<?php | <?php |
/** | /** |
* Databaase class. | * Databaase class. |
*/ | */ |
class SetteeDatabase { | class SetteeDatabase { |
/** | /** |
* Base URL of the CouchDB REST API | * Base URL of the CouchDB REST API |
*/ | */ |
private $conn_url; | private $conn_url; |
/** | /** |
* HTTP REST Client instance | * HTTP REST Client instance |
*/ | */ |
protected $rest_client; | protected $rest_client; |
/** | /** |
* Name of the database | * Name of the database |
*/ | */ |
private $dbname; | private $dbname; |
/** | /** |
* Default constructor | * Default constructor |
*/ | */ |
function __construct($conn_url, $dbname) { | function __construct($conn_url, $dbname) { |
$this->conn_url = $conn_url; | $this->conn_url = $conn_url; |
$this->dbname = $dbname; | $this->dbname = $dbname; |
$this->rest_client = SetteeRestClient::get_instance($this->conn_url); | $this->rest_client = SetteeRestClient::get_instance($this->conn_url); |
} | } |
/** | |
/** | * Get UUID from CouchDB |
* Get UUID from CouchDB | * |
* | * @return |
* @return | * CouchDB-generated UUID string |
* CouchDB-generated UUID string | * |
* | */ |
*/ | function gen_uuid() { |
function gen_uuid() { | $ret = $this->rest_client->http_get('_uuids'); |
$ret = $this->rest_client->http_get('_uuids'); | return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking |
return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking | } |
} | |
/** | |
/** | * Create or update a document database |
* Create or update a document database | * |
* | * @param $document |
* @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. |
* 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). |
* <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. |
* 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. |
* <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 |
* 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 |
* 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. |
* not provide "_id" since that is an invalid input. | * |
* | * @param $allowRevAutoDetection |
* @param $allowRevAutoDetection | * Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision |
* Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision | * for a document and use it. This option is "false" by default because it involves an extra http HEAD request and |
* for a document and use it. This option is "false" by default because it involves an extra http HEAD request and | * therefore can make save() operation slightly slower if such auto-detection is not required. |
* therefore can make save() operation slightly slower if such auto-detection is not required. | * |
* | * @return |
* @return | * document object with the database id (uuid) and revision attached; |
* document object with the database id (uuid) and revision attached; | * |
* | * @throws SetteeCreateDatabaseException |
* @throws SetteeCreateDatabaseException | */ |
*/ | function save($document, $allowRevAutoDetection = false) { |
function save($document, $allowRevAutoDetection = false) { | if (is_string($document)) { |
if (is_string($document)) { | $document = json_decode($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) | |
// Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter) | if (is_array($document)) { |
if(is_array($document)) { | $document = (object) $document; |
$document = (object) $document; | } |
} | |
if (empty($document->_id) && empty($document->_rev)) { | |
if (empty($document->_id) && empty($document->_rev)) { | $id = $this->gen_uuid(); |
$id = $this->gen_uuid(); | } elseif (empty($document->_id) && !empty($document->_rev)) { |
} | throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id"); |
elseif (empty($document->_id) && !empty($document->_rev)) { | } else { |
throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id"); | $id = $document->_id; |
} | |
else { | if ($allowRevAutoDetection) { |
$id = $document->_id; | try { |
$rev = $this->get_rev($id); | |
if ($allowRevAutoDetection) { | } catch (SetteeRestClientException $e) { |
try { | // auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error |
$rev = $this->get_rev($id); | } |
} catch (SetteeRestClientException $e) { | if (!empty($rev)) { |
// auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error | $document->_rev = $rev; |
} | } |
if (!empty($rev)) { | } |
$document->_rev = $rev; | } |
} | |
} | $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); |
} | $document_json = json_encode($document, JSON_NUMERIC_CHECK); |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | $ret = $this->rest_client->http_put($full_uri, $document_json); |
$document_json = json_encode($document, JSON_NUMERIC_CHECK); | |
$document->_id = $ret['decoded']->id; | |
$ret = $this->rest_client->http_put($full_uri, $document_json); | $document->_rev = $ret['decoded']->rev; |
$document->_id = $ret['decoded']->id; | return $document; |
$document->_rev = $ret['decoded']->rev; | } |
return $document; | /** |
} | * @param $doc |
* @param $name | |
/** | * @param $content |
* @param $doc | * Content of the attachment in a string-buffer format. This function will automatically base64-encode content for |
* @param $name | * you, so you don't have to do it. |
* @param $content | * @param $mime_type |
* Content of the attachment in a string-buffer format. This function will automatically base64-encode content for | * Optional. Will be auto-detected if not provided |
* you, so you don't have to do it. | * @return void |
* @param $mime_type | */ |
* Optional. Will be auto-detected if not provided | public function add_attachment($doc, $name, $content, $mime_type = null) { |
* @return void | if (empty($doc->_attachments) || !is_object($doc->_attachments)) { |
*/ | $doc->_attachments = new stdClass(); |
public function add_attachment($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); |
} | |
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); | |
$doc->_attachments->$name = new stdClass(); | } |
$doc->_attachments->$name->content_type = $mime_type; | |
$doc->_attachments->$name->data = base64_encode($content); | /** |
} | * @param $doc |
* @param $name | |
/** | * @param $file |
* @param $doc | * Full path to a file (e.g. as returned by PHP's realpath function). |
* @param $name | * @param $mime_type |
* @param $file | * Optional. Will be auto-detected if not provided |
* Full path to a file (e.g. as returned by PHP's realpath function). | * @return void |
* @param $mime_type | */ |
* Optional. Will be auto-detected if not provided | public function add_attachment_file($doc, $name, $file, $mime_type = null) { |
* @return void | $content = file_get_contents($file); |
*/ | $this->add_attachment($doc, $name, $content, $mime_type); |
public function add_attachment_file($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 |
* Retrieve a document from CouchDB | * |
* | * @param $id |
* @throws SetteeWrongInputException | * Unique ID (usually: UUID) of the document to be retrieved. |
* | * @return |
* @param $id | * database document in PHP object format. |
* Unique ID (usually: UUID) of the document to be retrieved. | */ |
* @return | function get($id) { |
* database document in PHP object format. | if (empty($id)) { |
*/ | throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); |
function get($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); | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | return $ret['decoded']; |
$full_uri = str_replace("%3Frev%3D","?rev=",$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 |
* Get the latest revision of a document with document id: $id in CouchDB. | * |
* | * @param $id |
* @throws SetteeWrongInputException | * Unique ID (usually: UUID) of the document to be retrieved. |
* | * @return |
* @param $id | * database document in PHP object format. |
* Unique ID (usually: UUID) of the document to be retrieved. | */ |
* @return | function get_rev($id) { |
* database document in PHP object format. | if (empty($id)) { |
*/ | throw new SetteeWrongInputException("Error: Can't query a document without a uuid."); |
function get_rev($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'])) { | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag"); |
$headers = $this->rest_client->http_head($full_uri); | } |
if (empty($headers['Etag'])) { | $etag = str_replace('"', '', $headers['Etag']); |
throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag"); | return $etag; |
} | } |
$etag = str_replace('"', '', $headers['Etag']); | |
return $etag; | /** |
} | * Delete a document |
* | |
/** | * @param $document |
* Delete a document | * a PHP object or JSON representation of the document that has _id and _rev fields. |
* | * |
* @param $document | * @return void |
* a PHP object or JSON representation of the document that has _id and _rev fields. | */ |
* | function delete($document) { |
* @return void | if (!is_object($document)) { |
*/ | $document = json_decode($document); |
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); |
} | |
$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. | |
/*----------------- View-related functions --------------*/ | * |
* @param $design_doc | |
/** | * @param $view_name |
* Create a new view or update an existing one. | * @param $map_src |
* | * Source code of the map function in Javascript |
* @param $design_doc | * @param $reduce_src |
* @param $view_name | * Source code of the reduce function in Javascript (optional) |
* @param $map_src | * @return void |
* Source code of the map function in Javascript | */ |
* @param $reduce_src | function save_view($design_doc, $view_name, $map_src, $reduce_src = null) { |
* Source code of the reduce function in Javascript (optional) | $obj = new stdClass(); |
* @return void | $obj->_id = "_design/" . urlencode($design_doc); |
*/ | $view_name = urlencode($view_name); |
function save_view($design_doc, $view_name, $map_src, $reduce_src = null) { | $obj->views->$view_name->map = $map_src; |
$obj = new stdClass(); | if (!empty($reduce_src)) { |
$obj->_id = "_design/" . urlencode($design_doc); | $obj->views->$view_name->reduce = $reduce_src; |
$view_name = urlencode($view_name); | } |
$obj->views->$view_name->map = $map_src; | |
if (!empty($reduce_src)) { | // allow safe updates (even if slightly slower due to extra: rev-detection check). |
$obj->views->$view_name->reduce = $reduce_src; | return $this->save($obj, true); |
} | } |
// 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 |
* Create a new view or update an existing one. | * @param $key |
* | * key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes |
* @param $design_doc | * that first element is startkey, second: endkey. |
* @param $view_name | * @param $descending |
* @param $key | * return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change |
* key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes | * order you also need to swap startkey and endkey values! |
* that first element is startkey, second: endkey. | * |
* @param $descending | * @return void |
* return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change | */ |
* order you also need to swap startkey and endkey values! | function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false, $reduce = null, $startdocid = null) { |
* | $id = "_design/" . urlencode($design_doc); |
* @return void | $view_name = urlencode($view_name); |
*/ | $id .= "/_view/$view_name"; |
function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false) { | |
$id = "_design/" . urlencode($design_doc); | $data = array(); |
$view_name = urlencode($view_name); | if (!empty($key)) { |
$id .= "/_view/$view_name"; | if (is_string($key)) { |
$data = "key=" . '"' . $key . '"'; | |
$data = array(); | } elseif (is_array($key)) { |
if (!empty($key)) { | list($startkey, $endkey) = $key; |
if (is_string($key)) { | $data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"'; |
$data = "key=" . '"' . $key . '"'; | } |
} | |
elseif (is_array($key)) { | if ($descending) { |
list($startkey, $endkey) = $key; | $data .= "&descending=true"; |
$data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"'; | } |
} | if ($startdocid != null) { |
$data .= "&startkey_docid='$startdocid'"; | |
if ($descending) { | } |
$data .= "&descending=true"; | if ($reduce === true) { |
} | $data .= "&reduce=true"; |
if ($limit) { | } else if ($reduce === false){ |
$data .= "&limit=".$limit; | |
} | $data .= "&reduce=false"; |
} | } |
if ($limit) { | |
$data .= "&limit=" . $limit; | |
} | |
if (empty($id)) { | } |
throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); | |
} | |
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id); | if (empty($id)) { |
$full_uri = str_replace("%253Fgroup%253D","?group=",$full_uri); | throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); |
