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();
}
?>
--- /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
@@ -112,15 +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
@@ -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";
}
--- a/documents/charts.php
+++ b/documents/charts.php
@@ -5,11 +5,20 @@
$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>
@@ -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/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -198,6 +198,19 @@
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()
@@ -234,21 +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:
- print "no id, using date as hash"
- 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.
$TestFeed->generateFeed();
--- a/documents/runScrapers.sh
+++ b/documents/runScrapers.sh
@@ -1,3 +1,4 @@
+#!/bin/bash
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
echo $DIR
cd $DIR
@@ -15,6 +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.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
if htcontent != None:
@@ -26,20 +26,23 @@
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 != []:
doc.update({'links': links})
if description != "":
doc.update({ 'description': description})
-
+ def getRows(self, table):
+ return table.find_all(class_ = "dl-row");
+ def findColumns(self, table):
+ return table.find_all('div');
def getColumnCount(self):
return 2
def getTable(self,soup):
- return soup.find(class_ = "ms-rteTable-default")
+ return soup.find(class_ = "foi-dl-list")
def getColumns(self,columns):
- (date, title) = columns
+ (title,date) = columns
return (title, date, title, title, None)
if __name__ == '__main__':
--- a/documents/scrapers/41a166419503bb50e410c58be54c102f.py
+++ b/documents/scrapers/41a166419503bb50e410c58be54c102f.py
@@ -8,7 +8,7 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getTable(self,soup):
- return soup.find(id= "ctl00_MSO_ContentDiv").table
+ return soup.find(class_ = "rgMasterTable")
def getColumns(self,columns):
(id, title, description, notes) = columns
--- 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/601aedeef4344638d635bdd761e9fdba.py
+++ b/documents/scrapers/601aedeef4344638d635bdd761e9fdba.py
@@ -6,8 +6,8 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
- #def getTable(self,soup):
- # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getTable(self,soup):
+ return soup.find(id = "main").table
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/8c9421f852c441910bf1d93a57b31d64.py
+++ b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
@@ -5,6 +5,8 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "page_content").table
def getColumns(self,columns):
(id, date, title, description, notes) = columns
return (id, date, title, description, notes)
--- 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/ad033512610d8e36886ab6a795f26561.py
+++ b/documents/scrapers/ad033512610d8e36886ab6a795f26561.py
@@ -6,8 +6,8 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
- def getTable(self,soup):
- return soup.find(id = "_ctl0__ctl0_MainContentPlaceHolder_MainContentPlaceHolder_ContentSpan").findAll("table")[3]
+# def getTable(self,soup):
+# return soup.find(_class = "content").table
def getColumnCount(self):
return 5
def getColumns(self,columns):
--- 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/bf16d4ba0d306ee03e5a1d32aaba3da1.py
+++ b/documents/scrapers/bf16d4ba0d306ee03e5a1d32aaba3da1.py
@@ -7,7 +7,7 @@
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getTable(self,soup):
- return soup.find(summary="This table shows every FOI request to date.")
+ return soup
def getColumnCount(self):
return 5
def getColumns(self,columns):