beginnings of document scrapers mark 2
[disclosr.git] / documents / scrapers / 8c9421f852c441910bf1d93a57b31d64.py
blob:a/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py -> blob:b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
--- a/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
+++ b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
@@ -1,1 +1,19 @@
-http://www.daff.gov.au/about/foi/ips/disclosure_log
+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 getTable(self,soup):
+                return soup.find(id = "page_content").table
+        def getColumns(self,columns):
+                (id, date, title, description, notes) = columns
+                return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+    ScraperImplementation().doScrape()
+
+