From: Alex Sadleir <maxious@lambdacomplex.org>
Date: Fri, 22 Feb 2013 12:38:36 +0000
Subject: add dataqld
X-Git-Url: http://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=f31cd9d6de3ced75f644b7e7736510a08c419b27
---
add dataqld


Former-commit-id: 421bd9295854615553f74ab2a00773dcdc878775
---


--- a/documents/datagov-export.py
+++ b/documents/datagov-export.py
@@ -121,28 +121,31 @@
             # Collect the package metadata.
             pkg_name = doc.value['url'].replace("http://data.gov.au/dataset/",'').replace('/','');                                                                  _
             tags = []
-            if len(doc.value['metadata']["Keywords / Tags"]) > 0:
-                if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
-                    tags = tags + doc.value['metadata']["Keywords / Tags"]
-                else:
-                    tags = tags + [doc.value['metadata']["Keywords / Tags"]]
-            if 'data.gov.au Category' in doc.value['metadata'].keys() and len(doc.value['metadata']['data.gov.au Category']) > 0:
-                if hasattr(doc.value['metadata']['data.gov.au Category'], '__iter__'):
-                    tags = tags + doc.value['metadata']['data.gov.au Category']
-                else:
-                    tags = tags + [doc.value['metadata']['data.gov.au Category']]
-            tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
-            print tags
-            package_entity = {
-                'name': pkg_name,
-                'title': doc.value['metadata']['DCTERMS.Title'],
-                'url': doc.value['metadata']['DCTERMS.Source.URI'],
-                'tags': tags, #tags are mandatory?
-                'author': doc.value['metadata']["DCTERMS.Creator"],
-                'maintainer': doc.value['metadata']["DCTERMS.Creator"],
-                'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']),
-                'notes': html2text.html2text(doc.value['metadata']['Description']),
-            }
+            if doc.value['agencyID'] == "AGIMO":
+                if len(doc.value['metadata']["Keywords / Tags"]) > 0:
+                    if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
+                        tags = tags + doc.value['metadata']["Keywords / Tags"]
+                    else:
+                        tags = tags + [doc.value['metadata']["Keywords / Tags"]]
+                if 'data.gov.au Category' in doc.value['metadata'].keys() and len(doc.value['metadata']['data.gov.au Category']) > 0:
+                    if hasattr(doc.value['metadata']['data.gov.au Category'], '__iter__'):
+                        tags = tags + doc.value['metadata']['data.gov.au Category']
+                    else:
+                        tags = tags + [doc.value['metadata']['data.gov.au Category']]
+                tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
+                print tags
+                package_entity = {
+                    'name': pkg_name,
+                    'title': doc.value['metadata']['DCTERMS.Title'],
+                    'url': doc.value['metadata']['DCTERMS.Source.URI'],
+                    'tags': tags, #tags are mandatory?
+                    'author': doc.value['metadata']["DCTERMS.Creator"],
+                    'maintainer': doc.value['metadata']["DCTERMS.Creator"],
+                    'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']),
+                    'notes': html2text.html2text(doc.value['metadata']['Description']),
+                }
+            if doc.value['agencyID'] == "qld":
+                package_entity = doc.value['metadata']
 
             try:
                 print package_entity

--- /dev/null
+++ b/documents/dataqld.py
@@ -1,1 +1,28 @@
+import sys, os
+import time
+import scrape
+from bs4 import BeautifulSoup
 
+from unidecode import unidecode
+import ckanclient
+
+# Instantiate the CKAN client.
+ckan = ckanclient.CkanClient(base_location='https://data.qld.gov.au/api')
+
+# Get the package list.
+package_list = ckan.package_register_get()
+for package_name in package_list:
+# Get the details of a package.
+    (url, mime_type, html) = scrape.fetchURL(scrape.docsdb,
+        "https://data.qld.gov.au/dataset/"+package_name , "data", "qld", False)
+    hash = scrape.mkhash(scrape.canonurl(url))
+    print hash
+    doc = scrape.docsdb.get(hash)
+    if "metadata" not in doc.keys() or True:
+        ckan.package_entity_get(package_name)
+        package_entity = ckan.last_message
+        doc['type'] = "dataset"
+        doc['metadata'] = package_entity
+        print package_entity
+        scrape.docsdb.save(doc)
+