<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | include_header_documents(""); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
echo "<table> | echo "<table> |
<tr><th>Agency Name</th><th>Disclosure Log URL recorded?</th><th>Do we monitor this URL?</th></tr>"; | <tr><th>Agency Name</th><th>Disclosure Log URL recorded?</th><th>Do we monitor this URL?</th></tr>"; |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$docsdb = $server->get_db('disclosr-documents'); | $docsdb = $server->get_db('disclosr-documents'); |
try { | try { |
$rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows; | $rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows; |
if ($rows) { | if ($rows) { |
foreach ($rows as $row) { | foreach ($rows as $row) { |
echo "<tr><td><b>" . $row->value->name . "</b> (".$row->id.")</td>\n"; | echo "<tr><td><b>" . $row->value->name . "</b>"; |
if ($ENV == "DEV") | |
echo "<td>"; | echo "<br>(" . $row->id . ")"; |
if (isset($row->value->FOIDocumentsURL)) { | echo "</td>\n"; |
echo '<a href="viewDocument.php?hash='.md5($row->value->FOIDocumentsURL).'">' | |
.$row->value->FOIDocumentsURL.'</a>'; | |
} else { | echo "<td>"; |
if (isset($row->value->FOIDocumentsURL)) { | |
echo '<a href="' . $row->value->FOIDocumentsURL . '">' | |
. $row->value->FOIDocumentsURL . '</a>'; | |
if ($ENV == "DEV") | |
echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">' | |
. 'view local copy</a>)</small>'; | |
} else { | |
echo "<font color='red'>✘</font>"; | echo "<font color='red'>✘</font>"; |
} | } |
echo "</td>\n<td>"; | echo "</td>\n<td>"; |
if (isset($row->value->FOIDocumentsURL)) { | if (isset($row->value->FOIDocumentsURL)) { |
if (file_exists("./scrapers/".$row->id.'.py')) { | if (file_exists("./scrapers/" . $row->id . '.py')) { |
echo "<font color='green'>✔</font>"; | echo "<font color='green'>✔</font>"; |
} else if (file_exists("./scrapers/".$row->id.'.txt')){ | } else if (file_exists("./scrapers/" . $row->id . '.txt')) { |
echo "<font color='blue'><b>▬</b></font>"; | echo "<font color='blue'><b>▬</b></font>"; |
} else { | } else { |
echo "<font color='red'>✘</font>"; | echo "<font color='red'>✘</font>"; |
} | } |
} | } |
echo "</td></tr>\n"; | echo "</td></tr>\n"; |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo "</table>"; | echo "</table>"; |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
import sys,os | import sys,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 |
import parsedatetime as pdt | import parsedatetime as pdt |
from time import mktime | from time import mktime |
from datetime import datetime | from datetime import datetime |
import feedparser | import feedparser |
import abc | import abc |
import unicodedata, re | import unicodedata, re |
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): | def remove_control_chars(self, input): |
return "".join([i for i in input if ord(i) in range(32, 127)]) | return "".join([i for i in input if ord(i) in range(32, 127)]) |
def getAgencyID(self): | def getAgencyID(self): |
""" disclosr agency id """ | """ disclosr agency id """ |
if self.agencyID == None: | if self.agencyID == None: |
self.agencyID = os.path.basename(sys.argv[0]).replace(".py","") | self.agencyID = os.path.basename(sys.argv[0]).replace(".py","") |
return self.agencyID | return self.agencyID |
def getURL(self): | def getURL(self): |
""" disclog URL""" | """ disclog URL""" |
if self.disclogURL == None: | if self.disclogURL == None: |
agency = scrape.agencydb.get(self.getAgencyID()) | agency = scrape.agencydb.get(self.getAgencyID()) |
self.disclogURL = agency['FOIDocumentsURL'] | self.disclogURL = agency['FOIDocumentsURL'] |
return self.disclogURL | return self.disclogURL |
@abc.abstractmethod | @abc.abstractmethod |
def doScrape(self): | def doScrape(self): |
""" do the scraping """ | """ do the scraping """ |
return | return |
@abc.abstractmethod | @abc.abstractmethod |
def getDescription(self, content, entry, doc): | def getDescription(self, content, entry, doc): |
""" get description""" | """ get description""" |
return | return |
