| import sys,os | import sys |
| import os | |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
| import scrape | import scrape |
| from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
| from time import mktime | from time import mktime |
| import feedparser | import feedparser |
| import abc | import abc |
| import unicodedata, re | import unicodedata |
| import re | |
| import dateutil | import dateutil |
| from dateutil.parser import * | from dateutil.parser import * |
| from datetime import * | from datetime import * |
| import codecs | import codecs |
| from StringIO import StringIO | from StringIO import StringIO |
| from docx import * | from docx import * |
| from lxml import etree | from lxml import etree |
| import zipfile | import zipfile |
| from pdfminer.pdfparser import PDFDocument, PDFParser | from pdfminer.pdfparser import PDFDocument, PDFParser |
| from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf | from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf |
| from pdfminer.pdfdevice import PDFDevice, TagExtractor | from pdfminer.pdfdevice import PDFDevice, TagExtractor |
| from pdfminer.converter import TextConverter | from pdfminer.converter import TextConverter |
| from pdfminer.cmapdb import CMapDB | from pdfminer.cmapdb import CMapDB |
| from pdfminer.layout import LAParams | from pdfminer.layout import LAParams |
| class GenericDisclogScraper(object): | class GenericDisclogScraper(object): |
| __metaclass__ = abc.ABCMeta | __metaclass__ = abc.ABCMeta |
| agencyID = None | agencyID = None |
| disclogURL = None | disclogURL = None |
| def remove_control_chars(self, input): | |
| return "".join([i for i in input if ord(i) in range(32, 127)]) | def remove_control_chars(self, input): |
| def getAgencyID(self): | return "".join([i for i in input if ord(i) in range(32, 127)]) |
| """ disclosr agency id """ | |
| if self.agencyID == None: | def getAgencyID(self): |
| self.agencyID = os.path.basename(sys.argv[0]).replace(".py","") | """ disclosr agency id """ |
| return self.agencyID | if self.agencyID is None: |
| self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "") | |
| def getURL(self): | return self.agencyID |
| """ disclog URL""" | |
| if self.disclogURL == None: | def getURL(self): |
| agency = scrape.agencydb.get(self.getAgencyID()) | """ disclog URL""" |
| self.disclogURL = agency['FOIDocumentsURL'] | if self.disclogURL is None: |
| return self.disclogURL | agency = scrape.agencydb.get(self.getAgencyID()) |
| self.disclogURL = agency['FOIDocumentsURL'] | |
| @abc.abstractmethod | return self.disclogURL |
| def doScrape(self): | |
| """ do the scraping """ | @abc.abstractmethod |
| return | def doScrape(self): |
| """ do the scraping """ | |
| return | |
| class GenericPDFDisclogScraper(GenericDisclogScraper): | class GenericPDFDisclogScraper(GenericDisclogScraper): |
| def doScrape(self): | def doScrape(self): |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
| (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID()) | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
| self.getURL(), "foidocuments", self.getAgencyID()) | |
| laparams = LAParams() | laparams = LAParams() |
| rsrcmgr = PDFResourceManager(caching=True) | |
| rsrcmgr = PDFResourceManager(caching=True) | |
| outfp = StringIO.StringIO() | outfp = StringIO.StringIO() |
| device = TextConverter(rsrcmgr, outfp, codec='utf-8', | |
| device = TextConverter(rsrcmgr, outfp, codec='utf-8', laparams=laparams) | laparams=laparams) |
| fp = StringIO.StringIO() | fp = StringIO.StringIO() |
| fp.write(content) | fp.write(content) |
| description = output.getvalue(); | description = output.getvalue() |
| process_pdf(rsrcmgr, device, fp, set(), caching=True, check_extractable=True) | process_pdf(rsrcmgr, device, fp, set(), caching=True, |
| check_extractable=True) | |
| fp.close() | fp.close() |
| device.close() | device.close() |
