[submodule "couchdb/couchdb-lucene"] | [submodule "couchdb/couchdb-lucene"] |
path = couchdb/couchdb-lucene | path = couchdb/couchdb-lucene |
url = https://github.com/rnewson/couchdb-lucene.git | url = https://github.com/rnewson/couchdb-lucene.git |
[submodule "couchdb/settee"] | |
path = couchdb/settee | |
url = https://github.com/inadarei/settee.git | |
[submodule "lib/php-diff"] | [submodule "lib/php-diff"] |
path = lib/php-diff | path = lib/php-diff |
url = https://github.com/chrisboulton/php-diff.git | url = https://github.com/chrisboulton/php-diff.git |
[submodule "lib/Requests"] | [submodule "lib/Requests"] |
path = lib/Requests | path = lib/Requests |
url = https://github.com/rmccue/Requests.git | url = https://github.com/rmccue/Requests.git |
[submodule "js/flotr2"] | [submodule "js/flotr2"] |
path = js/flotr2 | path = js/flotr2 |
url = https://github.com/HumbleSoftware/Flotr2.git | url = https://github.com/HumbleSoftware/Flotr2.git |
[submodule "lib/phpquery"] | [submodule "lib/phpquery"] |
path = lib/phpquery | path = lib/phpquery |
url = https://github.com/TobiaszCudnik/phpquery.git | url = https://github.com/TobiaszCudnik/phpquery.git |
[submodule "js/sigma"] | [submodule "js/sigma"] |
path = js/sigma | path = js/sigma |
url = https://github.com/jacomyal/sigma.js.git | url = https://github.com/jacomyal/sigma.js.git |
[submodule "js/bubbletree"] | [submodule "js/bubbletree"] |
path = js/bubbletree | path = js/bubbletree |
url = https://github.com/okfn/bubbletree.git | url = https://github.com/okfn/bubbletree.git |
[submodule "lib/querypath"] | [submodule "lib/querypath"] |
path = lib/querypath | path = lib/querypath |
url = https://github.com/technosophos/querypath.git | url = https://github.com/technosophos/querypath.git |
[submodule "lib/amon-php"] | [submodule "lib/amon-php"] |
path = lib/amon-php | path = lib/amon-php |
url = https://github.com/martinrusev/amon-php.git | url = https://github.com/martinrusev/amon-php.git |
[submodule "documents/lib/parsedatetime"] | [submodule "documents/lib/parsedatetime"] |
path = documents/lib/parsedatetime | path = documents/lib/parsedatetime |
url = git://github.com/bear/parsedatetime.git | url = git://github.com/bear/parsedatetime.git |
[submodule "lib/FeedWriter"] | |
path = lib/FeedWriter | |
url = https://github.com/mibe/FeedWriter | |
<?php | <?php |
include_once("../include/common.inc.php"); | include_once("../include/common.inc.php"); |
$format = "csv"; | $format = "csv"; |
//$format = "json"; | //$format = "json"; |
if (isset($_REQUEST['format'])) $format = $_REQUEST['format']; | if (isset($_REQUEST['format'])) |
$format = $_REQUEST['format']; | |
setlocale(LC_CTYPE, 'C'); | setlocale(LC_CTYPE, 'C'); |
if ($format == "csv") { | if ($format == "csv") { |
$headers = Array("name"); | $headers = Array("name"); |
} else { | } else { |
$headers = Array(); | $headers = Array(); |
} | } |
$db = $server->get_db('disclosr-agencies'); | $db = $server->get_db('disclosr-agencies'); |
try { | try { |
$rows = $db->get_view("app", "all", null, true)->rows; | $rows = $db->get_view("app", "all", null, true)->rows; |
$dataValues = Array(); | $dataValues = Array(); |
foreach ($rows as $row) { | foreach ($rows as $row) { |
if (isset($row->value->statistics->employees)) { | if (isset($row->value->statistics->employees)) { |
$headers = array_unique(array_merge($headers, array_keys(object_to_array($row->value->statistics->employees)))); | $headers = array_unique(array_merge($headers, array_keys(object_to_array($row->value->statistics->employees)))); |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
$fp = fopen('php://output', 'w'); | $fp = fopen('php://output', 'w'); |
if ($fp && $db) { | if ($fp && $db) { |
if ($format == "csv") { | if ($format == "csv") { |
header('Content-Type: text/csv; charset=utf-8'); | header('Content-Type: text/csv; charset=utf-8'); |
header('Content-Disposition: attachment; filename="export.employeestats.' . date("c") . '.csv"'); | header('Content-Disposition: attachment; filename="export.employeestats.' . date("c") . '.csv"'); |
} | } |
header('Pragma: no-cache'); | header('Pragma: no-cache'); |
header('Expires: 0'); | header('Expires: 0'); |
if ($format == "csv") { | if ($format == "csv") { |
fputcsv($fp, $headers); | fputcsv($fp, $headers); |
} else if ($format == "json") { | } else if ($format == "json") { |
echo '{ | echo '{ |
"labels" : ["' . implode('","', $headers) . '"],'.PHP_EOL; | "labels" : ["' . implode('","', $headers) . '"],' . PHP_EOL; |
} | } |
try { | try { |
$agencies = $db->get_view("app", "all", null, true)->rows; | $agencies = $db->get_view("app", "all", null, true)->rows; |
//print_r($agencies); | //print_r($agencies); |
$first = true; | $first = true; |
if ($format == "json") { | if ($format == "json") { |
echo '"data" : ['.PHP_EOL; | echo '"data" : [' . PHP_EOL; |
} | } |
foreach ($agencies as $agency) { | foreach ($agencies as $agency) { |
if (isset($agency->value->statistics->employees)) { | if (isset($agency->value->statistics->employees)) { |
$row = Array(); | $row = Array(); |
$agencyEmployeesArray = object_to_array($agency->value->statistics->employees); | $agencyEmployeesArray = object_to_array($agency->value->statistics->employees); |
foreach ($headers as $i => $fieldName) { | foreach ($headers as $i => $fieldName) { |
if ($format == "csv") { | |
if (isset($agencyEmployeesArray[$fieldName])) { | |
$row[] = $agencyEmployeesArray[$fieldName]["value"] ; | |
} else if ($i == 0) { | |
$row[] = $agency->value->name; | |
} else { | |
$row[] = 0; | |
} | |
} else if ($format == "json") { | |
if (isset($agencyEmployeesArray[$fieldName])) { | if (isset($agencyEmployeesArray[$fieldName])) { |
$row[] = '['.$i.','.$agencyEmployeesArray[$fieldName]["value"].']'; | $row[] = '[' . $i . ',' . $agencyEmployeesArray[$fieldName]["value"] . ']'; |
} else { | } else { |
$row[] = '['.$i.',0]'; | $row[] = '[' . $i . ',0]'; |
} | } |
} | |
} | } |
if ($format == "csv") { | if ($format == "csv") { |
fputcsv($fp, array_values($row)); | fputcsv($fp, array_values($row)); |
} else if ($format == "json") { | } else if ($format == "json") { |
if (!$first) echo ","; | if (!$first) |
echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "'.$agency->value->name.'", "lines" : { "show" : true }, "points" : { "show" : true }}'.PHP_EOL; | echo ","; |
echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "' . $agency->value->name . '", "lines" : { "show" : true }, "points" : { "show" : true }}' . PHP_EOL; | |
$first = false; | $first = false; |
} | } |
} | } |
} | } |
if ($format == "json") { | if ($format == "json") { |
echo '] | echo '] |
}'.PHP_EOL; | }' . PHP_EOL; |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
die; | die; |
} | } |
?> | ?> |
<?php | <?php |
require_once '../include/common.inc.php'; | require_once '../include/common.inc.php'; |
$db = $server->get_db('disclosr-agencies'); | $db = $server->get_db('disclosr-agencies'); |
$rows = $db->get_view("app", "byName")->rows; | $rows = $db->get_view("app", "byName")->rows; |
$nametoid = Array(); | $nametoid = Array(); |
$sums = Array(); | $sums = Array(); |
foreach ($rows as $row) { | foreach ($rows as $row) { |
$nametoid[trim($row->key)] = $row->value; | $nametoid[trim($row->key)] = $row->value; |
} | } |
$employeeCSVs = Array("2002-2003" => "0203apsemployees.csv", | $employeeCSVs = Array("2002-2003" => "0203apsemployees.csv", |
"2003-2004" => "0304apsemployees.csv", | "2003-2004" => "0304apsemployees.csv", |
"2004-2005" => "0405apsemployees.csv", | "2004-2005" => "0405apsemployees.csv", |
"2005-2006" => "0506apsemployees.csv", | "2005-2006" => "0506apsemployees.csv", |
"2006-2007" => "0607apsemployees.csv", | "2006-2007" => "0607apsemployees.csv", |
"2007-2008" => "0708apsemployees.csv", | "2007-2008" => "0708apsemployees.csv", |
"2008-2009" => "0809apsemployees.csv", | "2008-2009" => "0809apsemployees.csv", |
"2009-2010" => "0910apsemployees.csv", | "2009-2010" => "0910apsemployees.csv", |
"2010-2011" => "1011apsemployees.csv" | "2010-2011" => "1011apsemployees.csv" |
); | ); |
foreach ($employeeCSVs as $timePeriod => $employeeCSV) { | foreach ($employeeCSVs as $timePeriod => $employeeCSV) { |
echo $employeeCSV . "<br>" . PHP_EOL; | echo $employeeCSV . "<br>" . PHP_EOL; |
$row = 1; | $row = 1; |
if (($handle = fopen($employeeCSV, "r")) !== FALSE) { | if (($handle = fopen($employeeCSV, "r")) !== FALSE) { |
while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) { | while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) { |
//print_r($data); | //print_r($data); |
$name = trim($data[0]); | $name = trim($data[0]); |
