From: maxious Date: Tue, 11 Dec 2012 11:14:37 +0000 Subject: fix reduce X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=6f6fe676cc95119445460b301166123a8dbd46b5 --- fix reduce Former-commit-id: 9bf62392d9d505afcc2ed31f23d49c84a98a2091 --- --- a/couchdb/settee/src/classes/SetteeDatabase.class.php +++ b/couchdb/settee/src/classes/SetteeDatabase.class.php @@ -1,317 +1,316 @@ conn_url = $conn_url; - $this->dbname = $dbname; - $this->rest_client = SetteeRestClient::get_instance($this->conn_url); - } - - - /** - * Get UUID from CouchDB - * - * @return - * CouchDB-generated UUID string - * - */ - function gen_uuid() { - $ret = $this->rest_client->http_get('_uuids'); - return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking - } - - /** - * Create or update a document database - * - * @param $document - * PHP object, a PHP associative array, or a JSON String representing the document to be saved. PHP Objects and arrays are JSON-encoded automatically. - * - *

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 $document has a "_rev" property (revision), document will be updated, rather than creating a new document. - * You have to provide "_rev" if you want to update an existing document, otherwise operation will be assumed to be - * one of creation and you will get a duplicate document exception from CouchDB. Also, you may not provide "_rev" but - * not provide "_id" since that is an invalid input. - * - * @param $allowRevAutoDetection - * Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision - * for a document and use it. This option is "false" by default because it involves an extra http HEAD request and - * therefore can make save() operation slightly slower if such auto-detection is not required. - * - * @return - * document object with the database id (uuid) and revision attached; - * - * @throws SetteeCreateDatabaseException - */ - function save($document, $allowRevAutoDetection = false) { - if (is_string($document)) { - $document = json_decode($document); - } - - // Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter) - if(is_array($document)) { - $document = (object) $document; - } - - if (empty($document->_id) && empty($document->_rev)) { - $id = $this->gen_uuid(); - } - elseif (empty($document->_id) && !empty($document->_rev)) { - throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id"); - } - else { - $id = $document->_id; - - if ($allowRevAutoDetection) { - try { - $rev = $this->get_rev($id); - } catch (SetteeRestClientException $e) { - // auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error - } - if (!empty($rev)) { - $document->_rev = $rev; - } - } - } - - $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); - $document_json = json_encode($document, JSON_NUMERIC_CHECK); - - $ret = $this->rest_client->http_put($full_uri, $document_json); - - $document->_id = $ret['decoded']->id; - $document->_rev = $ret['decoded']->rev; - - return $document; - } - - /** - * @param $doc - * @param $name - * @param $content - * Content of the attachment in a string-buffer format. This function will automatically base64-encode content for - * you, so you don't have to do it. - * @param $mime_type - * Optional. Will be auto-detected if not provided - * @return void - */ - public function add_attachment($doc, $name, $content, $mime_type = null) { - if (empty($doc->_attachments) || !is_object($doc->_attachments)) { - $doc->_attachments = new stdClass(); - } - - if (empty($mime_type)) { - $mime_type = $this->rest_client->content_mime_type($content); - } - - $doc->_attachments->$name = new stdClass(); - $doc->_attachments->$name->content_type = $mime_type; - $doc->_attachments->$name->data = base64_encode($content); - } - - /** - * @param $doc - * @param $name - * @param $file - * Full path to a file (e.g. as returned by PHP's realpath function). - * @param $mime_type - * Optional. Will be auto-detected if not provided - * @return void - */ - public function add_attachment_file($doc, $name, $file, $mime_type = null) { - $content = file_get_contents($file); - $this->add_attachment($doc, $name, $content, $mime_type); - } - - /** - * - * Retrieve a document from CouchDB - * - * @throws SetteeWrongInputException - * - * @param $id - * Unique ID (usually: UUID) of the document to be retrieved. - * @return - * database document in PHP object format. - */ - function get($id) { - if (empty($id)) { - throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); - } - - $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); -$full_uri = str_replace("%3Frev%3D","?rev=",$full_uri); - $ret = $this->rest_client->http_get($full_uri); - return $ret['decoded']; - } - - /** - * - * Get the latest revision of a document with document id: $id in CouchDB. - * - * @throws SetteeWrongInputException - * - * @param $id - * Unique ID (usually: UUID) of the document to be retrieved. - * @return - * database document in PHP object format. - */ - function get_rev($id) { - if (empty($id)) { - throw new SetteeWrongInputException("Error: Can't query a document without a uuid."); - } - - $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); - $headers = $this->rest_client->http_head($full_uri); - if (empty($headers['Etag'])) { - throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag"); - } - $etag = str_replace('"', '', $headers['Etag']); - return $etag; - } - - /** - * Delete a document - * - * @param $document - * a PHP object or JSON representation of the document that has _id and _rev fields. - * - * @return void - */ - function delete($document) { - if (!is_object($document)) { - $document = json_decode($document); - } - - $full_uri = $this->dbname . "/" . $this->safe_urlencode($document->_id) . "?rev=" . $document->_rev; - $this->rest_client->http_delete($full_uri); - } - - - /*----------------- View-related functions --------------*/ - - /** - * Create a new view or update an existing one. - * - * @param $design_doc - * @param $view_name - * @param $map_src - * Source code of the map function in Javascript - * @param $reduce_src - * Source code of the reduce function in Javascript (optional) - * @return void - */ - function save_view($design_doc, $view_name, $map_src, $reduce_src = null) { - $obj = new stdClass(); - $obj->_id = "_design/" . urlencode($design_doc); - $view_name = urlencode($view_name); - $obj->views->$view_name->map = $map_src; - if (!empty($reduce_src)) { - $obj->views->$view_name->reduce = $reduce_src; - } - - // allow safe updates (even if slightly slower due to extra: rev-detection check). - return $this->save($obj, true); - } - - /** - * Create a new view or update an existing one. - * - * @param $design_doc - * @param $view_name - * @param $key - * key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes - * that first element is startkey, second: endkey. - * @param $descending - * return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change - * order you also need to swap startkey and endkey values! - * - * @return void - */ - function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false, $reduce=false) { - $id = "_design/" . urlencode($design_doc); - $view_name = urlencode($view_name); - $id .= "/_view/$view_name"; - - $data = array(); - if (!empty($key)) { - if (is_string($key)) { - $data = "key=" . '"' . $key . '"'; - } - elseif (is_array($key)) { - list($startkey, $endkey) = $key; - $data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"'; - } - - if ($descending) { - $data .= "&descending=true"; - } - if ($reduce) { - $data .= "&reduce=true"; - } else { - $data .= "&reduce=false"; - } - if ($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); - -$full_uri = str_replace("%253Fgroup%253D","?group=",$full_uri); -$full_uri = str_replace("%253Flimit%253D","?limit=",$full_uri); - $ret = $this->rest_client->http_get($full_uri, $data); - //$ret['decoded'] = str_replace("?k","&k",$ret['decoded']); - return $ret['decoded']; - - } - - /** - * @param $id - * @return - * return a properly url-encoded id. - */ - private function safe_urlencode($id) { - //-- System views like _design can have "/" in their URLs. - $id = rawurlencode($id); - if (substr($id, 0, 1) == '_') { - $id = str_replace('%2F', '/', $id); - } - return $id; - } - - /** Getter for a database name */ - function get_name() { - return $this->dbname; - } + /** + * Base URL of the CouchDB REST API + */ + private $conn_url; + + /** + * HTTP REST Client instance + */ + protected $rest_client; + + /** + * Name of the database + */ + private $dbname; + + /** + * Default constructor + */ + function __construct($conn_url, $dbname) { + $this->conn_url = $conn_url; + $this->dbname = $dbname; + $this->rest_client = SetteeRestClient::get_instance($this->conn_url); + } + + /** + * Get UUID from CouchDB + * + * @return + * CouchDB-generated UUID string + * + */ + function gen_uuid() { + $ret = $this->rest_client->http_get('_uuids'); + return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking + } + + /** + * Create or update a document database + * + * @param $document + * PHP object, a PHP associative array, or a JSON String representing the document to be saved. PHP Objects and arrays are JSON-encoded automatically. + * + *