| outfp.close() | outfp.close() |
| dochash = scrape.mkhash(description) | |
| hash = scrape.mkhash(description) | doc = foidocsdb.get(dochash) |
| #print hash | if doc is None: |
| doc = foidocsdb.get(hash) | print "saving " + dochash |
| #print doc | edate = datetime.fromtimestamp(mktime()).strftime("%Y-%m-%d") |
| if doc == None: | doc = {'_id': dochash, 'agencyID': self.getAgencyID() |
| print "saving "+ hash | , 'url': self.getURL(), 'docID': dochash, |
| edate = datetime.fromtimestamp(mktime( )).strftime("%Y-%m-%d") | "date": edate, "title": "Disclosure Log Updated"} |
| doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': hash, | self.getDescription(entry, entry, doc) |
| "date": edate,"title": "Disclosure Log Updated"} | foidocsdb.save(doc) |
| self.getDescription(entry,entry, doc) | else: |
| foidocsdb.save(doc) | print "already saved" |
| class GenericDOCXDisclogScraper(GenericDisclogScraper): | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb | |
| , self.getURL(), "foidocuments", self.getAgencyID()) | |
| mydoc = zipfile.ZipFile(file) | |
| xmlcontent = mydoc.read('word/document.xml') | |
| document = etree.fromstring(xmlcontent) | |
| ## Fetch all the text out of the document we just created | |
| paratextlist = getdocumenttext(document) | |
| # Make explicit unicode version | |
| newparatextlist = [] | |
| for paratext in paratextlist: | |
| newparatextlist.append(paratext.encode("utf-8")) | |
| ## Print our documnts test with two newlines under each paragraph | |
| description = '\n\n'.join(newparatextlist) | |
| dochash = scrape.mkhash(description) | |
| doc = foidocsdb.get(dochash) | |
| if doc is None: | |
| print "saving " + dochash | |
| edate = datetime.fromtimestamp(mktime()).strftime("%Y-%m-%d") | |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID() | |
| , 'url': self.getURL(), 'docID': dochash, | |
| "date": edate, "title": "Disclosure Log Updated"} | |
| self.getDescription(entry, entry, doc) | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| class GenericRSSDisclogScraper(GenericDisclogScraper): | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
| self.getURL(), "foidocuments", self.getAgencyID()) | |
| feed = feedparser.parse(content) | |
| for entry in feed.entries: | |
| #print entry | |
| print entry.id | |
| dochash = scrape.mkhash(entry.id) | |
| doc = foidocsdb.get(dochash) | |
| #print doc | |
| if doc is None: | |
| print "saving " + dochash | |
| edate = datetime.fromtimestamp( | |
| mktime(entry.published_parsed)).strftime("%Y-%m-%d") | |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID(), | |
| 'url': entry.link, 'docID': entry.id, | |
| "date": edate, "title": entry.title} | |
| self.getDescription(entry, entry, doc) | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| def getDescription(self, content, entry, doc): | |
| """ get description from rss entry""" | |
| doc.update({'description': content.summary}) | |
| return | |
| class GenericOAICDisclogScraper(GenericDisclogScraper): | |
| __metaclass__ = abc.ABCMeta | |
| @abc.abstractmethod | |
| def getColumns(self, columns): | |
| """ rearranges columns if required """ | |
| return | |
| def getColumnCount(self): | |
| return 5 | |
| def getDescription(self, content, entry, doc): | |
| """ get description from rss entry""" | |
| descriptiontxt = "" | |
| for string in content.stripped_strings: | |
| descriptiontxt = descriptiontxt + " \n" + string | |
| doc.update({'description': descriptiontxt}) | |
| def getTitle(self, content, entry, doc): | |
| doc.update({'title': (''.join(content.stripped_strings))}) | |
| def getTable(self, soup): | |
| return soup.table | |
| def getRows(self, table): | |
| return table.find_all('tr') | |
| def getDate(self, content, entry, doc): | |
| date = ''.join(content.stripped_strings).strip() | |
| (a, b, c) = date.partition("(") | |
| date = self.remove_control_chars(a.replace("Octber", "October")) | |