if (isset($nametoid[$name])) { | if (isset($nametoid[$name])) { |
$id = $nametoid[$name]; | $id = $nametoid[$name]; |
//echo $id . "<br>" . PHP_EOL; | //echo $id . "<br>" . PHP_EOL; |
@$sums[$id][$timePeriod] += $data[1]; | @$sums[$id][$timePeriod] += $data[1]; |
} else { | } else { |
echo "<br>ERROR NAME MISSING FROM ID LIST<br><bR>" . PHP_EOL; | echo "<br>ERROR NAME MISSING FROM ID LIST<br><bR>" . PHP_EOL; |
die(); | die(); |
} | } |
} | } |
fclose($handle); | fclose($handle); |
} | } |
} | } |
foreach ($sums as $id => $sum) { | foreach ($sums as $id => $sum) { |
echo $id . "<br>" . PHP_EOL; | echo $id . "<br>" . PHP_EOL; |
$doc = $db->get($id); | $doc = $db->get($id); |
echo $doc->name . "<br>" . PHP_EOL; | echo $doc->name . "<br>" . PHP_EOL; |
// print_r($doc); | // print_r($doc); |
$changed = false; | $changed = false; |
if (!isset($doc->statistics)) { | if (!isset($doc->statistics)) { |
$changed = true; | $changed = true; |
$doc->statistics = Array(); | $doc->statistics = new stdClass(); |
} | |
if (!isset($doc->statistics->employees)) { | |
$changed = true; | |
$doc->statistics->employees = new stdClass(); | |
} | } |
foreach ($sum as $timePeriod => $value) { | foreach ($sum as $timePeriod => $value) { |
if (!isset($doc->statistics->employees->$timePeriod->value) | if (!isset($doc->statistics->employees->$timePeriod->value) |
|| $doc->statistics->employees->$timePeriod->value != $value) { | || $doc->statistics->employees->$timePeriod->value != $value) { |
$changed = true; | $changed = true; |
$doc->statistics["employees"][$timePeriod] = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/"); | $doc->statistics->employees->$timePeriod = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/"); |
} | } |
} | } |
if ($changed) { | if ($changed) { |
$db->save($doc); | $db->save($doc); |
} else { | } else { |
echo "not changed" . "<br>" . PHP_EOL; | echo "not changed" . "<br>" . PHP_EOL; |
} | } |
} | } |
// employees: timeperiod, source = apsc state of service, value | // employees: timeperiod, source = apsc state of service, value |
?> | ?> |
<?php | |
require_once '../include/common.inc.php'; | |
require($basePath . 'lib/phpquery/phpQuery/phpQuery.php'); | |
$db = $server->get_db('disclosr-agencies'); | |
$rows = $db->get_view("app", "byName")->rows; | |
$nametoid = Array(); | |
$sums = Array(); | |
$functions = Array(); | |
foreach ($rows as $row) { | |
$nametoid[trim($row->key)] = $row->value; | |
} | |
$request = Requests::get("http://www.apsc.gov.au/publications-and-media/parliamentary/state-of-the-service/new-sosr/appendix-2-aps-agencies"); | |
$doc = phpQuery::newDocumentHTML($request->body); | |
phpQuery::selectDocument($doc); | |
foreach (pq('tr')->elements as $tr) { | |
//echo $tr->nodeValue.PHP_EOL; | |
$agency = ""; | |
$employees = ""; | |
$function = ""; | |
$i = 0; | |
foreach ($tr->childNodes as $td) { | |
//echo $td->nodeValue." $i <br>"; | |
if ($i == 0) | |
$agency = $td->nodeValue; | |
if ($i == 2) { | |
$employees = trim(str_replace(",", "", $td->nodeValue)); | |
} | |
if ($i == 4) { | |
$function = $td->nodeValue; | |
} | |
$i++; | |
} | |
if ($agency != "" && $employees != "" && $function != "") { | |
$name = trim(str_replace('2','',$agency)); | |
//echo "$name<br><bR>" . PHP_EOL; | |
if (isset($nametoid[$name])) { | |
$id = $nametoid[$name]; | |
//echo $id . "<br>" . PHP_EOL; | |
@$sums[$id]["2011-2012"] += $employees; | |
$functions[$id] = $function; | |
} else if ($agency != "Agency"){ | |
echo "<br>ERROR NAME '$agency' MISSING FROM ID LIST<br><bR>" . PHP_EOL; | |
die(); | |
} | |
} else { | |
echo "skipped $agency"; | |
} | |
} | |
//print_r($sums); | |
foreach ($sums as $id => $sum) { | |
echo $id . "<br>" . PHP_EOL; | |
$doc = $db->get($id); | |
echo $doc->name . "<br>" . PHP_EOL; | |
// print_r($doc); | |
$changed = false; | |
if (!isset($doc->statistics)) { | |
$changed = true; | |
$doc->statistics = new stdClass(); | |
} | |
if (!isset($doc->statistics->employees)) { | |
$changed = true; | |
$doc->statistics->employees = new stdClass(); | |
} | |
foreach ($sum as $timePeriod => $value) { | |
if (!isset($doc->statistics->employees->$timePeriod->value) | |
|| $doc->statistics->employees->$timePeriod->value != $value) { | |
$changed = true; | |
$doc->statistics->employees->$timePeriod = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/"); | |
$doc->employees = $value; | |
$doc->functionClassification = $functions[$id]; | |
} | |
} | |
if ($changed) { | |
$db->save($doc); | |
} else { | |
echo "not changed" . "<br>" . PHP_EOL; | |
} | |
} | |
// employees: timeperiod, source = apsc state of service, value | |
?> | |
<?php | <?php |
require_once '../include/common.inc.php'; | require_once '../include/common.inc.php'; |
//function createFOIDocumentsDesignDoc() { | //function createFOIDocumentsDesignDoc() { |
$foidb = $server->get_db('disclosr-foidocuments'); | $foidb = $server->get_db('disclosr-foidocuments'); |
$obj = new stdClass(); | $obj = new stdClass(); |
$obj->_id = "_design/" . urlencode("app"); | $obj->_id = "_design/" . urlencode("app"); |
$obj->language = "javascript"; | $obj->language = "javascript"; |
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; | $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) { emit(doc.date, doc); };"; |
$obj->views->byDate->reduce = "_count"; | $obj->views->byDate->reduce = "_count"; |
$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };"; | $obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };"; |
$obj->views->byAgencyID->reduce = "_count"; | $obj->views->byDateMonthYear->reduce = "_count"; |
$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };"; | |
$obj->views->byAgencyID->reduce = "_count"; | |
// allow safe updates (even if slightly slower due to extra: rev-detection check). | // allow safe updates (even if slightly slower due to extra: rev-detection check). |
$foidb->save($obj, true); | $foidb->save($obj, true); |
function createDocumentsDesignDoc() { | //function createDocumentsDesignDoc() { |
/* | $docdb = $server->get_db('disclosr-documents'); |
global $db; | |
$obj = new stdClass(); | $obj = new stdClass(); |
$obj->_id = "_design/" . urlencode("app"); | $obj->_id = "_design/" . urlencode("app"); |
$obj->language = "javascript"; | $obj->language = "javascript"; |
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; | $obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}"; |
$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; | $obj->views->web_server->reduce = "function (key, values, rereduce) {\n return sum(values);\n}"; |
"views": { | $obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}"; |
"web_server": { | $obj->views->byAgency->reduce = "function (key, values, rereduce) {\n return sum(values);\n}"; |
"map": "function(doc) {\n emit(doc.web_server, 1);\n}", | $obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}"; |
"reduce": "function (key, values, rereduce) {\n return sum(values);\n}" | $obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}"; |
}, | $obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}"; |
"byAgency": { | $obj->views->getValidationRequired = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"; |
"map": "function(doc) {\n emit(doc.agencyID, 1);\n}", | |
"reduce": "function (key, values, rereduce) {\n return sum(values);\n}" | |
}, | |
"byURL": { | |
"map": "function(doc) {\n emit(doc.url, doc);\n}" | |
}, | |
"agency": { | |
"map": "function(doc) {\n emit(doc.agencyID, doc);\n}" | |
}, | |
"byWebServer": { | |
"map": "function(doc) {\n emit(doc.web_server, doc);\n}" | |
}, | |
"getValidationRequired": { | |
"map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}" | |
} | |
} */ | |
} | |
//function createAgencyDesignDoc() { | //function createAgencyDesignDoc() { |
$db = $server->get_db('disclosr-agencies'); | $db = $server->get_db('disclosr-agencies'); |
$obj = new stdClass(); | $obj = new stdClass(); |
$obj->_id = "_design/" . urlencode("app"); | $obj->_id = "_design/" . urlencode("app"); |
$obj->language = "javascript"; | $obj->language = "javascript"; |
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; | $obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; |
$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; | $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; |
$obj->views->byCanonicalName->map = "function(doc) { | $obj->views->byCanonicalName->map = "function(doc) { |
if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') { | if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') { |
emit(doc.name, doc); | emit(doc.name, doc); |
} | } |
};"; | };"; |
$obj->views->byDeptStateName->map = "function(doc) { | $obj->views->byDeptStateName->map = "function(doc) { |