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 $document has a "_rev" property (revision), document will be updated, rather than creating a new document. + * You have to provide "_rev" if you want to update an existing document, otherwise operation will be assumed to be + * one of creation and you will get a duplicate document exception from CouchDB. Also, you may not provide "_rev" but + * not provide "_id" since that is an invalid input. + * + * @param $allowRevAutoDetection + * Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision + * for a document and use it. This option is "false" by default because it involves an extra http HEAD request and + * therefore can make save() operation slightly slower if such auto-detection is not required. + * + * @return + * document object with the database id (uuid) and revision attached; + * + * @throws SetteeCreateDatabaseException + */ + function save($document, $allowRevAutoDetection = false) { + if (is_string($document)) { + $document = json_decode($document); + } + + // Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter) + if (is_array($document)) { + $document = (object) $document; + } + + if (empty($document->_id) && empty($document->_rev)) { + $id = $this->gen_uuid(); + } elseif (empty($document->_id) && !empty($document->_rev)) { + throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id"); + } else { + $id = $document->_id; + + if ($allowRevAutoDetection) { + try { + $rev = $this->get_rev($id); + } catch (SetteeRestClientException $e) { + // auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error + } + if (!empty($rev)) { + $document->_rev = $rev; + } + } + } + + $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); + $document_json = json_encode($document, JSON_NUMERIC_CHECK); + + $ret = $this->rest_client->http_put($full_uri, $document_json); + + $document->_id = $ret['decoded']->id; + $document->_rev = $ret['decoded']->rev; + + return $document; + } + + /** + * @param $doc + * @param $name + * @param $content + * Content of the attachment in a string-buffer format. This function will automatically base64-encode content for + * you, so you don't have to do it. + * @param $mime_type + * Optional. Will be auto-detected if not provided + * @return void + */ + public function add_attachment($doc, $name, $content, $mime_type = null) { + if (empty($doc->_attachments) || !is_object($doc->_attachments)) { + $doc->_attachments = new stdClass(); + } + + if (empty($mime_type)) { + $mime_type = $this->rest_client->content_mime_type($content); + } + + $doc->_attachments->$name = new stdClass(); + $doc->_attachments->$name->content_type = $mime_type; + $doc->_attachments->$name->data = base64_encode($content); + } + + /** + * @param $doc + * @param $name + * @param $file + * Full path to a file (e.g. as returned by PHP's realpath function). + * @param $mime_type + * Optional. Will be auto-detected if not provided + * @return void + */ + public function add_attachment_file($doc, $name, $file, $mime_type = null) { + $content = file_get_contents($file); + $this->add_attachment($doc, $name, $content, $mime_type); + } + + /** + * + * Retrieve a document from CouchDB + * + * @throws SetteeWrongInputException + * + * @param $id + * Unique ID (usually: UUID) of the document to be retrieved. + * @return + * database document in PHP object format. + */ + function get($id) { + if (empty($id)) { + throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid."); + } + + $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); + $full_uri = str_replace("%3Frev%3D", "?rev=", $full_uri); + $ret = $this->rest_client->http_get($full_uri); + return $ret['decoded']; + } + + /** + * + * Get the latest revision of a document with document id: $id in CouchDB. + * + * @throws SetteeWrongInputException + * + * @param $id + * Unique ID (usually: UUID) of the document to be retrieved. + * @return + * database document in PHP object format. + */ + function get_rev($id) { + if (empty($id)) { + throw new SetteeWrongInputException("Error: Can't query a document without a uuid."); + } + + $full_uri = $this->dbname . "/" . $this->safe_urlencode($id); + $headers = $this->rest_client->http_head($full_uri); + if (empty($headers['Etag'])) { + throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag"); + } + $etag = str_replace('"', '', $headers['Etag']); + return $etag; + } + + /** + * Delete a document + * + * @param $document + * a PHP object or JSON representation of the document that has _id and _rev fields. + * + * @return void + */ + function delete($document) { + if (!is_object($document)) { + $document = json_decode($document); + } + + $full_uri = $this->dbname . "/" . $this->safe_urlencode($document->_id) . "?rev=" . $document->_rev; + $this->rest_client->http_delete($full_uri); + } + + /* ----------------- View-related functions -------------- */ + + /** + * Create a new view or update an existing one. + * + * @param $design_doc + * @param $view_name + * @param $map_src + * Source code of the map function in Javascript + * @param $reduce_src + * Source code of the reduce function in Javascript (optional) + * @return void + */ + function save_view($design_doc, $view_name, $map_src, $reduce_src = null) { + $obj = new stdClass(); + $obj->_id = "_design/" . urlencode($design_doc); + $view_name = urlencode($view_name); + $obj->views->$view_name->map = $map_src; + if (!empty($reduce_src)) { + $obj->views->$view_name->reduce = $reduce_src; + } + + // allow safe updates (even if slightly slower due to extra: rev-detection check). + return $this->save($obj, true); + } + + /** + * Create a new view or update an existing one. + * + * @param $design_doc + * @param $view_name + * @param $key + * key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes + * that first element is startkey, second: endkey. + * @param $descending + * return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change + * order you also need to swap startkey and endkey values! + * + * @return void + */ + function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false, $reduce = null, $startdocid = null) { + $id = "_design/" . urlencode($design_doc); + $view_name = urlencode($view_name); + $id .= "/_view/$view_name"; + + $data = array(); + if (!empty($key)) { + if (is_string($key)) { + $data = "key=" . '"' . $key . '"'; + } elseif (is_array($key)) { + list($startkey, $endkey) = $key; + $data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"'; + } + + if ($descending) { + $data .= "&descending=true"; + } + if ($startdocid != null) { + $data .= "&startkey_docid='$startdocid'"; + } + if ($reduce === true) { + $data .= "&reduce=true"; + } else if ($reduce === false){ + + $data .= "&reduce=false"; + } + if ($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); + + $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, $data); + //$ret['decoded'] = str_replace("?k","&k",$ret['decoded']); + return $ret['decoded']; + } + + /** + * @param $id + * @return + * return a properly url-encoded id. + */ + private function safe_urlencode($id) { + //-- System views like _design can have "/" in their URLs. + $id = rawurlencode($id); + if (substr($id, 0, 1) == '_') { + $id = str_replace('%2F', '/', $id); + } + return $id; + } + + /** Getter for a database name */ + function get_name() { + return $this->dbname; + } } + --- a/couchdb/settee/src/classes/SetteeRestClient.class.php +++ b/couchdb/settee/src/classes/SetteeRestClient.class.php @@ -244,3 +244,4 @@ } class SetteeRestClientException extends Exception {} + --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -13,6 +13,8 @@ from datetime import * import codecs +import difflib + from StringIO import StringIO from pdfminer.pdfparser import PDFDocument, PDFParser @@ -49,6 +51,31 @@ """ do the scraping """ 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): @@ -62,7 +89,7 @@ device = TextConverter(rsrcmgr, outfp, codec='utf-8', laparams=laparams) fp = StringIO() - fp.write(content.read()) + fp.write(content) process_pdf(rsrcmgr, device, fp, set(), caching=True, check_extractable=True) --- a/documents/index.php +++ b/documents/index.php @@ -1,9 +1,9 @@