| print date | |
| edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
| print edate | |
| doc.update({'date': edate}) | |
| return | |
| def getLinks(self, content, entry, doc): | |
| links = [] | |
| for atag in entry.find_all("a"): | |
| if atag.has_key('href'): | |
| links.append(scrape.fullurl(content, atag['href'])) | |
| if links != []: | |
| doc.update({'links': links}) | |
| return | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
| self.getURL(), "foidocuments", self.getAgencyID()) | |
| if content is not None: | |
| if mime_type is "text/html"\ | |
| or mime_type is "application/xhtml+xml"\ | |
| or mime_type is"application/xml": | |
| # http://www.crummy.com/software/BeautifulSoup/documentation.html | |
| soup = BeautifulSoup(content) | |
| table = self.getTable(soup) | |
| for row in self.getRows(table): | |
| columns = row.find_all('td') | |
| 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: | else: |
| print "already saved" | dochash = scrape.mkhash( |
| self.remove_control_chars( | |
| url + (''.join(id.stripped_strings)))) | |
| class GenericDOCXDisclogScraper(GenericDisclogScraper): | doc = foidocsdb.get(hash) |
| def doScrape(self): | if doc is None: |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | print "saving " + hash |
| (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID()) | doc = {'_id': hash, |
| 'agencyID': self.getAgencyID(), | |
| mydoc = zipfile.ZipFile(file) | 'url': self.getURL(), |
| xmlcontent = mydoc.read('word/document.xml') | 'docID': (''.join(id.stripped_strings))} |
| document = etree.fromstring(xmlcontent) | self.getLinks(self.getURL(), row, doc) |
| self.getTitle(title, row, doc) | |
| ## Fetch all the text out of the document we just created | self.getDate(date, row, doc) |
| paratextlist = getdocumenttext(document) | self.getDescription(description, row, doc) |
| if notes is not None: | |
| # Make explicit unicode version | doc.update({ 'notes': ( |
| newparatextlist = [] | ''.join(notes.stripped_strings))}) |
| for paratext in paratextlist: | badtitles = ['-','Summary of FOI Request' |
| newparatextlist.append(paratext.encode("utf-8")) | , 'FOI request(in summary form)' |
| , 'Summary of FOI request received by the ASC', | |
| ## Print our documnts test with two newlines under each paragraph | 'Summary of FOI request received by agency/minister', |
| description = '\n\n'.join(newparatextlist) | 'Description of Documents Requested','FOI request', |
| 'Description of FOI Request','Summary of request','Description','Summary', | |
| hash = scrape.mkhash(description) | |
| #print hash | |
| doc = foidocsdb.get(hash) | |
| #print doc | |
| if doc == None: | |
| print "saving "+ hash | |
| edate = datetime.fromtimestamp(mktime()).strftime("%Y-%m-%d") | |
| doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': hash, | |
| "date": edate,"title": "Disclosure Log Updated"} | |
| self.getDescription(entry,entry, doc) | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| class GenericRSSDisclogScraper(GenericDisclogScraper): | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID()) | |
| feed = feedparser.parse(content) | |
| for entry in feed.entries: | |
| #print entry | |
| print entry.id | |
| hash = scrape.mkhash(entry.id) | |
| #print hash | |
| doc = foidocsdb.get(hash) | |
| #print doc | |
| if doc == None: | |
| print "saving "+ hash | |
| edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d") | |
| doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id, | |
| "date": edate,"title": entry.title} | |
| self.getDescription(entry,entry, doc) | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| def getDescription(self, content, entry, doc): | |
| """ get description from rss entry""" | |
| doc.update({'description': content.summary}) | |
| return | |
| class GenericOAICDisclogScraper(GenericDisclogScraper): | |