if (doc.orgType == 'FMA-DepartmentOfState') { | if (doc.orgType == 'FMA-DepartmentOfState') { |
emit(doc.name, doc._id); | emit(doc.name, doc._id); |
} | } |
};"; | };"; |
$obj->views->parentOrgs->map = "function(doc) { | $obj->views->parentOrgs->map = "function(doc) { |
if (doc.parentOrg) { | if (doc.parentOrg) { |
emit(doc._id, doc.parentOrg); | emit(doc._id, doc.parentOrg); |
} | } |
};"; | };"; |
$obj->views->byName->map = 'function(doc) { | $obj->views->byName->map = 'function(doc) { |
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { | if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { |
emit(doc.name, doc._id); | emit(doc.name, doc._id); |
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) { | if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) { |
emit(doc.shortName, doc._id); | emit(doc.shortName, doc._id); |
} | } |
for (name in doc.otherNames) { | for (name in doc.otherNames) { |
if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) { | if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) { |
emit(doc.otherNames[name], doc._id); | emit(doc.otherNames[name], doc._id); |
} | } |
} | } |
for (name in doc.foiBodies) { | for (name in doc.foiBodies) { |
if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) { | if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) { |
emit(doc.foiBodies[name], doc._id); | emit(doc.foiBodies[name], doc._id); |
} | } |
} | } |
for (name in doc.positions) { | for (name in doc.positions) { |
if (doc.positions[name] != "" && doc.positions[name] != doc.name) { | if (doc.positions[name] != "" && doc.positions[name] != doc.name) { |
emit(doc.positions[name], doc._id); | emit(doc.positions[name], doc._id); |
} | } |
} | } |
} | } |
};'; | };'; |
$obj->views->foiEmails->map = "function(doc) { | $obj->views->foiEmails->map = "function(doc) { |
emit(doc._id, doc.foiEmail); | emit(doc._id, doc.foiEmail); |
};"; | };"; |
$obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }"; | $obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }"; |
$obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };'; | $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };'; |
$obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };'; | $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };'; |
$obj->views->getScrapeRequired->map = "function(doc) { | $obj->views->getScrapeRequired->map = "function(doc) { |
var lastScrape = Date.parse(doc.metadata.lastScraped); | var lastScrape = Date.parse(doc.metadata.lastScraped); |
var today = new Date(); | var today = new Date(); |
if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) { | if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) { |
emit(doc._id, doc); | emit(doc._id, doc); |
} | } |
};"; | };"; |
$obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };"; | $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };"; |
$obj->views->getConflicts->map = "function(doc) { | $obj->views->getConflicts->map = "function(doc) { |
if (doc._conflicts) { | if (doc._conflicts) { |
emit(null, [doc._rev].concat(doc._conflicts)); | emit(null, [doc._rev].concat(doc._conflicts)); |
} | } |
}"; | }"; |
// http://stackoverflow.com/questions/646628/javascript-startswith | // http://stackoverflow.com/questions/646628/javascript-startswith |
$obj->views->score->map = 'if(!String.prototype.startsWith){ | $obj->views->score->map = 'if(!String.prototype.startsWith){ |
String.prototype.startsWith = function (str) { | String.prototype.startsWith = function (str) { |
return !this.indexOf(str); | return !this.indexOf(str); |
} | } |
} | } |
function(doc) { | function(doc) { |
count = 0; | count = 0; |
if (doc["status"] != "suspended") { | if (doc["status"] != "suspended") { |
for(var propName in doc) { | for(var propName in doc) { |
if(typeof(doc[propName]) != "undefined" && doc[propName] != "") { | if(typeof(doc[propName]) != "undefined" && doc[propName] != "") { |
count++; | count++; |
} | } |
} | } |
portfolio = doc.parentOrg; | portfolio = doc.parentOrg; |
if (doc.orgType == "FMA-DepartmentOfState") { | if (doc.orgType == "FMA-DepartmentOfState") { |
portfolio = doc._id; | portfolio = doc._id; |
} | } |
if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") { | if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") { |
portfolio = doc.orgType; | portfolio = doc.orgType; |
} | } |
emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio}); | emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio}); |
} | } |
}'; | }'; |
$obj->views->scoreHas->map = 'if(!String.prototype.startsWith){ | $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){ |
String.prototype.startsWith = function (str) { | String.prototype.startsWith = function (str) { |
return !this.indexOf(str); | return !this.indexOf(str); |
} | } |
} | } |
if(!String.prototype.endsWith){ | if(!String.prototype.endsWith){ |
String.prototype.endsWith = function(suffix) { | String.prototype.endsWith = function(suffix) { |
return this.indexOf(suffix, this.length - suffix.length) !== -1; | return this.indexOf(suffix, this.length - suffix.length) !== -1; |
}; | }; |
} | } |
function(doc) { | function(doc) { |
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { | if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { |
for(var propName in doc) { | for(var propName in doc) { |
if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) { | if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) { |
emit(propName, 1); | emit(propName, 1); |
} | } |
} | } |
emit("total", 1); | emit("total", 1); |
} | } |
}'; | }'; |
$obj->views->scoreHas->reduce = 'function (key, values, rereduce) { | $obj->views->scoreHas->reduce = 'function (key, values, rereduce) { |
return sum(values); | return sum(values); |
}'; | }'; |
$obj->views->fieldNames->map = ' | $obj->views->fieldNames->map = ' |
function(doc) { | function(doc) { |
for(var propName in doc) { | for(var propName in doc) { |
emit(propName, doc._id); | emit(propName, doc._id); |
} | } |
}'; | }'; |
$obj->views->fieldNames->reduce = 'function (key, values, rereduce) { | $obj->views->fieldNames->reduce = 'function (key, values, rereduce) { |
return values.length; | return values.length; |
}'; | }'; |
// allow safe updates (even if slightly slower due to extra: rev-detection check). | // allow safe updates (even if slightly slower due to extra: rev-detection check). |
$db->save($obj, true); | $db->save($obj, true); |
?> | ?> |
<?php | |
/** | |
* Databaase class. | |
*/ | |
class SetteeDatabase { | |
/** | |
* Base URL of the CouchDB REST API | |
*/ | |
private $conn_url; | |
/** | |
* HTTP REST Client instance | |
*/ | |
protected $rest_client; | |
/** | |
* Name of the database | |
*/ | |
private $dbname; | |
/** | |
* Default constructor | |
*/ | |
function __construct($conn_url, $dbname) { | |
$this->conn_url = $conn_url; | |
$this->dbname = $dbname; | |
$this->rest_client = SetteeRestClient::get_instance($this->conn_url); | |
} | |
/** | |
* Get UUID from CouchDB | |
* | |
* @return | |
* CouchDB-generated UUID string | |
* | |
*/ | |
function gen_uuid() { | |
$ret = $this->rest_client->http_get('_uuids'); | |
return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking | |
} | |
/** | |
* Create or update a document database | |
* | |
* @param $document | |
* PHP object, a PHP associative array, or a JSON String representing the document to be saved. PHP Objects and arrays are JSON-encoded automatically. | |
* | |
* <p>If $document has a an "_id" property set, it will be used as document's unique id (even for "create" operation). | |
* If "_id" is missing, CouchDB will be used to generate a UUID. | |
* | |
* <p>If $document has a "_rev" property (revision), document will be updated, rather than creating a new document. | |
* You have to provide "_rev" if you want to update an existing document, otherwise operation will be assumed to be | |
* one of creation and you will get a duplicate document exception from CouchDB. Also, you may not provide "_rev" but | |
* not provide "_id" since that is an invalid input. | |
* | |
* @param $allowRevAutoDetection | |
* Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision | |
* for a document and use it. This option is "false" by default because it involves an extra http HEAD request and | |
* therefore can make save() operation slightly slower if such auto-detection is not required. | |
* | |
* @return | |
* document object with the database id (uuid) and revision attached; | |
* | |
* @throws SetteeCreateDatabaseException | |
*/ | |
function save($document, $allowRevAutoDetection = false) { | |
if (is_string($document)) { | |
