rm settee
Former-commit-id: 2fe3d86753e524fca7ee4e095a794727c0556d79
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,9 +1,6 @@
[submodule "couchdb/couchdb-lucene"]
path = couchdb/couchdb-lucene
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"]
path = lib/php-diff
url = https://github.com/chrisboulton/php-diff.git
@@ -31,4 +28,7 @@
[submodule "documents/lib/parsedatetime"]
path = documents/lib/parsedatetime
url = git://github.com/bear/parsedatetime.git
+[submodule "lib/FeedWriter"]
+ path = lib/FeedWriter
+ url = https://github.com/mibe/FeedWriter
--- a/admin/exportEmployees.csv.php
+++ b/admin/exportEmployees.csv.php
@@ -4,7 +4,8 @@
$format = "csv";
//$format = "json";
-if (isset($_REQUEST['format'])) $format = $_REQUEST['format'];
+if (isset($_REQUEST['format']))
+ $format = $_REQUEST['format'];
setlocale(LC_CTYPE, 'C');
if ($format == "csv") {
$headers = Array("name");
@@ -21,7 +22,6 @@
if (isset($row->value->statistics->employees)) {
$headers = array_unique(array_merge($headers, array_keys(object_to_array($row->value->statistics->employees))));
-
}
}
} catch (SetteeRestClientException $e) {
@@ -40,15 +40,14 @@
fputcsv($fp, $headers);
} else if ($format == "json") {
echo '{
- "labels" : ["' . implode('","', $headers) . '"],'.PHP_EOL;
+ "labels" : ["' . implode('","', $headers) . '"],' . PHP_EOL;
}
try {
$agencies = $db->get_view("app", "all", null, true)->rows;
//print_r($agencies);
$first = true;
if ($format == "json") {
- echo '"data" : ['.PHP_EOL;
-
+ echo '"data" : [' . PHP_EOL;
}
foreach ($agencies as $agency) {
@@ -56,25 +55,35 @@
$row = Array();
$agencyEmployeesArray = object_to_array($agency->value->statistics->employees);
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])) {
- $row[] = '['.$i.','.$agencyEmployeesArray[$fieldName]["value"].']';
+ $row[] = '[' . $i . ',' . $agencyEmployeesArray[$fieldName]["value"] . ']';
} else {
- $row[] = '['.$i.',0]';
+ $row[] = '[' . $i . ',0]';
}
+ }
}
if ($format == "csv") {
fputcsv($fp, array_values($row));
} else if ($format == "json") {
- if (!$first) echo ",";
- echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "'.$agency->value->name.'", "lines" : { "show" : true }, "points" : { "show" : true }}'.PHP_EOL;
+ if (!$first)
+ echo ",";
+ echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "' . $agency->value->name . '", "lines" : { "show" : true }, "points" : { "show" : true }}' . PHP_EOL;
$first = false;
}
}
}
if ($format == "json") {
- echo ']
- }'.PHP_EOL;
-
+ echo ']
+ }' . PHP_EOL;
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
--- a/admin/importAPSCEmployees.php
+++ b/admin/importAPSCEmployees.php
@@ -47,13 +47,17 @@
$changed = false;
if (!isset($doc->statistics)) {
$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 => $value) {
if (!isset($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/");
+ $doc->statistics->employees->$timePeriod = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/");
}
}
if ($changed) {
--- /dev/null
+++ b/admin/importAPSCEmployees2012.php
@@ -1,1 +1,86 @@
+<?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
+?>
+
--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -4,74 +4,62 @@
//function createFOIDocumentsDesignDoc() {
$foidb = $server->get_db('disclosr-foidocuments');
- $obj = new stdClass();
- $obj->_id = "_design/" . urlencode("app");
- $obj->language = "javascript";
- $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
- $obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };";
- $obj->views->byDate->reduce = "_count";
- $obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
- $obj->views->byAgencyID->reduce = "_count";
+$obj = new stdClass();
+$obj->_id = "_design/" . urlencode("app");
+$obj->language = "javascript";
+$obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
+$obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };";
+$obj->views->byDate->reduce = "_count";
+$obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };";
+$obj->views->byDateMonthYear->reduce = "_count";
+$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).
- $foidb->save($obj, true);
+// allow safe updates (even if slightly slower due to extra: rev-detection check).
