fix dept of finance scraper
Former-commit-id: 8111dc99a1087b94bd5e1fae0d1099b4022a9ddf
--- 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);
--- 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
@@ -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/e2a845e55bc9986e6c75c5ad2c508b8d.py
+++ b/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py
@@ -1,16 +1,54 @@
import sys,os
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
import genericScrapers
-#RSS feed not detailed
+import dateutil
+from dateutil.parser import *
+from datetime import *
+import scrape
+from bs4 import BeautifulSoup
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
-#http://www.doughellmann.com/PyMOTW/abc/
-class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
- def getColumns(self,columns):
- (id, date, title, description, notes) = columns
- return (id, date, title, description, notes)
+ def __init__(self):
+ super(ScraperImplementation, self).__init__()
+ def getTable(self, soup):
+ return soup.find(id='content')
+
+ def getDescription(self,content, entry,doc):
+ link = None
+ links = []
+ description = ""
+ for atag in entry.find_all('a'):
+ 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:
+ if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
+ soup = BeautifulSoup(htcontent)
+ row = soup.find(id="foidetails")
+ if row == None:
+ row = soup.find(id="content").table
+ if row == None:
+ row = soup.find(id="content")
+ description = ''.join(row.stripped_strings)
+ for atag in row.find_all("a"):
+ 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 getColumnCount(self):
+ return 3
+
+ def getColumns(s 