$full_uri = str_replace("%253Flimit%253D","?limit=",$full_uri); | } |
$ret = $this->rest_client->http_get($full_uri, $data); | |
return $ret['decoded']; | $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); |
} | $full_uri = str_replace("%253Fgroup%253D", "?group=", $full_uri); |
$full_uri = str_replace("%253Flimit%253D", "?limit=", $full_uri); | |
/** | $ret = $this->rest_client->http_get($full_uri, $data); |
* @param $id | //$ret['decoded'] = str_replace("?k","&k",$ret['decoded']); |
* @return | return $ret['decoded']; |
* return a properly url-encoded id. | } |
*/ | |
private function safe_urlencode($id) { | /** |
//-- System views like _design can have "/" in their URLs. | * @param $id |
$id = rawurlencode($id); | * @return |
if (substr($id, 0, 1) == '_') { | * return a properly url-encoded id. |
$id = str_replace('%2F', '/', $id); | */ |
} | private function safe_urlencode($id) { |
return $id; | //-- System views like _design can have "/" in their URLs. |
} | $id = rawurlencode($id); |
if (substr($id, 0, 1) == '_') { | |
/** Getter for a database name */ | $id = str_replace('%2F', '/', $id); |
function get_name() { | } |
return $this->dbname; | return $id; |
} | } |
/** Getter for a database name */ | |
function get_name() { | |
return $this->dbname; | |
} | |
} | } |
<?php | <?php |
/** | /** |
* HTTP REST Client for CouchDB API | * HTTP REST Client for CouchDB API |
*/ | */ |
class SetteeRestClient { | class SetteeRestClient { |
/** | /** |
* HTTP Timeout in Milliseconds | * HTTP Timeout in Milliseconds |
*/ | */ |
const HTTP_TIMEOUT = 2000; | const HTTP_TIMEOUT = 2000; |
private $base_url; | private $base_url; |
private $curl; | private $curl; |
private static $curl_workers = array(); | private static $curl_workers = array(); |
/** | /** |
* Singleton factory method | * Singleton factory method |
*/ | */ |
static function get_instance($base_url) { | static function get_instance($base_url) { |
if (empty(self::$curl_workers[$base_url])) { | if (empty(self::$curl_workers[$base_url])) { |
self::$curl_workers[$base_url] = new SetteeRestClient($base_url); | self::$curl_workers[$base_url] = new SetteeRestClient($base_url); |
} | } |
return self::$curl_workers[$base_url]; | return self::$curl_workers[$base_url]; |
} | } |
/** | /** |
* Class constructor | * Class constructor |
*/ | */ |
private function __construct($base_url) { | private function __construct($base_url) { |
$this->base_url = $base_url; | $this->base_url = $base_url; |
$curl = curl_init(); | $curl = curl_init(); |
curl_setopt($curl, CURLOPT_USERAGENT, "Settee CouchDB Client/1.0"); | curl_setopt($curl, CURLOPT_USERAGENT, "Settee CouchDB Client/1.0"); |
curl_setopt($curl, CURLOPT_HTTPHEADER, array('Content-Type: application/json')); | curl_setopt($curl, CURLOPT_HTTPHEADER, array('Content-Type: application/json')); |
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); | curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); |
curl_setopt($curl, CURLOPT_HEADER, 0); | curl_setopt($curl, CURLOPT_HEADER, 0); |
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1); | curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1); |
curl_setopt($curl, CURLOPT_TIMEOUT_MS, self::HTTP_TIMEOUT); | curl_setopt($curl, CURLOPT_TIMEOUT_MS, self::HTTP_TIMEOUT); |
curl_setopt($curl, CURLOPT_FORBID_REUSE, false); // Connection-pool for CURL | curl_setopt($curl, CURLOPT_FORBID_REUSE, false); // Connection-pool for CURL |
$this->curl = $curl; | $this->curl = $curl; |
} | } |
/** | /** |
* Class destructor cleans up any resources | * Class destructor cleans up any resources |
*/ | */ |
function __destruct() { | function __destruct() { |
curl_close($this->curl); | curl_close($this->curl); |
} | } |
/** | /** |
* HTTP HEAD | * HTTP HEAD |
* | * |
* @return | * @return |
* Raw HTTP Headers of the response. | * Raw HTTP Headers of the response. |
* | * |
* @see: http://www.php.net/manual/en/context.params.php | * @see: http://www.php.net/manual/en/context.params.php |
* | * |
*/ | */ |
function http_head($uri) { | function http_head($uri) { |
curl_setopt($this->curl, CURLOPT_HEADER, 1); | curl_setopt($this->curl, CURLOPT_HEADER, 1); |
$full_url = $this->get_full_url($uri); | $full_url = $this->get_full_url($uri); |
curl_setopt($this->curl, CURLOPT_URL, $full_url); | curl_setopt($this->curl, CURLOPT_URL, $full_url); |
curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, 'HEAD'); | curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, 'HEAD'); |
curl_setopt($this->curl, CURLOPT_NOBODY, true); | curl_setopt($this->curl, CURLOPT_NOBODY, true); |
$response = curl_exec($this->curl); | $response = curl_exec($this->curl); |
// Restore default values | // Restore default values |
curl_setopt($this->curl, CURLOPT_NOBODY, false); | curl_setopt($this->curl, CURLOPT_NOBODY, false); |
curl_setopt($this->curl, CURLOPT_HEADER, false); | curl_setopt($this->curl, CURLOPT_HEADER, false); |
$resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE); | $resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE); |
if ($resp_code == 404 ) { | if ($resp_code == 404 ) { |
throw new SetteeRestClientException("Couch document not found at: '$full_url'"); | throw new SetteeRestClientException("Couch document not found at: '$full_url'"); |
} | } |
if (function_exists('http_parse_headers')) { | if (function_exists('http_parse_headers')) { |
$headers = http_parse_headers($response); | $headers = http_parse_headers($response); |
} | } |
else { | else { |
$headers = $this->_http_parse_headers($response); | $headers = $this->_http_parse_headers($response); |
} | } |
return $headers; | return $headers; |
} | } |
/** | /** |
* Backup PHP impl. for when PECL http_parse_headers() function is not available | * Backup PHP impl. for when PECL http_parse_headers() function is not available |
* | * |
* @param $header | * @param $header |
* @return array | * @return array |
* @source http://www.php.net/manual/en/function.http-parse-headers.php#77241 | * @source http://www.php.net/manual/en/function.http-parse-headers.php#77241 |
*/ | */ |
private function _http_parse_headers( $header ) { | private function _http_parse_headers( $header ) { |
$retVal = array(); | $retVal = array(); |
$fields = explode("\r\n", preg_replace('/\x0D\x0A[\x09\x20]+/', ' ', $header)); | $fields = explode("\r\n", preg_replace('/\x0D\x0A[\x09\x20]+/', ' ', $header)); |
foreach( $fields as $field ) { | foreach( $fields as $field ) { |
if( preg_match('/([^:]+): (.+)/m', $field, $match) ) { | if( preg_match('/([^:]+): (.+)/m', $field, $match) ) { |
$match[1] = preg_replace('/(?<=^|[\x09\x20\x2D])./e', 'strtoupper("\0")', strtolower(trim($match[1]))); | $match[1] = preg_replace('/(?<=^|[\x09\x20\x2D])./e', 'strtoupper("\0")', strtolower(trim($match[1]))); |
if( isset($retVal[$match[1]]) ) { | if( isset($retVal[$match[1]]) ) { |
$retVal[$match[1]] = array($retVal[$match[1]], $match[2]); | $retVal[$match[1]] = array($retVal[$match[1]], $match[2]); |
} else { | } else { |
$retVal[$match[1]] = trim($match[2]); | $retVal[$match[1]] = trim($match[2]); |
} | } |
} | } |
} | } |
return $retVal; | return $retVal; |
} | } |
/** | /** |
* HTTP GET | * HTTP GET |
*/ | */ |
function http_get($uri, $data = array()) { | function http_get($uri, $data = array()) { |
$data = (is_array($data)) ? http_build_query($data) : $data; | $data = (is_array($data)) ? http_build_query($data) : $data; |
if (!empty($data)) { | if (!empty($data)) { |
$uri .= "?$data"; | $uri .= "?$data"; |
} | } |
return $this->http_request('GET', $uri); | return $this->http_request('GET', $uri); |
} | } |
/** | /** |
* HTTP PUT | * HTTP PUT |
*/ | */ |
function http_put($uri, $data = array()) { | function http_put($uri, $data = array()) { |
return $this->http_request('PUT', $uri, $data); | return $this->http_request('PUT', $uri, $data); |
} | } |
/** | /** |
* HTTP DELETE | * HTTP DELETE |
*/ | */ |
function http_delete($uri, $data = array()) { | function http_delete($uri, $data = array()) { |
return $this->http_request('DELETE', $uri, $data); | return $this->http_request('DELETE', $uri, $data); |
} | } |
/** | /** |
* Generic implementation of a HTTP Request. | * Generic implementation of a HTTP Request. |
* | * |
* @param $http_method | * @param $http_method |
* @param $uri | * @param $uri |
* @param array $data | * @param array $data |
* @return | * @return |
* an array containing json and decoded versions of the response. | * an array containing json and decoded versions of the response. |
*/ | */ |
private function http_request($http_method, $uri, $data = array()) { | private function http_request($http_method, $uri, $data = array()) { |
$data = (is_array($data)) ? http_build_query($data) : $data; | $data = (is_array($data)) ? http_build_query($data) : $data; |
if (!empty($data)) { | if (!empty($data)) { |
curl_setopt($this->curl, CURLOPT_HTTPHEADER, array('Content-Length: ' . strlen($data))); | curl_setopt($this->curl, CURLOPT_HTTPHEADER, array('Content-Length: ' . strlen($data))); |
curl_setopt($this->curl, CURLOPT_POSTFIELDS, $data); | curl_setopt($this->curl, CURLOPT_POSTFIELDS, $data); |
} | } |
curl_setopt($this->curl, CURLOPT_URL, $this->get_full_url($uri)); | curl_setopt($this->curl, CURLOPT_URL, $this->get_full_url($uri)); |
curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, $http_method); | curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, $http_method); |
$response = curl_exec($this->curl); | $response = curl_exec($this->curl); |
$response_decoded = $this->decode_response($response); | $response_decoded = $this->decode_response($response); |
$response = array('json' => $response, 'decoded'=>$response_decoded); | $response = array('json' => $response, 'decoded'=>$response_decoded); |
$this->check_status($response,$uri); | $this->check_status($response,$uri); |
return $response; | return $response; |
} | } |
/** | /** |
* Check http status for safe return codes | * Check http status for safe return codes |
* | * |
* @throws SetteeRestClientException | * @throws SetteeRestClientException |
*/ | */ |
private function check_status($response,$uri) { | private function check_status($response,$uri) { |
$resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE); | $resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE); |
if ($resp_code < 199 || $resp_code > 399 || !empty($response['decoded']->error)) { | if ($resp_code < 199 || $resp_code > 399 || !empty($response['decoded']->error)) { |
$msg = "CouchDB returned: \"HTTP 1.1. $resp_code\". ERROR: " . $response['json'] . $uri; | $msg = "CouchDB returned: \"HTTP 1.1. $resp_code\". ERROR: " . $response['json'] . $uri; |
throw new SetteeRestClientException($msg); | throw new SetteeRestClientException($msg); |
} | } |
} | } |
/** | /** |
* @param $path | * @param $path |
* Full path to a file (e.g. as returned by PHP's realpath function). | * Full path to a file (e.g. as returned by PHP's realpath function). |
* @return void | * @return void |
*/ | */ |
public function file_mime_type ($path) { | public function file_mime_type ($path) { |
$ftype = 'application/octet-stream'; | $ftype = 'application/octet-stream'; |
if (function_exists("finfo_file")) { | if (function_exists("finfo_file")) { |
$finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK); | $finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK); |
$fres = $finfo->file($path); | $fres = $finfo->file($path); |
if (is_string($fres) && !empty($fres)) { | if (is_string($fres) && !empty($fres)) { |
$ftype = $fres; | $ftype = $fres; |
} | } |
} | } |
return $ftype; | return $ftype; |
} | } |
/** | /** |
* @param $content | * @param $content |
* content of a file in a string buffer format. | * content of a file in a string buffer format. |
* @return void | * @return void |
*/ | */ |
public function content_mime_type ($content) { | public function content_mime_type ($content) { |
$ftype = 'application/octet-stream'; | $ftype = 'application/octet-stream'; |
if (function_exists("finfo_file")) { | if (function_exists("finfo_file")) { |
$finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK); | $finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK); |
$fres = $finfo->buffer($content); | $fres = $finfo->buffer($content); |
if (is_string($fres) && !empty($fres)) { | if (is_string($fres) && !empty($fres)) { |
$ftype = $fres; | $ftype = $fres; |
} | } |
} | } |
return $ftype; | return $ftype; |
} | } |
/** | /** |
* | * |
* @param $json | * @param $json |
* json-encoded response from CouchDB | * json-encoded response from CouchDB |
* | * |
* @return | * @return |
* decoded PHP object | * decoded PHP object |
*/ | */ |
private function decode_response($json) { | private function decode_response($json) { |