+$foidb->save($obj, true);
-function createDocumentsDesignDoc() {
- /*
- global $db;
- $obj = new stdClass();
- $obj->_id = "_design/" . urlencode("app");
- $obj->language = "javascript";
- $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
- $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
- "views": {
- "web_server": {
- "map": "function(doc) {\n emit(doc.web_server, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byAgency": {
- "map": "function(doc) {\n emit(doc.agencyID, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byURL": {
- "map": "function(doc) {\n emit(doc.url, doc);\n}"
- },
- "agency": {
- "map": "function(doc) {\n emit(doc.agencyID, doc);\n}"
- },
- "byWebServer": {
- "map": "function(doc) {\n emit(doc.web_server, doc);\n}"
- },
- "getValidationRequired": {
- "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"
- }
- } */
-}
+//function createDocumentsDesignDoc() {
+$docdb = $server->get_db('disclosr-documents');
+
+$obj = new stdClass();
+$obj->_id = "_design/" . urlencode("app");
+$obj->language = "javascript";
+$obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}";
+$obj->views->web_server->reduce = "function (key, values, rereduce) {\n return sum(values);\n}";
+$obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}";
+$obj->views->byAgency->reduce = "function (key, values, rereduce) {\n return sum(values);\n}";
+$obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}";
+$obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}";
+$obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}";
+$obj->views->getValidationRequired = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}";
+
+
+
//function createAgencyDesignDoc() {
$db = $server->get_db('disclosr-agencies');
- $obj = new stdClass();
- $obj->_id = "_design/" . urlencode("app");
- $obj->language = "javascript";
- $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
- $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
- $obj->views->byCanonicalName->map = "function(doc) {
+$obj = new stdClass();
+$obj->_id = "_design/" . urlencode("app");
+$obj->language = "javascript";
+$obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
+$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
+$obj->views->byCanonicalName->map = "function(doc) {
if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc);
}
};";
- $obj->views->byDeptStateName->map = "function(doc) {
+$obj->views->byDeptStateName->map = "function(doc) {
if (doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc._id);
}
};";
- $obj->views->parentOrgs->map = "function(doc) {
+$obj->views->parentOrgs->map = "function(doc) {
if (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") {
emit(doc.name, doc._id);
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
@@ -95,14 +83,14 @@
}
};';
- $obj->views->foiEmails->map = "function(doc) {
+$obj->views->foiEmails->map = "function(doc) {
emit(doc._id, doc.foiEmail);
};";
- $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->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
- $obj->views->getScrapeRequired->map = "function(doc) {
+$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->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
+$obj->views->getScrapeRequired->map = "function(doc) {
var lastScrape = Date.parse(doc.metadata.lastScraped);
@@ -113,14 +101,14 @@
}
};";
- $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
- $obj->views->getConflicts->map = "function(doc) {
+$obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
+$obj->views->getConflicts->map = "function(doc) {
if (doc._conflicts) {
emit(null, [doc._rev].concat(doc._conflicts));
}
}";
- // http://stackoverflow.com/questions/646628/javascript-startswith
- $obj->views->score->map = 'if(!String.prototype.startsWith){
+// http://stackoverflow.com/questions/646628/javascript-startswith
+$obj->views->score->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) {
return !this.indexOf(str);
}
@@ -144,7 +132,7 @@
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) {
return !this.indexOf(str);
}
@@ -164,22 +152,20 @@
emit("total", 1);
}
}';
- $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
+$obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
return sum(values);
}';
- $obj->views->fieldNames->map = '
+$obj->views->fieldNames->map = '
function(doc) {
for(var propName in doc) {
emit(propName, doc._id);
}
}';
- $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
+$obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
return values.length;
}';
- // allow safe updates (even if slightly slower due to extra: rev-detection check).
- $db->save($obj, true);
-
-
+// allow safe updates (even if slightly slower due to extra: rev-detection check).
