From: Maxious <maxious@lambdacomplex.org>
Date: Wed, 09 Oct 2013 12:10:14 +0000
Subject: fix that darn CASA scraper
X-Git-Url: http://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=9fb69fa7fa874357953c98c7fbdb5ff6c2595883
---
fix that darn CASA scraper


Former-commit-id: 288d5ab60033e36608bf898869eecdf64180ba59
---


--- a/admin/logo.svg
+++ b/admin/logo.svg
@@ -1,34 +1,34 @@
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="100px"
-	 height="100px" viewBox="0 -25.635 100 100" enable-background="new 0 -25.635 100 100" xml:space="preserve">
-<g id="docs">
-	<path fill="#C2A385" d="M86.108-9.909l5.229,9.952c0,0-1.832,0.083-5.297,1.95c-2.312,1.249-6.468,6.246-6.468,6.246L71.827-2.909
-		c0,0,4.201-3.996,6.513-5.242C81.805-10.022,86.108-9.909,86.108-9.909"/>
-	<path fill="#C2A385" d="M65.604,20.731l-3.152-9.868c0,0-5.441,3.56-8.017,4.074c-1.008,0.202-1.93,0.335-2.749,0.425
-		L65.604,20.731z"/>
-	<path fill="#C2A385" d="M72.326,23.321c0.268-0.226,0.537-0.44,0.804-0.616c3.104-2.054,6.139-3.685,6.268-3.755l1.882-1.005
-		l1.369,1.634l2.864,3.417l3.198-4.334L76.68,9.783l-8.74,11.847L72.326,23.321z"/>
-	<path fill="#C2A385" d="M39.918,10.823l4.825,1.86l3.33,0.212c0.04,0.001,0.269,0.015,0.652,0.015c0.91,0,2.798-0.072,5.196-0.551
-		c1.427-0.284,5.007-2.332,7.092-3.695l2.889-1.888l1.05,3.285l2.496,7.812l5.889-7.985l-4.625,0.163l1.348-6.225L55.133,0.593
-		l-2.095,9.667c-0.531-2.599-1.841-5.727-1.841-5.727L37.709,6.055c0,0,0.885,2.206,1.586,4.529L39.918,10.823z"/>
-	<path fill="#C2A385" d="M91.233,45.562c-1.102-0.691-2.323-1.142-3.415-1.433l-3.779,9.804c1.932,1.246,5.197,5.738,5.197,5.738
-		l7.336-9.206C96.572,50.466,93.162,46.771,91.233,45.562z"/>
-	<path fill="#C2A385" d="M93.192,32.166l-3.656,1.224c-0.019,0.007-1.779,0.613-4.117,2.069l2.817,4.868l0.626,1.08
-		c3.306-0.562,7.727-1.922,7.727-1.922l-2.332-15.261c0,0-2.934,1.277-5.852,2.221l2.318,2.765L93.192,32.166z"/>
-	<path fill="#C2A385" d="M79.272,25.999l0.864,0.334l0.46,0.801l3.503,6.05c2.646-1.636,4.611-2.287,4.611-2.287l-8.075-9.632
-		c0,0-2.584,1.391-5.376,3.188L79.272,25.999z"/>
-</g>
-<g id="trunk">
-	<circle fill="#C00000" cx="66.019" cy="52.945" r="7.877"/>
-	<circle fill="#C00000" cx="22.693" cy="52.945" r="7.877"/>
-	<path fill="#C00000" d="M22.693,42.441c1.915,0,3.705,0.522,5.251,1.421V28.001H12.191L3,37.192v14.439h9.281
-		C12.931,46.459,17.347,42.441,22.693,42.441z"/>
-	<path fill="#C00000" d="M55.925,50.075l-9.583-3.695H30.88c1.186,1.476,1.978,3.28,2.225,5.252h22.502
-		C55.674,51.1,55.78,50.58,55.925,50.075z"/>
