more scrapers
Former-commit-id: 96bfae466ef6496e0bc9469d556f599c5e0e3d92
--- a/.gitmodules
+++ b/.gitmodules
@@ -31,4 +31,7 @@
[submodule "documents/lib/parsedatetime"]
path = documents/lib/parsedatetime
url = git://github.com/bear/parsedatetime.git
+[submodule "lib/FeedWriter"]
+ path = lib/FeedWriter
+ url = https://github.com/mibe/FeedWriter
--- /dev/null
+++ b/documents/.gitignore
@@ -1,1 +1,2 @@
+*.pyc
--- a/documents/disclogsList.php
+++ b/documents/disclogsList.php
@@ -35,18 +35,18 @@
echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">'
. 'view local copy</a>)</small>';
} else {
- echo "<font color='red'>✘</font>";
+ echo "<font color='red'><abbr title='No'>✘</abbr></font>";
}
echo "</td>\n<td>";
if (isset($row->value->FOIDocumentsURL)) {
if (file_exists("./scrapers/" . $row->id . '.py')) {
- echo "<font color='green'>✔</font>";
+ echo "<font color='green'><abbr title='Yes'>✔</abbr></font>";
$green++;
} else if (file_exists("./scrapers/" . $row->id . '.txt')) {
- echo "<font color='orange'><b>▬</b></font>";
+ echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>";
$orange++;
} else {
- echo "<font color='red'>✘</font>";
+ echo "<font color='red'><abbr title='No'>✘</abbr></font>";
$red++;
}
}
@@ -57,7 +57,8 @@
setteErrorHandler($e);
}
echo "</table>";
-echo $agencies." agencies ".(($disclogs/$agencies)*100)."% with disclosure logs, ".(($green/$disclogs)*100)."% with scrapers ".(($red/$disclogs)*100)."% without scrapers ".(($orange/$disclogs)*100)."% WIP scrapers ";
+echo $agencies." agencies, ".round(($disclogs/$agencies)*100)."% with disclosure logs; "
+.round(($green/$disclogs)*100)."% logs with scrapers ".round(($red/$disclogs)*100)."% logs without scrapers ".round(($orange/$disclogs)*100)."% logs Work-In-Progress scrapers ";
include_footer_documents();
?>
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -92,7 +92,8 @@
return table.find_all('tr')
def getDate(self, content, entry, doc):
date = ''.join(content.stripped_strings).strip()
- date = str.replace("Octber","October",date)
+ date = date.replace("Octber","October")
+ print date
edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
print edate
doc.update({'date': edate})
--- a/documents/index.php
+++ b/documents/index.php
@@ -20,7 +20,7 @@
if ($rows) {
foreach ($rows as $row) {
-displayLogEntry($row,$idtoname);
+echo displayLogEntry($row,$idtoname);
}
}
} catch (SetteeRestClientException $e) {
--- a/documents/robots.txt
+++ b/documents/robots.txt
@@ -2,4 +2,5 @@
# http://code.google.com/web/controlcrawlindex/
User-agent: *
-
+Disallow: /admin/
+Sitemap: http://disclosurelo.gs/sitemap.xml.php
--- a/documents/rss.xml.php
+++ b/documents/rss.xml.php
@@ -3,28 +3,38 @@
// Agency X updated Y, new files, diff of plain text/link text,
// feed for just one agency or all
// This is a minimum example of using the Universal Feed Generator Class
-include("lib/FeedWriter.php");
+include("../lib/FeedWriter/FeedTypes.php");
+include_once('../include/common.inc.php');
//Creating an instance of FeedWriter class.