return json_decode($json); | return json_decode($json); |
} | } |
/** | /** |
* Get full URL from a partial one | * Get full URL from a partial one |
*/ | */ |
private function get_full_url($uri) { | private function get_full_url($uri) { |
// We do not want "/", "?", "&" and "=" separators to be encoded!!! | // We do not want "/", "?", "&" and "=" separators to be encoded!!! |
$uri = str_replace(array('%2F', '%3F', '%3D', '%26'), array('/', '?', '=', '&'), urlencode($uri)); | $uri = str_replace(array('%2F', '%3F', '%3D', '%26'), array('/', '?', '=', '&'), urlencode($uri)); |
return $this->base_url . '/' . $uri; | return $this->base_url . '/' . $uri; |
} | } |
} | } |
class SetteeRestClientException extends Exception {} | class SetteeRestClientException extends Exception {} |
<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | include_header_documents("About"); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
?> | ?> |
<h1>About</h1> | <h1>About</h1> |
<?php | <?php |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
<?php | |
include('template.inc.php'); | |
include_once('../include/common.inc.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 = $server->get_db('disclosr-foidocuments'); | |
include_header_documents((isset($_REQUEST['id']) ? $idtoname[$_REQUEST['id']] : 'Entries by Agency')); | |
$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99'); | |
?> | |
<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div> | |
<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br> | |
<?php | |
try { | |
if ($_REQUEST['id']) { | |
$rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows; | |
foreach ($rows as $row) { | |
//print_r($rows); | |
echo displayLogEntry($row, $idtoname); | |
if (!isset($startkey)) | |
$startkey = $row->key; | |
$endkey = $row->key; | |
} | |
} else { | |
$rows = $foidocsdb->get_view("app", "byAgencyID?group=true", null, false, false, true)->rows; | |
if ($rows) { | |
foreach ($rows as $row) { | |
echo '<a href="agency.php?id=' . $row->key . '">' . $idtoname[$row->key] . " (" . $row->value . " records)</a> <br>\n"; | |
} | |
} | |
} | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>"; | |
include_footer_documents(); | |
?> |
<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | include_header_documents("Charts"); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$idtoname = Array(); | $idtoname = Array(); |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { |
$idtoname[$row->id] = trim($row->value->name); | $idtoname[$row->id] = trim($row->value->name); |
} | } |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | $foidocsdb = $server->get_db('disclosr-foidocuments'); |
?> | ?> |
<div class="foundation-header"> | <div class="foundation-header"> |
<h1><a href="about.php">Charts</a></h1> | <h1><a href="about.php">Charts</a></h1> |
<h4 class="subheader">Lorem ipsum.</h4> | <h4 class="subheader">Lorem ipsum.</h4> |
</div> | </div> |
<div id="employees" style="width:1000px;height:900px;"></div> | <div id="bydate" style="width:1000px;height:300px;"></div> |
<div id="byagency" style="width:1200px;height:300px;"></div> | |
<script id="source"> | <script id="source"> |
window.onload = function() { | window.onload = function() { |
$(document).ready(function() { | $(document).ready(function() { |
var | var |
d1 = [], | d1 = [], |
start = new Date("2009/01/01 01:00").getTime(), | options1, |
options, | o1; |
graph, | |
i, x, o; | |
<?php | <?php |
try { | try { |
$rows = $foidocsdb->get_view("app", "byDate?group=true", null, true)->rows; | $rows = $foidocsdb->get_view("app", "byDateMonthYear?group=true",null, false,false,true)->rows; |
$dataValues = Array(); | $dataValues = Array(); |
foreach ($rows as $row) { | foreach ($rows as $row) { |
$dataValues[$row->value] = $row->key; | $dataValues[$row->key] = $row->value; |
} | } |
$i = 0; | $i = 0; |
ksort($dataValues); | ksort($dataValues); |
foreach ($dataValues as $value => $key) { | foreach ($dataValues as $key => $value) { |
$date = date_create_from_format('Y-m-d', $key); | $date = date_create_from_format('Y-m-d', $key); |
if (date_format($date, 'U') != "") { | if (date_format($date, 'U') != "") { |
echo " d1.push([".date_format($date, 'U')."000, $value]);" . PHP_EOL; | echo " d1.push([".date_format($date, 'U')."000, $value]);" . PHP_EOL; |
// echo " emplabels.push('$key');" . PHP_EOL; | // echo " emplabels.push('$key');" . PHP_EOL; |
$i++; | $i++; |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
?> | ?> |
options = { | options1 = { |
xaxis : { | xaxis : { |
mode : 'time', | mode : 'time', |
labelsAngle : 45 | labelsAngle : 45 |
}, | }, |
selection : { | selection : { |
mode : 'x' | mode : 'x' |
}, | }, |
HtmlText : false, | HtmlText : false, |
title : 'Time' | title : 'Time' |
}; | }; |
// Draw graph with default options, overwriting with passed options | // Draw graph with default options, overwriting with passed options |
function drawGraph (opts) { | function drawGraph (opts) { |
// Clone the options, so the 'options' variable always keeps intact. | // Clone the options, so the 'options' variable always keeps intact. |
o = Flotr._.extend(Flotr._.clone(options), opts || {}); | o1 = Flotr._.extend(Flotr._.clone(options1), opts || {}); |
// Return a new graph. | // Return a new graph. |
return Flotr.draw( | return Flotr.draw( |
document.getElementById("employees"), | document.getElementById("bydate"), |
[ d1 ], | [ d1 ], |
o | o1 |
); | ); |
} | } |
graph = drawGraph(); | graph = drawGraph(); |
Flotr.EventAdapter.observe(container, 'flotr:select', function(area){ | Flotr.EventAdapter.observe(document.getElementById("bydate"), 'flotr:select', function(area){ |
// Draw selected area | // Draw selected area |
graph = drawGraph({ | graph = drawGraph({ |
xaxis : { min : area.x1, max : area.x2, mode : 'time', labelsAngle : 45 }, | xaxis : { min : area.x1, max : area.x2, mode : 'time', labelsAngle : 45 }, |
yaxis : { min : area.y1, max : area.y2 } | yaxis : { min : area.y1, max : area.y2 } |
}); | }); |
}); | }); |
// When graph is clicked, draw the graph with default area. | // When graph is clicked, draw the graph with default area. |
Flotr.EventAdapter.observe(container, 'flotr:click', function () { graph = drawGraph(); }); | Flotr.EventAdapter.observe(document.getElementById("bydate"), 'flotr:click', function () { graph = drawGraph(); }); |
}); | }); |
}; | }; |
var d2 = []; | |
var agencylabels = []; | |
function agencytrackformatter(obj) { | |
return agencylabels[Math.floor(obj.x)] +" = "+obj.y; | |
} | |
function agencytickformatter(val, axis) { | |
if (agencylabels[Math.floor(val)]) { | |
return '<p style="margin-top:8em;-webkit-transform:rotate(-90deg);">'+(agencylabels[Math.floor(val)])+"</b>"; | |
} else { | |
return ""; | |
} | |
} | |
<?php | |
try { | |
$rows = $foidocsdb->get_view("app", "byAgencyID?group=true",null, false,false,true)->rows; | |
$dataValues = Array(); | |
$i = 0; | |
foreach ($rows as $row) { | |
echo " d2.push([".$i.", $row->value]);" . PHP_EOL; | |
echo " agencylabels.push(['".str_replace("'","",$idtoname[$row->key])."']);" . PHP_EOL; | |
$i++; | |
} | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
?> | |
// Draw the graph | |
Flotr.draw( | |
document.getElementById("byagency"), | |
[d2], | |
{ | |
bars : { | |
show : true, | |
horizontal : false, | |
shadowSize : 0, | |
barWidth : 0.5 | |
}, | |
mouse : { | |
track : true, | |
relative : true, | |
trackFormatter: agencytrackformatter | |
}, | |
yaxis : { | |
min : 0, | |
autoscaleMargin : 1 | |
}, | |
xaxis: { | |
minorTickFreq: 1, | |
noTicks: agencylabels.length, | |
showMinorLabels: true, | |
tickFormatter: agencytickformatter | |
}, | |
legend: { | |
show: false | |
} | |
} | |
); | |
</script> | </script> |
<?php | <?php |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
<?php | |
include('template.inc.php'); | |
include_header_documents("Entries by Date"); | |
include_once('../include/common.inc.php'); | |
$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99'); | |
?> | |
<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div> | |
<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br> | |
<?php | |
/*$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 { | |
$rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20)->rows; | |
if ($rows) { | |
foreach ($rows as $key => $row) { | |
echo displayLogEntry($row, $idtoname); | |
if (!isset($startkey)) $startkey = $row->key; | |
$endkey = $row->key; | |
} | |
} | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>"; | |
*/ | |
include_footer_documents(); | |
?> | |
<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | include_header_documents("List of Disclosure Logs"); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
echo "<table> | echo "<table> |
<tr><th>Agency Name</th><th>Disclosure Log URL recorded?</th><th>Do we monitor this URL?</th></tr>"; | <tr><th>Agency Name</th><th>Disclosure Log URL recorded?</th><th>Do we monitor this URL?</th></tr>"; |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$docsdb = $server->get_db('disclosr-documents'); | $docsdb = $server->get_db('disclosr-documents'); |
$agencies = 0; | $agencies = 0; |
$disclogs = 0; | $disclogs = 0; |
$red = 0; | $red = 0; |
$green = 0; | $green = 0; |
$yellow = 0; | $yellow = 0; |
$orange = 0; | $orange = 0; |
try { | try { |
$rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows; | $rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows; |
if ($rows) { | if ($rows) { |
foreach ($rows as $row) { | foreach ($rows as $row) { |
if ((!isset($row->value->status) || $row->value->status != "suspended") && isset($row->value->foiEmail)) { | if ((!isset($row->value->status) || $row->value->status != "suspended") && isset($row->value->foiEmail)) { |
echo "<tr><td>"; | echo "<tr><td>"; |
if (isset($row->value->website)) echo "<a href='" . $row->value->website . "'>"; | if (isset($row->value->website)) echo "<a href='" . $row->value->website . "'>"; |
echo "<b>" . $row->value->name . "</b>"; | echo "<b>" . $row->value->name . "</b>"; |
if (isset($row->value->website)) echo "</a>"; | if (isset($row->value->website)) echo "</a>"; |
if ($ENV == "DEV") | if ($ENV == "DEV") |
echo "<br>(" . $row->id . ")"; | echo "<br>(" . $row->id . ")"; |
echo "</td>\n"; | echo "</td>\n"; |
$agencies++; | $agencies++; |
echo "<td>"; | echo "<td>"; |
if (isset($row->value->FOIDocumentsURL)) { | if (isset($row->value->FOIDocumentsURL)) { |
$disclogs++; | $disclogs++; |
echo '<a href="' . $row->value->FOIDocumentsURL . '">' | echo '<a href="' . $row->value->FOIDocumentsURL . '">' |
. $row->value->FOIDocumentsURL . '</a>'; | . $row->value->FOIDocumentsURL . '</a>'; |
if ($ENV == "DEV") | if ($ENV == "DEV") |
echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">' | echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">' |
. 'view local copy</a>)</small>'; | . 'view local copy</a>)</small>'; |
} else { | } else { |
echo "<font color='red'><abbr title='No'>✘</abbr></font>"; | echo "<font color='red'><abbr title='No'>✘</abbr></font>"; |
} | } |
echo "</td>\n<td>"; | echo "</td>\n<td>"; |
if (isset($row->value->FOIDocumentsURL)) { | if (isset($row->value->FOIDocumentsURL)) { |
if (file_exists("./scrapers/" . $row->id . '.py')) { | if (file_exists("./scrapers/" . $row->id . '.py')) { |
echo "<font color='green'><abbr title='Yes'>✔</abbr></font>"; | echo "<font color='green'><abbr title='Yes'>✔</abbr></font>"; |
$green++; | $green++; |
} else if (file_exists("./scrapers/" . $row->id . '.txt')) { | } else if (file_exists("./scrapers/" . $row->id . '.txt')) { |
if (trim(file_get_contents("./scrapers/" . $row->id . '.txt')) == "no disclog") { | 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>"; | echo "<font color='yellow'><abbr title='No log table exists at URL to scrape'><b>◎</b></abbr></font>"; |
$yellow++; | $yellow++; |
} else { | } else { |
echo file_get_contents("./scrapers/" . $row->id . '.txt'); | echo file_get_contents("./scrapers/" . $row->id . '.txt'); |
echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>"; | echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>"; |
$orange++; | $orange++; |
} | } |
} else { | } else { |
echo "<font color='red'><abbr title='No'>✘</abbr></font>"; | echo "<font color='red'><abbr title='No'>✘</abbr></font>"; |
$red++; | $red++; |
} | } |
} | } |
echo "</td></tr>\n"; | echo "</td></tr>\n"; |
} | } |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo "</table>"; | echo "</table>"; |
echo $agencies . " agencies, " . round(($disclogs / $agencies) * 100) . "% with disclosure logs; " | 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 / $disclogs) * 100) . "% logs Work-In-Progress scrapers "; | . round(($green / $disclogs) * 100) . "% logs with scrapers " . round(($red / $disclogs) * 100) . "% logs without scrapers " . round(($orange / $disclogs) * 100) . "% logs Work-In-Progress scrapers "; |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