-	<path fill="#C00000" d="M79.312,28.328L39.961,13.149l-9.384,24.335l26.381,10.174c1.824-3.115,5.198-5.218,9.062-5.218
-		c5.791,0,10.503,4.712,10.503,10.502c0,0.744-0.081,1.471-0.229,2.173l4.713,1.817L86.95,41.52L79.312,28.328z"/>
-</g>
-</svg>
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="100px"
+	 height="100px" viewBox="0 -25.635 100 100" enable-background="new 0 -25.635 100 100" xml:space="preserve">
+<g id="docs">
+	<path fill="#C2A385" d="M86.108-9.909l5.229,9.952c0,0-1.832,0.083-5.297,1.95c-2.312,1.249-6.468,6.246-6.468,6.246L71.827-2.909
+		c0,0,4.201-3.996,6.513-5.242C81.805-10.022,86.108-9.909,86.108-9.909"/>
+	<path fill="#C2A385" d="M65.604,20.731l-3.152-9.868c0,0-5.441,3.56-8.017,4.074c-1.008,0.202-1.93,0.335-2.749,0.425
+		L65.604,20.731z"/>
+	<path fill="#C2A385" d="M72.326,23.321c0.268-0.226,0.537-0.44,0.804-0.616c3.104-2.054,6.139-3.685,6.268-3.755l1.882-1.005
+		l1.369,1.634l2.864,3.417l3.198-4.334L76.68,9.783l-8.74,11.847L72.326,23.321z"/>
+	<path fill="#C2A385" d="M39.918,10.823l4.825,1.86l3.33,0.212c0.04,0.001,0.269,0.015,0.652,0.015c0.91,0,2.798-0.072,5.196-0.551
+		c1.427-0.284,5.007-2.332,7.092-3.695l2.889-1.888l1.05,3.285l2.496,7.812l5.889-7.985l-4.625,0.163l1.348-6.225L55.133,0.593
+		l-2.095,9.667c-0.531-2.599-1.841-5.727-1.841-5.727L37.709,6.055c0,0,0.885,2.206,1.586,4.529L39.918,10.823z"/>
+	<path fill="#C2A385" d="M91.233,45.562c-1.102-0.691-2.323-1.142-3.415-1.433l-3.779,9.804c1.932,1.246,5.197,5.738,5.197,5.738
+		l7.336-9.206C96.572,50.466,93.162,46.771,91.233,45.562z"/>
+	<path fill="#C2A385" d="M93.192,32.166l-3.656,1.224c-0.019,0.007-1.779,0.613-4.117,2.069l2.817,4.868l0.626,1.08
+		c3.306-0.562,7.727-1.922,7.727-1.922l-2.332-15.261c0,0-2.934,1.277-5.852,2.221l2.318,2.765L93.192,32.166z"/>
+	<path fill="#C2A385" d="M79.272,25.999l0.864,0.334l0.46,0.801l3.503,6.05c2.646-1.636,4.611-2.287,4.611-2.287l-8.075-9.632
+		c0,0-2.584,1.391-5.376,3.188L79.272,25.999z"/>
+</g>
+<g id="trunk">
+	<circle fill="#C00000" cx="66.019" cy="52.945" r="7.877"/>
+	<circle fill="#C00000" cx="22.693" cy="52.945" r="7.877"/>
+	<path fill="#C00000" d="M22.693,42.441c1.915,0,3.705,0.522,5.251,1.421V28.001H12.191L3,37.192v14.439h9.281
+		C12.931,46.459,17.347,42.441,22.693,42.441z"/>
+	<path fill="#C00000" d="M55.925,50.075l-9.583-3.695H30.88c1.186,1.476,1.978,3.28,2.225,5.252h22.502
+		C55.674,51.1,55.78,50.58,55.925,50.075z"/>
+	<path fill="#C00000" d="M79.312,28.328L39.961,13.149l-9.384,24.335l26.381,10.174c1.824-3.115,5.198-5.218,9.062-5.218
+		c5.791,0,10.503,4.712,10.503,10.502c0,0.744-0.081,1.471-0.229,2.173l4.713,1.817L86.95,41.52L79.312,28.328z"/>
+</g>
+</svg>
 