| __metaclass__ = abc.ABCMeta | |
| @abc.abstractmethod | |
| def getColumns(self,columns): | |
| """ rearranges columns if required """ | |
| return | |
| def getColumnCount(self): | |
| return 5 | |
| def getDescription(self, content, entry, doc): | |
| """ get description from rss entry""" | |
| descriptiontxt = "" | |
| for string in content.stripped_strings: | |
| descriptiontxt = descriptiontxt + " \n" + string | |
| doc.update({'description': descriptiontxt}) | |
| return | |
| def getTitle(self, content, entry, doc): | |
| doc.update({'title': (''.join(content.stripped_strings))}) | |
| return | |
| def getTable(self, soup): | |
| return soup.table | |
| def getRows(self, table): | |
| return table.find_all('tr') | |
| def getDate(self, content, entry, doc): | |
| date = ''.join(content.stripped_strings).strip() | |
| (a,b,c) = date.partition("(") | |
| date = self.remove_control_chars(a.replace("Octber","October")) | |
| print date | |
| edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
| print edate | |
| doc.update({'date': edate}) | |
| return | |
| def getLinks(self, content, entry, doc): | |
| links = [] | |
| for atag in entry.find_all("a"): | |
| if atag.has_key('href'): | |
| links.append(scrape.fullurl(content,atag['href'])) | |
| if links != []: | |
| doc.update({'links': links}) | |
| return | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID()) | |
| if content != 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(content) | |
| table = self.getTable(soup) | |
| for row in self.getRows(table): | |
| columns = row.find_all('td') | |
| if len(columns) == self.getColumnCount(): | |
| (id, date, title, description, notes) = self.getColumns(columns) | |
| print self.remove_control_chars(''.join(id.stripped_strings)) | |
| if id.string == None: | |
| hash = scrape.mkhash(self.remove_control_chars(url+(''.join(date.stripped_strings)))) | |
| else: | |
| hash = scrape.mkhash(self.remove_control_chars(url+(''.join(id.stripped_strings)))) | |
| doc = foidocsdb.get(hash) | |
| if doc == None: | |
| print "saving " +hash | |
| doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': (''.join(id.stripped_strings))} | |
| self.getLinks(self.getURL(),row,doc) | |
| self.getTitle(title,row, doc) | |
| self.getDate(date,row, doc) | |
| self.getDescription(description,row, doc) | |
| if notes != None: | |
| doc.update({ 'notes': (''.join(notes.stripped_strings))}) | |
| badtitles = ['-','Summary of FOI Request','FOI request(in summary form)','Summary of FOI request received by the ASC', | |
| 'Summary of FOI request received by agency/minister','Description of Documents Requested','FOI request','Description of FOI Request','Summary of request','Description','Summary', | |
| 'Summary of FOIrequest received by agency/minister','Summary of FOI request received','Description of FOI Request',"FOI request",'Results 1 to 67 of 67'] | 'Summary of FOIrequest received by agency/minister','Summary of FOI request received','Description of FOI Request',"FOI request",'Results 1 to 67 of 67'] |
| if doc['title'] not in badtitles and doc['description'] != '': | if doc['title'] not in badtitles\ |
| and doc['description'] != '': | |
| print "saving" | print "saving" |
| foidocsdb.save(doc) | foidocsdb.save(doc) |
| else: | else: |
| print "already saved "+hash | print "already saved " + dochash |
| elif len(row.find_all('th')) == self.getColumnCount(): | elif len(row.find_all('th')) is self.getColumnCount(): |
| print "header row" | print "header row" |
| else: | else: |
| print "ERROR number of columns incorrect" | print "ERROR number of columns incorrect" |
| print row | print row |
| <?php | <?php |
| // Agency X updated Y, new files, diff of plain text/link text, | // Agency X updated Y, new files, diff of plain text/link text, |
| // feed for just one agency or all | // feed for just one agency or all |
