Use RDFa for semantic markup
Former-commit-id: bff09f0408b049c7c7d7a6c1a35b890b9ed693e2
--- a/getAgency.php
+++ b/getAgency.php
@@ -13,8 +13,8 @@
if (is_array($value)) {
echo "<ol>";
foreach ($value as $subkey => $subvalue) {
- if (isset($schemas['agency']["properties"][$key]['x-itemprop'])) {
- echo '<li itemprop="' . $schemas['agency']["properties"][$key]['x-itemprop'] . '">';
+ if (isset($schemas['agency']["properties"][$key]['x-property'])) {
+ echo '<li property="' . $schemas['agency']["properties"][$key]['x-property'] . '">';
} else {
echo "<li>";
}
@@ -22,8 +22,8 @@
}
echo "</ol></td></tr>";
} else {
- if (isset($schemas['agency']["properties"][$key]['x-itemprop'])) {
- echo '<span itemprop="' . $schemas['agency']["properties"][$key]['x-itemprop'] . '">';
+ if (isset($schemas['agency']["properties"][$key]['x-property'])) {
+ echo '<span property="' . $schemas['agency']["properties"][$key]['x-property'] . '">';
} else {
echo "<span>";
}
@@ -128,7 +128,7 @@
}
if ($mode == "view") {
- echo '<div itemscope itemtype ="http://schema.org/GovernmentOrganisation"><table width="100%">';
+ echo '<div typeof="schema:GovernmentOrganisation" about="#' . $row['_id'] . '"><table width="100%">';
echo '<tr> <td colspan="2"><h3>' . $row['name'] . "</h3></td></tr>";
echo "<tr><th>Field Name</th><th>Field Value</th></tr>";
}
@@ -178,15 +178,19 @@
} */
$rows = $db->get_view("app", "byName")->rows;
//print_r($rows);
+echo '<ul>';
foreach ($rows as $row) {
// print_r($row);
- echo '<li itemscope itemtype="http://schema.org/GovernmentOrganization"><a href="getAgency.php?id=' . $row->value . '" itemprop="url"><span itemprop="name">' .
+ echo '<li typeof="schema:GovernmentOrganisation foaf:Organization" about="getAgency.php?id=' . $row->value . '">
+<a href="getAgency.php?id=' . $row->value . '" rel="schema:url foaf:page" property="schema:name foaf:name">' .
$row->key
- . '</span></a></li>';
+ . '</a></li>';
}
+echo "</ul>";
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
}
include_footer();
?>
+
--- a/include/template.inc.php
+++ b/include/template.inc.php
@@ -33,7 +33,7 @@
<![endif]-->
</head>
- <body>
+ <body xmlns:schema="http://schema.org/" xmlns:foaf="http://xmlns.com/foaf/0.1/">
<!-- navBar -->
<div id="navbar" class="container">
@@ -70,10 +70,11 @@
<script src="<?php echo $basePath; ?>javascripts/app.js"></script>
<script src="http://code.jquery.com/jquery-1.7.1.min.js"></script>
- <!--<script language="javascript" type="text/javascript" src="javascripts/jquery.js"></script>-->
- <script language="javascript" type="text/javascript" src="javascripts/flot/jquery.flot.js"></script>
+ <!--<script type="text/javascript" src="javascripts/jquery.js"></script>-->
+ <script type="text/javascript" src="javascripts/flot/jquery.flot.js"></script>
</body>
</html>
<?php }
+
--- a/schemas/agency.json.php
+++ b/schemas/agency.json.php
@@ -4,18 +4,18 @@
"description" => "Representation of government agency and online transparency measures",
"type" => "object",
"properties" => Array(
- "name" => Array("type" => "string", "required" => true, "x-itemprop" => "name", "x-title" => "Name", "description" => "Name, most recent and broadest"),
+ "name" => Array("type" => "string", "required" => true, "x-property" => "schema:name foaf:name", "x-title" => "Name", "description" => "Name, most recent and broadest"),
"shortName" => Array("type" => "string", "required" => false, "x-title" => "Short Name", "description" => "Name shortened, usually to an acronym"),
"foiEmail" => Array("type" => "string", "required" => false, "x-title" => "FOI Contact Email", "description" => "FOI contact email if not foi@"),
- "sameAs" => Array("type" => "array", "required" => false, "x-itemprop"=>"http://www.w3.org/2002/07/owl#sameAs","x-title" => "Same As", "description" => "Same as other URLs/URIs for this entity",
+ "sameAs" => Array("type" => "array", "required" => false, "x-property"=>"owl:sameAs","x-title" => "Same As", "description" => "Same as other URLs/URIs for this entity",
"items" => Array("type" => "string")),
"otherNames" => Array("type" => "array", "required" => true, "x-title" => "Past/Other Names", "description" => "Other names for organisation",