--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -8,21 +8,13 @@
 $obj->_id = "_design/" . urlencode("app");
 $obj->language = "javascript";
 $obj->views->all->map = "function(doc) {   emit(doc._id, doc); };";
-$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->reduce = "_count";
 $obj->views->byAgencyID->map = "function(doc) {   emit(doc.agencyID, doc); };";
 $obj->views->byAgencyID->reduce = "_count";
-$obj->views->fieldNames->map = '
-function(doc) {
-for(var propName in doc) {
-     	emit(propName, doc._id);
-	}
-
-}';
-$obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
-    return values.length;
-}';
+$obj->views->fieldNames->map = 'function(doc) { for(var propName in doc) {      	emit(propName, doc._id); 	}}';
+$obj->views->fieldNames->reduce = 'function (key, values, rereduce) {      return values.length; }';
 // allow safe updates (even if slightly slower due to extra: rev-detection check).
 $foidb->save($obj, true);
 

--- a/documents/agency.php
+++ b/documents/agency.php
@@ -19,7 +19,7 @@
     <br>
 <?php
 try {
-    if ($_REQUEST['id']) {
+    if (isset($_REQUEST['id'])) {
         $rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows;
         foreach ($rows as $row) {
             //print_r($rows);
@@ -42,3 +42,4 @@
 echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>";
 include_footer_documents();
 ?>
+

--- a/documents/charts.php
+++ b/documents/charts.php
@@ -16,7 +16,7 @@
     <h4 class="subheader"></h4>
 </div>
 <div id="bydate" style="width:1000px;height:300px;"></div>
-<div id="byagency" style="width:1200px;height:800px;"></div>
+<div id="byagency" style="width:1000px;height:1400px;"></div>
 <script id="source">
     window.onload = function () {
         $(document).ready(function () {

--- a/documents/datagov-export-groups.py
+++ b/documents/datagov-export-groups.py
@@ -10,7 +10,11 @@
 # Instantiate the CKAN client.
 #ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api',    api_key='b47b24cd-591d-40c1-8677-d73101d56d1b')
 api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
-ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api',
+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)
 couch = couchdb.Server('http://127.0.0.1:5984/')
 #couch = couchdb.Server('http://192.168.1.113:5984/')

--- a/documents/datagov-export.py
+++ b/documents/datagov-export.py
@@ -14,6 +14,7 @@
 
 import tempfile
 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:
 	format = "xls"
     if "pdf" in url:
@@ -27,8 +28,12 @@
     if mime_type in ["application/xlsx","application/x-xlsx","application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]:
 	format = "xlsx"
 
-    if content != None:
-	    tf = tempfile.NamedTemporaryFile(delete=False)
+    #put file extensions on for windows users downloading files
+    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)
 	    print tfName
 	    tf.seek(0)
@@ -196,7 +201,7 @@
             pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
                               doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
             print pkg_name
-            if pkg_name != "":
+            if pkg_name != "" :
 
                 #add to or create organization using direct API
                 agency = doc.value['metadata']["Agency"]
@@ -262,7 +267,7 @@
                         'author': creator,
                         'maintainer': creator,
                         '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,
                         'extras': extras,
                         'private': (pkg_name not in goodcsvdata and pkg_name not in goodotherdata)

--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -199,10 +199,21 @@
     def getRows(self, table):
         return table.find_all('tr')
 
+    def getDocHash(self, id,date, url):
+                        if id.string is None:
+			    print "no id, using date as hash"
+                            return scrape.mkhash(
+                                self.remove_control_chars(
+                                    url + (''.join(date.stripped_strings))))
+                        else:
+                            return scrape.mkhash(
+                                self.remove_control_chars(
+                                    url + (''.join(id.stripped_strings))))
+
     def getDate(self, content, entry, doc):
         strdate = ''.join(content.stripped_strings).strip()
         (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
         try:
 		edate = parse(strdate, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
@@ -240,14 +251,7 @@
                          description, notes) = self.getColumns(columns)
                         print self.remove_control_chars(
                             ''.join(id.stripped_strings))
-                        if id.string is None:
-                            dochash = scrape.mkhash(
-                                self.remove_control_chars(
-                                    url + (''.join(date.stripped_strings))))
-                        else:
-                            dochash = scrape.mkhash(
-                                self.remove_control_chars(
-                                    url + (''.join(id.stripped_strings))))
+                        dochash = self.getDocHash(id,date,url)
                         doc = foidocsdb.get(dochash)
 
                         if doc is None:

--- a/documents/robots.txt
+++ b/documents/robots.txt
@@ -3,4 +3,5 @@
 
 User-agent: *
 Disallow: /admin/
+Disallow: /viewDocument.php
 Sitemap: http://disclosurelo.gs/sitemap.xml.php

--- a/documents/runScrapers.sh
+++ b/documents/runScrapers.sh
@@ -1,7 +1,9 @@
+#!/bin/bash
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+echo $DIR
 cd $DIR
 echo "" > /tmp/disclosr-error
-for f in scrapers/*.py; do
+for f in $DIR/scrapers/*.py; do
 	echo "Processing $f file..";
 	md5=`md5sum /tmp/disclosr-error`
 	python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error;

--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -197,7 +197,7 @@
                 links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-"))
                 linkurls = set([])
                 for link in links:
-                    if link.has_key("href"):
+                    if link.has_attr("href"):
                         if link['href'].startswith("http"):
                             # lets not do external links for now
                             # linkurls.add(link['href'])