$document = json_decode($document); | |
} | |
// Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter) | |
if(is_array($document)) { | |
$document = (object) $document; | |
} | |
if (empty($document->_id) && empty($document->_rev)) { | |
$id = $this->gen_uuid(); | |
} | |
elseif (empty($document->_id) && !empty($document->_rev)) { | |
throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id"); | |
} | |
else { | |
$id = $document->_id; | |
if ($allowRevAutoDetection) { | |
try { | |
$rev = $this->get_rev($id); | |
} catch (SetteeRestClientException $e) { | |
// auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error | |
} | |
if (!empty($rev)) { | |
$document->_rev = $rev; | |
} | |
} | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | |
$document_json = json_encode($document, JSON_NUMERIC_CHECK); | |
$ret = $this->rest_client->http_put($full_uri, $document_json); | |
$document->_id = $ret['decoded']->id; | |
$document->_rev = $ret['decoded']->rev; | |
return $document; | |
} | |
/** | |
* @param $doc | |
* @param $name | |
* @param $content | |
* Content of the attachment in a string-buffer format. This function will automatically base64-encode content for | |
* you, so you don't have to do it. | |
* @param $mime_type | |
* Optional. Will be auto-detected if not provided | |
* @return void | |
*/ | |
public function add_attachment($doc, $name, $content, $mime_type = null) { | |
if (empty($doc->_attachments) || !is_object($doc->_attachments)) { | |
$doc->_attachments = new stdClass(); | |
} | |
if (empty($mime_type)) { | |
$mime_type = $this->rest_client->content_mime_type($content); | |
} | |
$doc->_attachments->$name = new stdClass(); | |
$doc->_attachments->$name->content_type = $mime_type; | |
$doc->_attachments->$name->data = base64_encode($content); | |
} | |
/** | |
* @param $doc | |
* @param $name | |
* @param $file | |
* Full path to a file (e.g. as returned by PHP's realpath function). | |
* @param $mime_type | |
* Optional. Will be auto-detected if not provided | |
* @return void | |
*/ | |
public function add_attachment_file($doc, $name, $file, $mime_type = null) { | |
$content = file_get_contents($file); | |
$this->add_attachment($doc, $name, $content, $mime_type); | |
} | |
/** | |
* | |
* Retrieve a document from CouchDB | |
* | |
* @throws SetteeWrongInputException | |
* | |
* @param $id | |
* Unique ID (usually: UUID) of the document to be retrieved. | |
* @return | |
* database document in PHP object format. | |
*/ | |
function get($id) { | |
if (empty($id)) { | |
throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | |
$full_uri = str_replace("%3Frev%3D","?rev=",$full_uri); | |
$ret = $this->rest_client->http_get($full_uri); | |
return $ret['decoded']; | |
} | |
/** | |
* | |
* Get the latest revision of a document with document id: $id in CouchDB. | |
* | |
* @throws SetteeWrongInputException | |
* | |
* @param $id | |
* Unique ID (usually: UUID) of the document to be retrieved. | |
* @return | |
* database document in PHP object format. | |
*/ | |
function get_rev($id) { | |
if (empty($id)) { | |
throw new SetteeWrongInputException("Error: Can't query a document without a uuid."); | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | |
$headers = $this->rest_client->http_head($full_uri); | |
if (empty($headers['Etag'])) { | |
throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag"); | |
} | |
$etag = str_replace('"', '', $headers['Etag']); | |
return $etag; | |
} | |
/** | |
* Delete a document | |
* | |
* @param $document | |
* a PHP object or JSON representation of the document that has _id and _rev fields. | |
* | |
* @return void | |
*/ | |
function delete($document) { | |
if (!is_object($document)) { | |
$document = json_decode($document); | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($document->_id) . "?rev=" . $document->_rev; | |
$this->rest_client->http_delete($full_uri); | |
} | |
/*----------------- View-related functions --------------*/ | |
/** | |
* Create a new view or update an existing one. | |
* | |
* @param $design_doc | |
* @param $view_name | |
* @param $map_src | |
* Source code of the map function in Javascript | |
* @param $reduce_src | |
* Source code of the reduce function in Javascript (optional) | |
* @return void | |
*/ | |
function save_view($design_doc, $view_name, $map_src, $reduce_src = null) { | |
$obj = new stdClass(); | |
$obj->_id = "_design/" . urlencode($design_doc); | |
$view_name = urlencode($view_name); | |
$obj->views->$view_name->map = $map_src; | |
if (!empty($reduce_src)) { | |
$obj->views->$view_name->reduce = $reduce_src; | |
} | |
// allow safe updates (even if slightly slower due to extra: rev-detection check). | |
return $this->save($obj, true); | |
} | |
/** | |
* Create a new view or update an existing one. | |
* | |
* @param $design_doc | |
* @param $view_name | |
* @param $key | |
* key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes | |
* that first element is startkey, second: endkey. | |
* @param $descending | |
* return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change | |
* order you also need to swap startkey and endkey values! | |
* | |
* @return void | |
*/ | |
function get_view($design_doc, $view_name, $key = null, $descending = false) { | |
$id = "_design/" . urlencode($design_doc); | |
$view_name = urlencode($view_name); | |
$id .= "/_view/$view_name"; | |
$data = array(); | |
if (!empty($key)) { | |
if (is_string($key)) { | |
$data = "key=" . '"' . $key . '"'; | |
} | |
elseif (is_array($key)) { | |
list($startkey, $endkey) = $key; | |
$data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"'; | |
} | |
if ($descending) { | |
$data .= "&descending=true"; | |
} | |
} | |
if (empty($id)) { | |
throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | |
$full_uri = str_replace("%253Fgroup%253Dtrue","?group=true",$full_uri); | |
$ret = $this->rest_client->http_get($full_uri, $data); | |
return $ret['decoded']; | |
} | |
/** | |
* @param $id | |
* @return | |
* return a properly url-encoded id. | |
*/ | |
private function safe_urlencode($id) { | |
//-- System views like _design can have "/" in their URLs. | |
$id = rawurlencode($id); | |
if (substr($id, 0, 1) == '_') { | |
$id = str_replace('%2F', '/', $id); | |
} | |
return $id; | |
} | |
/** Getter for a database name */ | |
function get_name() { | |
return $this->dbname; | |
} | |
} |
*.pyc |
<?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'); |
$agencies = 0; | $agencies = 0; |
$disclogs = 0; | $disclogs = 0; |
$red = 0; | $red = 0; |
$green = 0; | $green = 0; |
$yellow = 0; | |
$orange = 0; | $orange = 0; |
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 $row) { |
if ((!isset($row->value->status) || $row->value->status != "suspended") && isset($row->value->foiEmail)) { | |
echo "<tr><td>"; | |
if (isset($row->value->website)) echo "<a href='" . $row->value->website . "'>"; | |
echo "<b>" . $row->value->name . "</b>"; | |
if (isset($row->value->website)) echo "</a>"; | |
if ($ENV == "DEV") | |
echo "<br>(" . $row->id . ")"; | |
echo "</td>\n"; | |
$agencies++; | |
echo "<tr><td><b>" . $row->value->name . "</b>"; | echo "<td>"; |
if ($ENV == "DEV") | if (isset($row->value->FOIDocumentsURL)) { |
echo "<br>(" . $row->id . ")"; | $disclogs++; |
echo "</td>\n"; | echo '<a href="' . $row->value->FOIDocumentsURL . '">' |
$agencies++; | . $row->value->FOIDocumentsURL . '</a>'; |
if ($ENV == "DEV") | |
echo "<td>"; | echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">' |
if (isset($row->value->FOIDocumentsURL)) { | . 'view local copy</a>)</small>'; |
$disclogs++; | } else { |
echo '<a href="' . $row->value->FOIDocumentsURL . '">' | echo "<font color='red'><abbr title='No'>✘</abbr></font>"; |
. $row->value->FOIDocumentsURL . '</a>'; | } |
if ($ENV == "DEV") | echo "</td>\n<td>"; |
echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">' | if (isset($row->value->FOIDocumentsURL)) { |
. 'view local copy</a>)</small>'; | if (file_exists("./scrapers/" . $row->id . '.py')) { |
} else { | echo "<font color='green'><abbr title='Yes'>✔</abbr></font>"; |
echo "<font color='red'>✘</font>"; | $green++; |
} else if (file_exists("./scrapers/" . $row->id . '.txt')) { | |
if (trim(file_get_contents("./scrapers/" . $row->id . '.txt')) == "no disclog") { | |
echo "<font color='yellow'><abbr title='No log table exists at URL to scrape'><b>◎</b></abbr></font>"; | |
$yellow++; | |
} else { | |
echo file_get_contents("./scrapers/" . $row->id . '.txt'); | |
echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>"; | |
$orange++; | |
} | |
} else { | |
echo "<font color='red'><abbr title='No'>✘</abbr></font>"; | |