"items" => Array("type" => "string")),
- "foiBodies" => Array("type" => "array", "required" => true, "x-title" => "FOI Bodies","x-itemprop"=>"members", "description" => "Organisational units within this agency that are subject to FOI Act but are not autonomous",
+ "foiBodies" => Array("type" => "array", "required" => true, "x-title" => "FOI Bodies","x-property"=>"schema:members foaf:knows", "description" => "Organisational units within this agency that are subject to FOI Act but are not autonomous",
"items" => Array("type" => "string")),
"orgType" => Array("type" => "string", "required" => true, "x-title" => "Organisation Type", "description" => "Org type based on legal formation via FMA/CAC legislation etc."),
"parentOrg" => Array("type" => "string", "required" => true, "x-title" => "Parent Organisation", "description" => "Parent organisation, usually a department of state"),
- "website" => Array("type" => "string", "required" => true, "x-title" => "Website", "x-itemprop" => "url", "description" => "Website URL"),
+ "website" => Array("type" => "string", "required" => true, "x-title" => "Website", "x-property" => "schema:url foaf:homepage", "description" => "Website URL"),
"abn" => Array("type" => "string", "required" => true, "x-title" => "Australian Business Number", "description" => "ABN from business register"),
"contractListURL" => Array("type" => "string", "required" => true, "x-title" => "Contract Listing", "description" => "Departmental and agency contracts, <a href='http://www.aph.gov.au/senate/pubs/standing_orders/d05.htm'>mandated by the Senate</a>"),
"grantsReportingURL" => Array("type" => "string", "required" => true, "x-title" => "Grants Awarded",
--- a/scrape.py
+++ b/scrape.py
@@ -7,6 +7,61 @@
from urlparse import urljoin
import time
import os
+import mimetypes
+import re
+import urllib
+import urlparse
+
+def canonurl(url):
+ r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
+ if the URL looks invalid.
+ >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws
+ 'http://xn--hgi.ws/'
+ """
+ # strip spaces at the ends and ensure it's prefixed with 'scheme://'
+ url = url.strip()
+ if not url:
+ return ''
+ if not urlparse.urlsplit(url).scheme:
+ url = 'http://' + url
+
+ # turn it into Unicode
+ #try:
+ # url = unicode(url, 'utf-8')
+ #except UnicodeDecodeError:
+ # return '' # bad UTF-8 chars in URL
+
+ # parse the URL into its components
+ parsed = urlparse.urlsplit(url)
+ scheme, netloc, path, query, fragment = parsed
+
+ # ensure scheme is a letter followed by letters, digits, and '+-.' chars
+ if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I):
+ return ''
+ scheme = str(scheme)
+
+ # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port]
+ match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I)
+ if not match:
+ return ''
+ domain, port = match.groups()
+ netloc = domain + (port if port else '')
+ netloc = netloc.encode('idna')
+
+ # ensure path is valid and convert Unicode chars to %-encoded
+ if not path:
+ path = '/' # eg: 'http://google.com' -> 'http://google.com/'
+ path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;')
+
+ # ensure query is valid
+ query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/')
+
+ # ensure fragment is valid
+ fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8')))
+
+ # piece it all back together, truncating it to a maximum of 4KB
+ url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
+ return url[:4096]
#http://diveintopython.org/http_web_services/etags.html
class NotModifiedHandler(urllib2.BaseHandler):
@@ -16,14 +71,18 @@
return addinfourl
def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True):
- hash = hashlib.md5(url).hexdigest()
+ url = canonurl(url)
+ hash = hashlib.md5(url).hexdigest().encode("utf-8")
req = urllib2.Request(url)
print "Fetching %s" % url
+ if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "":
+ print "Not a valid HTTP url"
+ return (None,None)
doc = docsdb.get(hash)
if doc == None:
doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName}
else:
- if (time.time() - doc['page_scraped']) < 3600:
+ if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 999999):
print "Uh oh, trying to scrape URL again too soon!"