--- a/documents/scrapers/0e46f8bd1414b1fdd4f0543d54a97500.py
+++ b/documents/scrapers/0e46f8bd1414b1fdd4f0543d54a97500.py
@@ -7,7 +7,7 @@
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
         def getTable(self,soup):
-                return soup.find(id = "maincontentcontainer").table
+               return soup.find(class_ = "contentcontainer").table
         def getColumnCount(self):
                 return 5
         def getColumns(self,columns):

--- a/documents/scrapers/1803322b27286950cab0c543168b5f21.py
+++ b/documents/scrapers/1803322b27286950cab0c543168b5f21.py
@@ -16,7 +16,7 @@
         links = []
         description = ""
         for atag in entry.find_all('a'):
-            if atag.has_key('href'):
+            if atag.has_attr('href'):
                 link = scrape.fullurl(self.getURL(), atag['href'])
                 (url, mime_type, htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                 if htcontent != None:
@@ -25,7 +25,7 @@
                         row  = soup.find(id="content_div_148050")
                         description = ''.join(row.stripped_strings)
                         for atag in row.find_all("a"):
-                                    if atag.has_key('href'):
+                                    if atag.has_attr('href'):
                                         links.append(scrape.fullurl(link, atag['href']))
 
         if links != []:

--- a/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py
+++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py
@@ -11,7 +11,7 @@
                 links = []
                 description = ""
 		for atag in entry.find_all('a'):
-			if atag.has_key('href'):
+			if atag.has_attr('href'):
 				link = scrape.fullurl(self.getURL(),atag['href'])			
                                 (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                                 if htcontent != None:
@@ -26,7 +26,7 @@
                                                                 for text in row.stripped_strings:
                                                                     description = description + text + "\n"
                                                      		for atag in row.find_all("a"):
-                                                                	if atag.has_key('href'):
+                                                                	if atag.has_attr('href'):
                                                                         	links.append(scrape.fullurl(link,atag['href']))
 
 		if links != []:

--- a/documents/scrapers/53d2884f8afd026096a27bd5051ec50e.py
+++ b/documents/scrapers/53d2884f8afd026096a27bd5051ec50e.py
@@ -16,7 +16,7 @@
 		link = None
                 links = []
 		for atag in entry.find_all('a'):
-			if atag.has_key('href'):
+			if atag.has_attr('href'):
 				link = scrape.fullurl(self.getURL(),atag['href'])			
                                 (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                                 if htcontent != None:
@@ -24,7 +24,7 @@
                                         # http://www.crummy.com/software/BeautifulSoup/documentation.html
                                                 soup = BeautifulSoup(htcontent)
                                                 for atag in soup.find(class_ = "article-content").find_all('a'):
-	                                               	if atag.has_key('href'):
+	                                               	if atag.has_attr('href'):
         	                                              	links.append(scrape.fullurl(link,atag['href']))
 
 		if links != []:

--- a/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py
+++ b/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py
@@ -6,6 +6,11 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+        def getDocHash(self, id,date, url):
+		''' url changes on ever request so ignore for hash '''
+		return scrape.mkhash(
+                                self.remove_control_chars(
+                                    ''.join(id.stripped_strings)))
         def getColumnCount(self):
                 return 4
         def getColumns(self,columns):

--- a/documents/scrapers/69d59284ef0ccd2677394d82d3292abc.py
+++ b/documents/scrapers/69d59284ef0ccd2677394d82d3292abc.py
@@ -6,8 +6,6 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
-        def getTable(self,soup):
-                return soup.find(id = "centercontent").table       
         def getColumnCount(self):
                 return 5
         def getColumns(self,columns):

--- a/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py
+++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py
@@ -11,7 +11,7 @@
                 links = []
                 description = ""
 		for atag in entry.find_all('a'):
-			if atag.has_key('href'):
+			if atag.has_attr('href'):
 				link = scrape.fullurl(self.getURL(),atag['href'])			
                                 (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                                 if htcontent != None:
@@ -22,7 +22,7 @@
                                                     description = description + text.encode('ascii', 'ignore')
 
