From: maxious <maxious@lambdacomplex.org>
Date: Sat, 10 Nov 2012 07:25:52 +0000
Subject: beginning deewr scraper
X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=79e0705f5d6bf210e7532cf04f77aa37e11a9580
---
beginning deewr scraper


Former-commit-id: c17beeeab98ca8e389303cfcc75566c09aaf49cc
---


--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -19,6 +19,12 @@
         def getURL(self):
                 """ disclog URL"""
                 return
+
+        def getDescription(self, entry, doc):
+                """ get description from rss entry"""
+                doc['description'] = entry.summary
+		return
+
        	def doScrape(self):
                	foidocsdb = scrape.couch['disclosr-foidocuments']
                 (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID())
@@ -26,13 +32,16 @@
 		for entry in feed.entries:
 			#print entry
 			print entry.id
-			hash = scrape.mkhash(entry.link)			
+			hash = scrape.mkhash(entry.id)
+			#print hash
 		  	doc = foidocsdb.get(hash)
+			#print doc
 			if doc == None:
                         	print "saving"
 				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, "description": entry.summary,"title": entry.title}
+                                doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id,
+                                "date": edate,"title": entry.title}
+				self.getDescription(entry, doc)
                                 foidocsdb.save(doc)
                         else:
                         	print "already saved"			
@@ -86,7 +95,7 @@
                                                         	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,
+							doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), "links": links, 'docID': id.string,
 			 				 "date": edate, "description": descriptiontxt,"title": title.string,"notes": notes.string}
 							foidocsdb.save(doc)
 						else:

--- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
+++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
@@ -2,7 +2,8 @@
 sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
 import genericScrapers
 #RSS feed not detailed
-
+import scrape
+from bs4 import BeautifulSoup
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
         def getAgencyID(self):
@@ -11,6 +12,34 @@
         def getURL(self):
                 return "http://foi.deewr.gov.au/disclosure-log/rss"
 
+	def getDescription(self,entry,doc):
+		(url,mime_type,content) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False)
+                if content != 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})
+
+
 if __name__ == '__main__':
     print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
     print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper)

--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -69,7 +69,7 @@
 
             </p>
             <ul class="nav">
-              <li class="active"><a href="#">Home</a></li>
+              <li><a href="index.php">Home</a></li>
               <li><a href="disclogsList.php">List of Disclosure Logs</a></li>
               <li><a href="about.php">About</a></li>