$red++; | |
} | |
} | |
echo "</td></tr>\n"; | |
} | } |
echo "</td>\n<td>"; | |
if (isset($row->value->FOIDocumentsURL)) { | |
if (file_exists("./scrapers/" . $row->id . '.py')) { | |
echo "<font color='green'>✔</font>"; | |
$green++; | |
} else if (file_exists("./scrapers/" . $row->id . '.txt')) { | |
echo "<font color='orange'><b>▬</b></font>"; | |
$orange++; | |
} else { | |
echo "<font color='red'>✘</font>"; | |
$red++; | |
} | |
} | |
echo "</td></tr>\n"; | |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo "</table>"; | echo "</table>"; |
echo $agencies." agencies ".(($disclogs/$agencies)*100)."% with disclosure logs, ".(($green/$disclogs)*100)."% with scrapers ".(($red/$disclogs)*100)."% without scrapers ".(($orange/$disclogs)*100)."% WIP scrapers "; | echo $agencies . " agencies, " . round(($disclogs / $agencies) * 100) . "% with disclosure logs; " |
. round(($green / $disclogs) * 100) . "% logs with scrapers " . round(($red / $disclogs) * 100) . "% logs without scrapers " . round(($orange / $disclogs) * 100) . "% logs Work-In-Progress scrapers "; | |
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 |
from time import mktime | from time import mktime |
import feedparser | import feedparser |
import abc | import abc |
import unicodedata, re | import unicodedata, re |
import dateutil | import dateutil |
from dateutil.parser import * | from dateutil.parser import * |
from datetime import * | from datetime import * |
import codecs | |
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 "+ hash | print "saving "+ hash |
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): | def getTitle(self, content, entry, doc): |
doc.update({'title': (''.join(content.stripped_strings))}) | doc.update({'title': (''.join(content.stripped_strings))}) |
return | return |
def getTable(self, soup): | def getTable(self, soup): |
return soup.table | return soup.table |
def getRows(self, table): | def getRows(self, table): |
return table.find_all('tr') | return table.find_all('tr') |
def getDate(self, content, entry, doc): | def getDate(self, content, entry, doc): |
date = ''.join(content.stripped_strings).strip() | date = ''.join(content.stripped_strings).strip() |
date = str.replace("Octber","October",date) | (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") | edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") |
print edate | print edate |
doc.update({'date': edate}) | doc.update({'date': edate}) |
return | return |
def getLinks(self, content, entry, doc): | def getLinks(self, content, entry, doc): |
links = [] | links = [] |
for atag in entry.find_all("a"): | for atag in entry.find_all("a"): |
if atag.has_key('href'): | if atag.has_key('href'): |
links.append(scrape.fullurl(content,atag['href'])) | links.append(scrape.fullurl(content,atag['href'])) |
if links != []: | if links != []: |
doc.update({'links': links}) | doc.update({'links': links}) |
return | return |
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()) |
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 self.getRows(table): | for row in self.getRows(table): |
columns = row.find_all('td') | columns = row.find_all('td') |
if len(columns) == self.getColumnCount(): | if len(columns) == self.getColumnCount(): |
(id, date, title, description, notes) = self.getColumns(columns) | (id, date, title, description, notes) = self.getColumns(columns) |
print ''.join(id.stripped_strings) | print self.remove_control_chars(''.join(id.stripped_strings)) |
if id.string == None: | if id.string == None: |
hash = scrape.mkhash(self.remove_control_chars(url+(''.join(date.stripped_strings)))) | hash = scrape.mkhash(self.remove_control_chars(url+(''.join(date.stripped_strings)))) |
else: | else: |
hash = scrape.mkhash(self.remove_control_chars(url+(''.join(id.stripped_strings)))) | hash = scrape.mkhash(self.remove_control_chars(url+(''.join(id.stripped_strings)))) |
doc = foidocsdb.get(hash) | doc = foidocsdb.get(hash) |
if doc == None: | if doc == None: |
print "saving " +hash | print "saving " +hash |
doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': (''.join(id.stripped_strings))} | doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': (''.join(id.stripped_strings))} |
self.getLinks(self.getURL(),row,doc) | self.getLinks(self.getURL(),row,doc) |
self.getTitle(title,row, doc) | self.getTitle(title,row, doc) |
self.getDate(date,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': (''.join(notes.stripped_strings))}) | doc.update({ 'notes': (''.join(notes.stripped_strings))}) |
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('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'); |
$startkey = (isset($_REQUEST['start_key']) ? $_REQUEST['start_key'] : '9999-99-99'); | |
?> | ?> |
<?php | <?php |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$idtoname = Array(); | $idtoname = Array(); |
foreach ($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'); |
try { | try { |
$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00'), true)->rows; | $rows = $foidocsdb->get_view("app", "byDate", Array($startkey, '0000-00-00'), true, 20)->rows; |
if ($rows) { | if ($rows) { |
foreach ($rows as $row) { | foreach ($rows as $key => $row) { |
displayLogEntry($row,$idtoname); | echo displayLogEntry($row, $idtoname); |
$endkey = $row->key; | |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo "<a href='?start_key=$endkey'>next page</a>"; | |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
# www.robotstxt.org/ | # www.robotstxt.org/ |
# http://code.google.com/web/controlcrawlindex/ | # http://code.google.com/web/controlcrawlindex/ |
User-agent: * | User-agent: * |
Disallow: /admin/ | |
Sitemap: http://disclosurelo.gs/sitemap.xml.php |
<?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.php"); | include("../lib/FeedWriter/FeedTypes.php"); |
include_once('../include/common.inc.php'); | |
//Creating an instance of FeedWriter class. | //Creating an instance of FeedWriter class. |
$TestFeed = new FeedWriter(RSS2); | $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('Last Modified - All'); | $TestFeed->setTitle('Last Modified - All'); |
$TestFeed->setLink('http://disclosr.lambdacomplex.org/rss.xml.php'); | $TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'); |
$TestFeed->setDescription('This is test of creating a RSS 2.0 feed Universal Feed Writer'); | $TestFeed->setDescription('This is test of creating a RSS 2.0 feed Universal Feed Writer'); |
$TestFeed->setChannelElement('language', 'en-us'); | |
$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time())); | |
//Retriving informations from database | //Retriving informations from database |
$rows = $db->get_view("app", "byLastModified")->rows; | $idtoname = Array(); |
$agenciesdb = $server->get_db('disclosr-agencies'); | |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | |
$idtoname[$row->id] = trim($row->value->name); | |
} | |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | |
$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00'), true)->rows; | |
//print_r($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['name']); | $newItem->setTitle($row->value->title); |
$newItem->setLink($row['id']); | $newItem->setLink("view.php?id=".$row->value->docID); |
$newItem->setDate(date("c", $row['metadata']['lastModified'])); | $newItem->setDate(date("c", strtotime($row->value->date))); |
$newItem->setDescription($row['name']); | $newItem->setDescription(displayLogEntry($row,$idtoname)); |
$newItem->addElement('guid', $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->genarateFeed(); | $TestFeed->generateFeed(); |
?> | ?> |
multipage | |
docx | |
ACMA style | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
multipage log | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "cphMain_C001_Col01").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "inner_content") | |
def getColumnCount(self): | |
return 2 | |
def getColumns(self,columns): | |
(date, title) = columns | |
return (date, date, title, title, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 3 | |
def getColumns(self,columns): | |
(id, title, date) = columns | |
return (id, date, title, title, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
aspx |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
import dateutil | |
from dateutil.parser import * | |
from datetime import * | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
si = ScraperImplementation() | |
si.doScrape() | |
parent | |
no disclog | |
no disclog | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(id, date, title, description) = columns | |
