From e511044601a1997d368d676b2de338d60ac4dca2 Mon Sep 17 00:00:00 2001
From: "duncan.parkes" <duncan.parkes@cf68f80a-222c-0410-aabe-5f79d0504a29>
Date: Mon, 9 Jun 2008 08:33:08 +0000
Subject: [PATCH] Add partially done Ocella scraper

---
 trunk/python_scrapers/Ocella.py | 103 ++++++++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100644 trunk/python_scrapers/Ocella.py

diff --git a/trunk/python_scrapers/Ocella.py b/trunk/python_scrapers/Ocella.py
new file mode 100644
index 0000000..8c36986
--- /dev/null
+++ b/trunk/python_scrapers/Ocella.py
@@ -0,0 +1,103 @@
+import urllib2
+import urllib
+import urlparse
+
+import datetime
+
+import cookielib
+
+cookie_jar = cookielib.CookieJar()
+
+from BeautifulSoup import BeautifulSoup
+
+from PlanningUtils import PlanningApplication, \
+    PlanningAuthorityResults, \
+    getPostcodeFromText
+
+date_format = "%d-%m-%Y"
+
+class OcellaParser:
+    def __init__(self,
+                 authority_name,
+                 authority_short_name,
+                 base_url,
+                 debug=False):
+
+        self.authority_name = authority_name
+        self.authority_short_name = authority_short_name
+        self.base_url = base_url
+
+        self.debug = debug
+
+        self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
+
+
+    def getResultsByDayMonthYear(self, day, month, year):
+        search_date = datetime.date(year, month, day)
+
+        # First get the search page
+        get_request = urllib2.Request(self.base_url)
+        get_response = urllib2.urlopen(get_request)
+
+        cookie_jar.extract_cookies(get_response, get_request)
+
+        get_soup = BeautifulSoup(get_response.read())
+
+        # We need to find where the post action goes
+        action = get_soup.form['action']
+        session_id = get_soup.find('input', {'name': 'p_session_id'})['value']
+
+        post_data = urllib.urlencode(
+            [#('p_object_name', 'FRM_WEEKLY_LIST.DEFAULT.SUBMIT_TOP.01'),
+             #('p_instance', '1'),
+             #('p_event_type', 'ON_CLICK'),
+             #('p_user_args', ''),
+             ('p_session_id', session_id),
+             #('p_page_url', self.base_url),
+             ('FRM_WEEKLY_LIST.DEFAULT.START_DATE.01', '02-06-2008'), #search_date.strftime(date_format),
+             ('FRM_WEEKLY_LIST.DEFAULT.END_DATE.01', '09-06-2008'),#search_date.strftime(date_format),
+             #('FRM_WEEKLY_LIST.DEFAULT.PARISH.01', ''),
+                ]
+            )
+        
+        post_request = urllib2.Request(action, post_data)
+        cookie_jar.add_cookie_header(post_request)
+
+        post_request.add_header('Referer', self.base_url)
+
+        post_response = urllib2.urlopen(post_request)
+
+        import pdb;pdb.set_trace()
+
+# # From Breckland
+
+# p_object_name=FRM_WEEKLY_LIST.DEFAULT.SUBMIT_TOP.01
+# p_instance=1
+# p_event_type=ON_CLICK
+# p_user_args=
+# p_session_id=53573
+# p_page_url=http%3A%2F%2Fwplan01.intranet.breckland.gov.uk%3A7778%2Fportal%2Fpage%3F_pageid%3D33%2C30988%26_dad%3Dportal%26_schema%3DPORTAL
+# FRM_WEEKLY_LIST.DEFAULT.START_DATE.01=02-06-2008
+# FRM_WEEKLY_LIST.DEFAULT.END_DATE.01=09-06-2008
+# FRM_WEEKLY_LIST.DEFAULT.PARISH.01=
+
+# # Mine
+# p_object_name=FRM_WEEKLY_LIST.DEFAULT.SUBMIT_TOP.01
+# p_user_args=
+# FRM_WEEKLY_LIST.DEFAULT.START_DATE.01=21-05-2008
+# FRM_WEEKLY_LIST.DEFAULT.END_DATE.01=21-05-2008
+# p_session_id=53576
+# p_instance=1
+# p_page_url=http%3A%2F%2Fwplan01.intranet.breckland.gov.uk%3A7778%2Fportal%2Fpage%3F_pageid%3D33%2C30988%26_dad%3Dportal%26_schema%3DPORTAL
+# FRM_WEEKLY_LIST.DEFAULT.PARISH.01=
+# p_event_type=ON_CLICK
+
+    def getResults(self, day, month, year):
+        return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
+
+
+if __name__ == '__main__':
+    parser = OcellaParser("Breckland Council", "Breckland", "http://wplan01.intranet.breckland.gov.uk:7778/portal/page?_pageid=33,30988&_dad=portal&_schema=PORTAL")
+    print parser.getResults(21,5,2008)
+
+