FOI stats importer fixed
Former-commit-id: 81a6a149848e27565b7a7052d2a7ff4e5aaa9310
--- a/admin/importOAICFOIrequests.php
+++ b/admin/importOAICFOIrequests.php
@@ -17,13 +17,13 @@
if ($row >= 1) {
// print_r($data);
$name = trim($data[2]);
- echo "$name <br>";
+// echo "$name <br>";
if ($data[0] != "TOTALS" && $data[0] != "") {
if (isset($nametoid[$name])) {
$id = $nametoid[$name];
$timePeriod = $data[0] . "-Q" . $data[1];
- echo "$timePeriod <br>";
+// echo "$timePeriod <br>";
unset($data[0]);
unset($data[1]);
unset($data[2]);
@@ -38,10 +38,13 @@
$result = Array("source" => "http://data.gov.au/dataset/freedom-of-information-quarterly-request-and-review-statistical-data-2011-12/");
foreach ($data as $key => $datum) {
if ($datum != 0) {
+// tODO prefix header with "FOI"
+if (isset($stats[$id][$timePeriod][$key])) $datum += $stats[$id][$timePeriod][$key];
$result[trim($headers[$key])] = $datum;
}
}
$stats[$id][$timePeriod] = $result;
+// TODO merge if already exists
//print_r($stats);
} else {
echo "<br>ERROR NAME MISSING FROM ID LIST<br><bR> $row" . PHP_EOL;
@@ -57,21 +60,24 @@
}
fclose($handle);
}
+echo "all stats loaded successfuly";
foreach ($stats as $id => $stat) {
echo $id . "<br>" . PHP_EOL;
- $doc = $db->get($id);
+ $doc = $db->get($id);
echo $doc->name . "<br>" . PHP_EOL;
- print_r($stat);
- die();
+// print_r($stat);
// print_r($doc);
$changed = false;
if (!isset($doc->statistics)) {
$changed = true;
$doc->statistics = Array();
+ } else {
+ $doc->statistics = object_to_array($doc->statistics);
}
foreach ($stat as $timePeriod => $value) {
- if (!isset($doc->statistics->foiRequests->$timePeriod)
- || $doc->statistics->foiRequests->$timePeriod != $value) {
+ if (!isset($doc->statistics["foiRequests"][$timePeriod])
+ || $doc->statistics["foiRequests"][$timePeriod] != $value
+ ) {
$changed = true;
$doc->statistics["foiRequests"][$timePeriod] = $value;
}
@@ -81,6 +87,7 @@
} else {
echo "not changed" . "<br>" . PHP_EOL;
}
+//print_r($doc);die();
}
?>
--- 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>
--- /dev/null
+++ b/admin/massdelete.sh
@@ -1,1 +1,10 @@
+for line in `curl "http://localhost:5984/disclosr-foidocuments/_design/app/_view/byAgencyID?reduce=false&keys=%5B\"5716ce0aacfe98f7d638b7a66b7f1040\"%5D&limit=600" | xargs -L1`; do
+# echo $line
+ id=`echo $line | grep -Po '_id:.*?[^\\\],' | perl -pe 's/_id://; s/^//; s/,$//'`
+ rev=`echo $line | grep -Po 'rev:.*?[^\\\],'| perl -pe 's/rev://; s/^//; s/,$//'`
+ if [ -n "$id" ]; then
+ echo "curl -X DELETE http://localhost:5984/disclosr-foidocuments/$id?rev=$rev"
+ curl -X DELETE http://localhost:5984/disclosr-foidocuments/$id?rev=$rev
+ fi
+done;
--- 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);
@@ -120,15 +112,25 @@
}
}";
$obj->views->getStatistics->map =
-"function(doc) {
- if (doc.statistics) {
- for (var statisticSet in doc.statistics) {
-for (var statisticPeriod in doc.statistics[statisticSet]) {
- emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']);
+"
+function (doc) {
+ if (doc.statistics) {
+ for (var statisticSet in doc.statistics) {
+ for (var statisticPeriod in doc.statistics[statisticSet]) {
+ if (doc.statistics[statisticSet][statisticPeriod]['value']) {
+ emit([statisticSet, statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']);
+ } else {
+ for (var statisticSubSet in doc.statistics[statisticSet][statisticPeriod]) {
