scrapers work
[disclosr.git] / documents / scrapers / 3cd40b1240e987cbcd3f0e67054ce259.py
blob:a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py -> blob:b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
--- a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
+++ b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
@@ -1,1 +1,15 @@
-http://www.apvma.gov.au/rss/disclosure.rss
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import scrape
+foidocsdb = scrape.couch['disclosr-foidocuments']
+
+#RSS feed not detailed
+from BeautifulSoup 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
+