import sys | import sys |
import os | import os |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
import scrape | import scrape |
from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
from time import mktime | from time import mktime |
import feedparser | import feedparser |
import abc | import abc |
import unicodedata | import unicodedata |
import re | import re |
import dateutil | import dateutil |
from dateutil.parser import * | from dateutil.parser import * |
from datetime import * | from datetime import * |
import codecs | import codecs |
import difflib | |
from StringIO import StringIO | from StringIO import StringIO |
from pdfminer.pdfparser import PDFDocument, PDFParser | from pdfminer.pdfparser import PDFDocument, PDFParser |
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf | from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf |
from pdfminer.pdfdevice import PDFDevice, TagExtractor | from pdfminer.pdfdevice import PDFDevice, TagExtractor |
from pdfminer.converter import TextConverter | from pdfminer.converter import TextConverter |
from pdfminer.cmapdb import CMapDB | from pdfminer.cmapdb import CMapDB |
from pdfminer.layout import LAParams | from pdfminer.layout import LAParams |
class GenericDisclogScraper(object): | class GenericDisclogScraper(object): |
__metaclass__ = abc.ABCMeta | __metaclass__ = abc.ABCMeta |
agencyID = None | agencyID = None |
disclogURL = None | disclogURL = None |
def remove_control_chars(self, input): | def remove_control_chars(self, input): |
return "".join([i for i in input if ord(i) in range(32, 127)]) | return "".join([i for i in input if ord(i) in range(32, 127)]) |
def getAgencyID(self): | def getAgencyID(self): |
""" disclosr agency id """ | """ disclosr agency id """ |
if self.agencyID is None: | if self.agencyID is None: |
self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "") | self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "") |
return self.agencyID | return self.agencyID |
def getURL(self): | def getURL(self): |
""" disclog URL""" | """ disclog URL""" |
if self.disclogURL is None: | if self.disclogURL is None: |
agency = scrape.agencydb.get(self.getAgencyID()) | agency = scrape.agencydb.get(self.getAgencyID()) |
self.disclogURL = agency['FOIDocumentsURL'] | self.disclogURL = agency['FOIDocumentsURL'] |
return self.disclogURL | return self.disclogURL |
@abc.abstractmethod | @abc.abstractmethod |
def doScrape(self): | def doScrape(self): |
""" do the scraping """ | """ do the scraping """ |
return | return |
class GenericHTMLDisclogScraper(GenericDisclogScraper): | |
def doScrape(self): | |
foidocsdb = scrape.couch['disclosr-foidocuments'] | |
(url, mime_type, rcontent) = scrape.fetchURL(scrape.docsdb, | |
self.getURL(), "foidocuments", self.getAgencyID()) | |
content = rcontent | |
dochash = scrape.mkhash(content) | |
doc = foidocsdb.get(dochash) | |
if doc is None: | |
print "saving " + dochash | |
description = "This log may have updated but as it was not in a table last time we viewed it, we cannot extract what has changed. Please refer to the agency's website Disclosure Log to see the most recent entries" | |
last_attach = scrape.getLastAttachment(scrape.docsdb, self.getURL()) | |
if last_attach != None: | |
html_diff = difflib.HtmlDiff() | |
description = description + "\nChanges: " | |
description = description + html_diff.make_table(last_attach.read().split('\n'), | |
content.split('\n')) | |
edate = date.today().strftime("%Y-%m-%d") | |
doc = {'_id': dochash, 'agencyID': self.getAgencyID() | |
, 'url': self.getURL(), 'docID': dochash, | |
"date": edate, "title": "Disclosure Log Updated", "description": description} | |
foidocsdb.save(doc) | |
else: | |
print "already saved" | |
class GenericPDFDisclogScraper(GenericDisclogScraper): | class GenericPDFDisclogScraper(GenericDisclogScraper): |
def doScrape(self): | def doScrape(self): |
foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
self.getURL(), "foidocuments", self.getAgencyID()) | self.getURL(), "foidocuments", self.getAgencyID()) |
laparams = LAParams() | laparams = LAParams() |
rsrcmgr = PDFResourceManager(caching=True) | rsrcmgr = PDFResourceManager(caching=True) |
outfp = StringIO() | outfp = StringIO() |
device = TextConverter(rsrcmgr, outfp, codec='utf-8', | device = TextConverter(rsrcmgr, outfp, codec='utf-8', |
laparams=laparams) | laparams=laparams) |
fp = StringIO() | fp = StringIO() |
fp.write(content.read()) | fp.write(content) |
process_pdf(rsrcmgr, device, fp, set(), caching=True, | process_pdf(rsrcmgr, device, fp, set(), caching=True, |
check_extractable=True) | check_extractable=True) |
description = outfp.getvalue() | description = outfp.getvalue() |
fp.close() | fp.close() |
device.close() | device.close() |
outfp.close() | outfp.close() |
dochash = scrape.mkhash(description) | dochash = scrape.mkhash(description) |
doc = foidocsdb.get(dochash) | doc = foidocsdb.get(dochash) |
if doc is None: | if doc is None: |
print "saving " + dochash | print "saving " + dochash |
edate = date.today().strftime("%Y-%m-%d") | edate = date.today().strftime("%Y-%m-%d") |
doc = {'_id': dochash, 'agencyID': self.getAgencyID() | doc = {'_id': dochash, 'agencyID': self.getAgencyID() |
, 'url': self.getURL(), 'docID': dochash, | , 'url': self.getURL(), 'docID': dochash, |
"date": edate, "title": "Disclosure Log Updated", "description": description} | "date": edate, "title": "Disclosure Log Updated", "description": description} |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved" | print "already saved" |
class GenericDOCXDisclogScraper(GenericDisclogScraper): | class GenericDOCXDisclogScraper(GenericDisclogScraper): |
def doScrape(self): | def doScrape(self): |
foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb |
, self.getURL(), "foidocuments", self.getAgencyID()) | , self.getURL(), "foidocuments", self.getAgencyID()) |
mydoc = zipfile.ZipFile(file) | mydoc = zipfile.ZipFile(file) |
xmlcontent = mydoc.read('word/document.xml') | xmlcontent = mydoc.read('word/document.xml') |
document = etree.fromstring(xmlcontent) | document = etree.fromstring(xmlcontent) |
## Fetch all the text out of the document we just created | ## Fetch all the text out of the document we just created |
paratextlist = getdocumenttext(document) | paratextlist = getdocumenttext(document) |
# Make explicit unicode version | # Make explicit unicode version |
newparatextlist = [] | newparatextlist = [] |
for paratext in paratextlist: | for paratext in paratextlist: |
newparatextlist.append(paratext.encode("utf-8")) | newparatextlist.append(paratext.encode("utf-8")) |
## Print our documnts test with two newlines under each paragraph | ## Print our documnts test with two newlines under each paragraph |
description = '\n\n'.join(newparatextlist).strip(' \t\n\r') | description = '\n\n'.join(newparatextlist).strip(' \t\n\r') |
dochash = scrape.mkhash(description) | dochash = scrape.mkhash(description) |
doc = foidocsdb.get(dochash) | doc = foidocsdb.get(dochash) |
if doc is None: | if doc is None: |
print "saving " + dochash | print "saving " + dochash |
edate = time().strftime("%Y-%m-%d") | edate = time().strftime("%Y-%m-%d") |
doc = {'_id': dochash, 'agencyID': self.getAgencyID() | doc = {'_id': dochash, 'agencyID': self.getAgencyID() |
, 'url': self.getURL(), 'docID': dochash, | , 'url': self.getURL(), 'docID': dochash, |
"date": edate, "title": "Disclosure Log Updated", "description": description} | "date": edate, "title": "Disclosure Log Updated", "description": description} |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved" | print "already saved" |
class GenericRSSDisclogScraper(GenericDisclogScraper): | class GenericRSSDisclogScraper(GenericDisclogScraper): |
def doScrape(self): | def doScrape(self): |
foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
self.getURL(), "foidocuments", self.getAgencyID()) | self.getURL(), "foidocuments", self.getAgencyID()) |
feed = feedparser.parse(content) | feed = feedparser.parse(content) |
for entry in feed.entries: | for entry in feed.entries: |
#print entry | #print entry |
print entry.id | print entry.id |
dochash = scrape.mkhash(entry.id) | dochash = scrape.mkhash(entry.id) |
doc = foidocsdb.get(dochash) | doc = foidocsdb.get(dochash) |
#print doc | #print doc |
if doc is None: | if doc is None: |
print "saving " + dochash | print "saving " + dochash |
edate = datetime.fromtimestamp( | edate = datetime.fromtimestamp( |
mktime(entry.published_parsed)).strftime("%Y-%m-%d") | mktime(entry.published_parsed)).strftime("%Y-%m-%d") |
doc = {'_id': dochash, 'agencyID': self.getAgencyID(), | doc = {'_id': dochash, 'agencyID': self.getAgencyID(), |
'url': entry.link, 'docID': entry.id, | 'url': entry.link, 'docID': entry.id, |
"date": edate, "title": entry.title} | "date": edate, "title": entry.title} |
self.getDescription(entry, entry, doc) | self.getDescription(entry, entry, doc) |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved" | print "already saved" |
def getDescription(self, content, entry, doc): | def getDescription(self, content, entry, doc): |
""" get description from rss entry""" | """ get description from rss entry""" |
doc.update({'description': content.summary}) | doc.update({'description': content.summary}) |
return | return |
class GenericOAICDisclogScraper(GenericDisclogScraper): | class GenericOAICDisclogScraper(GenericDisclogScraper): |
__metaclass__ = abc.ABCMeta | __metaclass__ = abc.ABCMeta |
@abc.abstractmethod | @abc.abstractmethod |
def getColumns(self, columns): | def getColumns(self, columns): |
""" rearranges columns if required """ | """ rearranges columns if required """ |
return | return |
def getColumnCount(self): | def getColumnCount(self): |
return 5 | return 5 |
def getDescription(self, content, entry, doc): | def getDescription(self, content, entry, doc): |
""" get description from rss entry""" | """ get description from rss entry""" |
descriptiontxt = "" | descriptiontxt = "" |
for string in content.stripped_strings: | for string in content.stripped_strings: |
descriptiontxt = descriptiontxt + " \n" + string | descriptiontxt = descriptiontxt + " \n" + string |
doc.update({'description': descriptiontxt}) | doc.update({'description': descriptiontxt}) |
def getTitle(self, content, entry, doc): | def getTitle(self, content, entry, doc): |
doc.update({'title': (''.join(content.stripped_strings))}) | doc.update({'title': (''.join(content.stripped_strings))}) |
def getTable(self, soup): | def getTable(self, soup): |
return soup.table | return soup.table |
def getRows(self, table): | def getRows(self, table): |
return table.find_all('tr') | return table.find_all('tr') |
def getDate(self, content, entry, doc): | def getDate(self, content, entry, doc): |
date = ''.join(content.stripped_strings).strip() | date = ''.join(content.stripped_strings).strip() |
(a, b, c) = date.partition("(") | (a, b, c) = date.partition("(") |
date = self.remove_control_chars(a.replace("Octber", "October")) | date = self.remove_control_chars(a.replace("Octber", "October")) |
print date | print date |
edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") |
print edate | print edate |
doc.update({'date': edate}) | doc.update({'date': edate}) |
return | return |
def getLinks(self, content, entry, doc): | def getLinks(self, content, entry, doc): |
links = [] | links = [] |
for atag in entry.find_all("a"): | for atag in entry.find_all("a"): |
if atag.has_key('href'): | if atag.has_key('href'): |
links.append(scrape.fullurl(content, atag['href'])) | links.append(scrape.fullurl(content, atag['href'])) |
if links != []: | if links != []: |
doc.update({'links': links}) | doc.update({'links': links}) |
return | return |
def doScrape(self): | def doScrape(self): |
foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
self.getURL(), "foidocuments", self.getAgencyID()) | self.getURL(), "foidocuments", self.getAgencyID()) |
if content is not None: | if content is not None: |
if mime_type is "text/html"\ | if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type == "application/xml": |
or mime_type is "application/xhtml+xml"\ | |
or mime_type is"application/xml": | |
# http://www.crummy.com/software/BeautifulSoup/documentation.html | # http://www.crummy.com/software/BeautifulSoup/documentation.html |
print "parsing" | |
soup = BeautifulSoup(content) | soup = BeautifulSoup(content) |
table = self.getTable(soup) | table = self.getTable(soup) |
for row in self.getRows(table): | for row in self.getRows(table): |
columns = row.find_all('td') | columns = row.find_all('td') |