class GenericRSSDisclogScraper(GenericDisclogScraper): | class GenericRSSDisclogScraper(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()) |
feed = feedparser.parse(content) | feed = feedparser.parse(content) |
for entry in feed.entries: | for entry in feed.entries: |
#print entry | #print entry |
print entry.id | print entry.id |
hash = scrape.mkhash(entry.id) | hash = scrape.mkhash(entry.id) |
#print hash | #print hash |
doc = foidocsdb.get(hash) | doc = foidocsdb.get(hash) |
#print doc | #print doc |
if doc == None: | if doc == None: |
print "saving" | print "saving" |
edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d") | edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d") |
doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id, | doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id, |
"date": edate,"title": entry.title} | "date": edate,"title": entry.title} |
self.getDescription(entry,entry, doc) | self.getDescription(entry,entry, doc) |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved" | print "already saved" |
def getDescription(self, content, entry, doc): | def getDescription(self, content, entry, doc): |
""" get description from rss entry""" | """ get description from rss entry""" |
doc.update({'description': content.summary}) | doc.update({'description': content.summary}) |
return | return |
class GenericOAICDisclogScraper(GenericDisclogScraper): | class GenericOAICDisclogScraper(GenericDisclogScraper): |
__metaclass__ = abc.ABCMeta | __metaclass__ = abc.ABCMeta |
@abc.abstractmethod | @abc.abstractmethod |
def getColumns(self,columns): | def getColumns(self,columns): |
""" rearranges columns if required """ | """ rearranges columns if required """ |
return | return |
def getColumnCount(self): | def getColumnCount(self): |
return 5 | return 5 |
def getDescription(self, content, entry, doc): | def getDescription(self, content, entry, doc): |
""" get description from rss entry""" | """ get description from rss entry""" |
descriptiontxt = "" | descriptiontxt = "" |
for string in content.stripped_strings: | for string in content.stripped_strings: |
descriptiontxt = descriptiontxt + " \n" + string | descriptiontxt = descriptiontxt + " \n" + string |
doc.update({'description': descriptiontxt}) | doc.update({'description': descriptiontxt}) |
return | return |
def getTitle(self, content, entry, doc): | |
doc.update({'title': content.string}) | |
return | |
def getTable(self, soup): | def getTable(self, soup): |
return soup.table | return soup.table |
def getDate(self, content, entry, doc): | |
dtresult = cal.parseDateText(content.string) | |
if len(dtresult) == 2: | |
(dtdate,dtr) = dtresult | |
edate = ""+str(dtdate[0])+'-'+str(dtdate[1])+'-'+str(dtdate[2]) | |
else: | |
edate = datetime.strptime(date.string.strip(), "%d %B %Y").strftime("%Y-%m-%d") | |
print edate | |
doc.update({'date': edate}) | |
return | |
def doScrape(self): | def doScrape(self): |
cal = pdt.Calendar() | cal = pdt.Calendar() |
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()) |
if content != None: | if content != None: |
if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": | if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": |
# http://www.crummy.com/software/BeautifulSoup/documentation.html | # http://www.crummy.com/software/BeautifulSoup/documentation.html |
soup = BeautifulSoup(content) | soup = BeautifulSoup(content) |
table = self.getTable(soup) | table = self.getTable(soup) |
for row in table.find_all('tr'): | for row in table.find_all('tr'): |
columns = row.find_all('td') | columns = row.find_all('td') |
if len(columns) == self.getColumnCount(): | if len(columns) == self.getColumnCount(): |
(id, date, description, title, notes) = self.getColumns(columns) | (id, date, description, title, notes) = self.getColumns(columns) |
print id.string | print id.string |
if id.string == None: | if id.string == None: |
hash = scrape.mkhash(self.remove_control_chars(url+date.string)) | hash = scrape.mkhash(self.remove_control_chars(url+date.string)) |
else: | else: |