return (id, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(date, title, description,notes) = columns | |
return (title, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
see parent dhs | no disclog |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
import dateutil | |
from dateutil.parser import * | |
from datetime import * | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
si = ScraperImplementation() | |
si.doScrape() | |
si.disclogURL = "http://www.fahcsia.gov.au/disclosure-log-2011-12-financial-year" | |
si.doScrape() | |
si.disclogURL = "http://www.fahcsia.gov.au/disclosure-log-2010-11-financial-year" | |
si.doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id="node-30609") | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
list style | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 3 | |
def getColumns(self,columns): | |
(id, date, description) = columns | |
return (id, date, description, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#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): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
import dateutil | |
from dateutil.parser import * | |
from datetime import * | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
si = ScraperImplementation() | |
si.doScrape() | |
weird div based log with tables of links | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "content-middle").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "cphMain_C001_Col01").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
no disclog | |
acma style |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 3 | |
def getColumns(self,columns): | |
(date, title, description) = columns | |
return (date, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getTitle(self, content, entry, doc): | |
doc.update({'title': content.stripped_strings.next()}) | |
return | |
def getColumnCount(self): | |
return 3 | |
def getColumns(self,columns): | |
(date, id, description) = columns | |
return (id, date, description, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
multiple pages | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
import codecs | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class NewScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getDescription(self,content, entry,doc): | |
link = None | |
links = [] | |
description = "" | |
for atag in entry.find_all('a'): | |
if atag.has_key('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": | |
# http://www.crummy.com/software/BeautifulSoup/documentation.html | |
soup = BeautifulSoup(htcontent) | |
for text in soup.find(id="divFullWidthColumn").stripped_strings: | |
description = description + text.encode('ascii', 'ignore') | |
for atag in soup.find(id="divFullWidthColumn").find_all("a"): | |
if atag.has_key('href'): | |
links.append(scrape.fullurl(link,atag['href'])) | |
if links != []: | |
doc.update({'links': links}) | |
if description != "": | |
doc.update({ 'description': description}) | |
def getColumnCount(self): | |
return 2 | |
def getTable(self,soup): | |
return soup.find(id = "TwoColumnSorting") | |
def getColumns(self,columns): | |
( title, date) = columns | |
return (title, date, title, title, None) | |
class OldScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getDescription(self,content, entry,doc): | |
link = None | |
links = [] | |
description = "" | |
for atag in entry.find_all('a'): | |
if atag.has_key('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": | |
# http://www.crummy.com/software/BeautifulSoup/documentation.html | |
soup = BeautifulSoup(htcontent) | |
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'): | |
links.append(scrape.fullurl(link,atag['href'])) | |
if links != []: | |
doc.update({'links': links}) | |
if description != "": | |
doc.update({ 'description': description}) | |
if links != []: | |
doc.update({'links': links}) | |
if description != "": | |
doc.update({ 'description': description}) | |
def getColumnCount(self): | |
return 2 | |
def getTable(self,soup): | |
return soup.find(class_ = "doc-list") | |
def getColumns(self,columns): | |
(date, title) = columns | |
return (title, date, title, title, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(NewScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(NewScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
#NewScraperImplementation().doScrape() | |
print 'Subclass:', issubclass(OldScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(OldScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
osi = OldScraperImplementation() | |
osi.disclogURL = "http://archive.treasury.gov.au/content/foi_publications.asp?year=-1&abstract=0&classification=&=&titl=Disclosure+Log+-+Documents+Released+Under+FOI" | |
osi.doScrape() | |
# old site too | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
import dateutil | |
from dateutil.parser import * | |
from datetime import * | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
si = ScraperImplementation() | |
si.doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(id, date, title, description) = columns | |
return (id, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(id, date,logdate, description) = columns | |
return (id, date, description, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
acma style | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 3 | |
def getColumns(self,columns): | |
(date, title, description) = columns | |
return (date, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id="ctl00_ContentPlaceHolderMainNoAjax_EdtrTD1494_2").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(blank,id, title,date) = columns | |
return (id, date, title, title, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
multipage immi | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "ctl00_PlaceHolderMain_Content__ControlWrapper_RichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
# does not have any disclog entries or table | no disclog |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(id, date, title, description) = columns | |
return (id, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(summary="This table shows every FOI request to date.") | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog yet | no disclog |
no log | no disclog |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "ctl00_PlaceHolderMain_ctl01__ControlWrapper_RichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(summary="This table lists the schedule of upcoming courses.") | |
def getColumnCount(self): | |
return 7 | |
def getColumns(self,columns): | |
(id, date, title, description,link,deldate,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#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): | |
(id, date, title, description,link,deldate,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
acma style |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 6 | |
def getColumns(self,columns): | |
(id, date, title, description,deldate, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 5 | |
def getColumns(self,columns): | |
(id, date, title, description,notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "inner_content") | |
def getColumnCount(self): | |
return 2 | |
def getColumns(self,columns): | |
(date, title) = columns | |
return (date, date, title, title, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
#def getTable(self,soup): | |
# return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table | |
def getColumnCount(self): | |
return 4 | |
def getColumns(self,columns): | |
(id, title, date, description) = columns | |
return (id, date, title, description, None) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id = "ctl00_PlaceHolderMain_PublishingPageContent__ControlWrapper_RichHtmlField").table | |
def getColumnCount(self): | |
return 7 | |
def getColumns(self,columns): | |
(id, date, title, description,link,deldate, notes) = columns | |
return (id, date, title, description, notes) | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
<?php | |
include ('../include/common.inc.php'); | |
$last_updated = date('Y-m-d', @filemtime('cbrfeed.zip')); | |
header("Content-Type: text/xml"); | |
echo "<?xml version='1.0' encoding='UTF-8'?>"; | |
echo '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' . "\n"; | |
echo " <url><loc>" . local_url() . "index.php</loc><priority>1.0</priority></url>\n"; | |
foreach (scandir("./") as $file) { | |
if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php") | |
echo " <url><loc>" . local_url() . "$file</loc><priority>0.6</priority></url>\n"; | |
} | |
$db = $server->get_db('disclosr-foidocuments'); | |
try { | |
