Merge branch 'master' of ssh://apples.lambdacomplex.org/git/disclosr
Former-commit-id: c29a791360b1cd169ea3062bf04c20cb4e7dced8
--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -1,7 +1,177 @@
<?php
require_once '../include/common.inc.php';
+//function createFOIDocumentsDesignDoc() {
+
+$foidb = $server->get_db('disclosr-foidocuments');
+ $obj = new stdClass();
+ $obj->_id = "_design/" . urlencode("app");
+ $obj->language = "javascript";
+ $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
+ $obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };";
+
+ // allow safe updates (even if slightly slower due to extra: rev-detection check).
+ $foidb->save($obj, true);
+
+
+function createDocumentsDesignDoc() {
+ /*
+ global $db;
+ $obj = new stdClass();
+ $obj->_id = "_design/" . urlencode("app");
+ $obj->language = "javascript";
+ $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
+ $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
+ "views": {
+ "web_server": {
+ "map": "function(doc) {\n emit(doc.web_server, 1);\n}",
+ "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
+ },
+ "byAgency": {
+ "map": "function(doc) {\n emit(doc.agencyID, 1);\n}",
+ "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
+ },
+ "byURL": {
+ "map": "function(doc) {\n emit(doc.url, doc);\n}"
+ },
+ "agency": {
+ "map": "function(doc) {\n emit(doc.agencyID, doc);\n}"
+ },
+ "byWebServer": {
+ "map": "function(doc) {\n emit(doc.web_server, doc);\n}"
+ },
+ "getValidationRequired": {
+ "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"
+ }
+ } */
+}
+
+//function createAgencyDesignDoc() {
$db = $server->get_db('disclosr-agencies');
-createAgencyDesignDoc();
+ $obj = new stdClass();
+ $obj->_id = "_design/" . urlencode("app");
+ $obj->language = "javascript";
+ $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
+ $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
+ $obj->views->byCanonicalName->map = "function(doc) {
+ if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
+ emit(doc.name, doc);
+ }
+};";
+ $obj->views->byDeptStateName->map = "function(doc) {
+ if (doc.orgType == 'FMA-DepartmentOfState') {
+ emit(doc.name, doc._id);
+ }
+};";
+ $obj->views->parentOrgs->map = "function(doc) {
+ if (doc.parentOrg) {
+ emit(doc._id, doc.parentOrg);
+ }
+};";
+ $obj->views->byName->map = 'function(doc) {
+ if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
+ emit(doc.name, doc._id);
+if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
+ emit(doc.shortName, doc._id);
+}
+ for (name in doc.otherNames) {
+if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
+ emit(doc.otherNames[name], doc._id);
+}
+ }
+ for (name in doc.foiBodies) {
+if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
+ emit(doc.foiBodies[name], doc._id);
+}
+ }
+ }
+};';
+
+ $obj->views->foiEmails->map = "function(doc) {
+ emit(doc._id, doc.foiEmail);
+};";
+
+ $obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }";
+ $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };';
+ $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
+ $obj->views->getScrapeRequired->map = "function(doc) {
+
+var lastScrape = Date.parse(doc.metadata.lastScraped);
+
+var today = new Date();
+
+if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
+ emit(doc._id, doc);
+}
+
+};";
+ $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
+ $obj->views->getConflicts->map = "function(doc) {
+ if (doc._conflicts) {
+ emit(null, [doc._rev].concat(doc._conflicts));
+ }
+}";
+ // http://stackoverflow.com/questions/646628/javascript-startswith
+ $obj->views->score->map = 'if(!String.prototype.startsWith){
+ String.prototype.startsWith = function (str) {
+ return !this.indexOf(str);
+ }
+}
+
+function(doc) {
+ count = 0;
+ if (doc["status"] != "suspended") {
+ for(var propName in doc) {
+ if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
+ count++;
+ }
+ }
+ portfolio = doc.parentOrg;
+ if (doc.orgType == "FMA-DepartmentOfState") {
+ portfolio = doc._id;
+ }
+ if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
+ portfolio = doc.orgType;
+ }
+ emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
+ }
+}';
+ $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
+ String.prototype.startsWith = function (str) {
+ return !this.indexOf(str);
+ }
+}
+if(!String.prototype.endsWith){
+ String.prototype.endsWith = function(suffix) {
+ return this.indexOf(suffix, this.length - suffix.length) !== -1;
+ };
+}
+function(doc) {
+if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
+for(var propName in doc) {
+ if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
+ emit(propName, 1);
+ }
+}
+ emit("total", 1);
+ }
+}';
+ $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
+ return sum(values);
+}';
+ $obj->views->fieldNames->map = '
+function(doc) {
+for(var propName in doc) {
+ emit(propName, doc._id);
+ }
+
+}';
+ $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
+ return values.length;
+}';
+ // allow safe updates (even if slightly slower due to extra: rev-detection check).