if len(columns) is self.getColumnCount(): | if len(columns) is self.getColumnCount(): |
(id, date, title, | (id, date, title, |
description, notes) = self.getColumns(columns) | description, notes) = self.getColumns(columns) |
print self.remove_control_chars( | print self.remove_control_chars( |
''.join(id.stripped_strings)) | ''.join(id.stripped_strings)) |
if id.string is None: | if id.string is None: |
dochash = scrape.mkhash( | dochash = scrape.mkhash( |
self.remove_control_chars( | self.remove_control_chars( |
url + (''.join(date.stripped_strings)))) | url + (''.join(date.stripped_strings)))) |
else: | else: |
dochash = scrape.mkhash( | dochash = scrape.mkhash( |
self.remove_control_chars( | self.remove_control_chars( |
url + (''.join(id.stripped_strings)))) | url + (''.join(id.stripped_strings)))) |
doc = foidocsdb.get(hash) | doc = foidocsdb.get(dochash) |
if doc is None: | if doc is None: |
print "saving " + hash | print "saving " + dochash |
doc = {'_id': hash, | doc = {'_id': dochash, |
'agencyID': self.getAgencyID(), | 'agencyID': self.getAgencyID(), |
'url': self.getURL(), | 'url': self.getURL(), |
'docID': (''.join(id.stripped_strings))} | 'docID': (''.join(id.stripped_strings))} |
self.getLinks(self.getURL(), row, doc) | self.getLinks(self.getURL(), row, doc) |
self.getTitle(title, row, doc) | self.getTitle(title, row, doc) |
self.getDate(date, row, doc) | self.getDate(date, row, doc) |
self.getDescription(description, row, doc) | self.getDescription(description, row, doc) |
if notes is not None: | if notes is not None: |
doc.update({ 'notes': ( | doc.update({ 'notes': ( |
''.join(notes.stripped_strings))}) | ''.join(notes.stripped_strings))}) |
badtitles = ['-','Summary of FOI Request' | badtitles = ['-','Summary of FOI Request' |
, 'FOI request(in summary form)' | , 'FOI request(in summary form)' |
, 'Summary of FOI request received by the ASC', | , 'Summary of FOI request received by the ASC', |
'Summary of FOI request received by agency/minister', | 'Summary of FOI request received by agency/minister', |
'Description of Documents Requested','FOI request', | 'Description of Documents Requested','FOI request', |
'Description of FOI Request','Summary of request','Description','Summary', | 'Description of FOI Request','Summary of request','Description','Summary', |
'Summary of FOIrequest received by agency/minister','Summary of FOI request received','Description of FOI Request',"FOI request",'Results 1 to 67 of 67'] | 'Summary of FOIrequest received by agency/minister','Summary of FOI request received','Description of FOI Request',"FOI request",'Results 1 to 67 of 67'] |
if doc['title'] not in badtitles\ | if doc['title'] not in badtitles\ |
and doc['description'] != '': | and doc['description'] != '': |
print "saving" | print "saving" |
foidocsdb.save(doc) | foidocsdb.save(doc) |
else: | else: |
print "already saved " + dochash | print "already saved " + dochash |
elif len(row.find_all('th')) is self.getColumnCount(): | elif len(row.find_all('th')) is self.getColumnCount(): |
print "header row" | print "header row" |
else: | else: |
print "ERROR number of columns incorrect" | print "ERROR number of columns incorrect" |
print row | print row |
Binary files /dev/null and b/documents/img/feed-icon-14x14.png differ
<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | include_header_documents(""); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
$startkey = (isset($_REQUEST['start_key']) ? $_REQUEST['start_key'] : '9999-99-99'); | $endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99'); |
$enddocid = (isset($_REQUEST['end_docid']) ? $_REQUEST['end_docid'] : null); | |
?> | ?> |
<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div> | |
<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br> | |
<?php | <?php |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$idtoname = Array(); | $idtoname = Array(); |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { |
$idtoname[$row->id] = trim($row->value->name); | $idtoname[$row->id] = trim($row->value->name); |
} | } |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | $foidocsdb = $server->get_db('disclosr-foidocuments'); |
try { | try { |
$rows = $foidocsdb->get_view("app", "byDate", Array($startkey, '0000-00-00'), true, 20)->rows; | $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20,null, $enddocid)->rows; |
if ($rows) { | if ($rows) { |
foreach ($rows as $key => $row) { | foreach ($rows as $key => $row) { |
echo displayLogEntry($row, $idtoname); | echo displayLogEntry($row, $idtoname); |
if (!isset($startkey)) | |
$startkey = $row->key; | |
$endkey = $row->key; | $endkey = $row->key; |
$enddocid = $row->value->_id; | |
} | } |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo "<a href='?start_key=$endkey'>next page</a>"; | echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey&end_docid=$enddocid' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>"; |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
<?php | <?php |
// Agency X updated Y, new files, diff of plain text/link text, | // Agency X updated Y, new files, diff of plain text/link text, |
// feed for just one agency or all | // feed for just one agency or all |
// This is a minimum example of using the Universal Feed Generator Class | // This is a minimum example of using the Universal Feed Generator Class |
include("../lib/FeedWriter/FeedTypes.php"); | include("../lib/FeedWriter/FeedTypes.php"); |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
//Creating an instance of FeedWriter class. | //Creating an instance of FeedWriter class. |
$TestFeed = new RSS2FeedWriter(); | $TestFeed = new RSS2FeedWriter(); |
//Setting the channel elements | //Setting the channel elements |
//Use wrapper functions for common channelelements | ////Retriving informations from database |
$TestFeed->setTitle('disclosurelo.gs Newest Entries - All'); | |
$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'); | |
$TestFeed->setDescription('disclosurelo.gs Newest Entries - All Agencies'); | |
$TestFeed->setChannelElement('language', 'en-us'); | |
$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time())); | |
//Retriving informations from database | |
$idtoname = Array(); | $idtoname = Array(); |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { |
$idtoname[$row->id] = trim($row->value->name); | $idtoname[$row->id] = trim($row->value->name); |
} | } |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | $foidocsdb = $server->get_db('disclosr-foidocuments'); |
$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows; | if (isset($_REQUEST['id'])) { |
$rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows; | |
$title = $idtoname[$_REQUEST['id']]; | |
} else { | |
$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows; | |
$title = 'All Agencies'; | |
} | |
//Use wrapper functions for common channelelements | |
$TestFeed->setTitle('disclosurelo.gs Newest Entries - '.$title); | |
$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'.(isset($_REQUEST['id'])? '?id='.$_REQUEST['id'] : '')); | |
$TestFeed->setDescription('disclosurelo.gs Newest Entries - '.$title); | |
$TestFeed->setChannelElement('language', 'en-us'); | |
$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time())); | |
//print_r($rows); | //print_r($rows); |
foreach ($rows as $row) { | foreach ($rows as $row) { |
//Create an empty FeedItem | //Create an empty FeedItem |
$newItem = $TestFeed->createNewItem(); | $newItem = $TestFeed->createNewItem(); |
//Add elements to the feed item | //Add elements to the feed item |
$newItem->setTitle($row->value->title); | $newItem->setTitle($row->value->title); |
$newItem->setLink("http://disclosurelo.gs/view.php?id=" . $row->value->_id); | $newItem->setLink("http://disclosurelo.gs/view.php?id=" . $row->value->_id); |
$newItem->setDate(strtotime($row->value->date)); | $newItem->setDate(strtotime($row->value->date)); |
$newItem->setDescription(displayLogEntry($row, $idtoname)); | $newItem->setDescription(displayLogEntry($row, $idtoname)); |
$newItem->setAuthor($idtoname[$row->value->agencyID]); | $newItem->setAuthor($idtoname[$row->value->agencyID]); |
$newItem->addElement('guid', "http://disclosurelo.gs/view.php?id=" . $row->value->_id, array('isPermaLink' => 'true')); | $newItem->addElement('guid', "http://disclosurelo.gs/view.php?id=" . $row->value->_id, array('isPermaLink' => 'true')); |
//Now add the feed item | //Now add the feed item |
$TestFeed->addItem($newItem); | $TestFeed->addItem($newItem); |
} | } |
//OK. Everything is done. Now genarate the feed. | //OK. Everything is done. Now genarate the feed. |
$TestFeed->generateFeed(); | $TestFeed->generateFeed(); |
?> | ?> |
for f in scrapers/*.py; do echo "Processing $f file.."; python $f; done | for f in scrapers/*.py; |
do echo "Processing $f file.."; | |
python $f; | |
if [ "$?" -ne "0" ]; then | |
echo "error"; | |
sleep 2; | |
fi | |
done | |
#http://packages.python.org/CouchDB/client.html | #http://packages.python.org/CouchDB/client.html |
import couchdb | import couchdb |
import urllib2 | import urllib2 |
from BeautifulSoup import BeautifulSoup | from BeautifulSoup import BeautifulSoup |
import re | import re |
import hashlib | import hashlib |
from urlparse import urljoin | from urlparse import urljoin |
import time | import time |
import os | import os |
import mimetypes | import mimetypes |
import urllib | import urllib |
import urlparse | import urlparse |
def mkhash(input): | def mkhash(input): |
return hashlib.md5(input).hexdigest().encode("utf-8") | return hashlib.md5(input).hexdigest().encode("utf-8") |
def canonurl(url): | def canonurl(url): |
r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or '' | r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or '' |
if the URL looks invalid. | if the URL looks invalid. |
>>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws | >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws |
'http://xn--hgi.ws/' | 'http://xn--hgi.ws/' |
""" | """ |
# strip spaces at the ends and ensure it's prefixed with 'scheme://' | # strip spaces at the ends and ensure it's prefixed with 'scheme://' |
url = url.strip() | url = url.strip() |
if not url: | if not url: |
return '' | return '' |
if not urlparse.urlsplit(url).scheme: | if not urlparse.urlsplit(url).scheme: |
url = 'http://' + url | url = 'http://' + url |
# turn it into Unicode | # turn it into Unicode |
#try: | #try: |
# url = unicode(url, 'utf-8') | # url = unicode(url, 'utf-8') |
#except UnicodeDecodeError: | #except UnicodeDecodeError: |
# return '' # bad UTF-8 chars in URL | # return '' # bad UTF-8 chars in URL |
# parse the URL into its components | # parse the URL into its components |
parsed = urlparse.urlsplit(url) | parsed = urlparse.urlsplit(url) |
scheme, netloc, path, query, fragment = parsed | scheme, netloc, path, query, fragment = parsed |
# ensure scheme is a letter followed by letters, digits, and '+-.' chars | # ensure scheme is a letter followed by letters, digits, and '+-.' chars |
if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I): | if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I): |
return '' | return '' |
scheme = str(scheme) | scheme = str(scheme) |
# ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port] | # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port] |
match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I) | match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I) |
if not match: | if not match: |
return '' | return '' |
domain, port = match.groups() | domain, port = match.groups() |
netloc = domain + (port if port else '') | netloc = domain + (port if port else '') |
netloc = netloc.encode('idna') | netloc = netloc.encode('idna') |
# ensure path is valid and convert Unicode chars to %-encoded | # ensure path is valid and convert Unicode chars to %-encoded |
if not path: | if not path: |
path = '/' # eg: 'http://google.com' -> 'http://google.com/' | path = '/' # eg: 'http://google.com' -> 'http://google.com/' |
path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;') | path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;') |
# ensure query is valid | # ensure query is valid |
query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/') | query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/') |
# ensure fragment is valid | # ensure fragment is valid |
fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8'))) | fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8'))) |
# piece it all back together, truncating it to a maximum of 4KB | # piece it all back together, truncating it to a maximum of 4KB |
url = urlparse.urlunsplit((scheme, netloc, path, query, fragment)) | url = urlparse.urlunsplit((scheme, netloc, path, query, fragment)) |