$rows = $db->get_view("app", "all")->rows; | |
foreach ($rows as $row) { | |
echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n"; | |
} | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
echo '</urlset>'; | |
?> | |
<?php | <?php |
function include_header_documents($title) { | function include_header_documents($title) { |
?> | ?> |
<!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"> |
<!-- Use the .htaccess and remove these lines to avoid edge case issues. | <!-- Use the .htaccess and remove these lines to avoid edge case issues. |
More info: h5bp.com/i/378 --> | More info: h5bp.com/i/378 --> |
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> | <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> |
<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"> |
<!-- 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>© Company 2012</p> | <p>© Company 2012</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 displayLogEntry($row, $idtoname) { | function displayLogEntry($row, $idtoname) { |
echo "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2> <p>".str_replace("\n","<br>",$row->value->description); | $result = ""; |
$result .= "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2> <p>".str_replace("\n","<br>",$row->value->description); | |
if (isset($row->value->notes)) { | if (isset($row->value->notes)) { |
echo " <br>Note: ".$row->value->notes; | $result .= " <br>Note: ".$row->value->notes; |
} | } |
echo "</p>"; | $result .= "</p>"; |
if (isset($row->value->links)){ | if (isset($row->value->links)){ |
echo "<h3>Links/Documents</h3><ul>"; | $result .= "<h3>Links/Documents</h3><ul>"; |
foreach ($row->value->links as $link) { | foreach ($row->value->links as $link) { |
echo "<li><a href='$link'>".$link."</a></li>"; | $result .= "<li><a href='$link'>".$link."</a></li>"; |
} | } |
echo "</ul>"; | $result .= "</ul>"; |
} | } |
echo "<small><A href='".$row->value->url."'>View original source...</a> ID: ".$row->value->docID."</small>"; | $result .= "<small><A href='".$row->value->url."'>View original source...</a> ID: ".strip_tags($row->value->docID)."</small>"; |
echo"</div>"; | $result .= "</div>"; |
return $result; | |
} | } |
<?php | |
include('template.inc.php'); | |
include_header_documents(""); | |
include_once('../include/common.inc.php'); | |
?> | |
<?php | |
$agenciesdb = $server->get_db('disclosr-agencies'); | |
$idtoname = Array(); | |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | |
$idtoname[$row->id] = trim($row->value->name); | |
} | |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | |
try { | |
$obj = new stdClass(); | |
$obj->value = $foidocsdb->get($_REQUEST['id']); | |
echo displayLogEntry($obj,$idtoname); | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
include_footer_documents(); | |
?> | |
<?php | |
/** | |
* Univarsel Feed Writer | |
* | |
* FeedItem class - Used as feed element in FeedWriter class | |
* | |
* @package UnivarselFeedWriter | |
* @author Anis uddin Ahmad <anisniit@gmail.com> | |
* @link http://www.ajaxray.com/projects/rss | |
*/ | |
class FeedItem | |
{ | |
private $elements = array(); //Collection of feed elements | |
private $version; | |
/** | |
* Constructor | |
* | |
* @param contant (RSS1/RSS2/ATOM) RSS2 is default. | |
*/ | |
function __construct($version = RSS2) | |
{ | |
$this->version = $version; | |
} | |
/** | |
* Add an element to elements array | |
* | |
* @access public | |
* @param srting The tag name of an element | |
* @param srting The content of tag | |
* @param array Attributes(if any) in 'attrName' => 'attrValue' format | |
* @return void | |
*/ | |
public function addElement($elementName, $content, $attributes = null) | |
{ | |
$this->elements[$elementName]['name'] = $elementName; | |
$this->elements[$elementName]['content'] = $content; | |
$this->elements[$elementName]['attributes'] = $attributes; | |
} | |
/** | |
* Set multiple feed elements from an array. | |
* Elements which have attributes cannot be added by this method | |
* | |
* @access public | |
* @param array array of elements in 'tagName' => 'tagContent' format. | |
* @return void | |
*/ | |
public function addElementArray($elementArray) | |
{ | |
if(! is_array($elementArray)) return; | |
foreach ($elementArray as $elementName => $content) | |
{ | |
$this->addElement($elementName, $content); | |
} | |
} | |
/** | |
* Return the collection of elements in this feed item | |
* | |
* @access public | |
* @return array | |
*/ | |
public function getElements() | |
{ | |
return $this->elements; | |
} | |
// Wrapper functions ------------------------------------------------------ | |
/** | |
* Set the 'dscription' element of feed item | |
* | |
* @access public | |
* @param string The content of 'description' element | |
* @return void | |
*/ | |
public function setDescription($description) | |
{ | |
$tag = ($this->version == ATOM)? 'summary' : 'description'; | |
$this->addElement($tag, $description); | |
} | |
/** | |
* @desc Set the 'title' element of feed item | |
* @access public | |
* @param string The content of 'title' element | |
* @return void | |
*/ | |
public function setTitle($title) | |
{ | |
$this->addElement('title', $title); | |
} | |
/** | |
* Set the 'date' element of feed item | |
* | |
* @access public | |
* @param string The content of 'date' element | |
* @return void | |
*/ | |
public function setDate($date) | |
{ | |
if(! is_numeric($date)) | |
{ | |
$date = strtotime($date); | |
} | |
if($this->version == ATOM) | |
{ | |
$tag = 'updated'; | |
$value = date(DATE_ATOM, $date); | |
} | |
elseif($this->version == RSS2) | |
{ | |
$tag = 'pubDate'; | |
$value = date(DATE_RSS, $date); | |
} | |
else | |
{ | |
$tag = 'dc:date'; | |
$value = date("Y-m-d", $date); | |
} | |
$this->addElement($tag, $value); | |
} | |
/** | |
* Set the 'link' element of feed item | |
* | |
* @access public | |
* @param string The content of 'link' element | |
* @return void | |
*/ | |
public function setLink($link) | |
{ | |
if($this->version == RSS2 || $this->version == RSS1) | |
{ | |
$this->addElement('link', $link); | |
} | |
else | |
{ | |
$this->addElement('link','',array('href'=>$link)); | |
$this->addElement('id', FeedWriter::uuid($link,'urn:uuid:')); | |
} | |
} | |
/** | |
* Set the 'encloser' element of feed item | |
* For RSS 2.0 only | |
* | |
* @access public | |
* @param string The url attribute of encloser tag | |
* @param string The length attribute of encloser tag | |
* @param string The type attribute of encloser tag | |
* @return void | |
*/ | |
public function setEncloser($url, $length, $type) | |
{ | |
$attributes = array('url'=>$url, 'length'=>$length, 'type'=>$type); | |
$this->addElement('enclosure','',$attributes); | |
} | |
} // end of class FeedItem | |
?> | |
<?php | |
// RSS 0.90 Officially obsoleted by 1.0 | |
// RSS 0.91, 0.92, 0.93 and 0.94 Officially obsoleted by 2.0 | |
// So, define constants for RSS 1.0, RSS 2.0 and ATOM | |
define('RSS1', 'RSS 1.0', true); | |
define('RSS2', 'RSS 2.0', true); | |
define('ATOM', 'ATOM', true); | |
/** | |
* Univarsel Feed Writer class | |
* | |
* Genarate RSS 1.0, RSS2.0 and ATOM Feed | |
* | |
* @package UnivarselFeedWriter | |
* @author Anis uddin Ahmad <anisniit@gmail.com> | |
* @link http://www.ajaxray.com/projects/rss | |
*/ | |
class FeedWriter | |
{ | |
private $channels = array(); // Collection of channel elements | |
private $items = array(); // Collection of items as object of FeedItem class. | |
private $data = array(); // Store some other version wise data | |
private $CDATAEncoding = array(); // The tag names which have to encoded as CDATA | |
private $version = null; | |
/** | |
* Constructor | |
* | |
* @param constant the version constant (RSS1/RSS2/ATOM). | |
*/ | |
function __construct($version = RSS2) | |
{ | |
$this->version = $version; | |
// Setting default value for assential channel elements | |
$this->channels['title'] = $version . ' Feed'; | |
$this->channels['link'] = 'http://www.ajaxray.com/blog'; | |
//Tag names to encode in CDATA | |
$this->CDATAEncoding = array('description', 'content:encoded', 'summary'); | |
} | |
// Start # public functions --------------------------------------------- | |
/** | |
* Set a channel element | |
* @access public | |
* @param srting name of the channel tag | |
* @param string content of the channel tag | |
* @return void | |
*/ | |
public function setChannelElement($elementName, $content) | |
{ | |
$this->channels[$elementName] = $content ; | |
} | |
/** | |
* Set multiple channel elements from an array. Array elements | |
* should be 'channelName' => 'channelContent' format. | |
* | |
* @access public | |