+$db->save($obj, true);
?>
--- a/couchdb/SetteeDatabase.class.php
+++ /dev/null
@@ -1,306 +1,1 @@
-<?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;
- }
-
-}
--- a/couchdb/settee
+++ /dev/null
--- /dev/null
+++ b/documents/.gitignore
@@ -1,1 +1,2 @@
+*.pyc
--- a/documents/disclogsList.php
+++ b/documents/disclogsList.php
@@ -8,45 +8,69 @@
<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');
$docsdb = $server->get_db('disclosr-documents');
+$agencies = 0;
+$disclogs = 0;
+$red = 0;
+$green = 0;
+$yellow = 0;
+$orange = 0;
try {
$rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows;
if ($rows) {
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>" . $row->value->name . "</b>";
- if ($ENV == "DEV")
- echo "<br>(" . $row->id . ")";
- echo "</td>\n";
-
-
- echo "<td>";
- if (isset($row->value->FOIDocumentsURL)) {
- echo '<a href="' . $row->value->FOIDocumentsURL . '">'
- . $row->value->FOIDocumentsURL . '</a>';
- if ($ENV == "DEV")
- echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">'
- . 'view local copy</a>)</small>';
- } else {
- echo "<font color='red'>✘</font>";
+ echo "<td>";
+ if (isset($row->value->FOIDocumentsURL)) {
+ $disclogs++;
+ echo '<a href="' . $row->value->FOIDocumentsURL . '">'
+ . $row->value->FOIDocumentsURL . '</a>';
+ if ($ENV == "DEV")
+ echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">'
+ . 'view local copy</a>)</small>';
+ } else {
+ echo "<font color='red'><abbr title='No'>✘</abbr></font>";
+ }
+ echo "</td>\n<td>";
+ if (isset($row->value->FOIDocumentsURL)) {
+ if (file_exists("./scrapers/" . $row->id . '.py')) {
+ echo "<font color='green'><abbr title='Yes'>✔</abbr></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>";
- } else if (file_exists("./scrapers/" . $row->id . '.txt')) {
- echo "<font color='blue'><b>▬</b></font>";
- } else {
- echo "<font color='red'>✘</font>";
- }
- }
- echo "</td></tr>\n";
}
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
echo "</table>";
+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();
?>
+
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -9,6 +9,7 @@
import dateutil
from dateutil.parser import *
from datetime import *
+import codecs
class GenericDisclogScraper(object):
__metaclass__ = abc.ABCMeta
@@ -55,7 +56,7 @@
doc = foidocsdb.get(hash)
#print doc
if doc == None:
- print "saving"
+ print "saving "+ hash
edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d")
doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id,
"date": edate,"title": entry.title}
@@ -84,14 +85,28 @@
doc.update({'description': descriptiontxt})
return
def getTitle(self, content, entry, doc):
- doc.update({'title': content.string})
+ doc.update({'title': (''.join(content.stripped_strings))})
return
def getTable(self, soup):
return soup.table
+ def getRows(self, table):
+ return table.find_all('tr')
def getDate(self, content, entry, doc):
- edate = parse(content.string.strip(), dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
+ date = ''.join(content.stripped_strings).strip()
+ (a,b,c) = date.partition("(")
+ date = self.remove_control_chars(a.replace("Octber","October"))
+ print date
+ edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
print edate
doc.update({'date': edate})
+ return
+ def getLinks(self, content, entry, doc):
+ links = []
+ for atag in entry.find_all("a"):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(content,atag['href']))
+ if links != []:
+ doc.update({'links': links})
return
def doScrape(self):
@@ -102,31 +117,26 @@
# http://www.crummy.com/software/BeautifulSoup/documentation.html
soup = BeautifulSoup(content)
table = self.getTable(soup)
- for row in table.find_all('tr'):
+ for row in self.getRows(table):
columns = row.find_all('td')
if len(columns) == self.getColumnCount():
- (id, date, description, title, notes) = self.getColumns(columns)
- print id.string
+ (id, date, title, description, notes) = self.getColumns(columns)
+ print self.remove_control_chars(''.join(id.stripped_strings))
if id.string == None:
- hash = scrape.mkhash(self.remove_control_chars(url+date.string))
+ hash = scrape.mkhash(self.remove_control_chars(url+(''.join(date.stripped_strings))))
else:
- hash = scrape.mkhash(self.remove_control_chars(url+id.string))
- links = []
- for atag in row.find_all("a"):
- if atag.has_key('href'):
- links.append(scrape.fullurl(url,atag['href']))
+ hash = scrape.mkhash(self.remove_control_chars(url+(''.join(id.stripped_strings))))
doc = foidocsdb.get(hash)
if doc == None:
- print "saving"
- doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string}
- if links != []:
- doc.update({'links': links})
+ print "saving " +hash
+ doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': (''.join(id.stripped_strings))}