+ if (statisticSubSet != 'source' && statisticSubSet != 'value') {
+ emit([statisticSubSet, statisticPeriod], doc.statistics[statisticSet][statisticPeriod][statisticSubSet]);
+ }
+ }
+ }
+ }
+ }
+ }
}
-}
- }
-}";
+";
$obj->views->getStatistics->reduce = '_sum';
// http://stackoverflow.com/questions/646628/javascript-startswith
$obj->views->score->map = 'if(!String.prototype.startsWith){
--- a/documents/about.php
+++ b/documents/about.php
@@ -5,6 +5,7 @@
include_once('../include/common.inc.php');
?>
<h1>About</h1>
+Written and managed by Alex Sadleir (maxious [at] lambdacomplex.org)
<?php
include_footer_documents();
?>
--- a/documents/agency.php
+++ b/documents/agency.php
@@ -19,7 +19,7 @@
<br>
<?php
try {
- if ($_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);
@@ -31,6 +31,12 @@
} else {
$rows = $foidocsdb->get_view("app", "byAgencyID?group=true", null, false, false, true)->rows;
if ($rows) {
+function cmp($a, $b)
+{
+ global $idtoname;
+ return strcmp($idtoname[$a->key], $idtoname[$b->key]);
+}
+usort($rows, "cmp");
foreach ($rows as $row) {
echo '<a href="agency.php?id=' . $row->key . '">' . $idtoname[$row->key] . " (" . $row->value . " records)</a> <br>\n";
}
@@ -42,3 +48,4 @@
echo "<a class='btn btn-large btn-primary' href='?end_key=$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
@@ -5,18 +5,27 @@
$agenciesdb = $server->get_db('disclosr-agencies');
$idtoname = Array();
+$idtofoirequestssuccessful = Array();
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
$idtoname[$row->id] = trim($row->value->name);
+ $foirequestssuccessful = 0;
+if(isset($row->value->statistics->foiRequests)) {
+ foreach ($row->value->statistics->foiRequests as $statperiod) {
+ $statperiod=object_to_array($statperiod);
+ if (isset($statperiod["Requests for other information granted in full"])) $foirequestssuccessful += $statperiod["Requests for other information granted in full"];
+ if (isset($statperiod["Requests for other information granted in part"])) $foirequestssuccessful += $statperiod["Requests for other information granted in part"];
+ }
+}
+ $idtofoirequestssuccessful[$row->id] =$foirequestssuccessful;
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
-
?>
<div class="foundation-header">
<h1><a href="about.php">Charts</a></h1>
<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 () {
@@ -28,7 +37,6 @@
<?php
try {
$rows = $foidocsdb->get_view("app", "byDateMonthYear?group=true",null, false,false,true)->rows;
-
$dataValues = Array();
foreach ($rows as $row) {
@@ -95,6 +103,7 @@
};
var d2 = [];
+ var d3 = [];
var agencylabels = [];
function agencytrackformatter(obj) {
@@ -112,12 +121,17 @@
<?php
try {
$rows = $foidocsdb->get_view("app", "byAgencyID?group=true",null, false,false,true)->rows;
-
+function cmp($a, $b)
+{
+ return $a->value > $b->value;
+}
+usort($rows, "cmp");
$dataValues = Array();
$i = 0;
foreach ($rows as $row) {
echo " d2.push([ $row->value,$i]);" . PHP_EOL;
+ echo " d3.push([ ".$idtofoirequestssuccessful[$row->key].",$i]);" . PHP_EOL;
echo " agencylabels.push(['".str_replace("'","",$idtoname[$row->key])."']);" . PHP_EOL;
$i++;
@@ -154,7 +168,7 @@
autoscaleMargin: 1
},
legend: {
- show: false
+ show: true
}
}
);
--- 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
@@ -198,11 +198,24 @@
def getRows(self, table):
return table.find_all('tr')