                                                 for atag in soup.find(id="SortingTable").find_all("a"):
-                                                      	if atag.has_key('href'):
+                                                      	if atag.has_attr('href'):
                                                               	links.append(scrape.fullurl(link,atag['href']))
 
 		if links != []:
@@ -43,7 +43,7 @@
                 links = []
                 description = ""
 		for atag in entry.find_all('a'):
-			if atag.has_key('href'):
+			if atag.has_attr('href'):
 				link = scrape.fullurl(self.getURL(),atag['href'])			
                                 (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                                 if htcontent != None:
@@ -53,7 +53,7 @@
                                                 for text in soup.find(id="content-item").stripped_strings:
                                                     description = description + text + " \n"
                                                 for atag in soup.find(id="content-item").find_all("a"):
-                                                    if atag.has_key('href'):
+                                                    if atag.has_attr('href'):
                                                         links.append(scrape.fullurl(link,atag['href']))
 		if links != []:
                  	doc.update({'links': links})

--- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
+++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
@@ -17,7 +17,7 @@
 				dldivs = soup.find('div',class_="download")
 				if dldivs != None:
                              		for atag in dldivs.find_all("a"):
-                                		if atag.has_key('href'):
+                                		if atag.has_attr('href'):
                                         		links.append(scrape.fullurl(url,atag['href']))
 				nodldivs = soup.find('div',class_="incompleteNotification")
 				if nodldivs != None and nodldivs.stripped_strings != None:

--- a/documents/scrapers/d1296c366287f7a9faedf235c7e6df01.py
+++ b/documents/scrapers/d1296c366287f7a9faedf235c7e6df01.py
@@ -6,8 +6,6 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
-        def getTable(self,soup):
-                return soup.find(id="main").table       
         def getColumnCount(self):
                 return 7
         def getColumns(self,columns):

--- a/documents/scrapers/f5ce2d1651739704634eb8ca4b2b46d3.py
+++ b/documents/scrapers/f5ce2d1651739704634eb8ca4b2b46d3.py
@@ -7,12 +7,12 @@
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
         def getTable(self,soup):
-                return soup.find(id = "ctl00_PlaceHolderMain_PublishingPageContent__ControlWrapper_RichHtmlField").table       
+                return soup.find(id = "block-system-main").table       
         def getColumnCount(self):
-                return 7
+                return 2
         def getColumns(self,columns):
-                (id, date, title, description,link,deldate, notes) = columns
-                return (id, date, title, description, notes)
+                (date, title) = columns
+                return (date, date, title, title, None)
 
 if __name__ == '__main__':
     print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)

--- a/documents/sitemap.xml.php
+++ b/documents/sitemap.xml.php
@@ -1,30 +1,48 @@
 <?php
 
 include ('../include/common.inc.php');
-$last_updated = date('Y-m-d', @filemtime('cbrfeed.zip'));
 header("Content-Type: text/xml");
 echo "<?xml version='1.0' encoding='UTF-8'?>";
 echo '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' . "\n";
 echo " <url><loc>" . local_url() . "index.php</loc><priority>1.0</priority></url>\n";
 foreach (scandir("./") as $file) {
-    if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php")
+    if (strpos($file, ".php") !== false && ($file != "index.php" && $file != "sitemap.xml.php"&& $file != "viewDocument.php")) {
         echo " <url><loc>" . local_url() . "$file</loc><priority>0.6</priority></url>\n";
+	}
 }
 $agenciesdb = $server->get_db('disclosr-agencies');
+$foidocsdb = $server->get_db('disclosr-foidocuments');
 try {
     $rows = $agenciesdb->get_view("app", "byCanonicalName")->rows;
     foreach ($rows as $row) {
         echo '<url><loc>' . local_url() . 'agency.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n";
     }
+	unset($rows);
+	$rows = null;
 } catch (SetteeRestClientException $e) {
     setteErrorHandler($e);
 }
-$foidocsdb = $server->get_db('disclosr-foidocuments');
+
+foreach (range(0, 8) as $number) {
 try {
-    $rows = $foidocsdb->get_view("app", "all")->rows;
+    $rows = $foidocsdb->get_view("app", "all", Array($number,$number+1))->rows;
     foreach ($rows as $row) {
         echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n";
     }
+	unset($rows);
+	$rows = null;
+} catch (SetteeRestClientException $e) {
+    setteErrorHandler($e);
+}
+}
+
+try {
+    $rows = $foidocsdb->get_view("app", "all", Array('9','fffffffff'))->rows;
+    foreach ($rows as $row) {
+        echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n";
+    }
+	unset($rows);
+	$rows = null;
 } catch (SetteeRestClientException $e) {
     setteErrorHandler($e);
 }

