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.
 
 
 
 
 
 

89 line
2.8 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. class FifeParser:
  11. def __init__(self, *args):
  12. self.authority_name = "Fife Council"
  13. self.authority_short_name = "Fife"
  14. self.base_url = "http://www.fifedirect.org.uk/topics/index.cfm"
  15. self.comment_url = "http://www.ukplanning.com/ukp/showCaseFile.do?councilName=Fife+Council&appNumber=%s"
  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. [("fuseaction", "planapps.list"),
  21. ("SUBJECTID", "104CC166-3ED1-4D22-B9F1E2FB8438478A"),
  22. ("src_fromdayRec", day),
  23. ("src_frommonthRec", month),
  24. ("src_fromyearRec", year),
  25. ("src_todayRec", day),
  26. ("src_tomonthRec", month),
  27. ("src_toyearRec", year),
  28. ("findroadworks", "GO"),
  29. ]
  30. )
  31. search_url = self.base_url + "?" + search_data
  32. response = urllib2.urlopen(search_url)
  33. soup = BeautifulSoup(response.read())
  34. results_table = soup.find("table", id="results")
  35. # Apart from the first tr, which contains headers, the trs come in pairs for each application
  36. trs = results_table.findAll("tr")[1:]
  37. tr_count = 0
  38. while tr_count < len(trs):
  39. tr = trs[tr_count]
  40. if tr_count % 2 == 0:
  41. application = PlanningApplication()
  42. application.date_received = search_date
  43. tds = tr.findAll("td")
  44. application.council_reference = tds[0].a.string.strip()
  45. application.comment_url = self.comment_url %(application.council_reference)
  46. application.info_url = urlparse.urljoin(self.base_url, tds[0].a['href'])
  47. application.address = ', '.join([x.strip() for x in tds[1].findAll(text=True)])
  48. application.postcode = getPostcodeFromText(application.address)
  49. else:
  50. # Get rid of the "Details: " at the beginning.
  51. application.description = tr.td.string.strip()[9:]
  52. self._results.addApplication(application)
  53. tr_count += 1
  54. return self._results
  55. def getResults(self, day, month, year):
  56. return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
  57. if __name__ == '__main__':
  58. parser = FifeParser()
  59. print parser.getResults(21,5,2008)
  60. # TODO
  61. # Paginates at 50. Unlikely on a single day, so we'll worry about it later.