From 4e824c66284306a51e4ace12ecf82d7a8e1f14ac Mon Sep 17 00:00:00 2001
From: "duncan.parkes" <duncan.parkes@cf68f80a-222c-0410-aabe-5f79d0504a29>
Date: Sun, 15 Jun 2008 14:21:08 +0000
Subject: [PATCH] Add Pendle scraper (this is basically the same as Maldon).

---
 python_scrapers/Maldon.py           | 34 ++++++++++++++++++++---------
 python_scrapers/SitesToGenerate.csv |  3 ++-
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/python_scrapers/Maldon.py b/python_scrapers/Maldon.py
index 0be19c3..e1703c8 100644
--- a/python_scrapers/Maldon.py
+++ b/python_scrapers/Maldon.py
@@ -17,12 +17,17 @@ date_format = "%d/%m/%Y"
 
 class MaldonParser:
     comment_email_address = "dc.planning@maldon.gov.uk"
-    info_url = "http://forms.maldon.gov.uk:8080/PlanApp/jsp/searchPlan.jsp"
-    def __init__(self, *args):
 
-        self.authority_name = "Maldon District Council"
-        self.authority_short_name = "Maldon"
-        self.base_url = "http://forms.maldon.gov.uk:8080/PlanApp/jsp/searchPlanApp-action.do"
+    def __init__(self, authority_name, authority_short_name, base_url, debug=False):
+
+        self.debug = debug
+
+        self.authority_name = authority_name
+        self.authority_short_name = authority_short_name
+        self.base_url = base_url
+
+        self.info_url = urlparse.urljoin(base_url, "searchPlan.jsp")
+
         self._split_base_url = urlparse.urlsplit(self.base_url)
 
         self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
@@ -44,6 +49,11 @@ class MaldonParser:
         response = urllib2.urlopen(search_url)
         soup = BeautifulSoup(response.read())
 
+        # First check if we have the no apps found page
+
+        if soup.find(text="No Applications Found"):
+            return self._results
+
         # Not a very good way of finding the table, but it works for the moment.
         results_table = soup.find("table", cellpadding="5px")
 
@@ -89,12 +99,16 @@ class MaldonParser:
     def getResults(self, day, month, year):
         return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
 
+
+class PendleParser(MaldonParser):
+    comment_email_address = "planning@pendle.gov.uk"
+
 if __name__ == '__main__':
-    parser = MaldonParser()
-    print parser.getResults(02,6,2008)
+    #parser = MaldonParser("Maldon District Council", "Maldon", "http://forms.maldon.gov.uk:8080/PlanApp/jsp/searchPlanApp-action.do")
+    parser = PendleParser("Pendle Borough Council", "Pendle", "http://bopdoccip.pendle.gov.uk/PlanApp/jsp/searchPlanApp-action.do")
+    print parser.getResults(21,5,2008)
 
 # TODO
 
-# 1) Check that it works ok on a no results page.
-# 2) Email the council about non-linkable info page.
-# 3) Email the council about missing descriptions?
+# 1) Email the council about non-linkable info page.
+# 2) Email the council about missing descriptions?
diff --git a/python_scrapers/SitesToGenerate.csv b/python_scrapers/SitesToGenerate.csv
index fe671ee..c349638 100644
--- a/python_scrapers/SitesToGenerate.csv
+++ b/python_scrapers/SitesToGenerate.csv
@@ -228,5 +228,6 @@
 "Fife Council", "Fife", "", "Fife", "FifeParser"
 "Forest of Dean District Council", "Forest of Dean", "", "ForestOfDean", "ForestOfDeanParser"
 "Flintshire County Council", "Flintshire", "", "Flintshire", "FlintshireParser"
-"Maldon District Council", "Maldon", "", "Maldon", "MaldonParser"
+"Maldon District Council", "Maldon", "http://forms.maldon.gov.uk:8080/PlanApp/jsp/searchPlanApp-action.do", "Maldon", "MaldonParser"
 "Medway Council", "Medway", "", "Medway", "MedwayParser"
+"Pendle Borough Council", "Pendle", "http://bopdoccip.pendle.gov.uk/PlanApp/jsp/searchPlanApp-action.do", "Maldon", "PendleParser"