| // This is a minimum example of using the Universal Feed Generator Class | // This is a minimum example of using the Universal Feed Generator Class |
| include("../lib/FeedWriter/FeedTypes.php"); | include("../lib/FeedWriter/FeedTypes.php"); |
| include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
| //Creating an instance of FeedWriter class. | //Creating an instance of FeedWriter class. |
| $TestFeed = new RSS2FeedWriter(); | $TestFeed = new RSS2FeedWriter(); |
| //Setting the channel elements | //Setting the channel elements |
| //Use wrapper functions for common channelelements | //Use wrapper functions for common channelelements |
| $TestFeed->setTitle('disclosurelo.gs Newest Entries - All'); | $TestFeed->setTitle('disclosurelo.gs Newest Entries - All'); |
| $TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'); | $TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'); |
| $TestFeed->setDescription('disclosurelo.gs Newest Entries - All Agencies'); | $TestFeed->setDescription('disclosurelo.gs Newest Entries - All Agencies'); |
| $TestFeed->setChannelElement('language', 'en-us'); | $TestFeed->setChannelElement('language', 'en-us'); |
| $TestFeed->setChannelElement('pubDate', date(DATE_RSS, time())); | $TestFeed->setChannelElement('pubDate', date(DATE_RSS, time())); |
| //Retriving informations from database | //Retriving informations from database |
| $idtoname = Array(); | $idtoname = Array(); |
| $agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
| foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { |
| $idtoname[$row->id] = trim($row->value->name); | $idtoname[$row->id] = trim($row->value->name); |
| } | } |
| $foidocsdb = $server->get_db('disclosr-foidocuments'); | $foidocsdb = $server->get_db('disclosr-foidocuments'); |
| $rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00', 50), true)->rows; | $rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows; |
| //print_r($rows); | //print_r($rows); |
| foreach ($rows as $row) { | foreach ($rows as $row) { |
| //Create an empty FeedItem | //Create an empty FeedItem |
| $newItem = $TestFeed->createNewItem(); | $newItem = $TestFeed->createNewItem(); |
| //Add elements to the feed item | //Add elements to the feed item |
| $newItem->setTitle($row->value->title); | $newItem->setTitle($row->value->title); |
| $newItem->setLink("http://disclosurelo.gs/view.php?id=".$row->value->_id); | $newItem->setLink("http://disclosurelo.gs/view.php?id=" . $row->value->_id); |
| $newItem->setDate(strtotime($row->value->date)); | $newItem->setDate(strtotime($row->value->date)); |
| $newItem->setDescription(displayLogEntry($row,$idtoname)); | $newItem->setDescription(displayLogEntry($row, $idtoname)); |
| $newItem->setAuthor($idtoname[$row->value->agencyID]); | $newItem->setAuthor($idtoname[$row->value->agencyID]); |
| $newItem->addElement('guid', "http://disclosurelo.gs/view.php?id=".$row->value->_id,array('isPermaLink'=>'true')); | $newItem->addElement('guid', "http://disclosurelo.gs/view.php?id=" . $row->value->_id, array('isPermaLink' => 'true')); |
| //Now add the feed item | //Now add the feed item |
| $TestFeed->addItem($newItem); | $TestFeed->addItem($newItem); |
| } | } |
| //OK. Everything is done. Now genarate the feed. | //OK. Everything is done. Now genarate the feed. |
| $TestFeed->generateFeed(); | $TestFeed->generateFeed(); |
| ?> | ?> |
| <?php | <?php |
| function include_header_documents($title) { | function include_header_documents($title) { |
| header('X-UA-Compatible: IE=edge,chrome=1'); | header('X-UA-Compatible: IE=edge,chrome=1'); |
| ?> | ?> |
| <!doctype html> | <!doctype html> |
| <!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ --> | <!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ --> |
| <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]--> | <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]--> |