+ $db->save($obj, true);
+
+
?>
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -30,13 +30,14 @@
""" do the scraping """
return
+ @abc.abstractmethod
+ def getDescription(self, content, entry, doc):
+ """ get description"""
+ return
+
class GenericRSSDisclogScraper(GenericDisclogScraper):
- def getDescription(self, entry, doc):
- """ get description from rss entry"""
- doc['description'] = entry.summary
- return
def doScrape(self):
foidocsdb = scrape.couch['disclosr-foidocuments']
@@ -54,16 +55,29 @@
edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d")
doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id,
"date": edate,"title": entry.title}
- self.getDescription(entry, doc)
+ self.getDescription(entry,entry, doc)
foidocsdb.save(doc)
else:
print "already saved"
+ def getDescription(self, content, entry, doc):
+ """ get description from rss entry"""
+ doc.update({'description': content.summary})
+ return
class GenericOAICDisclogScraper(GenericDisclogScraper):
__metaclass__ = abc.ABCMeta
@abc.abstractmethod
def getColumns(self,columns):
""" rearranges columns if required """
+ return
+ def getColumnCount(self):
+ return 5
+ def getDescription(self, content, entry, doc):
+ """ get description from rss entry"""
+ descriptiontxt = ""
+ for string in content.stripped_strings:
+ descriptiontxt = descriptiontxt + " \n" + string
+ doc.update({'description': descriptiontxt})
return
def doScrape(self):
@@ -76,7 +90,7 @@
soup = BeautifulSoup(content)
for row in soup.table.find_all('tr'):
columns = row.find_all('td')
- if len(columns) == 5:
+ if len(columns) == self.getColumnCount():
(id, date, description, title, notes) = self.getColumns(columns)
print id.string
hash = scrape.mkhash(url+id.string)
@@ -85,9 +99,6 @@
if atag.has_key('href'):
links.append(scrape.fullurl(url,atag['href']))
doc = foidocsdb.get(hash)
- descriptiontxt = ""
- for string in description.stripped_strings:
- descriptiontxt = descriptiontxt + " \n" + string
if doc == None:
print "saving"
@@ -97,14 +108,20 @@
print dtdate
edate = ""+str(dtdate[0])+'-'+str(dtdate[1])+'-'+str(dtdate[2])
else:
- edate = ""
- doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), "links": links, 'docID': id.string,
- "date": edate, "description": descriptiontxt,"title": title.string,"notes": notes.string}
+ edate = datetime.strptime(date.string, "%d %B %Y").strftime("%Y-%m-%d")
+ doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string,
+ "date": edate,"title": title.string}
+ self.getDescription(description,row, doc)
+
+ if links != []:
+ doc.update({'links': links})
+ if notes != None:
+ doc.update({ 'notes': notes.string})
foidocsdb.save(doc)
else:
- print "already saved"
+ print "already saved "+hash
- elif len(row.find_all('th')) == 5:
+ elif len(row.find_all('th')) == self.getColumnCount():
print "header row"
else:
--- /dev/null
+++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py
@@ -1,1 +1,48 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getDescription(self,content, entry,doc):
+ link = None
+ for atag in entry.find_all('a'):
+ if atag.has_key('href'):
+ link = scrape.fullurl(url,atag['href'])
+ (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
+ if htcontent != None:
+ if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
+ # http://www.crummy.com/software/BeautifulSoup/documentation.html
+ soup = BeautifulSoup(content)
+ links = []
+ description = ""
+ dldivs = soup.find('div',class_="download")
+ if dldivs != None:
+ for atag in dldivs.find_all("a"):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(url,atag['href']))
+ nodldivs = soup.find('div',class_="incompleteNotification")
+ if nodldivs != None and nodldivs.stripped_strings != None:
+ for text in nodldivs.stripped_strings:
+ description = description + text
+ for row in soup.table.find_all('tr'):
+ if row != None:
+ description = description + "\n" + row.find('th').string + ": "
+ for text in row.find('div').stripped_strings:
+ description = description + text
+ if links != []:
+ doc.update({'links': links})
+ if description != "":
+ doc.update({ 'description': description})
+ def getColumnCount(self):
+ return 2
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (title, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/820c3df09aa62f6ee7468c73bea0e323.py
@@ -1,1 +1,18 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumnCount(self):
+ return 2
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (title, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
@@ -1,1 +1,2 @@
+# does not have any disclog entries or table
--- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
+++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
@@ -6,9 +6,9 @@
from bs4 import BeautifulSoup
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
- def getDescription(self,entry,doc):
- (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False)
- if content != None:
+ def getDescription(self,content, entry,doc):
+ (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False)
+ if htcontent != None:
if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
# http://www.crummy.com/software/BeautifulSoup/documentation.html
soup = BeautifulSoup(content)
--- /dev/null