+ def findColumns(self, row):
+ return row.find_all('td')
+
+ 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")
@@ -234,20 +247,13 @@
soup = BeautifulSoup(content)
table = self.getTable(soup)
for row in self.getRows(table):
- columns = row.find_all('td')
+ columns = self.findColumns(row)
if len(columns) is self.getColumnCount():
(id, date, title,
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/index.php
+++ b/documents/index.php
@@ -18,6 +18,7 @@
$idtoname[$row->id] = trim($row->value->name);
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
+//print_r($foidocsdb);
try {
$rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20, null, $enddocid)->rows;
if ($rows) {
--- 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/rss.xml.php
+++ b/documents/rss.xml.php
@@ -31,11 +31,12 @@
//print_r($rows);
+$i =0;
foreach ($rows as $row) {
//Create an empty FeedItem
$newItem = $TestFeed->createNewItem();
//Add elements to the feed item
- $newItem->setTitle($row->value->title);
+ $newItem->setTitle(preg_replace('/[\x00-\x1F\x80-\xFF]/', '', $row->value->title));
$newItem->setLink("http://disclosurelo.gs/view.php?id=" . $row->value->_id);
$newItem->setDate(strtotime($row->value->date));
$newItem->setDescription(displayLogEntry($row, $idtoname));
@@ -43,6 +44,8 @@
$newItem->addElement('guid', "http://disclosurelo.gs/view.php?id=" . $row->value->_id, array('isPermaLink' => 'true'));
//Now add the feed item
$TestFeed->addItem($newItem);
+$i++;
+if ($i > 50) break;
}
//OK. Everything is done. Now genarate the feed.
$TestFeed->generateFeed();
--- a/documents/runScrapers.sh
+++ b/documents/runScrapers.sh
@@ -1,7 +1,9 @@
+#!/bin/bash
DIR="$( 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;
@@ -14,6 +16,7 @@
sleep 1;
fi
done
+curl "localhost:5984/disclosr-foidocuments/_design/app/_view/byDate?startkey=\"9999-99-99\"&endkey=\"0000-00-00\"&descending=true&limit=20"
if [ -s /tmp/disclosr-error ] ; then
echo "emailling logs..";
mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /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 != []:
@@ -45,14 +45,5 @@
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
nsi = ScraperImplementation()
- nsi.disclogURL = "http://www.dbcde.gov.au/about_us/freedom_of_information_disclosure_log/foi_list?result_146858_result_page=1"
- nsi.doScrape()
- nsi.disclogURL = "http://www.dbcde.gov.au/about_us/freedom_of_information_disclosure_log/foi_list?result_146858_result_page=2"
- nsi.doScrape()
- nsi.disclogURL = "http://www.dbcde.gov.au/about_us/freedom_of_information_disclosure_log/foi_list?result_146858_result_page=3"
- nsi.doScrape()
- nsi.disclogURL = "http://www.dbcde.gov.au/about_us/freedom_of_information_disclosure_log/foi_list?result_146858_result_page=4"
- nsi.doScrape()
- nsi.disclogURL = "http://www.dbcde.gov.au/about_us/freedom_of_information_disclosure_log/foi_list?result_146858_result_page=5"
nsi.doScrape()
--- a/documents/scrapers/1d404c4934f74feacd00dcb434e7c10a.py
+++ b/documents/scrapers/1d404c4934f74feacd00dcb434e7c10a.py
@@ -6,8 +6,8 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
- #def getTable(self,soup):
- # return soup.find(id = "cphMain_C001_Col01").table
+ def getTable(self,soup):
+ return soup.findAll('table')[1]
def getColumnCount(self):
return 5
def getColumns(self,columns):
--- 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 