return url[:4096] | return url[:4096] |
def fullurl(url,href): | def fullurl(url,href): |
href = href.replace(" ","%20") | href = href.replace(" ","%20") |
href = re.sub('#.*$','',href) | href = re.sub('#.*$','',href) |
return urljoin(url,href) | return urljoin(url,href) |
#http://diveintopython.org/http_web_services/etags.html | #http://diveintopython.org/http_web_services/etags.html |
class NotModifiedHandler(urllib2.BaseHandler): | class NotModifiedHandler(urllib2.BaseHandler): |
def http_error_304(self, req, fp, code, message, headers): | def http_error_304(self, req, fp, code, message, headers): |
addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url()) | addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url()) |
addinfourl.code = code | addinfourl.code = code |
return addinfourl | return addinfourl |
def getLastAttachment(docsdb,url): | |
hash = mkhash(url) | |
doc = docsdb.get(hash) | |
if doc != None: | |
last_attachment_fname = doc["_attachments"].keys()[-1] | |
last_attachment = docsdb.get_attachment(doc,last_attachment_fname) | |
return last_attachment | |
else: | |
return None | |
def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True): | def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True): |
url = canonurl(url) | url = canonurl(url) |
hash = mkhash(url) | hash = mkhash(url) |
req = urllib2.Request(url) | req = urllib2.Request(url) |
print "Fetching %s (%s)" % (url,hash) | print "Fetching %s (%s)" % (url,hash) |
if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "": | if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "": |
print "Not a valid HTTP url" | print "Not a valid HTTP url" |
return (None,None,None) | return (None,None,None) |
doc = docsdb.get(hash) | doc = docsdb.get(hash) |
if doc == None: | if doc == None: |
doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName} | doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName} |
else: | else: |
if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 60*24*14*1000): | if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 60*24*14*1000): |
print "Uh oh, trying to scrape URL again too soon!"+hash | print "Uh oh, trying to scrape URL again too soon!"+hash |
last_attachment_fname = doc["_attachments"].keys()[-1] | last_attachment_fname = doc["_attachments"].keys()[-1] |
last_attachment = docsdb.get_attachment(doc,last_attachment_fname) | last_attachment = docsdb.get_attachment(doc,last_attachment_fname) |
content = last_attachment | content = last_attachment |
return (doc['url'],doc['mime_type'],content) | return (doc['url'],doc['mime_type'],content.read()) |
if scrape_again == False: | if scrape_again == False: |
print "Not scraping this URL again as requested" | print "Not scraping this URL again as requested" |
return (None,None,None) | return (doc['url'],doc['mime_type'],content.read()) |
req.add_header("User-Agent", "Mozilla/4.0 (compatible; Prometheus webspider; owner maxious@lambdacomplex.org)") | req.add_header("User-Agent", "Mozilla/4.0 (compatible; Prometheus webspider; owner maxious@lambdacomplex.org)") |
#if there is a previous version stored in couchdb, load caching helper tags | #if there is a previous version stored in couchdb, load caching helper tags |
if doc.has_key('etag'): | if doc.has_key('etag'): |
req.add_header("If-None-Match", doc['etag']) | req.add_header("If-None-Match", doc['etag']) |
if doc.has_key('last_modified'): | if doc.has_key('last_modified'): |
req.add_header("If-Modified-Since", doc['last_modified']) | req.add_header("If-Modified-Since", doc['last_modified']) |
opener = urllib2.build_opener(NotModifiedHandler()) | opener = urllib2.build_opener(NotModifiedHandler()) |
try: | try: |
url_handle = opener.open(req) | url_handle = opener.open(req) |
doc['url'] = url_handle.geturl() # may have followed a redirect to a new url | doc['url'] = url_handle.geturl() # may have followed a redirect to a new url |
headers = url_handle.info() # the addinfourls have the .info() too | headers = url_handle.info() # the addinfourls have the .info() too |
doc['etag'] = headers.getheader("ETag") | doc['etag'] = headers.getheader("ETag") |
doc['last_modified'] = headers.getheader("Last-Modified") | doc['last_modified'] = headers.getheader("Last-Modified") |
doc['date'] = headers.getheader("Date") | doc['date'] = headers.getheader("Date") |
doc['page_scraped'] = time.time() | doc['page_scraped'] = time.time() |
doc['web_server'] = headers.getheader("Server") | doc['web_server'] = headers.getheader("Server") |
doc['via'] = headers.getheader("Via") | doc['via'] = headers.getheader("Via") |
doc['powered_by'] = headers.getheader("X-Powered-By") | doc['powered_by'] = headers.getheader("X-Powered-By") |
doc['file_size'] = headers.getheader("Content-Length") | doc['file_size'] = headers.getheader("Content-Length") |
content_type = headers.getheader("Content-Type") | content_type = headers.getheader("Content-Type") |
if content_type != None: | if content_type != None: |
doc['mime_type'] = content_type.split(";")[0] | doc['mime_type'] = content_type.split(";")[0] |
else: | else: |
(type,encoding) = mimetypes.guess_type(url) | (type,encoding) = mimetypes.guess_type(url) |
doc['mime_type'] = type | doc['mime_type'] = type |
if hasattr(url_handle, 'code'): | if hasattr(url_handle, 'code'): |
if url_handle.code == 304: | if url_handle.code == 304: |
print "the web page has not been modified"+hash | print "the web page has not been modified"+hash |
last_attachment_fname = doc["_attachments"].keys()[-1] | last_attachment_fname = doc["_attachments"].keys()[-1] |
last_attachment = docsdb.get_attachment(doc,last_attachment_fname) | last_attachment = docsdb.get_attachment(doc,last_attachment_fname) |
content = last_attachment | content = last_attachment |
return (doc['url'],doc['mime_type'],content) | return (doc['url'],doc['mime_type'],content.read()) |
else: | else: |
print "new webpage loaded" | print "new webpage loaded" |
content = url_handle.read() | content = url_handle.read() |
docsdb.save(doc) | docsdb.save(doc) |
doc = docsdb.get(hash) # need to get a _rev | doc = docsdb.get(hash) # need to get a _rev |
docsdb.put_attachment(doc, content, str(time.time())+"-"+os.path.basename(url), doc['mime_type']) | docsdb.put_attachment(doc, content, str(time.time())+"-"+os.path.basename(url), doc['mime_type']) |
return (doc['url'], doc['mime_type'], content) | return (doc['url'], doc['mime_type'], content) |
#store as attachment epoch-filename | #store as attachment epoch-filename |
except urllib2.URLError as e: | except urllib2.URLError as e: |
print "error!" | print "error!" |
error = "" | error = "" |
if hasattr(e, 'reason'): | if hasattr(e, 'reason'): |
error = "error %s in downloading %s" % (str(e.reason), url) | error = "error %s in downloading %s" % (str(e.reason), url) |
elif hasattr(e, 'code'): | elif hasattr(e, 'code'): |
error = "error %s in downloading %s" % (e.code, url) | error = "error %s in downloading %s" % (e.code, url) |
print error | print error |
doc['error'] = error | doc['error'] = error |
docsdb.save(doc) | docsdb.save(doc) |
return (None,None,None) | return (None,None,None) |
def scrapeAndStore(docsdb, url, depth, fieldName, agencyID): | def scrapeAndStore(docsdb, url, depth, fieldName, agencyID): |
(url,mime_type,content) = fetchURL(docsdb, url, fieldName, agencyID) | (url,mime_type,content) = fetchURL(docsdb, url, fieldName, agencyID) |
badURLs = ["http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report"] | badURLs = ["http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report"] |
if content != None and depth > 0 and url != "http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report": | if content != None and depth > 0 and url != "http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report": |
if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": | if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": |
# http://www.crummy.com/software/BeautifulSoup/documentation.html | # http://www.crummy.com/software/BeautifulSoup/documentation.html |
soup = BeautifulSoup(content) | soup = BeautifulSoup(content) |
navIDs = soup.findAll(id=re.compile('nav|Nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')) | navIDs = soup.findAll(id=re.compile('nav|Nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')) |
for nav in navIDs: | for nav in navIDs: |
print "Removing element", nav['id'] | print "Removing element", nav['id'] |
nav.extract() | nav.extract() |
navClasses = soup.findAll(attrs={'class' : re.compile('nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')}) | navClasses = soup.findAll(attrs={'class' : re.compile('nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')}) |
for nav in navClasses: | for nav in navClasses: |
print "Removing element", nav['class'] | print "Removing element", nav['class'] |
nav.extract() | nav.extract() |
links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-")) | links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-")) |
linkurls = set([]) | linkurls = set([]) |
for link in links: | for link in links: |
if link.has_key("href"): | if link.has_key("href"): |
if link['href'].startswith("http"): | if link['href'].startswith("http"): |
# lets not do external links for now | # lets not do external links for now |
# linkurls.add(link['href']) | # linkurls.add(link['href']) |
None | None |
if link['href'].startswith("mailto"): | if link['href'].startswith("mailto"): |
# not http | # not http |
None | None |
if link['href'].startswith("javascript"): | if link['href'].startswith("javascript"): |
# not http | # not http |
None | None |
else: | else: |
# remove anchors and spaces in urls | # remove anchors and spaces in urls |
linkurls.add(fullurl(url,link['href'])) | linkurls.add(fullurl(url,link['href'])) |
for linkurl in linkurls: | for linkurl in linkurls: |
#print linkurl | #print linkurl |
scrapeAndStore(docsdb, linkurl, depth-1, fieldName, agencyID) | scrapeAndStore(docsdb, linkurl, depth-1, fieldName, agencyID) |
#couch = couchdb.Server('http://192.168.1.148:5984/') | #couch = couchdb.Server('http://192.168.1.148:5984/') |
couch = couchdb.Server('http://127.0.0.1:5984/') | couch = couchdb.Server('http://127.0.0.1:5984/') |
# select database | # select database |
agencydb = couch['disclosr-agencies'] | agencydb = couch['disclosr-agencies'] |
docsdb = couch['disclosr-documents'] | docsdb = couch['disclosr-documents'] |
if __name__ == "__main__": | if __name__ == "__main__": |
for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view? | for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view? |
agency = agencydb.get(row.id) | agency = agencydb.get(row.id) |
print agency['name'] | print agency['name'] |
for key in agency.keys(): | for key in agency.keys(): |
if key == "FOIDocumentsURL" and "status" not in agency.keys: | if key == "FOIDocumentsURL" and "status" not in agency.keys: |
scrapeAndStore(docsdb, agency[key],0,key,agency['_id']) | scrapeAndStore(docsdb, agency[key],0,key,agency['_id']) |
if key == 'website' and False: | if key == 'website' and False: |
scrapeAndStore(docsdb, agency[key],0,key,agency['_id']) | scrapeAndStore(docsdb, agency[key],0,key,agency['_id']) |
agency['metadata']['lastScraped'] = time.time() | agency['metadata']['lastScraped'] = time.time() |
if key.endswith('URL') and False: | if key.endswith('URL') and False: |
print key | print key |
depth = 1 | depth = 1 |
if 'scrapeDepth' in agency.keys(): | if 'scrapeDepth' in agency.keys(): |
depth = agency['scrapeDepth'] | depth = agency['scrapeDepth'] |
scrapeAndStore(docsdb, agency[key],depth,key,agency['_id']) | scrapeAndStore(docsdb, agency[key],depth,key,agency['_id']) |
agencydb.save(agency) | agencydb.save(agency) |
import sys | import sys |
import os | import os |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
import genericScrapers | import genericScrapers |
class ScraperImplementation(genericScrapers.GenericPDFDisclogScraper): | class ScraperImplementation(genericScrapers.GenericPDFDisclogScraper): |
def __init__(self): | def __init__(self): |
super(ScraperImplementation, self).__init__() | super(ScraperImplementation, self).__init__() |
if __name__ == '__main__': | if __name__ == '__main__': |
print 'Subclass:', issubclass(ScraperImplementation, | print 'Subclass:', issubclass(ScraperImplementation, |
genericScrapers.GenericOAICDisclogScraper) | genericScrapers.GenericPDFDisclogScraper) |
print 'Instance:', isinstance(ScraperImplementation(), | print 'Instance:', isinstance(ScraperImplementation(), |
genericScrapers.GenericOAICDisclogScraper) | genericScrapers.GenericPDFDisclogScraper) |
ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericPDFDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericPDFDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericPDFDisclogScraper) | |