+++ b/documents/scrapers/c43ca6780764f4e61918e8836be74420.py
@@ -1,1 +1,16 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getColumns(self,columns):
+ (id, date, title,description,notes) = columns
+ return (id, date, description, title, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/include/common.inc.php
+++ b/include/common.inc.php
@@ -8,6 +8,7 @@
|| strstr($_SERVER['PHP_SELF'], "lib/")
|| strstr($_SERVER['PHP_SELF'], "include/")
|| strstr($_SERVER['PHP_SELF'], "documents/")
+ || $_SERVER['SERVER_NAME'] == "disclosurelo.gs"
)
$basePath = "../";
--- a/include/couchdb.inc.php
+++ b/include/couchdb.inc.php
@@ -3,169 +3,6 @@
include $basePath . "schemas/schemas.inc.php";
require ($basePath . 'couchdb/settee/src/settee.php');
-function createFOIDocumentsDesignDoc() {
- /* "map": "function(doc) {\n emit(doc.web_server, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byAgency": {
- "map": "function(doc) {\n emit(doc.agencyID, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byURL": {
- "map": "function(doc) {\n emit(doc.url, doc);\n}"
-*/
-}
-function createDocumentsDesignDoc() {
- /* "views": {
- "web_server": {
- "map": "function(doc) {\n emit(doc.web_server, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byAgency": {
- "map": "function(doc) {\n emit(doc.agencyID, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byURL": {
- "map": "function(doc) {\n emit(doc.url, doc);\n}"
- },
- "agency": {
- "map": "function(doc) {\n emit(doc.agencyID, doc);\n}"
- },
- "byWebServer": {
- "map": "function(doc) {\n emit(doc.web_server, doc);\n}"
- },
- "getValidationRequired": {
- "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"
- }
- } */
-}
-
-function createAgencyDesignDoc() {
- global $db;
- $obj = new stdClass();
- $obj->_id = "_design/" . urlencode("app");
- $obj->language = "javascript";
- $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
- $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
- $obj->views->byCanonicalName->map = "function(doc) {
- if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
- emit(doc.name, doc);
- }
-};";
- $obj->views->byDeptStateName->map = "function(doc) {
- if (doc.orgType == 'FMA-DepartmentOfState') {
- emit(doc.name, doc._id);
- }
-};";
- $obj->views->parentOrgs->map = "function(doc) {
- if (doc.parentOrg) {
- emit(doc._id, doc.parentOrg);
- }
-};";
- $obj->views->byName->map = 'function(doc) {
- if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
- emit(doc.name, doc._id);
-if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
- emit(doc.shortName, doc._id);
-}
- for (name in doc.otherNames) {
-if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
- emit(doc.otherNames[name], doc._id);
-}
- }
- for (name in doc.foiBodies) {
-if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
- emit(doc.foiBodies[name], doc._id);
-}
- }
- }
-};';
-
- $obj->views->foiEmails->map = "function(doc) {
- emit(doc._id, doc.foiEmail);
-};";
-
- $obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }";
- $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };';
- $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
- $obj->views->getScrapeRequired->map = "function(doc) {
-
-var lastScrape = Date.parse(doc.metadata.lastScraped);
-
-var today = new Date();
-
-if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
- emit(doc._id, doc);
-}
-
-};";
- $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
- $obj->views->getConflicts->map = "function(doc) {
- if (doc._conflicts) {
- emit(null, [doc._rev].concat(doc._conflicts));
- }
-}";
- // http://stackoverflow.com/questions/646628/javascript-startswith
- $obj->views->score->map = 'if(!String.prototype.startsWith){
- String.prototype.startsWith = function (str) {
- return !this.indexOf(str);
- }
-}
-
-function(doc) {
- count = 0;
- if (doc["status"] != "suspended") {
- for(var propName in doc) {
- if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
- count++;
- }
- }
- portfolio = doc.parentOrg;
- if (doc.orgType == "FMA-DepartmentOfState") {
- portfolio = doc._id;
- }
- if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
- portfolio = doc.orgType;
- }
- emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
- }
-}';
- $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
- String.prototype.startsWith = function (str) {
- return !this.indexOf(str);
- }
-}
-if(!String.prototype.endsWith){
- String.prototype.endsWith = function(suffix) {
- return this.indexOf(suffix, this.length - suffix.length) !== -1;
- };
-}
-function(doc) {
-if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
-for(var propName in doc) {
- if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
- emit(propName, 1);
- }
-}
- emit("total", 1);
- }
-}';
- $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
- return sum(values);
-}';
- $obj->views->fieldNames->map = '
-function(doc) {
-for(var propName in doc) {
- emit(propName, doc._id);
- }
-
-}';
- $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
- return values.length;
-}';
- // allow safe updates (even if slightly slower due to extra: rev-detection check).
- return $db->save($obj, true);
-}
if (php_uname('n') == "vanille") {
$serverAddr = 'http://192.168.178.21:5984/';