--- /dev/null
+++ b/exportAgencies.csv.php
@@ -1,1 +1,88 @@
+<?php
+// use https://github.com/okfn/publicbodies/blob/master/data/nz.csv format
+include_once("include/common.inc.php");
 
+setlocale(LC_CTYPE, 'C');
+
+$headers = Array("title","abbr","key","category","parent","parent_key","description","url","jurisdiction","jurisdiction_code","source","source_url","address","contact","email","tags","created_at","updated_at");
+
+$db = $server->get_db('disclosr-agencies');
+
+
+$foiEmail = Array();
+try {
+    $rows = $db->get_view("app", "foiEmails", null, true)->rows;
+    //print_r($rows);
+    foreach ($rows as $row) {
+        $foiEmail[$row->key] = $row->value;
+    }
+} catch (SetteeRestClientException $e) {
+    setteErrorHandler($e);
+    die();
+}
+
+$fp = fopen('php://output', 'w');
+if ($fp && $db) {
+    header('Content-Type: text/csv; charset=utf-8');
+    header('Content-Disposition: attachment; filename="export.' . date("c") . '.csv"');
+    header('Pragma: no-cache');
+    header('Expires: 0');
+    fputcsv($fp, $headers);
+    try {
+        $agencies = $db->get_view("app", "byCanonicalName", null, true)->rows;
+        //print_r($rows);
+        foreach ($agencies as $agency) {
+            // print_r($agency);
+
+            if (isset($agency->value->foiEmail) && $agency->value->foiEmail != "null" && !isset($agency->value->status)) {
+                $row = Array();
+                $row["title"] = trim($agency->value->name);
+                $row["abbr"] = (isset($agency->value->shortName) ? $agency->value->shortName : "");
+                $row["key"] = (isset($agency->value->shortName) ? "au/".strtolower($agency->value->shortName) : "");
+                $row["category"] ="";
+                 $row["parent"] ="";
+                 $row["parentkey"] ="";
+                $row["description"] = (isset($agency->value->description) ? $agency->value->description : "");
+                $row["url"] = (isset($agency->value->website) ? $agency->value->website : "");
+                $row["jurisdiction"] = "Australia";
+                $row["jurisdiction_code"] = "au";
+
+                 $row["source"] ="";
+                 $row["source_url"] ="";
+                 $row["address"] ="";
+                 $row["contact"] ="";
+
+                $row["email"] = (isset($agency->value->foiEmail) ? $agency->value->foiEmail : "");
+                 $row["tags"] ="";
+                 $row["created_at"] ="";
+                 $row["updated_at"] ="";
+
+
+                $otherBodies = Array();
+                if (isset($agency->value->foiBodies)) {
+                    $otherBodies = array_merge($otherBodies, $agency->value->foiBodies);
+                }
+                if (isset($agency->value->positions)) {
+                    $positions = Array();
+                    foreach ($agency->value->positions as $position) {
+                        $positions[] = "Office of the ".$position;
+                    }
+                    $otherBodies = array_merge($otherBodies, $positions);
+                }
+                sort($otherBodies);
+                if (count($otherBodies) > 0) {
+                    $row["description"] .= "<br/> This department also responds to requests for information held by " . implode(", ", $otherBodies);
+                }
+
+
+                fputcsv($fp, array_values($row));
+            }
+        }
+    } catch (SetteeRestClientException $e) {
+        setteErrorHandler($e);
+    }
+
+    die;
+}
+?>
+

--- a/getAgency.php
+++ b/getAgency.php
@@ -188,7 +188,7 @@
           </div><!--/.well -->
         </div><!--/span-->
         <div class="span9">';
-    echo '<div itemscope itemtype="http://schema.org/GovernmentOrganization" typeof="schema:GovernmentOrganization" about="#' . $row['_id'] . '">';
+    echo '<div itemscope itemtype="http://schema.org/GovernmentOrganization" typeof="schema:GovernmentOrganization org:Organization" about="#' . $row['_id'] . '">';
     echo '<div class="hero-unit">
             <h1 itemprop="name">' . $row['name'] . '</h1>';
     if (isset($row['description'])) {

