Former-commit-id: e85a6fcfab76f7ea0b140471a810430aa544e81d
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -1,155 +1,260 @@
-import sys,os
+import sys
+import os
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
import scrape
from bs4 import BeautifulSoup
from time import mktime
import feedparser
import abc
-import unicodedata, re
+import unicodedata
+import re
import dateutil
from dateutil.parser import *
from datetime import *
import codecs
+from StringIO import StringIO
+
+from docx import *
+from lxml import etree
+import zipfile
+
+from pdfminer.pdfparser import PDFDocument, PDFParser
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
+from pdfminer.pdfdevice import PDFDevice, TagExtractor
+from pdfminer.converter import TextConverter
+from pdfminer.cmapdb import CMapDB
+from pdfminer.layout import LAParams
+
+
class GenericDisclogScraper(object):
- __metaclass__ = abc.ABCMeta
- agencyID = None
- disclogURL = None
- def remove_control_chars(self, input):
- return "".join([i for i in input if ord(i) in range(32, 127)])
- def getAgencyID(self):
- """ disclosr agency id """
- if self.agencyID == None:
- self.agencyID = os.path.basename(sys.argv[0]).replace(".py","")
- return self.agencyID
-
- def getURL(self):
- """ disclog URL"""
- if self.disclogURL == None:
- agency = scrape.agencydb.get(self.getAgencyID())
- self.disclogURL = agency['FOIDocumentsURL']
- return self.disclogURL
-
- @abc.abstractmethod
- def doScrape(self):
- """ do the scraping """
- return
-
- @abc.abstractmethod
- def getDescription(self, content, entry, doc):
- """ get description"""
- return
-
+ __metaclass__ = abc.ABCMeta
+ agencyID = None
+ disclogURL = None
+
+ def remove_control_chars(self, input):
+ return "".join([i for i in input if ord(i) in range(32, 127)])
+
+ def getAgencyID(self):
+ """ disclosr agency id """
+ if self.agencyID is None:
+ self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "")
+ return self.agencyID
+
+ def getURL(self):
+ """ disclog URL"""
+ if self.disclogURL is None:
+ agency = scrape.agencydb.get(self.getAgencyID())
+ self.disclogURL = agency['FOIDocumentsURL']
+ return self.disclogURL
+
+ @abc.abstractmethod
+ def doScrape(self):
+ """ do the scraping """
+ return
+
+
+class GenericPDFDisclogScraper(GenericDisclogScraper):
+
+ def doScrape(self):
+ foidocsdb = scrape.couch['disclosr-foidocuments']
+ (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
+ self.getURL(), "foidocuments", self.getAgencyID())
+ laparams = LAParams()
+ rsrcmgr = PDFResourceManager(caching=True)
+ outfp = StringIO.StringIO()
+ device = TextConverter(rsrcmgr, outfp, codec='utf-8',
+ laparams=laparams)
+ fp = StringIO.StringIO()
+ fp.write(content)
+ description = output.getvalue()
+ process_pdf(rsrcmgr, device, fp, set(), caching=True,
+ check_extractable=True)
+ fp.close()
+ device.close()
+ outfp.close()
+ 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 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
- 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)
+ 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:
- 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',
+ dochash = scrape.mkhash(
+ self.remove_control_chars(
+ url + (''.join(id.stripped_strings))))
+ doc = foidocsdb.get(hash)
+
+ if doc is 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 is not 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']
- if doc['title'] not in badtitles and doc['description'] != '':
+ if doc['title'] not in badtitles\
+ and doc['description'] != '':
print "saving"
foidocsdb.save(doc)
- else:
- print "already saved "+hash
-
- elif len(row.find_all('th')) == self.getColumnCount():
- print "header row"
-
- else:
- print "ERROR number of columns incorrect"
- print row
-
+ else:
+ print "already saved " + dochash
+
+ elif len(row.find_all('th')) is self.getColumnCount():
+ print "header row"
+
+ else:
+ print "ERROR number of columns incorrect"
+ print row
+
--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -1,167 +1,175 @@
<?php
function include_header_documents($title) {
-?>
-<!doctype html>
-<!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ -->
-<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]-->
-<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]-->
-<!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]-->
-<!-- Consider adding a manifest.appcache: h5bp.com/d/Offline -->
-<!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]-->
-<head>
- <meta charset="utf-8">
+ header('X-UA-Compatible: IE=edge,chrome=1');
+ ?>
+ <!doctype html>
+ <!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ -->
+ <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]-->
+ <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]-->
+ <!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]-->
+ <!-- Consider adding a manifest.appcache: h5bp.com/d/Offline -->
+ <!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]-->
+ <head>
+ <meta charset="utf-8">
- <!-- Use the .htaccess and remove these lines to avoid edge case issues.