+ self.getLinks(self.getURL(),row,doc)
self.getTitle(title,row, doc)
self.getDate(date,row, doc)
self.getDescription(description,row, doc)
if notes != None:
- doc.update({ 'notes': notes.string})
+ doc.update({ 'notes': (''.join(notes.stripped_strings))})
foidocsdb.save(doc)
else:
print "already saved "+hash
--- a/documents/index.php
+++ b/documents/index.php
@@ -1,11 +1,11 @@
<?php
+
include('template.inc.php');
include_header_documents("");
include_once('../include/common.inc.php');
+$startkey = (isset($_REQUEST['start_key']) ? $_REQUEST['start_key'] : '9999-99-99');
?>
<?php
-
-
$agenciesdb = $server->get_db('disclosr-agencies');
@@ -15,17 +15,17 @@
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
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 ($rows) {
- foreach ($rows as $row) {
-displayLogEntry($row,$idtoname);
+ foreach ($rows as $key => $row) {
+ echo displayLogEntry($row, $idtoname);
+ $endkey = $row->key;
}
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
+echo "<a href='?start_key=$endkey'>next page</a>";
include_footer_documents();
?>
--- a/documents/robots.txt
+++ b/documents/robots.txt
@@ -2,4 +2,5 @@
# http://code.google.com/web/controlcrawlindex/
User-agent: *
-
+Disallow: /admin/
+Sitemap: http://disclosurelo.gs/sitemap.xml.php
--- a/documents/rss.xml.php
+++ b/documents/rss.xml.php
@@ -3,28 +3,38 @@
// Agency X updated Y, new files, diff of plain text/link text,
// feed for just one agency or all
// This is a minimum example of using the Universal Feed Generator Class
-include("lib/FeedWriter.php");
+include("../lib/FeedWriter/FeedTypes.php");
+include_once('../include/common.inc.php');
//Creating an instance of FeedWriter class.
-$TestFeed = new FeedWriter(RSS2);
+$TestFeed = new RSS2FeedWriter();
//Setting the channel elements
//Use wrapper functions for common channelelements
$TestFeed->setTitle('Last Modified - All');
-$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->setChannelElement('language', 'en-us');
+ $TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
//Retriving informations from database
-$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);
foreach ($rows as $row) {
//Create an empty FeedItem
$newItem = $TestFeed->createNewItem();
//Add elements to the feed item
- $newItem->setTitle($row['name']);
- $newItem->setLink($row['id']);
- $newItem->setDate(date("c", $row['metadata']['lastModified']));
- $newItem->setDescription($row['name']);
+ $newItem->setTitle($row->value->title);
+ $newItem->setLink("view.php?id=".$row->value->docID);
+ $newItem->setDate(date("c", strtotime($row->value->date)));
+ $newItem->setDescription(displayLogEntry($row,$idtoname));
+ $newItem->addElement('guid', $row->value->_id,array('isPermaLink'=>'true'));
//Now add the feed item
$TestFeed->addItem($newItem);
}
//OK. Everything is done. Now genarate the feed.
-$TestFeed->genarateFeed();
+$TestFeed->generateFeed();
?>
--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -204,12 +204,12 @@
scrapeAndStore(docsdb, agency[key],0,key,agency['_id'])
if key == 'website' and False:
scrapeAndStore(docsdb, agency[key],0,key,agency['_id'])
+ agency['metadata']['lastScraped'] = time.time()
if key.endswith('URL') and False:
print key
depth = 1
if 'scrapeDepth' in agency.keys():
depth = agency['scrapeDepth']
scrapeAndStore(docsdb, agency[key],depth,key,agency['_id'])
- agency['metadata']['lastScraped'] = time.time()
agencydb.save(agency)
--- /dev/null
+++ b/documents/scrapers/0049d35216493c545ef5f7f000e6b252.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/00a294de663db69062ca09aede7c0487.txt
@@ -1,1 +1,2 @@
+multipage
--- /dev/null
+++ b/documents/scrapers/0324e4b1654fd6dd651307abcef67094.py
@@ -1,1 +1,19 @@
+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 getColumnCount(self):
+ return 6
+ def getColumns(self,columns):
+ (id, date, title, description, notes,link) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/0372b19123076338d483f624c433727b.txt
@@ -1,1 +1,2 @@
+docx
--- /dev/null
+++ b/documents/scrapers/0603dfcc930a791efaa64f31ae5fceda.py
@@ -1,1 +1,21 @@
+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="body-content").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()
+
--- /dev/null
+++ b/documents/scrapers/0ae822d1a748e60d90f0b79b97d5a3e5.txt
@@ -1,1 +1,2 @@
+ACMA style
--- /dev/null
+++ b/documents/scrapers/0ced9dd2de36100c3cabdb7fd8e843a9.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/0e46f8bd1414b1fdd4f0543d54a97500.py
@@ -1,1 +1,21 @@
+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 = "maincontentcontainer").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (date, disclogdate, title, description, notes) = columns