--- a/graph.php
+++ b/graph.php
@@ -9,13 +9,13 @@
 function add_node($id, $label, $parent="") {
     global $format;
     if ($format == "html") {
-       // echo "nodes[\"$id\"] = graph.newNode({label: \"$label\"});" . PHP_EOL;
+      //  echo "nodes[\"$id\"] = graph.newNode({label: \"$label\"});" . PHP_EOL;
     }
      if ($format == "dot" && $label != "") {
-         echo "$id [label=\"$label\"];". PHP_EOL;
+         echo "\"$id\" [label=\"$label\", shape=plaintext];". PHP_EOL;
      }
       if ($format == "gexf") {
-          echo "<node id='$id' label=\"".htmlentities($label,ENT_XML1)."\" ".($parent != ""? "pid='$parent'><viz:size value='1'/>":"><viz:size value='2'/>")
+          echo "<node id='$id' label=\"".htmlentities($label)."\" ".($parent != ""? "pid='$parent'><viz:size value='1'/>":"><viz:size value='2'/>")
               ."<viz:color b='".rand(0,255)."' g='".rand(0,255)."' r='".rand(0,255)."'/>"
                   ."</node>". PHP_EOL;
       }
@@ -27,7 +27,7 @@
      //   echo "graph.newEdge(nodes[\"$from\"], nodes['$to'], {color: '$color'});" . PHP_EOL;
     }
     if ($format == "dot") {
-        echo "$from -> $to ".($color != ""? "[color=$color]":"").";". PHP_EOL;
+        echo "\"$from\" -> \"$to\" ".($color != ""? "[color=$color]":"").";". PHP_EOL;
     }
      if ($format == "gexf") {
           echo "<edge id='$from$to' source='$from' target='$to' />". PHP_EOL;
@@ -55,7 +55,7 @@
     $rows = $db->get_view("app", "byCanonicalName", null, true)->rows;
 //print_r($rows);
     foreach ($rows as $row) {
-        add_node($row->id, $row->key);
+        add_node($row->id, $row->value->name);
     }
 } catch (SetteeRestClientException $e) {
     setteErrorHandler($e);

--- a/include/common.inc.php
+++ b/include/common.inc.php
@@ -10,6 +10,7 @@
         || strstr($_SERVER['PHP_SELF'], "documents/")
 	|| $_SERVER['SERVER_NAME'] == "disclosurelo.gs"
 	|| $_SERVER['SERVER_NAME'] == "www.disclosurelo.gs"
+	|| $_SERVER['SERVER_NAME'] == "direct.disclosurelo.gs"
         )
     $basePath = "../";
 

--- a/include/template.inc.php
+++ b/include/template.inc.php
@@ -44,7 +44,7 @@
             <![endif]-->
 
         </head>
-        <body xmlns:schema="http://schema.org/"  xmlns:foaf="http://xmlns.com/foaf/0.1/">
+        <body xmlns:schema="http://schema.org/"  xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:org="http://www.w3.org/ns/org#" xmlns:skos="http://www.w3.org/2004/02/skos/core#">
 <div class="navbar navbar-inverse navbar-fixed-top">
                 <div class="navbar-inner">
                     <div class="container-fluid">

--- a/js/bubbletree
+++ b/js/bubbletree

--- a/js/flotr2
+++ b/js/flotr2

--- a/js/sigma
+++ b/js/sigma

--- a/lib/amon-php
+++ b/lib/amon-php

--- a/lib/phpquery
+++ b/lib/phpquery

--- a/ranking.php
+++ b/ranking.php
@@ -32,8 +32,12 @@
                 $columnKeys = array_unique(array_merge($columnKeys, array_keys($columns)));
                 //print_r($columnKeys);
                 $score = count($columns);
-                $scores[$score]++;
-                $scoredagencies[] = Array("id"=> $row->key, "website"=> $row->value->website, "name" => $row->value->name, "columns" => $columns, "score" => $score);
+                if (isset($scores[$score])){
+$scores[$score]++;
+} else {
+$scores[$score] =1;
+}
+                $scoredagencies[] = Array("id"=> $row->key, "website"=> (isset($row->value->website)?$row->value->website:""), "name" => $row->value->name, "columns" => $columns, "score" => $score);
             }
         }
 
@@ -74,7 +78,7 @@
                 } else {
                     $href = $value;
                 }
-                if ($href[0] == "@") {
+                if (isset($href[0]) && $href[0] == "@") {
                     $href = str_replace("@","https://twitter.com/",$href);
                 }
                 //$href= urlencode($href);

--- a/robots.txt
+++ b/robots.txt
@@ -3,4 +3,5 @@
 
 User-agent: *
 Disallow: /admin/
+Disallow: /viewDocument.php
 Sitemap: http://orgs.disclosurelo.gs/sitemap.xml.php