- More info: h5bp.com/i/378 -->
- <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+ <title>Australian Disclosure Logs<?php if ($title != "") echo " - $title"; ?></title>
+ <meta name="description" content="">
- <title>Australian Disclosure Logs<?php if ($title != "") echo " - $title";?></title>
- <meta name="description" content="">
+ <!-- Mobile viewport optimized: h5bp.com/viewport -->
+ <meta name="viewport" content="width=device-width">
+ <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 -->
+ <meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" />
- <!-- Mobile viewport optimized: h5bp.com/viewport -->
- <meta name="viewport" content="width=device-width">
-<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 -->
-<meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" />
+ <!-- Le styles -->
+ <link href="css/bootstrap.min.css" rel="stylesheet">
+ <style type="text/css">
+ body {
+ padding-top: 60px;
+ padding-bottom: 40px;
+ }
+ .sidebar-nav {
+ padding: 9px 0;
+ }
+ </style>
+ <link href="css/bootstrap-responsive.min.css" rel="stylesheet">
- <!-- Le styles -->
- <link href="css/bootstrap.min.css" rel="stylesheet">
- <style type="text/css">
- body {
- padding-top: 60px;
- padding-bottom: 40px;
- }
- .sidebar-nav {
- padding: 9px 0;
- }
- </style>
- <link href="css/bootstrap-responsive.min.css" rel="stylesheet">
+ <!-- HTML5 shim, for IE6-8 support of HTML5 elements -->
+ <!--[if lt IE 9]>
+ <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
+ <![endif]-->
+ <!-- More ideas for your <head> here: h5bp.com/d/head-Tips -->
- <!-- HTML5 shim, for IE6-8 support of HTML5 elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
- <!-- More ideas for your <head> here: h5bp.com/d/head-Tips -->
+ <!-- All JavaScript at the bottom, except this Modernizr build.
+ Modernizr enables HTML5 elements & feature detects for optimal performance.
+ Create your own custom Modernizr build: www.modernizr.com/download/
+ <script src="js/libs/modernizr-2.5.3.min.js"></script>-->
+ <script src="js/jquery.js"></script>
+ <script type="text/javascript" src="js/flotr2.min.js"></script>
- <!-- All JavaScript at the bottom, except this Modernizr build.
- Modernizr enables HTML5 elements & feature detects for optimal performance.
- Create your own custom Modernizr build: www.modernizr.com/download/
- <script src="js/libs/modernizr-2.5.3.min.js"></script>-->
- <script src="js/jquery.js"></script>
- <script type="text/javascript" src="js/flotr2.min.js"></script>
-
-</head>
-<body>
- <div class="navbar navbar-inverse navbar-fixed-top">
- <div class="navbar-inner">
- <div class="container-fluid">
- <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>
- </a>
- <a class="brand" href="#">Australian Disclosure Logs</a>
- <div class="nav-collapse collapse">
- <p class="navbar-text pull-right">
- Check out our subsites on:
-<a href="http://orgs.disclosurelo.gs">Government Agencies</a>
-• <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a>
-• <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a>
+ </head>
+ <body>
+ <div class="navbar navbar-inverse navbar-fixed-top">
+ <div class="navbar-inner">
+ <div class="container-fluid">
+ <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>
+ </a>
+ <a class="brand" href="#">Australian Disclosure Logs</a>
+ <div class="nav-collapse collapse">
+ <p class="navbar-text pull-right">
+ Check out our subsites on:
+ <a href="http://orgs.disclosurelo.gs">Government Agencies</a>
+ • <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a>
+ • <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a>
- </p>
- <ul class="nav">
- <li><a href="index.php">Home</a></li>
- <li><a href="disclogsList.php">List of Disclosure Logs</a></li>
- <li><a href="about.php">About</a></li>
-
- </ul>
- </div><!--/.nav-collapse -->
- </div>
- </div>
- </div>
- <div class="container">
- <?php
-}
-function include_footer_documents() {
- ?>
- </div> <!-- /container -->
- <hr>
+ </p>
+ <ul class="nav">