-$TestFeed = new FeedWriter(RSS2);
+$TestFeed = new RSS2FeedWriter();
//Setting the channel elements
//Use wrapper functions for common channelelements
$TestFeed->setTitle('Last Modified - All');
-$TestFeed->setLink('http://disclosr.lambdacomplex.org/rss.xml.php');
+$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php');
$TestFeed->setDescription('This is test of creating a RSS 2.0 feed Universal Feed Writer');
+ $TestFeed->setChannelElement('language', 'en-us');
+ $TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
//Retriving informations from database
-$rows = $db->get_view("app", "byLastModified")->rows;
+$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 = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00'), true)->rows;
//print_r($rows);
foreach ($rows as $row) {
//Create an empty FeedItem
$newItem = $TestFeed->createNewItem();
//Add elements to the feed item
- $newItem->setTitle($row['name']);
- $newItem->setLink($row['id']);
- $newItem->setDate(date("c", $row['metadata']['lastModified']));
- $newItem->setDescription($row['name']);
+ $newItem->setTitle($row->value->title);
+ $newItem->setLink("view.php?id=".$row->value->docID);
+ $newItem->setDate(date("c", strtotime($row->value->date)));
+ $newItem->setDescription(displayLogEntry($row,$idtoname));
+ $newItem->addElement('guid', $row->value->_id,array('isPermaLink'=>'true'));
//Now add the feed item
$TestFeed->addItem($newItem);
}
//OK. Everything is done. Now genarate the feed.
-$TestFeed->genarateFeed();
+$TestFeed->generateFeed();
?>
--- /dev/null
+++ b/documents/scrapers/00a294de663db69062ca09aede7c0487.txt
@@ -1,1 +1,2 @@
+multipage
--- /dev/null
+++ b/documents/scrapers/1803322b27286950cab0c543168b5f21.txt
@@ -1,1 +1,2 @@
+multipage log
--- /dev/null
+++ b/documents/scrapers/24bd71114d3975ed9a63ad29624c62c9.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "inner_content")
+ def getColumnCount(self):
+ return 2
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (date, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/31685505438d393f45a90f442b8fa27f.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/41a166419503bb50e410c58be54c102f.txt
@@ -1,1 +1,1 @@
-
+aspx
--- /dev/null
+++ b/documents/scrapers/4934000fddd6a5b1094f398798341290.py
@@ -1,1 +1,23 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+import dateutil
+from dateutil.parser import *
+from datetime import *
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ si = ScraperImplementation()
+ si.doScrape()
+
--- /dev/null
+++ b/documents/scrapers/601aedeef4344638d635bdd761e9fdba.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#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 getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (date, title, description,notes) = columns
+ return (title, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/649b053f5e2884906ddc7174c2cd4b38.py
@@ -1,1 +1,28 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+import dateutil
+from dateutil.parser import *
+from datetime import *
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ si = ScraperImplementation()
+ si.doScrape()
+ si.disclogURL = "http://www.fahcsia.gov.au/disclosure-log-2011-12-financial-year"
+ si.doScrape()
+ si.disclogURL = "http://www.fahcsia.gov.au/disclosure-log-2010-11-financial-year"
+ si.doScrape()
+
+
--- /dev/null
+++ b/documents/scrapers/6afdde1d4ff1ad8d8cfe1a8675ea83bd.txt
@@ -1,1 +1,2 @@
+PDF
--- /dev/null
+++ b/documents/scrapers/6cf3870aedeeecfd6394b5c0abed4c55.py
@@ -1,1 +1,23 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+import dateutil
+from dateutil.parser import *
+from datetime import *
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ si = ScraperImplementation()
+ si.doScrape()
+
--- /dev/null
+++ b/documents/scrapers/72a295f10734d64e8185f651fd2b39ea.txt
@@ -1,1 +1,2 @@
+weird div based log with tables of links
--- /dev/null
+++ b/documents/scrapers/75d8f1c605ef9da0c2590264b7aa046b.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "content-middle").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/8796220032faf94501bd366763263685.txt
@@ -1,1 +1,2 @@
+multiple pages
--- /dev/null
+++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.txt
@@ -1,1 +1,49 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getDescription(self,content, entry,doc):
+ link = None
+ links = []
+ description = ""
+ for atag in entry.find_all('a'):
+ if atag.has_key('href'):
+ link = scrape.fullurl(self.getURL(),atag['href'])
