Automatically exported from code.google.com/p/planningalerts
Вы не можете выбрать более 25 тем Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
 
 
 
 
 
 

70 строки
3.0 KiB

  1. import urllib2
  2. import cgi
  3. import urlparse
  4. import datetime, time
  5. import BeautifulSoup
  6. from PlanningUtils import PlanningApplication, PlanningAuthorityResults
  7. date_format = "%d/%m/%Y"
  8. class CrawleyParser:
  9. comment_url_template = "http://www.crawley.gov.uk/stellent/idcplg?IdcService=SS_GET_PAGE&nodeId=561&pageCSS=&pAppNo=%(pAppNo)s&pAppDocName=%(pAppDocName)s"
  10. def __init__(self, *args):
  11. self.authority_name = "Crawley Borough Council"
  12. self.authority_short_name = "Crawley"
  13. self.base_url = "http://www.crawley.gov.uk/stellent/idcplg?IdcService=SS_GET_PAGE&nodeId=560&is_NextRow=1&accept=yes&strCSS=null&pApplicationNo=&pProposal=&pLocation=&pPostcode=&pWard=&pDateType=received&pDayFrom=%(dayFrom)s&pMonthFrom=%(monthFrom)s&pYearFrom=%(yearFrom)s&pDayTo=%(dayTo)s&pMonthTo=%(monthTo)s&pYearTo=%(yearTo)s&submit=Search"
  14. self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
  15. def getResultsByDayMonthYear(self, day, month, year):
  16. search_day = datetime.date(year, month, day)
  17. #- Crawley only allows searches from-to, so:
  18. next = self.base_url %{
  19. "dayFrom": day,
  20. "monthFrom": month,
  21. "yearFrom": year,
  22. "dayTo": day,
  23. "monthTo": month,
  24. "yearTo": year,
  25. }
  26. # Now get the search page
  27. response = urllib2.urlopen(next)
  28. soup = BeautifulSoup.BeautifulSoup(response.read())
  29. if soup.table: #- Empty result set has no table
  30. trs = soup.table.findAll("tr")[1:] # First one is just headers
  31. for tr in trs:
  32. tds = tr.findAll("td")
  33. application = PlanningApplication()
  34. application.council_reference = tds[0].a.contents[0].strip().replace("/", "/")
  35. application.info_url = urlparse.urljoin(self.base_url, tds[0].a['href'])
  36. info_qs = cgi.parse_qs(urlparse.urlsplit(application.info_url)[3])
  37. comment_qs = {
  38. "pAppNo": application.council_reference,
  39. "pAppDocName": info_qs["ssDocName"][0],
  40. }
  41. application.comment_url = self.comment_url_template %comment_qs
  42. application.address = tds[1].string.strip()
  43. if tds[2].string: #- if postcode present, append it to the address too
  44. application.postcode = tds[2].string.replace(" ", " ").strip()
  45. application.address += ", " + application.postcode
  46. application.description = tds[3].string.strip()
  47. application.date_received = datetime.datetime(*(time.strptime(tds[4].string.strip(), date_format)[0:6]))
  48. self._results.addApplication(application)
  49. return self._results
  50. def getResults(self, day, month, year):
  51. return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
  52. if __name__ == '__main__':
  53. parser = CrawleyParser()
  54. print parser.getResults(12,6,2008)