ScraperImplementation().doScrape() | |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
import sys,os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from bs4 import BeautifulSoup | |
from datetime import date | |
#http://www.doughellmann.com/PyMOTW/abc/ | |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
def getTable(self,soup): | |
return soup.find(id= "ctl00_MSO_ContentDiv").table | |
def getColumns(self,columns): | |
(id, title, description, notes) = columns | |
return (id, title, title, description, notes) | |
def getDate(self, content, entry, doc): | |
edate = date.today().strftime("%Y-%m-%d") | |
doc.update({'date': edate}) | |
return | |
def getColumnCount(self): | |
return 4 | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
ScraperImplementation().doScrape() | |
aspx |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
apsc has ACMA style disclog | ACMA style |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from datetime import date | |
from pyquery import PyQuery as pq | |
from lxml import etree | |
import urllib | |
import dateutil | |
from dateutil.parser import * | |
class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): | |
def doScrape(self): | |
foidocsdb = scrape.couch['disclosr-foidocuments'] | |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
self.getURL(), "foidocuments", self.getAgencyID()) | |
d = pq(content) | |
d.make_links_absolute(base_url = self.getURL()) | |
for table in d('table').items(): | |
title= table('thead').text() | |
print title | |
(idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) | |
links = table('a').map(lambda i, e: pq(e).attr('href')) | |
description = descA+" "+descB | |
edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
print edate | |
dochash = scrape.mkhash(self.remove_control_chars(title)) | |
doc = foidocsdb.get(dochash) | |
if doc is None: | |
print "saving " + dochash | |
edate = date.today().strftime("%Y-%m-%d") | |
doc = {'_id': dochash, 'agencyID': self.getAgencyID() | |
, 'url': self.getURL(), 'docID': dochash, | |
"links": links, | |
"date": edate, "notes": notes, "title": title, "description": description} | |
#print doc | |
foidocsdb.save(doc) | |
else: | |
print "already saved" | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ACMADisclogScraper, | |
genericScrapers.GenericDisclogScraper) | |
print 'Instance:', isinstance(ACMADisclogScraper(), | |
genericScrapers.GenericDisclogScraper) | |
ACMADisclogScraper().doScrape() | |
acma style |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
uses RET disclog | parent |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
import scrape | |
from datetime import date | |
from pyquery import PyQuery as pq | |
from lxml import etree | |
import urllib | |
import dateutil | |
from dateutil.parser import * | |
class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): | |
def doScrape(self): | |
foidocsdb = scrape.couch['disclosr-foidocuments'] | |
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
self.getURL(), "foidocuments", self.getAgencyID()) | |
d = pq(content) | |
d.make_links_absolute(base_url = self.getURL()) | |
for item in d('.item-list').items(): | |
title= item('h3').text() | |
print title | |
links = item('a').map(lambda i, e: pq(e).attr('href')) | |
description = title= item('ul').text() | |
edate = date.today().strftime("%Y-%m-%d") | |
print edate | |
dochash = scrape.mkhash(self.remove_control_chars(title)) | |
doc = foidocsdb.get(dochash) | |
if doc is None: | |
print "saving " + dochash | |
doc = {'_id': dochash, 'agencyID': self.getAgencyID() | |
, 'url': self.getURL(), 'docID': dochash, | |
"links": links, | |
"date": edate, "title": title, "description": description} | |
#print doc | |
foidocsdb.save(doc) | |
else: | |
print "already saved" | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ACMADisclogScraper, | |
genericScrapers.GenericDisclogScraper) | |
print 'Instance:', isinstance(ACMADisclogScraper(), | |
genericScrapers.GenericDisclogScraper) | |
ACMADisclogScraper().doScrape() | |
acma style |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog |
import sys | |
import os | |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
import genericScrapers | |
class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): | |
def __init__(self): | |
super(ScraperImplementation, self).__init__() | |
if __name__ == '__main__': | |
print 'Subclass:', issubclass(ScraperImplementation, | |
genericScrapers.GenericHTMLDisclogScraper) | |
print 'Instance:', isinstance(ScraperImplementation(), | |
genericScrapers.GenericHTMLDisclogScraper) | |
ScraperImplementation().doScrape() | |
no disclog | |
<?php | <?php |
include ('../include/common.inc.php'); | include ('../include/common.inc.php'); |
$last_updated = date('Y-m-d', @filemtime('cbrfeed.zip')); | $last_updated = date('Y-m-d', @filemtime('cbrfeed.zip')); |
header("Content-Type: text/xml"); | header("Content-Type: text/xml"); |
echo "<?xml version='1.0' encoding='UTF-8'?>"; | echo "<?xml version='1.0' encoding='UTF-8'?>"; |
echo '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' . "\n"; | 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"; | echo " <url><loc>" . local_url() . "index.php</loc><priority>1.0</priority></url>\n"; |
foreach (scandir("./") as $file) { | foreach (scandir("./") as $file) { |
if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php") | if (strpos($file, ".php") !== false && $file != "index.php" && $file != "sitemap.xml.php") |
echo " <url><loc>" . local_url() . "$file</loc><priority>0.6</priority></url>\n"; | echo " <url><loc>" . local_url() . "$file</loc><priority>0.6</priority></url>\n"; |
} | } |
$agenciesdb = $server->get_db('disclosr-agencies'); | |
$db = $server->get_db('disclosr-foidocuments'); | |
try { | try { |
$rows = $db->get_view("app", "all")->rows; | $rows = $agenciesdb->get_view("app", "byCanonicalName")->rows; |
foreach ($rows as $row) { | |
echo '<url><loc>' . local_url() . 'agency.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n"; | |
} | |
} catch (SetteeRestClientException $e) { | |
setteErrorHandler($e); | |
} | |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | |
try { | |
$rows = $foidocsdb->get_view("app", "all")->rows; | |
foreach ($rows as $row) { | foreach ($rows as $row) { |
echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n"; | echo '<url><loc>' . local_url() . 'view.php?id=' . $row->value->_id . "</loc><priority>0.3</priority></url>\n"; |
} | } |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
echo '</urlset>'; | echo '</urlset>'; |
?> | ?> |
<?php | <?php |
function include_header_documents($title) { | function include_header_documents($title) { |
header('X-UA-Compatible: IE=edge,chrome=1'); | header('X-UA-Compatible: IE=edge,chrome=1'); |
?> | ?> |
<!doctype html> | <!doctype html> |
<!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ --> | <!-- paulirish.com/2008/conditional-stylesheets-vs-css-hacks-answer-neither/ --> |
<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]--> | <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7" lang="en"> <![endif]--> |
<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]--> | <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8" lang="en"> <![endif]--> |
<!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]--> | <!--[if IE 8]> <html class="no-js lt-ie9" lang="en"> <![endif]--> |
<!-- Consider adding a manifest.appcache: h5bp.com/d/Offline --> | <!-- Consider adding a manifest.appcache: h5bp.com/d/Offline --> |
<!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]--> | <!--[if gt IE 8]><!--> <html class="no-js" lang="en"> <!--<![endif]--> |
<head> | <head> |
<meta charset="utf-8"> | <meta charset="utf-8"> |
<title>Australian Disclosure Logs<?php if ($title != "") echo " - $title"; ?></title> | <title>Australian Disclosure Logs<?php if ($title != "") echo " - $title"; ?></title> |
<meta name="description" content=""> | <meta name="description" content=""> |
<!-- Mobile viewport optimized: h5bp.com/viewport --> | <!-- Mobile viewport optimized: h5bp.com/viewport --> |
<meta name="viewport" content="width=device-width"> | <meta name="viewport" content="width=device-width"> |
<link rel="alternate" type="application/rss+xml" title="Latest Disclosure Log Entries" href="rss.xml.php" /> | <link rel="alternate" type="application/rss+xml" title="Latest Disclosure Log Entries" href="rss.xml.php" /> |
<!-- Place favicon.ico and apple-touch-icon.png in the root directory: mathiasbynens.be/notes/touch-icons --> | <!-- Place favicon.ico and apple-touch-icon.png in the root directory: mathiasbynens.be/notes/touch-icons --> |
<meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" /> | <meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" /> |
<!-- Le styles --> | <!-- Le styles --> |
<link href="css/bootstrap.min.css" rel="stylesheet"> | <link href="css/bootstrap.min.css" rel="stylesheet"> |
<style type="text/css"> | <style type="text/css"> |
body { | body { |
padding-top: 60px; | padding-top: 60px; |
padding-bottom: 40px; | padding-bottom: 40px; |
} | } |
.sidebar-nav { | .sidebar-nav { |
padding: 9px 0; | padding: 9px 0; |
} | } |
</style> | </style> |
<link href="css/bootstrap-responsive.min.css" rel="stylesheet"> | <link href="css/bootstrap-responsive.min.css" rel="stylesheet"> |
<!-- HTML5 shim, for IE6-8 support of HTML5 elements --> | <!-- HTML5 shim, for IE6-8 support of HTML5 elements --> |
<!--[if lt IE 9]> | <!--[if lt IE 9]> |
<script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script> | <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script> |
<![endif]--> | <![endif]--> |
<!-- More ideas for your <head> here: h5bp.com/d/head-Tips --> | <!-- More ideas for your <head> here: h5bp.com/d/head-Tips --> |
<!-- All JavaScript at the bottom, except this Modernizr build. | <!-- All JavaScript at the bottom, except this Modernizr build. |
Modernizr enables HTML5 elements & feature detects for optimal performance. | Modernizr enables HTML5 elements & feature detects for optimal performance. |
Create your own custom Modernizr build: www.modernizr.com/download/ | Create your own custom Modernizr build: www.modernizr.com/download/ |
<script src="js/libs/modernizr-2.5.3.min.js"></script>--> | <script src="js/libs/modernizr-2.5.3.min.js"></script>--> |
<script src="js/jquery.js"></script> | <script src="js/jquery.js"></script> |
<script type="text/javascript" src="js/flotr2.min.js"></script> | <script type="text/javascript" src="js/flotr2.min.js"></script> |
</head> | </head> |
<body> | <body> |
<div class="navbar navbar-inverse navbar-fixed-top"> | <div class="navbar navbar-inverse navbar-fixed-top"> |
<div class="navbar-inner"> | <div class="navbar-inner"> |
<div class="container-fluid"> | <div class="container-fluid"> |
<a class="btn btn-navbar" data-toggle="collapse" data-target=".nav-collapse"> | <a class="btn btn-navbar" data-toggle="collapse" data-target=".nav-collapse"> |
<span class="icon-bar"></span> | <span class="icon-bar"></span> |
<span class="icon-bar"></span> | <span class="icon-bar"></span> |
<span class="icon-bar"></span> | <span class="icon-bar"></span> |
</a> | </a> |
<a class="brand" href="#">Australian Disclosure Logs</a> | <a class="brand" href="#">Australian Disclosure Logs</a> |
<div class="nav-collapse collapse"> | <div class="nav-collapse collapse"> |
<p class="navbar-text pull-right"> | <p class="navbar-text pull-right"> |
Check out our subsites on: | <small> |
Subsites on: | |
</small> | |
<a href="http://orgs.disclosurelo.gs">Government Agencies</a> | <a href="http://orgs.disclosurelo.gs">Government Agencies</a> |
• <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a> | • <a href="http://lobbyists.disclosurelo.gs">Political Lobbyists</a> |
• <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a> | • <a href="http://contracts.disclosurelo.gs">Government Contracts and Spending</a> |
</p> | </p> |
<ul class="nav"> | <ul class="nav"> |
<li><a href="index.php">Home</a></li> | <li><a href="agency.php">By Agency</a></li> |
<li><a href="date.php">By Date</a></li> | |
<li><a href="disclogsList.php">List of Disclosure Logs</a></li> | <li><a href="disclogsList.php">List of Disclosure Logs</a></li> |
<li><a href="about.php">About</a></li> | <li><a href="about.php">About</a></li> |
</ul> | </ul> |
</div><!--/.nav-collapse --> | </div><!--/.nav-collapse --> |
</div> | </div> |
</div> | </div> |
</div> | </div> |
<div class="container"> | <div class="container"> |
<?php | <?php |
} | } |
function include_footer_documents() { | function include_footer_documents() { |
global $ENV; | |
?> | ?> |
</div> <!-- /container --> | </div> <!-- /container --> |
