add innovation scrAper
Former-commit-id: 80558a9217d1bcad0766200d0e1d42aa022ff501
--- a/couchdb/settee/src/classes/SetteeDatabase.class.php
+++ b/couchdb/settee/src/classes/SetteeDatabase.class.php
@@ -251,7 +251,7 @@
*
* @return void
*/
- function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false) {
+ function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false, $reduce=null) {
$id = "_design/" . urlencode($design_doc);
$view_name = urlencode($view_name);
$id .= "/_view/$view_name";
@@ -269,6 +269,13 @@
if ($descending) {
$data .= "&descending=true";
}
+ if ($reduce != null) {
+ if ($reduce == true) {
+ $data .= "&reduce=true";
+ } else {
+ $data .= "&reduce=false";
+ }
+ }
if ($limit) {
$data .= "&limit=".$limit;
}
@@ -281,9 +288,11 @@
}
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+
$full_uri = str_replace("%253Fgroup%253D","?group=",$full_uri);
$full_uri = str_replace("%253Flimit%253D","?limit=",$full_uri);
$ret = $this->rest_client->http_get($full_uri, $data);
+ //$ret['decoded'] = str_replace("?k","&k",$ret['decoded']);
return $ret['decoded'];
}
--- /dev/null
+++ b/documents/agency.php
@@ -1,1 +1,41 @@
+<?php
+include('template.inc.php');
+include_once('../include/common.inc.php');
+$agenciesdb = $server->get_db('disclosr-agencies');
+$idtoname = Array();
+foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
+ $idtoname[$row->id] = trim($row->value->name);
+}
+$foidocsdb = $server->get_db('disclosr-foidocuments');
+
+include_header_documents((isset($_REQUEST['id']) ? $idtoname[$_REQUEST['id']] : 'Entries by Agency'));
+$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99');
+?>
+<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div>
+<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br>
+<?php
+try {
+ if ($_REQUEST['id']) {
+ $rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows;
+ foreach ($rows as $row) {
+ //print_r($rows);
+ echo displayLogEntry($row, $idtoname);
+ if (!isset($startkey))
+ $startkey = $row->key;
+ $endkey = $row->key;
+ }
+ } else {
+ $rows = $foidocsdb->get_view("app", "byAgencyID?group=true", null, false, false, true)->rows;
+ if ($rows) {
+ foreach ($rows as $row) {
+ echo '<a href="agency.php?id=' . $row->key . '">' . $idtoname[$row->key] . " (" . $row->value . " records)</a> <br>\n";
+ }
+ }
+ }
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+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
@@ -27,7 +27,7 @@
<?php
try {
- $rows = $foidocsdb->get_view("app", "byDateMonthYear?group=true")->rows;
+ $rows = $foidocsdb->get_view("app", "byDateMonthYear?group=true",null, false,false,true)->rows;
$dataValues = Array();
@@ -110,7 +110,7 @@
}
<?php
try {
- $rows = $foidocsdb->get_view("app", "byAgencyID?group=true")->rows;
+ $rows = $foidocsdb->get_view("app", "byAgencyID?group=true",null, false,false,true)->rows;
$dataValues = Array();
--- /dev/null
+++ b/documents/date.php
@@ -1,1 +1,34 @@
+<?php
+include('template.inc.php');
+include_header_documents("Entries by Date");
+include_once('../include/common.inc.php');
+$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99');
+?>
+<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div>
+<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br>
+<?php
+/*$agenciesdb = $server->get_db('disclosr-agencies');
+
+$idtoname = Array();
+foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
+ $idtoname[$row->id] = trim($row->value->name);
+}
+$foidocsdb = $server->get_db('disclosr-foidocuments');
+try {
+ $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20)->rows;
+ if ($rows) {
+ foreach ($rows as $key => $row) {
+ echo displayLogEntry($row, $idtoname);
+ if (!isset($startkey)) $startkey = $row->key;
+ $endkey = $row->key;
+ }
+ }
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+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/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -13,6 +13,8 @@
from datetime import *
import codecs
+import difflib
+
from StringIO import StringIO
from pdfminer.pdfparser import PDFDocument, PDFParser
@@ -49,6 +51,31 @@
""" do the scraping """
return
+class GenericHTMLDisclogScraper(GenericDisclogScraper):
+
+ def doScrape(self):
+ foidocsdb = scrape.couch['disclosr-foidocuments']
+ (url, mime_type, rcontent) = scrape.fetchURL(scrape.docsdb,
+ self.getURL(), "foidocuments", self.getAgencyID())
+ content = rcontent.read()
+ dochash = scrape.mkhash(content)
+ doc = foidocsdb.get(dochash)
+ if doc is None:
+ 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"
+ last_attach = scrape.getLastAttachment(scrape.docsdb, self.getURL())
+ if last_attach != None:
+ html_diff = difflib.HtmlDiff()
+ description = description + "\nChanges: "
+ description = description + html_diff.make_table(last_attach.read().split('\n'),
+ content.split('\n'))
+ edate = date.today().strftime("%Y-%m-%d")
+ doc = {'_id': dochash, 'agencyID': self.getAgencyID()
+ , 'url': self.getURL(), 'docID': dochash,
+ "date": edate, "title": "Disclosure Log Updated", "description": description}
+ foidocsdb.save(doc)
+ else:
+ print "already saved"
class GenericPDFDisclogScraper(GenericDisclogScraper):
--- a/documents/rss.xml.php
+++ b/documents/rss.xml.php
@@ -8,21 +8,28 @@
//Creating an instance of FeedWriter class.