+ return (date, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/1097fa8afdcf5db89d212d0979226667.py
@@ -1,1 +1,17 @@
+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 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()
+
--- a/documents/scrapers/157cbe654bdaa0a48e6650152ae34489.py
+++ b/documents/scrapers/157cbe654bdaa0a48e6650152ae34489.py
@@ -10,7 +10,7 @@
return 5
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
def getTable(self,soup):
return soup.find_all('table')[4]
--- /dev/null
+++ b/documents/scrapers/1803322b27286950cab0c543168b5f21.txt
@@ -1,1 +1,2 @@
+multipage log
--- /dev/null
+++ b/documents/scrapers/1ad74ca88932f90f0b92b69387171441.py
@@ -1,1 +1,17 @@
+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 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()
+
--- /dev/null
+++ b/documents/scrapers/1d404c4934f74feacd00dcb434e7c10a.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/1fda9544d2a3fa4cd92aec4b206a6763.py
@@ -1,1 +1,21 @@
+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(_class = "article-content").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, title, date, 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()
+
--- /dev/null
+++ b/documents/scrapers/24bd71114d3975ed9a63ad29624c62c9.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/269680be088f3d8e663251655f3825b4.py
@@ -1,1 +1,17 @@
+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 getColumns(self,columns):
+ (date, id, 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()
+
--- /dev/null
+++ b/documents/scrapers/2cac2cd1f42687db2d04fa20b5b6a538.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/31685505438d393f45a90f442b8fa27f.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/31b7c75cf484747b6b120680bddd33b0.py
@@ -1,1 +1,19 @@
+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 getColumnCount(self):
+ return 2
+ def getColumns(self,columns):
+ (title, date) = columns
+ return (date, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/329fccdca068b78ab7edd550e2957398.py
@@ -1,1 +1,21 @@
+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 getColumnCount(self):
+ return 7
+ def getTable(self,soup):
+ return soup.find(class_ = "foi-disclosure")
+ def getColumns(self,columns):
+ (disclogid, id, date, title, link, removedate, notes) = columns
+ return (id, date, title, title, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/38ca99d2790975a40dde3fae41dbdc3d.py
@@ -1,1 +1,32 @@
+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 3
+ def getColumns(self,columns):
+ (date, title, description) = columns
+ return (date, date, title, description, None)
+ def getTitle(self, content, entry, doc):
+ i = 0
+ title = ""
+ for string in content.stripped_strings:
+ if i < 2:
+ title = title + string
+ i = i+1
+ doc.update({'title': title})
+ print title
+ return
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/3b54190e3f409380e109fae29e1917aa.py
@@ -1,1 +1,19 @@
+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 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()
+
--- a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
+++ b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
@@ -7,7 +7,7 @@
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns):
(id, date, description, title, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
--- /dev/null
+++ b/documents/scrapers/3d426eb8c85c8f04b814eee597efd866.py
@@ -1,1 +1,21 @@
+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 = "primary").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()
+
--- /dev/null
+++ b/documents/scrapers/3d5871a44abbbc81ef5b3a420070755d.py
@@ -1,1 +1,47 @@
+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 getTable(self,soup):
+ return soup.find(class_ = "inner-column").table
+ def getRows(self,table):
+ return table.tbody.find_all('tr',recursive=False)
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (date, title, description) = columns
+ return (date, date, title, description, None)
+ def getDate(self, content, entry, doc):
+ i = 0
+ date = ""
+ for string in content.stripped_strings:
+ if i ==1:
+ date = string
+ i = i+1
+ edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
+ print edate
+ doc.update({'date': edate})
+ return
+ def getTitle(self, content, entry, doc):
+ i = 0
+ title = ""
+ for string in content.stripped_strings:
+ if i < 2:
+ title = title + string
+ i = i+1
+ doc.update({'title': title})
+ #print title
+ return
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/3e2f110af49d62833a835bd257771ffb.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/41a166419503bb50e410c58be54c102f.txt
@@ -1,1 +1,1 @@
-
+aspx
--- /dev/null
+++ b/documents/scrapers/4934000fddd6a5b1094f398798341290.py