Read all the information released by Australian Federal Government agencies under the FOI Act in one place!
RSS Icon All Agencies RSS Feed
@@ -16,18 +16,20 @@ } $foidocsdb = $server->get_db('disclosr-foidocuments'); try { - $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20)->rows; + $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20,null, $enddocid)->rows; if ($rows) { foreach ($rows as $key => $row) { echo displayLogEntry($row, $idtoname); - if (!isset($startkey)) $startkey = $row->key; + if (!isset($startkey)) + $startkey = $row->key; $endkey = $row->key; + $enddocid = $row->value->_id; } } } catch (SetteeRestClientException $e) { setteErrorHandler($e); } -echo "next page "; +echo "next page "; include_footer_documents(); ?> --- a/documents/runScrapers.sh +++ b/documents/runScrapers.sh @@ -1,3 +1,10 @@ -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 --- a/documents/scrape.py +++ b/documents/scrape.py @@ -76,6 +76,16 @@ addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url()) addinfourl.code = code 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): url = canonurl(url) @@ -94,10 +104,10 @@ last_attachment_fname = doc["_attachments"].keys()[-1] last_attachment = docsdb.get_attachment(doc,last_attachment_fname) content = last_attachment - return (doc['url'],doc['mime_type'],content) + return (doc['url'],doc['mime_type'],content.read()) if scrape_again == False: 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)") #if there is a previous version stored in couchdb, load caching helper tags @@ -131,7 +141,7 @@ last_attachment_fname = doc["_attachments"].keys()[-1] last_attachment = docsdb.get_attachment(doc,last_attachment_fname) content = last_attachment - return (doc['url'],doc['mime_type'],content) + return (doc['url'],doc['mime_type'],content.read()) else: print "new webpage loaded" content = url_handle.read() --- a/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py +++ b/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py @@ -12,8 +12,8 @@ if __name__ == '__main__': print 'Subclass:', issubclass(ScraperImplementation, - genericScrapers.GenericOAICDisclogScraper) + genericScrapers.GenericPDFDisclogScraper) print 'Instance:', isinstance(ScraperImplementation(), - genericScrapers.GenericOAICDisclogScraper) + genericScrapers.GenericPDFDisclogScraper) ScraperImplementation().doScrape() --- /dev/null +++ b/documents/scrapers/0ae822d1a748e60d90f0b79b97d5a3e5.py @@ -1,1 +1,19 @@ +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() + --- /dev/null +++ b/documents/scrapers/31685505438d393f45a90f442b8fa27f.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/31685505438d393f45a90f442b8fa27f.txt +++ /dev/null @@ -1,2 +1,1 @@ -pdf --- /dev/null +++ b/documents/scrapers/3e2f110af49d62833a835bd257771ffb.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/3e2f110af49d62833a835bd257771ffb.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- /dev/null +++ b/documents/scrapers/41a166419503bb50e410c58be54c102f.py @@ -1,1 +1,27 @@ +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() + --- a/documents/scrapers/41a166419503bb50e410c58be54c102f.txt +++ /dev/null @@ -1,1 +1,1 @@ -aspx + --- /dev/null +++ b/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- a/documents/scrapers/50601505ef69483121a6d130bb0515e4.txt +++ b/documents/scrapers/50601505ef69483121a6d130bb0515e4.txt @@ -1,1 +1,1 @@ -apsc has ACMA style disclog +ACMA style --- /dev/null +++ b/documents/scrapers/525c3953187da08cd702359b2fc2997f.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/525c3953187da08cd702359b2fc2997f.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- /dev/null +++ b/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- /dev/null +++ b/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- /dev/null +++ b/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py +++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py @@ -7,6 +7,8 @@ from pyquery import PyQuery as pq from lxml import etree import urllib +import dateutil +from dateutil.parser import * class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): @@ -16,21 +18,28 @@ self.getURL(), "foidocuments", self.getAgencyID()) d = pq(content) - d.make_links_absolute() - d.table.filter('.ncTAF_DataTABLE') - print [i.text() for i in d.items('span')] - description = "" - dochash = scrape.mkhash(description) - 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, - "date": edate, "title": "Disclosure Log Updated", "description": description} - #foidocsdb.save(doc) - else: - print "already saved" + 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__': --- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt +++ /dev/null @@ -1,1 +1,1 @@ -acma style + --- /dev/null +++ b/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- /dev/null +++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- /dev/null +++ b/documents/scrapers/bf6e587f166040b63681cd2ff76fbfdf.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/bf6e587f166040b63681cd2ff76fbfdf.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- a/documents/scrapers/c1302c8d7cbbd911f0d4d8a4128f8079.txt +++ b/documents/scrapers/c1302c8d7cbbd911f0d4d8a4128f8079.txt @@ -1,1 +1,1 @@ -uses RET disclog +parent --- /dev/null +++ b/documents/scrapers/cb7f40e3495b682de6eee61bf09c1cfc.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/cb7f40e3495b682de6eee61bf09c1cfc.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- /dev/null +++ b/documents/scrapers/d72744fb1e5d6e87af9a5ea16cc27fa5.py @@ -1,1 +1,49 @@ +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() + --- a/documents/scrapers/d72744fb1e5d6e87af9a5ea16cc27fa5.txt +++ /dev/null @@ -1,1 +1,1 @@ -acma style + --- /dev/null +++ b/documents/scrapers/e770921522a49dc77de208cc724ce134.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/e770921522a49dc77de208cc724ce134.txt +++ /dev/null @@ -1,1 +1,1 @@ -no disclog + --- /dev/null +++ b/documents/scrapers/f189459fc43f941e0d4ecfba52c666f3.py @@ -1,1 +1,19 @@ +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() + --- a/documents/scrapers/f189459fc43f941e0d4ecfba52c666f3.txt +++ /dev/null @@ -1,2 +1,1 @@ -no disclog --- a/documents/template.inc.php +++ b/documents/template.inc.php @@ -61,7 +61,9 @@ Australian Disclosure Logs