+ <li><a href="index.php">Home</a></li>
+ <li><a href="disclogsList.php">List of Disclosure Logs</a></li>
+ <li><a href="about.php">About</a></li>
- <footer>
- <p>Not affiliated with or endorsed by any government agency.</p>
- </footer>
- <script type="text/javascript">
+ </ul>
+ </div><!--/.nav-collapse -->
+ </div>
+ </div>
+ </div>
+ <div class="container">
+ <?php
+ }
- var _gaq = _gaq || [];
- _gaq.push(['_setAccount', 'UA-12341040-4']);
- _gaq.push(['_setDomainName', 'disclosurelo.gs']);
- _gaq.push(['_setAllowLinker', true]);
- _gaq.push(['_trackPageview']);
+ function include_footer_documents() {
+ ?>
+ </div> <!-- /container -->
+ <hr>
- (function() {
- 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';
- var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
- })();
+ <footer>
+ <p>Not affiliated with or endorsed by any government agency.</p>
+ </footer>
+ <script type="text/javascript">
-</script>
- <!-- Le javascript
- ================================================== -->
- <!-- Placed at the end of the document so the pages load faster -->
-<!--
- <script src="js/bootstrap-transition.js"></script>
- <script src="js/bootstrap-alert.js"></script>
- <script src="js/bootstrap-modal.js"></script>
- <script src="js/bootstrap-dropdown.js"></script>
- <script src="js/bootstrap-scrollspy.js"></script>
- <script src="js/bootstrap-tab.js"></script>
- <script src="js/bootstrap-tooltip.js"></script>
- <script src="js/bootstrap-popover.js"></script>
- <script src="js/bootstrap-button.js"></script>
- <script src="js/bootstrap-collapse.js"></script>
- <script src="js/bootstrap-carousel.js"></script>
- <script src="js/bootstrap-typeahead.js"></script>-->
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-12341040-4']);
+ _gaq.push(['_setDomainName', 'disclosurelo.gs']);
+ _gaq.push(['_setAllowLinker', true]);
+ _gaq.push(['_trackPageview']);
+
+ (function() {
+ 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';
+ var s = document.getElementsByTagName('script')[0];
+ s.parentNode.insertBefore(ga, s);
+ })();
+
+ </script>
+ <!-- Le javascript
+ ================================================== -->
+ <!-- Placed at the end of the document so the pages load faster -->
+ <!--
+ <script src="js/bootstrap-transition.js"></script>
+ <script src="js/bootstrap-alert.js"></script>
+ <script src="js/bootstrap-modal.js"></script>
+ <script src="js/bootstrap-dropdown.js"></script>
+ <script src="js/bootstrap-scrollspy.js"></script>
+ <script src="js/bootstrap-tab.js"></script>
+ <script src="js/bootstrap-tooltip.js"></script>
+ <script src="js/bootstrap-popover.js"></script>
+ <script src="js/bootstrap-button.js"></script>
+ <script src="js/bootstrap-collapse.js"></script>
+ <script src="js/bootstrap-carousel.js"></script>
+ <script src="js/bootstrap-typeahead.js"></script>-->
- </body>
-</html>
-<?php
+ </body>
+ </html>
+ <?php
}
-function truncate($string, $length, $stopanywhere=false) {
+
+function truncate($string, $length, $stopanywhere = false) {
//truncates a string to a certain char length, stopping on a word if not specified otherwise.
if (strlen($string) > $length) {
//limit hit!
- $string = substr($string,0,($length -3));
+ $string = substr($string, 0, ($length - 3));
if ($stopanywhere) {
//stop anywhere
$string .= '...';
- } else{
+ } else {
//stop on a word.
- $string = substr($string,0,strrpos($string,' ')).'...';
+ $string = substr($string, 0, strrpos($string, ' ')) . '...';
}
}
return $string;
}
+
function displayLogEntry($row, $idtoname) {
$result = "";
- $result .= "<div><h2>".$row->value->date.": ".truncate($row->value->title, 80)." (".$idtoname[$row->value->agencyID].")</h2>";
- echo "<p> Title".$row->value->title."<br/>".str_replace("\n","<br>",$row->value->description);
-if (isset($row->value->notes)) {
-$result .= " <br>Note: ".$row->value->notes;
-}
-$result .= "</p>";
+ $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 .= '(<span itemprop="author publisher creator">' . $idtoname[$row->