last_attachment_fname = doc["_attachments"].keys()[-1]
last_attachment = docsdb.get_attachment(doc,last_attachment_fname)
@@ -41,17 +100,23 @@
req.add_header("If-Modified-Since", doc['last_modified'])
opener = urllib2.build_opener(NotModifiedHandler())
- url_handle = opener.open(req)
- headers = url_handle.info() # the addinfourls have the .info() too
- doc['etag'] = headers.getheader("ETag")
- doc['last_modified'] = headers.getheader("Last-Modified")
- doc['date'] = headers.getheader("Date")
- doc['page_scraped'] = time.time()
- doc['web_server'] = headers.getheader("Server")
- doc['powered_by'] = headers.getheader("X-Powered-By")
- doc['file_size'] = headers.getheader("Content-Length")
- doc['mime_type'] = headers.getheader("Content-Type").split(";")[0]
- if hasattr(url_handle, 'code'):
+ try:
+ url_handle = opener.open(req)
+ headers = url_handle.info() # the addinfourls have the .info() too
+ doc['etag'] = headers.getheader("ETag")
+ doc['last_modified'] = headers.getheader("Last-Modified")
+ doc['date'] = headers.getheader("Date")
+ doc['page_scraped'] = time.time()
+ doc['web_server'] = headers.getheader("Server")
+ doc['powered_by'] = headers.getheader("X-Powered-By")
+ doc['file_size'] = headers.getheader("Content-Length")
+ content_type = headers.getheader("Content-Type")
+ if content_type != None:
+ doc['mime_type'] = content_type.split(";")[0]
+ else:
+ (type,encoding) = mimetypes.guess_type(url)
+ doc['mime_type'] = type
+ if hasattr(url_handle, 'code'):
if url_handle.code == 304:
print "the web page has not been modified"
return (None,None)
@@ -61,10 +126,15 @@
doc = docsdb.get(hash) # need to get a _rev
docsdb.put_attachment(doc, content, str(time.time())+"-"+os.path.basename(url), doc['mime_type'])
return (doc['mime_type'], content)
- #store as attachment epoch-filename
- else:
- print "error %s in downloading %s" % url_handle.code, URL
- doc['error'] = "error %s in downloading %s" % url_handle.code, URL
+ #store as attachment epoch-filename
+ except urllib2.URLError as e:
+ error = ""
+ if hasattr(e, 'reason'):
+ error = "error %s in downloading %s" % (str(e.reason), url)
+ elif hasattr(e, 'code'):
+ error = "error %s in downloading %s" % (e.code, url)
+ print error
+ doc['error'] = error
docsdb.save(doc)
return (None,None)
@@ -92,6 +162,12 @@
# lets not do external links for now
# linkurls.add(link['href'])
None
+ if link['href'].startswith("mailto"):
+ # not http
+ None
+ if link['href'].startswith("javascript"):
+ # not http
+ None
else:
linkurls.add(urljoin(url,link['href'].replace(" ","%20")))
for linkurl in linkurls:
@@ -108,9 +184,15 @@
agency = agencydb.get(row.id)
print agency['name']
for key in agency.keys():
- if key == 'website' or key.endswith('URL'):
- print key
- scrapeAndStore(docsdb, agency[key],agency['scrapeDepth'],key,agency['_id'])
- agency['metadata']['lastscraped'] = time.time()
+ if key == 'website':
+ scrapeAndStore(docsdb, agency[key],0,key,agency['_id'])
+ if key.endswith('URL'):
+ print key
+ depth = 1
+ if 'scrapeDepth' in agency.keys():
+ depth = agency['scrapeDepth']
+ scrapeAndStore(docsdb, agency[key],depth,key,agency['_id'])
+
+ agency['metadata']['lastScraped'] = time.time()
agencydb.save(agency)