- Check out our subsites on: + + Subsites on: + Government Agencies • Political Lobbyists • Government Contracts and Spending @@ -83,6 +85,7 @@ } function include_footer_documents() { + global $ENV; ?>

@@ -154,8 +157,8 @@ function displayLogEntry($row, $idtoname) { $result = ""; $result .= '
'; - $result .= '

: " . truncate($row->value->title, 120) . ""; - $result .= ' (' . $idtoname[$row->value->agencyID] . ')

'; + $result .= '

: " . truncate($row->value->title, 120) . ""; + $result .= ' (' . $idtoname[$row->value->agencyID] . ')

'; $result .= "

Title: " . $row->value->title . "
"; if (isset($row->value->description)) { $result .= str_replace("\n", "
", preg_replace("/(^[\r\n]*|[\r\n]+)[\s\t]*[\r\n]+/", "",trim($row->value->description))); @@ -168,7 +171,7 @@ if (isset($row->value->links)) { $result .= '

Links/Documents

"; --- a/include/common.inc.php +++ b/include/common.inc.php @@ -9,6 +9,7 @@ || strstr($_SERVER['PHP_SELF'], "include/") || strstr($_SERVER['PHP_SELF'], "documents/") || $_SERVER['SERVER_NAME'] == "disclosurelo.gs" + || $_SERVER['SERVER_NAME'] == "www.disclosurelo.gs" ) $basePath = "../";