From: Maxious <maxious@lambdacomplex.org>
Date: Wed, 09 Oct 2013 12:10:14 +0000
Subject: fix that darn CASA scraper
X-Git-Url: http://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=9fb69fa7fa874357953c98c7fbdb5ff6c2595883
---
fix that darn CASA scraper


Former-commit-id: 288d5ab60033e36608bf898869eecdf64180ba59
---


--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -199,6 +199,17 @@
     def getRows(self, table):
         return table.find_all('tr')
 
+    def getDocHash(self, id,date, url):
+                        if id.string is None:
+			    print "no id, using date as hash"
+                            return scrape.mkhash(
+                                self.remove_control_chars(
+                                    url + (''.join(date.stripped_strings))))
+                        else:
+                            return scrape.mkhash(
+                                self.remove_control_chars(
+                                    url + (''.join(id.stripped_strings))))
+
     def getDate(self, content, entry, doc):
         strdate = ''.join(content.stripped_strings).strip()
         (a, b, c) = strdate.partition("(")
@@ -240,15 +251,7 @@
                          description, notes) = self.getColumns(columns)
                         print self.remove_control_chars(
                             ''.join(id.stripped_strings))
-                        if id.string is None:
-			    print "no id, using date as hash"
-                            dochash = scrape.mkhash(
-                                self.remove_control_chars(
-                                    url + (''.join(date.stripped_strings))))
-                        else:
-                            dochash = scrape.mkhash(
-                                self.remove_control_chars(
-                                    url + (''.join(id.stripped_strings))))
+                        dochash = self.getDocHash(id,date,url)
                         doc = foidocsdb.get(dochash)
 
                         if doc is None:

--- a/documents/runScrapers.sh
+++ b/documents/runScrapers.sh
@@ -1,3 +1,4 @@
+#!/bin/bash
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 echo $DIR
 cd $DIR

--- a/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py
+++ b/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py
@@ -6,6 +6,11 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+        def getDocHash(self, id,date, url):
+		''' url changes on ever request so ignore for hash '''
+		return scrape.mkhash(
+                                self.remove_control_chars(
+                                    ''.join(id.stripped_strings)))
         def getColumnCount(self):
                 return 4
         def getColumns(self,columns):