@@ -1,1 +1,23 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/4c57389dda9bd454bcb08bc1e5ed87bf.txt
@@ -1,1 +1,2 @@
+parent
--- /dev/null
+++ b/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/50601505ef69483121a6d130bb0515e4.txt
@@ -1,1 +1,1 @@
-
+apsc has ACMA style disclog
--- /dev/null
+++ b/documents/scrapers/525c3953187da08cd702359b2fc2997f.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/53b14397c8f27c29ff07b6319f7a0ec5.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/53d2884f8afd026096a27bd5051ec50e.py
@@ -1,1 +1,39 @@
+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(class_ = "ms-rtestate-field").table
+ def getColumns(self,columns):
+ (id, date, title, description, notes) = columns
+ return (id, date, title, description, notes)
+
+ def getLinks(self, content, entry, doc):
+ link = None
+ links = []
+ 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 atag in soup.find(class_ = "article-content").find_all('a'):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(link,atag['href']))
+
+ if links != []:
+ doc.update({'links': links})
+ doc.update({'url': link})
+ return
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/54cbb3439276062b7a9f007f9f69d1f6.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/55b69726fde4b4898ecf6d7217d1d1d2.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py
@@ -1,1 +1,19 @@
+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 getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (date, id, 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()
+
--- /dev/null
+++ b/documents/scrapers/5d05365e981d87e746b596d63e35b1dc.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/601aedeef4344638d635bdd761e9fdba.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/649b053f5e2884906ddc7174c2cd4b38.py
@@ -1,1 +1,28 @@
+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()
+
+
--- /dev/null
+++ b/documents/scrapers/655d4d67333536bda18d68265dfe7e80.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/656f7bb1884f4b9d31ebe2a5f5f58064.txt
@@ -1,1 +1,2 @@
+list style
--- /dev/null
+++ b/documents/scrapers/65ec17101b00519e6d88c5a9f33c2c46.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/69d59284ef0ccd2677394d82d3292abc.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/6ac74a939f420c6194ae29224809734a.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/6afdde1d4ff1ad8d8cfe1a8675ea83bd.txt
@@ -1,1 +1,2 @@
+PDF
--- /dev/null
+++ b/documents/scrapers/6cf3870aedeeecfd6394b5c0abed4c55.py
@@ -1,1 +1,23 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/6fa04af95fbe7de96daa2c7560e0aad3.py
@@ -1,1 +1,19 @@
+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_div_50269").table
+ 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()
+
--- /dev/null
+++ b/documents/scrapers/6fe3c812a99d486963133459b2768cf6.py
@@ -1,1 +1,17 @@
+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 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()
+
--- /dev/null
+++ b/documents/scrapers/72a295f10734d64e8185f651fd2b39ea.txt
@@ -1,1 +1,2 @@
+weird div based log with tables of links
--- /dev/null
+++ b/documents/scrapers/734f12db07e844b30cd11dc98500f2ce.py
@@ -1,1 +1,19 @@
+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 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()
+
--- /dev/null
+++ b/documents/scrapers/75d8f1c605ef9da0c2590264b7aa046b.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/768bbbfb34115873af361af8519b38a9.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/77f02f713e3c37bff73882fb90828379.py
@@ -1,1 +1,22 @@
+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("table",width="571")
+#findAll("table")[3]
+ 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()
+
--- /dev/null
+++ b/documents/scrapers/794ea270edc9aa4f70f2a84bbc5ecc7a.py
@@ -1,1 +1,21 @@
+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()
+
--- a/documents/scrapers/795c33ed030293dbdb155c909ea47e37.py
+++ b/documents/scrapers/795c33ed030293dbdb155c909ea47e37.py
@@ -10,7 +10,7 @@
return 7
def getColumns(self,columns):
(id, date, title, description, notes, deletedate, otherinfo) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
#def getTable(self,soup):
# return soup.find(class_ = "box").table
--- /dev/null
+++ b/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt
@@ -1,1 +1,1 @@
-
+acma style
--- /dev/null
+++ b/documents/scrapers/7ec28d7d97fcf493b1350acd03e3642e.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/7f55a3c42ad7460254906aa043a6e324.py
@@ -1,1 +1,24 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/8317df630946937864d31a4728ad8ee8.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/8796220032faf94501bd366763263685.txt
@@ -1,1 +1,2 @@
+multiple pages