* @param array array of channels | |
* @return void | |
*/ | |
public function setChannelElementsFromArray($elementArray) | |
{ | |
if(! is_array($elementArray)) return; | |
foreach ($elementArray as $elementName => $content) | |
{ | |
$this->setChannelElement($elementName, $content); | |
} | |
} | |
/** | |
* Genarate the actual RSS/ATOM file | |
* | |
* @access public | |
* @return void | |
*/ | |
public function genarateFeed() | |
{ | |
header("Content-type: text/xml"); | |
$this->printHead(); | |
$this->printChannels(); | |
$this->printItems(); | |
$this->printTale(); | |
} | |
/** | |
* Create a new FeedItem. | |
* | |
* @access public | |
* @return object instance of FeedItem class | |
*/ | |
public function createNewItem() | |
{ | |
$Item = new FeedItem($this->version); | |
return $Item; | |
} | |
/** | |
* Add a FeedItem to the main class | |
* | |
* @access public | |
* @param object instance of FeedItem class | |
* @return void | |
*/ | |
public function addItem($feedItem) | |
{ | |
$this->items[] = $feedItem; | |
} | |
// Wrapper functions ------------------------------------------------------------------- | |
/** | |
* Set the 'title' channel element | |
* | |
* @access public | |
* @param srting value of 'title' channel tag | |
* @return void | |
*/ | |
public function setTitle($title) | |
{ | |
$this->setChannelElement('title', $title); | |
} | |
/** | |
* Set the 'description' channel element | |
* | |
* @access public | |
* @param srting value of 'description' channel tag | |
* @return void | |
*/ | |
public function setDescription($desciption) | |
{ | |
$this->setChannelElement('description', $desciption); | |
} | |
/** | |
* Set the 'link' channel element | |
* | |
* @access public | |
* @param srting value of 'link' channel tag | |
* @return void | |
*/ | |
public function setLink($link) | |
{ | |
$this->setChannelElement('link', $link); | |
} | |
/** | |
* Set the 'image' channel element | |
* | |
* @access public | |
* @param srting title of image | |
* @param srting link url of the imahe | |
* @param srting path url of the image | |
* @return void | |
*/ | |
public function setImage($title, $link, $url) | |
{ | |
$this->setChannelElement('image', array('title'=>$title, 'link'=>$link, 'url'=>$url)); | |
} | |
/** | |
* Set the 'about' channel element. Only for RSS 1.0 | |
* | |
* @access public | |
* @param srting value of 'about' channel tag | |
* @return void | |
*/ | |
public function setChannelAbout($url) | |
{ | |
$this->data['ChannelAbout'] = $url; | |
} | |
/** | |
* Genarates an UUID | |
* @author Anis uddin Ahmad <admin@ajaxray.com> | |
* @param string an optional prefix | |
* @return string the formated uuid | |
*/ | |
public function uuid($key = null, $prefix = '') | |
{ | |
$key = ($key == null)? uniqid(rand()) : $key; | |
$chars = md5($key); | |
$uuid = substr($chars,0,8) . '-'; | |
$uuid .= substr($chars,8,4) . '-'; | |
$uuid .= substr($chars,12,4) . '-'; | |
$uuid .= substr($chars,16,4) . '-'; | |
$uuid .= substr($chars,20,12); | |
return $prefix . $uuid; | |
} | |
// End # public functions ---------------------------------------------- | |
// Start # private functions ---------------------------------------------- | |
/** | |
* Prints the xml and rss namespace | |
* | |
* @access private | |
* @return void | |
*/ | |
private function printHead() | |
{ | |
$out = '<?xml version="1.0" encoding="utf-8"?>' . "\n"; | |
if($this->version == RSS2) | |
{ | |
$out .= '<rss version="2.0" | |
xmlns:content="http://purl.org/rss/1.0/modules/content/" | |
xmlns:wfw="http://wellformedweb.org/CommentAPI/" | |
>' . PHP_EOL; | |
} | |
elseif($this->version == RSS1) | |
{ | |
$out .= '<rdf:RDF | |
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" | |
xmlns="http://purl.org/rss/1.0/" | |
xmlns:dc="http://purl.org/dc/elements/1.1/" | |
>' . PHP_EOL;; | |
} | |
else if($this->version == ATOM) | |
{ | |
$out .= '<feed xmlns="http://www.w3.org/2005/Atom">' . PHP_EOL;; | |
} | |
echo $out; | |
} | |
/** | |
* Closes the open tags at the end of file | |
* | |
* @access private | |
* @return void | |
*/ | |
private function printTale() | |
{ | |
if($this->version == RSS2) | |
{ | |
echo '</channel>' . PHP_EOL . '</rss>'; | |
} | |
elseif($this->version == RSS1) | |
{ | |
echo '</rdf:RDF>'; | |
} | |
else if($this->version == ATOM) | |
{ | |
echo '</feed>'; | |
} | |
} | |
/** | |
* Creates a single node as xml format | |
* | |
* @access private | |
* @param srting name of the tag | |
* @param mixed tag value as string or array of nested tags in 'tagName' => 'tagValue' format | |
* @param array Attributes(if any) in 'attrName' => 'attrValue' format | |
* @return string formatted xml tag | |
*/ | |
private function makeNode($tagName, $tagContent, $attributes = null) | |
{ | |
$nodeText = ''; | |
$attrText = ''; | |
if(is_array($attributes)) | |
{ | |
foreach ($attributes as $key => $value) | |
{ | |
$attrText .= " $key=\"$value\" "; | |
} | |
} | |
if(is_array($tagContent) && $this->version == RSS1) | |
{ | |
$attrText = ' rdf:parseType="Resource"'; | |
} | |
$attrText .= (in_array($tagName, $this->CDATAEncoding) && $this->version == ATOM)? ' type="html" ' : ''; | |
$nodeText .= (in_array($tagName, $this->CDATAEncoding))? "<{$tagName}{$attrText}><![CDATA[" : "<{$tagName}{$attrText}>"; | |
if(is_array($tagContent)) | |
{ | |
foreach ($tagContent as $key => $value) | |
{ | |
$nodeText .= $this->makeNode($key, $value); | |
} | |
} | |
else | |
{ | |
$nodeText .= (in_array($tagName, $this->CDATAEncoding))? $tagContent : htmlentities($tagContent); | |
} | |
$nodeText .= (in_array($tagName, $this->CDATAEncoding))? "]]></$tagName>" : "</$tagName>"; | |
return $nodeText . PHP_EOL; | |
} | |
/** | |
* @desc Print channels | |
* @access private | |
* @return void | |
*/ | |
private function printChannels() | |
{ | |
//Start channel tag | |
switch ($this->version) | |
{ | |
case RSS2: | |
echo '<channel>' . PHP_EOL; | |
break; | |
case RSS1: | |
echo (isset($this->data['ChannelAbout']))? "<channel rdf:about=\"{$this->data['ChannelAbout']}\">" : "<channel rdf:about=\"{$this->channels['link']}\">"; | |
break; | |
} | |
//Print Items of channel | |
foreach ($this->channels as $key => $value) | |
{ | |
if($this->version == ATOM && $key == 'link') | |
{ | |
// ATOM prints link element as href attribute | |
echo $this->makeNode($key,'',array('href'=>$value)); | |
//Add the id for ATOM | |
echo $this->makeNode('id',$this->uuid($value,'urn:uuid:')); | |
} | |
else | |
{ | |
echo $this->makeNode($key, $value); | |
} | |
} | |
//RSS 1.0 have special tag <rdf:Seq> with channel | |
if($this->version == RSS1) | |
{ | |
echo "<items>" . PHP_EOL . "<rdf:Seq>" . PHP_EOL; | |
foreach ($this->items as $item) | |
{ | |
$thisItems = $item->getElements(); | |
echo "<rdf:li resource=\"{$thisItems['link']['content']}\"/>" . PHP_EOL; | |
} | |
echo "</rdf:Seq>" . PHP_EOL . "</items>" . PHP_EOL . "</channel>" . PHP_EOL; | |
} | |
} | |
/** | |
* Prints formatted feed items | |
* | |
* @access private | |
* @return void | |
*/ | |
private function printItems() | |
{ | |
foreach ($this->items as $item) | |
{ | |
$thisItems = $item->getElements(); | |
//the argument is printed as rdf:about attribute of item in rss 1.0 | |
echo $this->startItem($thisItems['link']['content']); | |
foreach ($thisItems as $feedItem ) | |
{ | |
echo $this->makeNode($feedItem['name'], $feedItem['content'], $feedItem['attributes']); | |
} | |
echo $this->endItem(); | |
} | |
} | |
/** | |
* Make the starting tag of channels | |
* | |
* @access private | |
* @param srting The vale of about tag which is used for only RSS 1.0 | |
* @return void | |
*/ | |
private function startItem($about = false) | |
{ | |
if($this->version == RSS2) | |
{ | |
echo '<item>' . PHP_EOL; | |
} | |
elseif($this->version == RSS1) | |
{ | |
if($about) | |
{ | |
echo "<item rdf:about=\"$about\">" . PHP_EOL; | |
} | |
else | |
{ | |
die('link element is not set .\n It\'s required for RSS 1.0 to be used as about attribute of item'); | |
} | |
} | |
else if($this->version == ATOM) | |
{ | |
echo "<entry>" . PHP_EOL; | |
} | |
} | |
/** | |
* Closes feed item tag | |
* | |
* @access private | |
* @return void | |
*/ | |
private function endItem() | |
{ | |
if($this->version == RSS2 || $this->version == RSS1) | |
{ | |
echo '</item>' . PHP_EOL; | |
} | |
else if($this->version == ATOM) | |
{ | |
echo "</entry>" . PHP_EOL; | |
} | |
} | |
// End # private functions ---------------------------------------------- | |
} // end of class FeedWriter | |
// autoload classes | |
function __autoload($class_name) | |
{ | |
require_once $class_name . '.php'; | |
} |