hash = scrape.mkhash(self.remove_control_chars(url+id.string)) | hash = scrape.mkhash(self.remove_control_chars(url+id.string)) |
links = [] | links = [] |
for atag in row.find_all("a"): | for atag in row.find_all("a"): |
if atag.has_key('href'): | if atag.has_key('href'): |
links.append(scrape.fullurl(url,atag['href'])) | links.append(scrape.fullurl(url,atag['href'])) |
doc = foidocsdb.get(hash) | doc = foidocsdb.get(hash) |
if doc == None: | if doc == None: |
print "saving" | print "saving" |
dtresult = cal.parseDateText(date.string) | doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string} |
if len(dtresult) == 2: | |
(dtdate,dtr) = dtresult | |
print dtdate | |
edate = ""+str(dtdate[0])+'-'+str(dtdate[1])+'-'+str(dtdate[2]) | |
else: | |
edate = datetime.strptime(date.string.strip(), "%d %B %Y").strftime("%Y-%m-%d") | |
doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string, | |
"date": edate,"title": title.string} | |
if links != []: | if links != []: |
doc.update({'links': links}) | doc.update({'links': links}) |
self.getTitle(title,row, doc) | |
self.getDate(date,row, doc) | |
self.getDescription(description,row, doc) | self.getDescription(description,row, doc) |
if notes != None: | if notes != None: |
doc.update({ 'notes': notes.string}) | doc.update({ 'notes': notes.string}) |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved "+hash | print "already saved "+hash |
elif len(row.find_all('th')) == self.getColumnCount(): | elif len(row.find_all('th')) == 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 |
include_once('include/common.inc.php'); | include_once('include/common.inc.php'); |
function displayValue($key, $value, $mode) { | function displayValue($key, $value, $mode) { |
global $db, $schemas; | global $db, $schemas; |
if ($mode == "view") { | if ($mode == "view") { |
if (strpos($key, "_") === 0 || $key == "metadata") | if (strpos($key, "_") === 0 || $key == "metadata") |
return; | return; |
echo "<tr>"; | echo "<tr>"; |
echo "<td>"; | echo "<td>"; |
if (isset($schemas['agency']["properties"][$key])) { | if (isset($schemas['agency']["properties"][$key])) { |
echo $schemas['agency']["properties"][$key]['x-title'] . "<br><small>" . $schemas['agency']["properties"][$key]['description'] . "</small>"; | echo $schemas['agency']["properties"][$key]['x-title'] . "<br><small>" . $schemas['agency']["properties"][$key]['description'] . "</small>"; |
} | } |
echo "</td><td>"; | echo "</td><td>"; |
if (is_array($value)) { | if (is_array($value)) { |
echo "<ol>"; | echo "<ol>"; |
foreach ($value as $subkey => $subvalue) { | foreach ($value as $subkey => $subvalue) { |
echo "<li "; | echo "<li "; |
if (isset($schemas['agency']["properties"][$key]['x-property'])) { | if (isset($schemas['agency']["properties"][$key]['x-property'])) { |
echo ' property="' . $schemas['agency']["properties"][$key]['x-property'] . '" '; | echo ' property="' . $schemas['agency']["properties"][$key]['x-property'] . '" '; |
} if (isset($schemas['agency']["properties"][$key]['x-itemprop'])) { | } if (isset($schemas['agency']["properties"][$key]['x-itemprop'])) { |
echo ' itemprop="' . $schemas['agency']["properties"][$key]['x-itemprop'] . '" '; | echo ' itemprop="' . $schemas['agency']["properties"][$key]['x-itemprop'] . '" '; |
} | } |
echo " >"; | echo " >"; |
echo "$subvalue</li>"; | echo "$subvalue</li>"; |
} | } |
echo "</ol></td></tr>"; | echo "</ol></td></tr>"; |
} else { | } else { |
if (isset($schemas['agency']["properties"][$key]['x-property'])) { | if (isset($schemas['agency']["properties"][$key]['x-property'])) { |
echo '<span property="' . $schemas['agency']["properties"][$key]['x-property'] . '">'; | echo '<span property="' . $schemas['agency']["properties"][$key]['x-property'] . '">'; |
} else { | } else { |
echo "<span>"; | echo "<span>"; |
} | } |
if ((strpos($key, "URL") > 0 || $key == 'website') && $value != "") { | if ((strpos($key, "URL") > 0 || $key == 'website') && $value != "") { |
echo "<a " . ($key == 'website' ? 'itemprop="url"' : '') . " href='$value'>$value</a>"; | echo "<a " . ($key == 'website' ? 'itemprop="url"' : '') . " href='$value'>$value</a>"; |
