From 9018285d288968c86198055fe0d06c86fadeed65 Mon Sep 17 00:00:00 2001 From: "duncan.parkes" Date: Sun, 8 Jun 2008 17:24:28 +0000 Subject: [PATCH] Set up planet scraper. This get's us 5 new councils (though one, Tewkesbury, has no postcodes) --- trunk/python_scrapers/OtherFilesToCopy.csv | 1 + trunk/python_scrapers/Planet.py | 9 ++++++++- trunk/python_scrapers/SitesToGenerate.csv | 7 ++++++- 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/trunk/python_scrapers/OtherFilesToCopy.csv b/trunk/python_scrapers/OtherFilesToCopy.csv index 26a708a..222cc80 100644 --- a/trunk/python_scrapers/OtherFilesToCopy.csv +++ b/trunk/python_scrapers/OtherFilesToCopy.csv @@ -19,3 +19,4 @@ "WestDorset.cgi", "493" "Christchurch.cgi", "493" "WAM.py", "420" +"Planet.py", "420" \ No newline at end of file diff --git a/trunk/python_scrapers/Planet.py b/trunk/python_scrapers/Planet.py index 1c34ef8..4ed567a 100644 --- a/trunk/python_scrapers/Planet.py +++ b/trunk/python_scrapers/Planet.py @@ -147,9 +147,16 @@ class PlanetParser: if __name__ == '__main__': -# parser = PlanetParser("Worcester City Council", "Worcester", "http://www.worcester.gov.uk:8080/planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", debug=True) # parser = PlanetParser("Elmbridge Borough Council", "Elmbridge", "http://www2.elmbridge.gov.uk/Planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry") # parser = PlanetParser("North Lincolnshire Council", "North Lincolnshire", "http://www.planning.northlincs.gov.uk/planet/ispforms.asp?ServiceKey=SysDoc-PlanetApplicationEnquiry") # parser = PlanetParser("Rydale District Council", "Rydale", "http://www.ryedale.gov.uk/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry") parser = PlanetParser("Tewkesbury Borough Council", "Tewkesbury", "http://planning.tewkesbury.gov.uk/Planet/ispforms.asp?serviceKey=07WCC04163103430") print parser.getResults(21,5,2008) +# parser = PlanetParser("Worcester City Council", "Worcester", "http://www.worcester.gov.uk:8080/planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", debug=True) + +# TODO + +# 1) Pagination +# 2) Work OK with no results. + +# 3) Use OSGB for Tewkesbury? diff --git a/trunk/python_scrapers/SitesToGenerate.csv b/trunk/python_scrapers/SitesToGenerate.csv index d779144..5dfca37 100644 --- a/trunk/python_scrapers/SitesToGenerate.csv +++ b/trunk/python_scrapers/SitesToGenerate.csv @@ -201,4 +201,9 @@ "Rother District Council", "Rother", "http://www.planning.rother.gov.uk/WAM/pas/searchApplications.do", "WAM", "WAMParser" "South Gloucestershire Council", "South Gloucestershire", "http://planning.southglos.gov.uk/WAM/pas/WeeklyApplications.do", "WAM", "BraintreeParser" "London Borough of Tower Hamlets", "Tower Hamlets", "http://194.201.98.213/WAM/weeklyApplications.do", "WAM", "BraintreeParser" -"Sheffield City Council", "Sheffield", "http://planning.sheffield.gov.uk/publicaccess/tdc/", "PublicAccess", "PublicAccessParser" \ No newline at end of file +"Sheffield City Council", "Sheffield", "http://planning.sheffield.gov.uk/publicaccess/tdc/", "PublicAccess", "PublicAccessParser" +"Elmbridge Borough Council", "Elmbridge", "http://www2.elmbridge.gov.uk/Planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", "Planet", "PlanetParser" +"North Lincolnshire Council", "North Lincolnshire", "http://www.planning.northlincs.gov.uk/planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", "Planet", "PlanetParser" +"Ryedale District Council", "Ryedale", "http://www.ryedale.gov.uk/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", "Planet", "PlanetParser" +"Tewkesbury Borough Council", "Tewkesbury", "http://planning.tewkesbury.gov.uk/Planet/ispforms.asp?serviceKey=07WCC04163103430", "Planet", "PlanetParser" +"Worcester City Council", "Worcester", "http://www.worcester.gov.uk:8080/planet/ispforms.asp?serviceKey=SysDoc-PlanetApplicationEnquiry", "Planet", "PlanetParser"