| <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]--> | <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]--> |
| <!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]--> | <!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]--> |
| <!-- Consider adding a manifest.appcache: h5bp.com/d/Offline --> | <!-- Consider adding a manifest.appcache: h5bp.com/d/Offline --> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]--> | <!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]--> |
| <head> | <head> |
| <meta charset="utf-8"> | <meta charset="utf-8"> |
| <title>Australian Disclosure Logs<?php if ($title != "") echo " - $title"; ?></title> | <title>Australian Disclosure Logs<?php if ($title != "") echo " - $title"; ?></title> |
| <meta name="description" content=""> | <meta name="description" content=""> |
| <!-- Mobile viewport optimized: h5bp.com/viewport --> | <!-- Mobile viewport optimized: h5bp.com/viewport --> |
| <meta name="viewport" content="width=device-width"> | <meta name="viewport" content="width=device-width"> |
| <link rel="alternate" type="application/rss+xml" title="Latest Disclosure Log Entries" href="rss.xml.php" /> | <link rel="alternate" type="application/rss+xml" title="Latest Disclosure Log Entries" href="rss.xml.php" /> |
| <!-- Place favicon.ico and apple-touch-icon.png in the root directory: mathiasbynens.be/notes/touch-icons --> | <!-- Place favicon.ico and apple-touch-icon.png in the root directory: mathiasbynens.be/notes/touch-icons --> |
| <meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" /> | <meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" /> |
| <!-- Le styles --> | <!-- Le styles --> |
| <link href="css/bootstrap.min.css" rel="stylesheet"> | <link href="css/bootstrap.min.css" rel="stylesheet"> |
| <style type="text/css"> | <style type="text/css"> |
| body { | body { |
| padding-top: 60px; | padding-top: 60px; |
| padding-bottom: 40px; | padding-bottom: 40px; |
| } | } |
| .sidebar-nav { | .sidebar-nav { |
| padding: 9px 0; | padding: 9px 0; |
| } | } |
| </style> | </style> |
| <link href="css/bootstrap-responsive.min.css" rel="stylesheet"> | <link href="css/bootstrap-responsive.min.css" rel="stylesheet"> |
| <!-- HTML5 shim, for IE6-8 support of HTML5 elements --> | <!-- HTML5 shim, for IE6-8 support of HTML5 elements --> |
| <!--[if lt IE 9]> | <!--[if lt IE 9]> |
| <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script> | <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script> |
| <![endif]--> | <![endif]--> |
| <!-- More ideas for your <head> here: h5bp.com/d/head-Tips --> | <!-- More ideas for your <head> here: h5bp.com/d/head-Tips --> |
| <!-- All JavaScript at the bottom, except this Modernizr build. | <!-- All JavaScript at the bottom, except this Modernizr build. |
| Modernizr enables HTML5 elements & feature detects for optimal performance. | Modernizr enables HTML5 elements & feature detects for optimal performance. |
| Create your own custom Modernizr build: www.modernizr.com/download/ | Create your own custom Modernizr build: www.modernizr.com/download/ |
| <script src="js/libs/modernizr-2.5.3.min.js"></script>--> | <script src="js/libs/modernizr-2.5.3.min.js"></script>--> |
| <script src="js/jquery.js"></script> | <script src="js/jquery.js"></script> |
| <script type="text/javascript" src="js/flotr2.min.js"></script> | <script type="text/javascript" src="js/flotr2.min.js"></script> |
| </head> | </head> |
| <body> | <body> |
| <div class="navbar navbar-inverse navbar-fixed-top"> | <div class="navbar navbar-inverse navbar-fixed-top"> |
| <div class="navbar-inner"> | <div class="navbar-inner"> |
| <div class="container-fluid"> | <div class="container-fluid"> |
| <a class="btn btn-navbar" data-toggle="collapse" data-target=".nav-collapse"> | <a class="btn btn-navbar" data-toggle="collapse" data-target=".nav-collapse"> |
| <span class="icon-bar"></span> | <span class="icon-bar"></span> |