} else if ($key == 'abn') { | } else if ($key == 'abn') { |
echo "<a href='http://www.abr.business.gov.au/SearchByAbn.aspx?SearchText=$value'>$value</a>"; | echo "<a href='http://www.abr.business.gov.au/SearchByAbn.aspx?SearchText=$value'>$value</a>"; |
} else { | } else { |
echo "$value"; | echo "$value"; |
} | } |
echo "</span>"; | echo "</span>"; |
} | } |
echo "</td></tr>"; | echo "</td></tr>"; |
} | } |
if ($mode == "edit") { | if ($mode == "edit") { |
if (is_array($value)) { | if (is_array($value)) { |
echo '<div class="row"> | echo '<div class="row"> |
<div class="seven columns"> | <div class="seven columns"> |
<fieldset> | <fieldset> |
<h5>' . $key . '</h5>'; | <h5>' . $key . '</h5>'; |
foreach ($value as $subkey => $subvalue) { | foreach ($value as $subkey => $subvalue) { |
echo "<label>$subkey</label><input class='input-text' type='text' id='$key$subkey' name='$key" . '[' . $subkey . "]' value='$subvalue'/></tr>"; | echo "<label>$subkey</label><input class='input-text' type='text' id='$key$subkey' name='$key" . '[' . $subkey . "]' value='$subvalue'/></tr>"; |
} | } |
echo "</fieldset> | echo "</fieldset> |
</div> | </div> |
</div>"; | </div>"; |
} else { | } else { |
if (strpos($key, "_") === 0) { | if (strpos($key, "_") === 0) { |
echo"<input type='hidden' id='$key' name='$key' value='$value'/>"; | echo"<input type='hidden' id='$key' name='$key' value='$value'/>"; |
} else if ($key == "parentOrg") { | } else if ($key == "parentOrg") { |
echo "<label for='$key'>$key</label><select id='$key' name='$key'><option value=''> Select... </option>"; | echo "<label for='$key'>$key</label><select id='$key' name='$key'><option value=''> Select... </option>"; |
$rows = $db->get_view("app", "byDeptStateName")->rows; | $rows = $db->get_view("app", "byDeptStateName")->rows; |
//print_r($rows); | //print_r($rows); |
foreach ($rows as $row) { | foreach ($rows as $row) { |
echo "<option value='{$row->value}'" . (($row->value == $value) ? "SELECTED" : "") . " >" . str_replace("Department of ", "", $row->key) . "</option>"; | echo "<option value='{$row->value}'" . (($row->value == $value) ? "SELECTED" : "") . " >" . str_replace("Department of ", "", $row->key) . "</option>"; |
} | } |
echo" </select>"; | echo" </select>"; |
} else { | } else { |
echo "<label>$key</label><input class='input-text' type='text' id='$key' name='$key' value='$value'/>"; | echo "<label>$key</label><input class='input-text' type='text' id='$key' name='$key' value='$value'/>"; |
if ((strpos($key, "URL") > 0 || $key == 'website') && $value != "") { | if ((strpos($key, "URL") > 0 || $key == 'website') && $value != "") { |
echo "<a " . ($key == 'website' ? 'itemprop="url"' : '') . " href='$value'>view</a>"; | echo "<a " . ($key == 'website' ? 'itemprop="url"' : '') . " href='$value'>view</a>"; |
} | } |
if ($key == 'abn') { | if ($key == 'abn') { |
echo "<a href='http://www.abr.business.gov.au/SearchByAbn.aspx?SearchText=$value'>view abn</a>"; | echo "<a href='http://www.abr.business.gov.au/SearchByAbn.aspx?SearchText=$value'>view abn</a>"; |
} | } |
} | } |
} | } |
} | } |
// | // |
} | } |
function addDefaultFields($row) { | function addDefaultFields($row) { |
global $schemas; | global $schemas; |
$defaultFields = array_keys($schemas['agency']['properties']); | $defaultFields = array_keys($schemas['agency']['properties']); |
foreach ($defaultFields as $defaultField) { | foreach ($defaultFields as $defaultField) { |
if (!isset($row[$defaultField])) { | if (!isset($row[$defaultField])) { |
if ($schemas['agency']['properties'][$defaultField]['type'] == "string") { | if ($schemas['agency']['properties'][$defaultField]['type'] == "string") { |
$row[$defaultField] = ""; | $row[$defaultField] = ""; |
} | } |
if ($schemas['agency']['properties'][$defaultField]['type'] == "array") { | if ($schemas['agency']['properties'][$defaultField]['type'] == "array") { |
$row[$defaultField] = Array(""); | $row[$defaultField] = Array(""); |
} | } |
} else if ($schemas['agency']['properties'][$defaultField]['type'] == "array") { | } |