+ (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
+ if htcontent != None:
+ if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
+ # http://www.crummy.com/software/BeautifulSoup/documentation.html
+ soup = BeautifulSoup(htcontent)
+ for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'):
+ if row != None:
+ rowtitle = row.find('th').string
+ description = description + "\n" + rowtitle + ": "
+ for text in row.find('td').stripped_strings:
+ description = description + text
+ for atag in row.find_all("a"):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(link,atag['href']))
+
+ if links != []:
+ doc.update({'links': links})
+ if description != "":
+ doc.update({ 'description': description})
+
+ def getColumnCount(self):
+ return 2
+ def getTable(self,soup):
+ return soup.find(class_ = "ms-rteTable-GreyAlternating")
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (title, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+# old site too http://archive.treasury.gov.au/content/foi_publications.asp
+
--- /dev/null
+++ b/documents/scrapers/905a1c409b6afb1de0074b13a5559560.py
@@ -1,1 +1,23 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+import dateutil
+from dateutil.parser import *
+from datetime import *
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ si = ScraperImplementation()
+ si.doScrape()
+
--- /dev/null
+++ b/documents/scrapers/b0a3281ba66efe173c5a33d5ef90ff76.txt
@@ -1,1 +1,2 @@
+multipage immi
--- /dev/null
+++ b/documents/scrapers/b0fb402314e685238537105ee0e70c84.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#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 getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/b7770c4584332cff42bb6abb3326e564.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "ctl00_PlaceHolderMain_Content__ControlWrapper_RichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/e90b1b7cbb83e3eed0b5f849c7e3af79.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "inner_content")
+ def getColumnCount(self):
+ return 2
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (date, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/f5ce2d1651739704634eb8ca4b2b46d3.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "ctl00_PlaceHolderMain_PublishingPageContent__ControlWrapper_RichHtmlField").table
+ def getColumnCount(self):
+ return 7
+ def getColumns(self,columns):
+ (id, date, title, description,link,deldate, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/sitemap.xml.php
@@ -1,1 +1,25 @@
+<?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" && $file != "sitemap.xml.php")
+ echo " <url><loc>" . local_url() . "$file</loc><priority>0.6</priority></url>\n";
+}
+
+$db = $server->get_db('disclosr-foidocuments');
+try {
+ $rows = $db->get_view("app", "all")->rows;
+ foreach ($rows as $row) {
+ echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n";
+ }
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+echo '</urlset>';
+?>
+
--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -130,21 +130,23 @@
}
function displayLogEntry($row, $idtoname) {
- echo "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2> <p>".str_replace("\n","<br>",$row->value->description);
+ $result = "";
+ $result .= "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2> <p>".str_replace("\n","<br>",$row->value->description);
if (isset($row->value->notes)) {
-echo " <br>Note: ".$row->value->notes;
+$result .= " <br>Note: ".$row->value->notes;
}
-echo "</p>";
+$result .= "</p>";
if (isset($row->value->links)){
-echo "<h3>Links/Documents</h3><ul>";
+$result .= "<h3>Links/Documents</h3><ul>";
foreach ($row->value->links as $link) {
- echo "<li><a href='$link'>".$link."</a></li>";
+ $result .= "<li><a href='$link'>".$link."</a></li>";
}
- echo "</ul>";
+ $result .= "</ul>";
}
- echo "<small><A href='".$row->value->url."'>View original source...</a> ID: ".$row->value->docID."</small>";
-echo"</div>";
+ $result .= "<small><A href='".$row->value->url."'>View original source...</a> ID: ".$row->value->docID."</small>";
+$result .= "</div>";
+return $result;
}
--- /dev/null
+++ b/documents/view.php
@@ -1,1 +1,27 @@
+<?php
+include('template.inc.php');
+include_header_documents("");
+include_once('../include/common.inc.php');
+?>
+<?php
+
+
+$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 {
+ $obj = new stdClass();
+ $obj->value = $foidocsdb->get($_REQUEST['id']);
+echo displayLogEntry($obj,$idtoname);
+
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+include_footer_documents();
+?>
+