$TestFeed = new RSS2FeedWriter();
//Setting the channel elements
-//Use wrapper functions for common channelelements
-$TestFeed->setTitle('disclosurelo.gs Newest Entries - All');
-$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php');
-$TestFeed->setDescription('disclosurelo.gs Newest Entries - All Agencies');
-$TestFeed->setChannelElement('language', 'en-us');
-$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
-
-//Retriving informations from database
+////Retriving informations from database
$idtoname = Array();
$agenciesdb = $server->get_db('disclosr-agencies');
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
$idtoname[$row->id] = trim($row->value->name);
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
-$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows;
+if (isset($_REQUEST['id'])) {
+ $rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows;
+ $title = $idtoname[$_REQUEST['id']];
+} else {
+ $rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows;
+ $title = 'All Agencies';
+}
+//Use wrapper functions for common channelelements
+$TestFeed->setTitle('disclosurelo.gs Newest Entries - '.$title);
+$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'.(isset($_REQUEST['id'])? '?id='.$_REQUEST['id'] : ''));
+$TestFeed->setDescription('disclosurelo.gs Newest Entries - '.$title);
+$TestFeed->setChannelElement('language', 'en-us');
+$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
+
+
//print_r($rows);
foreach ($rows as $row) {
//Create an empty FeedItem
--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -76,6 +76,16 @@
addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
addinfourl.code = code
return addinfourl
+
+def getLastAttachment(docsdb,url):
+ hash = mkhash(url)
+ doc = docsdb.get(hash)
+ if doc != None:
+ last_attachment_fname = doc["_attachments"].keys()[-1]
+ last_attachment = docsdb.get_attachment(doc,last_attachment_fname)
+ return last_attachment
+ else:
+ return None
def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True):
url = canonurl(url)
--- a/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py
+++ b/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py
@@ -12,8 +12,8 @@
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation,
- genericScrapers.GenericOAICDisclogScraper)
+ genericScrapers.GenericPDFDisclogScraper)
print 'Instance:', isinstance(ScraperImplementation(),
- genericScrapers.GenericOAICDisclogScraper)
+ genericScrapers.GenericPDFDisclogScraper)
ScraperImplementation().doScrape()
--- /dev/null
+++ b/documents/scrapers/0ae822d1a748e60d90f0b79b97d5a3e5.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/31685505438d393f45a90f442b8fa27f.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericPDFDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericPDFDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericPDFDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/31685505438d393f45a90f442b8fa27f.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-pdf
--- /dev/null
+++ b/documents/scrapers/3e2f110af49d62833a835bd257771ffb.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/3e2f110af49d62833a835bd257771ffb.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-no disclog
--- /dev/null
+++ b/documents/scrapers/41a166419503bb50e410c58be54c102f.py
@@ -1,1 +1,27 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+from datetime import date
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id= "ctl00_MSO_ContentDiv").table
+
+ def getColumns(self,columns):
+ (id, title, description, notes) = columns
+ return (id, title, title, description, notes)
+ def getDate(self, content, entry, doc):
+ edate = date.today().strftime("%Y-%m-%d")
+ doc.update({'date': edate})
+ return
+ def getColumnCount(self):
+ return 4
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/41a166419503bb50e410c58be54c102f.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-aspx
+
--- /dev/null
+++ b/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-no disclog
--- a/documents/scrapers/50601505ef69483121a6d130bb0515e4.txt
+++ b/documents/scrapers/50601505ef69483121a6d130bb0515e4.txt
@@ -1,1 +1,1 @@
-apsc has ACMA style disclog
+ACMA style
--- /dev/null
+++ b/documents/scrapers/525c3953187da08cd702359b2fc2997f.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/525c3953187da08cd702359b2fc2997f.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-no disclog
--- /dev/null
+++ b/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-no disclog
+
--- /dev/null
+++ b/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-no disclog
--- /dev/null
+++ b/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.txt
+++ /dev/null
@@ -1,2 +1,1 @@
-no disclog
--- /dev/null
+++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py
@@ -1,1 +1,51 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from datetime import date
+from pyquery import PyQuery as pq
+from lxml import etree
+import urllib
+import dateutil
+from dateutil.parser import *
+class ACMADisclogScraper(genericScrapers.GenericDisclogScraper):
+
+ def doScrape(self):
+ foidocsdb = scrape.couch['disclosr-foidocuments']
+ (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
+ self.getURL(), "foidocuments", self.getAgencyID())
+
+ d = pq(content.read())
+ d.make_links_absolute(base_url = self.getURL())
+ for table in d('table').items():
+ title= table('thead').text()
+ print title
+ (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text())
+ links = table('a').map(lambda i, e: pq(e).attr('href'))
+ description = descA+" "+descB
+ edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
+ print edate
+ dochash = scrape.mkhash(self.remove_control_chars(title))
+ doc = foidocsdb.get(dochash)
+ if doc is None:
+ print "saving " + dochash
+ edate = date.today().strftime("%Y-%m-%d")
+ doc = {'_id': dochash, 'agencyID': self.getAgencyID()
+ , 'url': self.getURL(), 'docID': dochash,
+ "links": links,
+ "date": edate, "notes": notes, "title": title, "description": description}
+ #print doc
+ foidocsdb.save(doc)
+ else:
+ print "already saved"
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ACMADisclogScraper,
+ genericScrapers.GenericDisclogScraper)
+ print 'Instance:', isinstance(ACMADisclogScraper(),
+ genericScrapers.GenericDisclogScraper)
+ ACMADisclogScraper().doScrape()
+
--- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-acma style
+
--- /dev/null
+++ b/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-no disclog
+
--- /dev/null
+++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.py
@@ -1,1 +1,19 @@
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+
+class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper):
+
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation,
+ genericScrapers.GenericHTMLDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(),
+ genericScrapers.GenericHTMLDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-no disclog
+