--- /dev/null
+++ b/documents/scrapers/8aae1c28db7f3ce10f232a0137be6bb2.py
@@ -1,1 +1,21 @@
+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()
+
--- a/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
+++ b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
@@ -7,7 +7,7 @@
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
--- /dev/null
+++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py
@@ -1,1 +1,86 @@
+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
+
--- /dev/null
+++ b/documents/scrapers/8ef0e5802f99800f514b3a148e013b75.py
@@ -1,1 +1,21 @@
+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 getColumnCount(self):
+ return 4;
+ def getTable(self,soup):
+ return soup.find(class_ = "content").table
+ 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()
+
--- /dev/null
+++ b/documents/scrapers/905a1c409b6afb1de0074b13a5559560.py
@@ -1,1 +1,23 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/9282306e244040c9e4ae5705f06f9548.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/93ce83e46f5c2c4ca1b7f199b59b4bd2.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/955dc4cb047b5439dfb65549ce2696a6.py
@@ -1,1 +1,17 @@
+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 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()
+
--- /dev/null
+++ b/documents/scrapers/99328d76c8efb56ff3f1da79b9d1b17f.txt
@@ -1,1 +1,2 @@
+acma style
--- /dev/null
+++ b/documents/scrapers/9961dc45e046288ad1431941653af20c.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/9f5cd66dea3e2ec958c17e28b27e60a7.txt
@@ -1,1 +1,2 @@
+acma style
--- /dev/null
+++ b/documents/scrapers/a1ab9c80ab473958676c62c1a25dd502.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/a2d871c5d28de1dde8a3b66c4957e1a5.py
@@ -1,1 +1,19 @@
+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 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()
+
--- /dev/null
+++ b/documents/scrapers/a43467fe82b840a353b380c4d7462a4c.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/a687a9eaab9e10e9e118d3fd7cf0e13a.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/ad033512610d8e36886ab6a795f26561.py
@@ -1,1 +1,21 @@
+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 = "_ctl0__ctl0_MainContentPlaceHolder_MainContentPlaceHolder_ContentSpan").findAll("table")[3]
+ 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()
+
--- /dev/null
+++ b/documents/scrapers/b0a3281ba66efe173c5a33d5ef90ff76.txt
@@ -1,1 +1,2 @@
+multipage immi
--- /dev/null
+++ b/documents/scrapers/b0fb402314e685238537105ee0e70c84.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/b506b87c8ee9e3a7ea8007914078c741.py
@@ -1,1 +1,19 @@
+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 getColumnCount(self):
+ return 6
+ def getColumns(self,columns):
+ (id, date, title, description,link,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()
+
--- /dev/null
+++ b/documents/scrapers/b7770c4584332cff42bb6abb3326e564.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/b91f866928eb61959dbbab56313214fc.py
@@ -1,1 +1,21 @@
+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()
+
--- a/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
+++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
@@ -1,2 +1,1 @@
-# does not have any disclog entries or table
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/bc91b878e2317fa231cc2c512e2027f0.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/bf16d4ba0d306ee03e5a1d32aaba3da1.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/bf6e587f166040b63681cd2ff76fbfdf.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/c1302c8d7cbbd911f0d4d8a4128f8079.txt
@@ -1,1 +1,1 @@
-
+uses RET disclog
--- /dev/null
+++ b/documents/scrapers/c25f628f9f38d889485d7a4bff873b23.py
@@ -1,1 +1,21 @@
+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(class_ = "ms-rtestate-field").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()
+
--- /dev/null
+++ b/documents/scrapers/c414e65ed728d05307d5b27f13e195e1.py
@@ -1,1 +1,19 @@
+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 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()
+
--- a/documents/scrapers/c43ca6780764f4e61918e8836be74420.py
+++ b/documents/scrapers/c43ca6780764f4e61918e8836be74420.py
@@ -7,7 +7,7 @@
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns):
(id, date, title,description,notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
--- /dev/null
+++ b/documents/scrapers/cb7f40e3495b682de6eee61bf09c1cfc.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/cca17a34bd490474a316fe0a1ca03c25.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/cde8eb4a2e40abb18d8b28d3b85bc9b0.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/ce34d1e9b55911e4272d2d388821f311.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/d1296c366287f7a9faedf235c7e6df01.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/d72744fb1e5d6e87af9a5ea16cc27fa5.txt