--- a/schemas/agency.json.php
+++ b/schemas/agency.json.php
@@ -4,7 +4,7 @@
     "description" => "Representation of government agency and online transparency measures",
     "type" => "object",
     "properties" => Array(
-        "name" => Array("type" => "string", "required" => true, "x-itemprop" => "name", "x-property" => "schema:name foaf:name", "x-title" => "Name", "description" => "Name, most recent and broadest"),
+        "name" => Array("type" => "string", "required" => true, "x-itemprop" => "name", "x-property" => "schema:name foaf:name skos:prefLabel ", "x-title" => "Name", "description" => "Name, most recent and broadest"),
         "shortName" => Array("type" => "string", "required" => false, "x-title" => "Short Name", "description" => "Name shortened, usually to an acronym"),
    "description" => Array("type" => "string", "required" => false, "x-title" => "Description", "description" => "Description of roles and responsiblities of organisation"),
         "foiEmail" => Array("type" => "string", "required" => false, "x-title" => "FOI Contact Email", "x-itemprop" => "email", "description" => "FOI contact email if not foi@"),
@@ -14,15 +14,15 @@
             "items" => Array("type" => "string")),
                 "positions" => Array("type" => "array", "required" => true, "x-title" => "Political Positions", "description" => "Ministers and Parliamentary Secretaries",
             "items" => Array("type" => "string")),
-        "foiBodies" => Array("type" => "array", "required" => true, "x-title" => "FOI Bodies","x-property"=>"schema:members foaf:knows",  "description" => "Organisational units within this agency that are subject to FOI Act but are not autonomous",
+        "foiBodies" => Array("type" => "array", "required" => true, "x-title" => "FOI Bodies","x-property"=>"schema:members foaf:knows org:hasSubOrganization",  "description" => "Organisational units within this agency that are subject to FOI Act but are not autonomous",
             "items" => Array("type" => "string")),
         "legislation" => Array("type" => "array", "required" => true, "x-title" => "Legislation", "description" => "Legislation administered by or created for the establishment of this organisation",
             "items" => Array("type" => "string")),
-        "orgType" => Array("type" => "string", "required" => true, "x-title" => "Organisation Type", "description" => "Org type based on legal formation via FMA/CAC legislation etc."),
-        "parentOrg" => Array("type" => "string", "required" => true, "x-title" => "Parent Organisation", "description" => "Parent organisation, usually a department of state"),
+        "orgType" => Array("type" => "string", "required" => true, "x-title" => "Organisation Type", "x-property" => "org:classification", "description" => "Org type based on legal formation via FMA/CAC legislation etc."),
+        "parentOrg" => Array("type" => "string", "required" => true, "x-title" => "Parent Organisation", "x-property" => "org:subOrganizationOf", "description" => "Parent organisation, usually a department of state"),
         "website" => Array("type" => "string", "required" => true, "x-title" => "Website", "x-itemprop" => "url", "x-property" => "schema:url foaf:homepage", "description" => "Website URL"),
-        "abn" => Array("type" => "string", "required" => true, "x-title" => "Australian Business Number", "description" => "ABN from business register"),
-        "established" => Array("type" => "string", "required" => true, "x-title" => "Date established", "description" => "Date established"),
+        "abn" => Array("type" => "string", "required" => true, "x-title" => "Australian Business Number", "x-property" => "org:identifier", "description" => "ABN from business register"),
+        "established" => Array("type" => "string", "required" => true, "x-title" => "Date established", "x-property" => "schema:foundingDate", "description" => "Date established"),
         "employees" => Array("type" => "string", "required" => true, "x-title" => "2010-2011 employees", "description" => "2010-2011 employees"),
         "contractListURL" => Array("type" => "string", "required" => true,  "x-title" => "Contract Listing", "description" => "Departmental and agency contracts, <a href='http://www.aph.gov.au/senate/pubs/standing_orders/d05.htm'>mandated by the Senate</a>" ),
         "budgetURL" => Array("type" => "string", "required" => true,"x-title" => "Budget", "description" => "Portfolio Budget Statements and Portfolio Additional Estimates Statements"),

--- a/sitemap.xml.php
+++ b/sitemap.xml.php
@@ -7,7 +7,7 @@
 echo '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' . "\n";
 echo " <url><loc>" . local_url() . "index.php</loc><priority>1.0</priority></url>\n";
 foreach (scandir("./") as $file) {
-    if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php")
+    if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php"&& $file != "viewDocument.php")
         echo " <url><loc>" . local_url() . "$file</loc><priority>0.3</priority></url>\n";
 }