| <span class="icon-bar"></span> | <span class="icon-bar"></span> |
| <span class="icon-bar"></span> | <span class="icon-bar"></span> |
| </a> | </a> |
| <a class="brand" href="#">Australian Disclosure Logs</a> | <a class="brand" href="#">Australian Disclosure Logs</a> |
| <div class="nav-collapse collapse"> | <div class="nav-collapse collapse"> |
| <p class="navbar-text pull-right"> | <p class="navbar-text pull-right"> |
| Check out our subsites on: | Check out our subsites on: |
| <a href="http://orgs.disclosurelo.gs">Government Agencies</a> | <a href="http://orgs.disclosurelo.gs">Government Agencies</a> |
| • <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a> | • <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a> |
| • <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a> | • <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a> |
| </p> | </p> |
| <ul class="nav"> | <ul class="nav"> |
| <li><a href="index.php">Home</a></li> | <li><a href="index.php">Home</a></li> |
| <li><a href="disclogsList.php">List of Disclosure Logs</a></li> | <li><a href="disclogsList.php">List of Disclosure Logs</a></li> |
| <li><a href="about.php">About</a></li> | <li><a href="about.php">About</a></li> |
| </ul> | </ul> |
| </div><!--/.nav-collapse --> | </div><!--/.nav-collapse --> |
| </div> | </div> |
| </div> | </div> |
| </div> | </div> |
| <div class="container"> | <div class="container"> |
| <?php | <?php |
| } | } |
| function include_footer_documents() { | function include_footer_documents() { |
| ?> | ?> |
| </div> <!-- /container --> | </div> <!-- /container --> |
| <hr> | <hr> |
| <footer> | <footer> |
| <p>Not affiliated with or endorsed by any government agency.</p> | <p>Not affiliated with or endorsed by any government agency.</p> |
| </footer> | </footer> |
| <script type="text/javascript"> | <script type="text/javascript"> |
| var _gaq = _gaq || []; | var _gaq = _gaq || []; |
| _gaq.push(['_setAccount', 'UA-12341040-4']); | _gaq.push(['_setAccount', 'UA-12341040-4']); |
| _gaq.push(['_setDomainName', 'disclosurelo.gs']); | _gaq.push(['_setDomainName', 'disclosurelo.gs']); |
| _gaq.push(['_setAllowLinker', true]); | _gaq.push(['_setAllowLinker', true]); |
| _gaq.push(['_trackPageview']); | _gaq.push(['_trackPageview']); |
| (function() { | (function() { |
| var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; | var ga = document.createElement('script'); |
| ga.type = 'text/javascript'; | |
| ga.async = true; | |
| ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; | ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
| var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); | var s = document.getElementsByTagName('script')[0]; |
| s.parentNode.insertBefore(ga, s); | |
| })(); | })(); |
| </script> | </script> |
| <!-- Le javascript | <!-- Le javascript |
| ================================================== --> | ================================================== --> |
| <!-- Placed at the end of the document so the pages load faster --> | <!-- Placed at the end of the document so the pages load faster --> |
| <!-- | <!-- |
| <script src="js/bootstrap-transition.js"></script> | <script src="js/bootstrap-transition.js"></script> |
| <script src="js/bootstrap-alert.js"></script> | <script src="js/bootstrap-alert.js"></script> |
| <script src="js/bootstrap-modal.js"></script> | <script src="js/bootstrap-modal.js"></script> |
| <script src="js/bootstrap-dropdown.js"></script> | <script src="js/bootstrap-dropdown.js"></script> |
| <script src="js/bootstrap-scrollspy.js"></script> | <script src="js/bootstrap-scrollspy.js"></script> |
| <script src="js/bootstrap-tab.js"></script> | <script src="js/bootstrap-tab.js"></script> |
| <script src="js/bootstrap-tooltip.js"></script> | <script src="js/bootstrap-tooltip.js"></script> |
| <script src="js/bootstrap-popover.js"></script> | <script src="js/bootstrap-popover.js"></script> |
