] ; then if [ -s /tmp/disclosr-error ] ; then
echo "emailling logs.."; echo "emailling logs..";
mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ; mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ;
fi fi