@@ -1,1 +1,1 @@
-
+acma style
--- /dev/null
+++ b/documents/scrapers/dae7e934f1c341ccc9547a89a8af917e.py
@@ -1,1 +1,21 @@
+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()
+
--- a/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py
+++ b/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py
@@ -8,7 +8,7 @@
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
def getTable(self,soup):
return soup.find(class_ = "content")
--- /dev/null
+++ b/documents/scrapers/e0614dc3a9e25d375370ffd82f7165ac.py
@@ -1,1 +1,21 @@
+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()
+
--- a/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py
+++ b/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py
@@ -7,7 +7,7 @@
class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
--- /dev/null
+++ b/documents/scrapers/e64c71f4986f78675a252104c5a5f359.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/e770921522a49dc77de208cc724ce134.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/e90b1b7cbb83e3eed0b5f849c7e3af79.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/ee30aad97f0bb32e74c4587404b67ce4.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/f0caafbcf292c90e7b8ad18ddcf9afc3.py
@@ -1,1 +1,21 @@
+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 = "genericContent").table.tbody
+ def getColumnCount(self):
+ return 3
+ 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()
+
--- /dev/null
+++ b/documents/scrapers/f189459fc43f941e0d4ecfba52c666f3.txt
@@ -1,1 +1,2 @@
+no disclog
--- a/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py
+++ b/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py
@@ -8,7 +8,7 @@
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
def getTable(self,soup):
return soup.find(id = "content").table
--- /dev/null
+++ b/documents/scrapers/f5ce2d1651739704634eb8ca4b2b46d3.py
@@ -1,1 +1,21 @@
+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()
+
--- /dev/null
+++ b/documents/scrapers/fa9b3badd6c686398c1c6982a4b02475.py
@@ -1,1 +1,17 @@
+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 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()
+
--- a/documents/scrapers/rtk.py
+++ b/documents/scrapers/rtk.py
@@ -7,7 +7,7 @@
class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
def getColumns(self,columns):
(id, date, title, description, notes) = columns
- return (id, date, description, title, notes)
+ return (id, date, title, description, notes)
if __name__ == '__main__':
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
--- /dev/null
+++ b/documents/sitemap.xml.php
@@ -1,1 +1,25 @@
+<?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>';
+?>
+
--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -130,21 +130,23 @@
}
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($row->value->notes)) {
-echo " <br>Note: ".$row->value->notes;
+$result .= " <br>Note: ".$row->value->notes;
}
-echo "</p>";
+$result .= "</p>";
if (isset($row->value->links)){
-echo "<h3>Links/Documents</h3><ul>";
+$result .= "<h3>Links/Documents</h3><ul>";
foreach ($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>";
-echo"</div>";
+ $result .= "<small><A href='".$row->value->url."'>View original source...</a> ID: ".strip_tags($row->value->docID)."</small>";
+$result .= "</div>";
+return $result;
}
--- /dev/null
+++ b/documents/view.php
@@ -1,1 +1,27 @@
+<?php
+include('template.inc.php');
+include_header_documents("");
+include_once('../include/common.inc.php');
+?>
+<?php
+
+
+$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();
+?>
+
--- a/documents/viewDocument.php
+++ b/documents/viewDocument.php
@@ -3,7 +3,13 @@
include_once('../include/common.inc.php');
$hash = $_REQUEST['hash'];
$docsdb = $server->get_db('disclosr-documents');
+try {
$doc = object_to_array($docsdb->get($hash));
+
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+
if (!isset($doc['_attachments']) || count($doc['_attachments']) == 0) die ("no attachments");
$attachments = $doc['_attachments'];
@@ -13,3 +19,4 @@
//echo $url;
$request = Requests::get($url);
echo ($request->body);
+
--- a/include/couchdb.inc.php
+++ b/include/couchdb.inc.php
@@ -10,6 +10,7 @@
if (php_uname('n') == "KYUUBEY") {
$serverAddr = 'http://192.168.1.148:5984/';
+ $serverAddr = 'http://127.0.0.1:5984/';
} else {
$serverAddr = 'http://127.0.0.1:5984/';
}
--- a/lib/FeedItem.php
+++ /dev/null
@@ -1,168 +1,1 @@
-<?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
-?>
--- a/lib/FeedWriter.php
+++ /dev/null
@@ -1,435 +1,1 @@
-<?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';
-}
+