| <script src="js/bootstrap-button.js"></script> | <script src="js/bootstrap-button.js"></script> |
| <script src="js/bootstrap-collapse.js"></script> | <script src="js/bootstrap-collapse.js"></script> |
| <script src="js/bootstrap-carousel.js"></script> | <script src="js/bootstrap-carousel.js"></script> |
| <script src="js/bootstrap-typeahead.js"></script>--> | <script src="js/bootstrap-typeahead.js"></script>--> |
| </body> | </body> |
| </html> | </html> |
| <?php | <?php |
| } | } |
| function truncate($string, $length, $stopanywhere = false) { | function truncate($string, $length, $stopanywhere = false) { |
| //truncates a string to a certain char length, stopping on a word if not specified otherwise. | //truncates a string to a certain char length, stopping on a word if not specified otherwise. |
| if (strlen($string) > $length) { | if (strlen($string) > $length) { |
| //limit hit! | //limit hit! |
| $string = substr($string, 0, ($length - 3)); | $string = substr($string, 0, ($length - 3)); |
| if ($stopanywhere) { | if ($stopanywhere) { |
| //stop anywhere | //stop anywhere |
| $string .= '...'; | $string .= '...'; |
| } else { | } else { |
| //stop on a word. | //stop on a word. |
| $string = substr($string, 0, strrpos($string, ' ')) . '...'; | $string = substr($string, 0, strrpos($string, ' ')) . '...'; |
| } | } |
| } | } |
| return $string; | return $string; |
| } | } |
| function displayLogEntry($row, $idtoname) { | function displayLogEntry($row, $idtoname) { |
| $result = ""; | $result = ""; |
| $result .= '<div itemscope itemtype="http://schema.org/Article">'; | $result .= '<div itemscope itemtype="http://schema.org/Article">'; |
| $result .= '<h2> <span itemprop="datePublished">' . $row->value->date . "</span>: <span itemprop='name headline'>" . truncate($row->value->title, 120)."</span>"; | $result .= '<h2> <span itemprop="datePublished">' . $row->value->date . "</span>: <span itemprop='name headline'>" . truncate($row->value->title, 120) . "</span>"; |
| $result .= '(<span itemprop="author publisher creator">' . $idtoname[$row->value->agencyID] . '</span>)</h2>'; | $result .= '(<span itemprop="author publisher creator">' . $idtoname[$row->value->agencyID] . '</span>)</h2>'; |
| $result .= "<p itemprop='description articleBody text'> Title" . $row->value->title . "<br/>" . str_replace("\n", "<br>", $row->value->description); | $result .= "<p itemprop='description articleBody text'> Title" . $row->value->title . "<br/>"; |
| if (isset($row->value->description)) { | |
| $result .= str_replace("\n", "<br>", $row->value->description); | |
| } | |
| if (isset($row->value->notes)) { | if (isset($row->value->notes)) { |
| $result .= " <br>Note: " . $row->value->notes; | $result .= " <br>Note: " . $row->value->notes; |
| } | } |
| $result .= "</p>"; | $result .= "</p>"; |
| if (isset($row->value->links)) { | if (isset($row->value->links)) { |
| $result .= '<h3>Links/Documents</h3><ul itemprop="associatedMedia">'; | $result .= '<h3>Links/Documents</h3><ul itemprop="associatedMedia">'; |
| foreach ($row->value->links as $link) { | foreach ($row->value->links as $link) { |
| $result .= '<li itemscope itemtype="http://schema.org/MediaObject"><a href='.$link.' itemprop="url contentURL">' . urlencode($link) . "</a></li>"; | $result .= '<li itemscope itemtype="http://schema.org/MediaObject"><a href=' . $link . ' itemprop="url contentURL">' . urlencode($link) . "</a></li>"; |
| } | } |
| $result .= "</ul>"; | $result .= "</ul>"; |
| } | } |
| $result .= "<small><A itemprop='url' href='" . $row->value->url . "'>View original source...</a> ID: " . strip_tags($row->value->docID) . "</small>"; | $result .= "<small><A itemprop='url' href='" . $row->value->url . "'>View original source...</a> ID: " . strip_tags($row->value->docID) . "</small>"; |
| $result .= "</div>"; | $result .= "</div>"; |
| return $result; | return $result; |
| } | } |