<hr> | <hr> |
<footer> | <footer> |
<p>Not affiliated with or endorsed by any government agency.</p> | <p>Not affiliated with or endorsed by any government agency.</p> |
</footer> | </footer> |
<script type="text/javascript"> | <?php |
if ($ENV != "DEV") { | |
echo "<script type='text/javascript'> | |
var _gaq = _gaq || []; | var _gaq = _gaq || []; |
_gaq.push(['_setAccount', 'UA-12341040-4']); | _gaq.push(['_setAccount', 'UA-12341040-4']); |
_gaq.push(['_setDomainName', 'disclosurelo.gs']); | _gaq.push(['_setDomainName', 'disclosurelo.gs']); |
_gaq.push(['_setAllowLinker', true]); | _gaq.push(['_setAllowLinker', true]); |
_gaq.push(['_trackPageview']); | _gaq.push(['_trackPageview']); |
(function() { | (function() { |
var ga = document.createElement('script'); | var ga = document.createElement('script'); |
ga.type = 'text/javascript'; | ga.type = 'text/javascript'; |
ga.async = true; | ga.async = true; |
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; | ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
var s = document.getElementsByTagName('script')[0]; | var s = document.getElementsByTagName('script')[0]; |
s.parentNode.insertBefore(ga, s); | s.parentNode.insertBefore(ga, s); |
})(); | })(); |
</script> | </script>"; |
} | |
?> | |
<!-- Le javascript | <!-- Le javascript |
================================================== --> | ================================================== --> |
<!-- Placed at the end of the document so the pages load faster --> | <!-- Placed at the end of the document so the pages load faster --> |
<!-- | <!-- |
<script src="js/bootstrap-transition.js"></script> | <script src="js/bootstrap-transition.js"></script> |
<script src="js/bootstrap-alert.js"></script> | <script src="js/bootstrap-alert.js"></script> |
<script src="js/bootstrap-modal.js"></script> | <script src="js/bootstrap-modal.js"></script> |
<script src="js/bootstrap-dropdown.js"></script> | <script src="js/bootstrap-dropdown.js"></script> |
<script src="js/bootstrap-scrollspy.js"></script> | <script src="js/bootstrap-scrollspy.js"></script> |
<script src="js/bootstrap-tab.js"></script> | <script src="js/bootstrap-tab.js"></script> |
<script src="js/bootstrap-tooltip.js"></script> | <script src="js/bootstrap-tooltip.js"></script> |
<script src="js/bootstrap-popover.js"></script> | <script src="js/bootstrap-popover.js"></script> |
<script src="js/bootstrap-button.js"></script> | <script src="js/bootstrap-button.js"></script> |
<script src="js/bootstrap-collapse.js"></script> | <script src="js/bootstrap-collapse.js"></script> |
<script src="js/bootstrap-carousel.js"></script> | <script src="js/bootstrap-carousel.js"></script> |
<script src="js/bootstrap-typeahead.js"></script>--> | <script src="js/bootstrap-typeahead.js"></script>--> |
</body> | </body> |
</html> | </html> |
<?php | <?php |
} | } |
function truncate($string, $length, $stopanywhere = false) { | function truncate($string, $length, $stopanywhere = false) { |
//truncates a string to a certain char length, stopping on a word if not specified otherwise. | //truncates a string to a certain char length, stopping on a word if not specified otherwise. |
if (strlen($string) > $length) { | if (strlen($string) > $length) { |
//limit hit! | //limit hit! |
$string = substr($string, 0, ($length - 3)); | $string = substr($string, 0, ($length - 3)); |
if ($stopanywhere) { | if ($stopanywhere) { |
//stop anywhere | //stop anywhere |
$string .= '...'; | $string .= '...'; |
} else { | } else { |
//stop on a word. | //stop on a word. |
$string = substr($string, 0, strrpos($string, ' ')) . '...'; | $string = substr($string, 0, strrpos($string, ' ')) . '...'; |
} | } |
} | } |
return $string; | return $string; |
} | } |
function displayLogEntry($row, $idtoname) { | function displayLogEntry($row, $idtoname) { |
$result = ""; | $result = ""; |
$result .= '<div itemscope itemtype="http://schema.org/Article">'; | $result .= '<div itemscope itemtype="http://schema.org/Article">'; |
$result .= '<h2> <span itemprop="datePublished">' . $row->value->date . "</span>: <span itemprop='name headline'>" . truncate($row->value->title, 120) . "</span>"; | $result .= '<h2><a href="http://disclosurelo.gs/view.php?id='.$row->value->_id.'"> <span itemprop="datePublished">' . $row->value->date . "</span>: <span itemprop='name headline'>" . truncate($row->value->title, 120) . "</span>"; |
$result .= ' (<span itemprop="author publisher creator">' . $idtoname[$row->value->agencyID] . '</span>)</h2>'; | $result .= ' (<span itemprop="author publisher creator">' . $idtoname[$row->value->agencyID] . '</span>)</a></h2>'; |
$result .= "<p itemprop='description articleBody text'> Title: " . $row->value->title . "<br/>"; | $result .= "<p itemprop='description articleBody text'> Title: " . $row->value->title . "<br/>"; |
if (isset($row->value->description)) { | if (isset($row->value->description)) { |
$result .= str_replace("\n", "<br>", preg_replace("/(^[\r\n]*|[\r\n]+)[\s\t]*[\r\n]+/", "",trim($row->value->description))); | $result .= str_replace("\n", "<br>", preg_replace("/(^[\r\n]*|[\r\n]+)[\s\t]*[\r\n]+/", "",trim($row->value->description))); |
} | } |
if (isset($row->value->notes)) { | if (isset($row->value->notes)) { |
$result .= " <br>Note: " . $row->value->notes; | $result .= " <br>Note: " . $row->value->notes; |
} | } |
$result .= "</p>"; | $result .= "</p>"; |
if (isset($row->value->links)) { | if (isset($row->value->links)) { |
$result .= '<h3>Links/Documents</h3><ul itemprop="associatedMedia">'; | $result .= '<h3>Links/Documents</h3><ul itemprop="associatedMedia">'; |
foreach ($row->value->links as $link) { | foreach ($row->value->links as $link) { |
$result .= '<li itemscope itemtype="http://schema.org/MediaObject"><a href=' . $link . ' itemprop="url contentURL">' . urlencode($link) . "</a></li>"; | $result .= '<li itemscope itemtype="http://schema.org/MediaObject"><a href="' . htmlspecialchars ($link) . '" itemprop="url contentURL">' . htmlspecialchars ( $link) . "</a></li>"; |
} | } |
$result .= "</ul>"; | $result .= "</ul>"; |
} | } |
$result .= "<small><A itemprop='url' href='" . $row->value->url . "'>View original source...</a> ID: " . strip_tags($row->value->docID) . "</small>"; | $result .= "<small><A itemprop='url' href='" . $row->value->url . "'>View original source...</a> ID: " . strip_tags($row->value->docID) . "</small>"; |
$result .= "</div>"; | $result .= "</div>\n"; |
return $result; | return $result; |
} | } |
<?php | <?php |
include('template.inc.php'); | include('template.inc.php'); |
include_header_documents(""); | |
include_once('../include/common.inc.php'); | include_once('../include/common.inc.php'); |
?> | ?> |
<?php | <?php |
$agenciesdb = $server->get_db('disclosr-agencies'); | $agenciesdb = $server->get_db('disclosr-agencies'); |
$idtoname = Array(); | $idtoname = Array(); |
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { | foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) { |
$idtoname[$row->id] = trim($row->value->name); | $idtoname[$row->id] = trim($row->value->name); |
} | } |
$foidocsdb = $server->get_db('disclosr-foidocuments'); | $foidocsdb = $server->get_db('disclosr-foidocuments'); |
try { | try { |
$obj = new stdClass(); | $obj = new stdClass(); |
$obj->value = $foidocsdb->get($_REQUEST['id']); | $obj->value = $foidocsdb->get($_REQUEST['id']); |
include_header_documents($obj->value->title); | |
echo displayLogEntry($obj,$idtoname); | echo displayLogEntry($obj,$idtoname); |
} catch (SetteeRestClientException $e) { | } catch (SetteeRestClientException $e) { |
setteErrorHandler($e); | setteErrorHandler($e); |
} | } |
include_footer_documents(); | include_footer_documents(); |
?> | ?> |
<?php | <?php |
date_default_timezone_set("Australia/Sydney"); | date_default_timezone_set("Australia/Sydney"); |
$basePath = ""; | $basePath = ""; |
if (strstr($_SERVER['PHP_SELF'], "alaveteli/") | if (strstr($_SERVER['PHP_SELF'], "alaveteli/") |
|| strstr($_SERVER['PHP_SELF'], "admin/") | || strstr($_SERVER['PHP_SELF'], "admin/") |
|| strstr($_SERVER['PHP_SELF'], "lib/") | || strstr($_SERVER['PHP_SELF'], "lib/") |
|| strstr($_SERVER['PHP_SELF'], "include/") | || strstr($_SERVER['PHP_SELF'], "include/") |
|| strstr($_SERVER['PHP_SELF'], "documents/") | || strstr($_SERVER['PHP_SELF'], "documents/") |
|| $_SERVER['SERVER_NAME'] == "disclosurelo.gs" | || $_SERVER['SERVER_NAME'] == "disclosurelo.gs" |
|| $_SERVER['SERVER_NAME'] == "www.disclosurelo.gs" | |
) | ) |
$basePath = "../"; | $basePath = "../"; |
include_once ('couchdb.inc.php'); | include_once ('couchdb.inc.php'); |
include_once ('template.inc.php'); | include_once ('template.inc.php'); |
require_once $basePath.'lib/Requests/library/Requests.php'; | require_once $basePath.'lib/Requests/library/Requests.php'; |
Requests::register_autoloader(); | Requests::register_autoloader(); |
$ENV = "DEV"; | $ENV = "DEV"; |
if (isset($_SERVER['SERVER_NAME']) && $_SERVER['SERVER_NAME'] != 'localhost') { | if (isset($_SERVER['SERVER_NAME']) && $_SERVER['SERVER_NAME'] != 'localhost') { |
require $basePath."lib/amon-php/amon.php"; | require $basePath."lib/amon-php/amon.php"; |
Amon::config(array('address'=> 'http://127.0.0.1:2464', | Amon::config(array('address'=> 'http://127.0.0.1:2464', |
'protocol' => 'http', | 'protocol' => 'http', |
'secret_key' => "I2LJ6dOMmlnXgVAkTPFXd5M3ejkga8Gd2FbBt6iqZdw")); | 'secret_key' => "I2LJ6dOMmlnXgVAkTPFXd5M3ejkga8Gd2FbBt6iqZdw")); |
Amon::setup_exception_handler(); | Amon::setup_exception_handler(); |
$ENV = "PROD"; | $ENV = "PROD"; |
} | } |
# Convert a stdClass to an Array. http://www.php.net/manual/en/language.types.object.php#102735 | # Convert a stdClass to an Array. http://www.php.net/manual/en/language.types.object.php#102735 |
function object_to_array(stdClass $Class) { | function object_to_array(stdClass $Class) { |
# Typecast to (array) automatically converts stdClass -> array. | # Typecast to (array) automatically converts stdClass -> array. |
$Class = (array) $Class; | $Class = (array) $Class; |
# Iterate through the former properties looking for any stdClass properties. | # Iterate through the former properties looking for any stdClass properties. |
# Recursively apply (array). | # Recursively apply (array). |
foreach ($Class as $key => $value) { | foreach ($Class as $key => $value) { |
if (is_object($value) && get_class($value) === 'stdClass') { | if (is_object($value) && get_class($value) === 'stdClass') { |
$Class[$key] = object_to_array($value); | $Class[$key] = object_to_array($value); |
} | } |
} | } |
return $Class; | return $Class; |
} | } |
# Convert an Array to stdClass. http://www.php.net/manual/en/language.types.object.php#102735 | # Convert an Array to stdClass. http://www.php.net/manual/en/language.types.object.php#102735 |
function array_to_object(array $array) { | function array_to_object(array $array) { |
# Iterate through our array looking for array values. | # Iterate through our array looking for array values. |
# If found recurvisely call itself. | # If found recurvisely call itself. |
foreach ($array as $key => $value) { | foreach ($array as $key => $value) { |
if (is_array($value)) { | if (is_array($value)) { |
$array[$key] = array_to_object($value); | $array[$key] = array_to_object($value); |
} | } |
} | } |
# Typecast to (object) will automatically convert array -> stdClass | # Typecast to (object) will automatically convert array -> stdClass |
return (object) $array; | return (object) $array; |
} | } |
function dept_to_portfolio($deptName) { | function dept_to_portfolio($deptName) { |
return trim(str_replace("Department of", "", str_replace("Department of the", "Department of", $deptName))); | return trim(str_replace("Department of", "", str_replace("Department of the", "Department of", $deptName))); |
} | } |
function phrase_to_tag ($phrase) { | function phrase_to_tag ($phrase) { |
return str_replace(" ","_",str_replace("'","",str_replace(",","",strtolower($phrase)))); | return str_replace(" ","_",str_replace("'","",str_replace(",","",strtolower($phrase)))); |
} | } |
function local_url() { | function local_url() { |
return "http://" . $_SERVER['HTTP_HOST'] . rtrim(dirname($_SERVER['PHP_SELF']), '/\\') . "/"; | return "http://" . $_SERVER['HTTP_HOST'] . rtrim(dirname($_SERVER['PHP_SELF']), '/\\') . "/"; |
} | } |
function GetDomain($url) | function GetDomain($url) |
{ | { |
$nowww = ereg_replace('www\.','',$url); | $nowww = ereg_replace('www\.','',$url); |
$domain = parse_url($nowww); | $domain = parse_url($nowww); |
if(!empty($domain["host"])) | if(!empty($domain["host"])) |
{ | { |
return $domain["host"]; | return $domain["host"]; |
} else | } else |
{ | { |
return $domain["path"]; | return $domain["path"]; |
} | } |
} | } |