From: Maxious <maxious@lambdacomplex.org>
Date: Wed, 24 Oct 2012 03:21:12 +0000
Subject: upgrade scrapers to beautifulsoup4
X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=500c1eeffebd290b000c01e79878c307d558f7e7
---
upgrade scrapers to beautifulsoup4


Former-commit-id: 350a28ba24aef1eb018e2db0275aa62fe3369728
---


--- a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
+++ b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
@@ -4,12 +4,21 @@
 foidocsdb = scrape.couch['disclosr-foidocuments']
 
 #RSS feed not detailed
-from BeautifulSoup import BeautifulSoup
+from bs4 import BeautifulSoup
 #http://www.apvma.gov.au/about/foi/disclosure/index.php
 (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, "http://www.apvma.gov.au/about/foi/disclosure/index.php", "foidocuments", "3cd40b1240e987cbcd3f0e67054ce259")
 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)
-		print soup.table.find_all('tr')[0].name
+		for row in soup.table.find_all('tr'):
+			columns = row.find_all('td')
+			if len(columns) == 5:
+				(id, date, description, title, notes) = columns
+				print id
+			elif len(row.find_all('th')) == 5:
+				print "header row"
+			else:
+				print "ERROR number of columns incorrect"
+				print row