Automatically exported from code.google.com/p/planningalerts
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 

76 regels
2.3 KiB

  1. import urllib2
  2. import urllib
  3. import urlparse
  4. import datetime, time
  5. import cgi
  6. from BeautifulSoup import BeautifulSoup
  7. from PlanningUtils import PlanningApplication, \
  8. PlanningAuthorityResults, \
  9. getPostcodeFromText
  10. date_format = "%Y%m%d"
  11. class ForestOfDeanParser:
  12. def __init__(self, *args):
  13. self.authority_name = "Forest of Dean District Council"
  14. self.authority_short_name = "Forest of Dean"
  15. self.base_url = "http://www.fdean.gov.uk/content.asp"
  16. self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
  17. def getResultsByDayMonthYear(self, day, month, year):
  18. search_date = datetime.date(year, month, day)
  19. search_data = urllib.urlencode(
  20. [
  21. ("parent_directory_id", "200"),
  22. ("nav", "679"),
  23. ("id", "13266"),
  24. ("RecStart", "1"),
  25. ("RecCount", "100"),
  26. ("SDate", search_date.strftime(date_format)),
  27. ("EDate", search_date.strftime(date_format)),
  28. ]
  29. )
  30. search_url = self.base_url + "?" + search_data
  31. response = urllib2.urlopen(search_url)
  32. soup = BeautifulSoup(response.read())
  33. results_table = soup.find("table", summary="List of planning applications that match your query")
  34. for tr in results_table.findAll("tr")[1:]:
  35. application = PlanningApplication()
  36. application.date_received = search_date
  37. tds = tr.findAll("td")
  38. application.council_reference = tds[0].a.string.strip()
  39. application.info_url = urlparse.urljoin(self.base_url, tds[0].a['href'])
  40. application.comment_url = application.info_url
  41. application.address = ' '.join(tds[1].string.strip().split())
  42. application.postcode = getPostcodeFromText(application.address)
  43. application.description = tds[2].string.strip()
  44. self._results.addApplication(application)
  45. return self._results
  46. def getResults(self, day, month, year):
  47. return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
  48. if __name__ == '__main__':
  49. parser = ForestOfDeanParser()
  50. print parser.getResults(21,5,2008)
  51. # TODO - looks like it paginates at 20