Automatically exported from code.google.com/p/planningalerts
您最多选择25个主题 主题必须以字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符

Herefordshire.py 3.0 KiB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485
  1. import urllib2
  2. import urllib
  3. import urlparse
  4. import datetime, time
  5. import cgi
  6. import re
  7. from BeautifulSoup import BeautifulSoup
  8. from PlanningUtils import PlanningApplication, \
  9. PlanningAuthorityResults, \
  10. getPostcodeFromText
  11. date_format = "%d/%m/%Y"
  12. class HerefordshireParser:
  13. comments_email_address = "Developmentcontrol@barnsley.gov.uk"
  14. def __init__(self, *args):
  15. self.authority_name = "Herefordshire Council"
  16. self.authority_short_name = "Herefordshire"
  17. self.base_url = "http://www.herefordshire.gov.uk/gis/planListResults.aspx?pc=&address=&querytype=current&startdate=%(date)s&enddate=%(date)s&startrecord=0"
  18. #As we are going to the info page, we may as well pick up the comment url from there.
  19. # self.comment_url = "http://www.herefordshire.gov.uk/gis/planDetailCommentAddress.aspx?ApplicationId=%s" # This need the reference inserting
  20. self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
  21. def getResultsByDayMonthYear(self, day, month, year):
  22. search_day = datetime.date(year, month, day)
  23. post_data = urllib.urlencode(
  24. (("show", "0"),
  25. ("Go", "GO"),
  26. )
  27. )
  28. # Now get the search page
  29. response = urllib2.urlopen(self.base_url %{"date": search_day.strftime(date_format)})
  30. soup = BeautifulSoup(response.read())
  31. if not soup.find(text=re.compile("Sorry, no matches found")):
  32. # There were apps for this date
  33. trs = soup.find("table", {"class": "gis_table"}).findAll("tr")[2:]
  34. for tr in trs:
  35. application = PlanningApplication()
  36. application.date_received = search_day
  37. application.info_url = urlparse.urljoin(self.base_url, tr.a['href'])
  38. application.council_reference = tr.a.string
  39. # application.comment_url = self.comment_url %(application.council_reference)
  40. tds = tr.findAll("td")
  41. application.address = tds[1].string
  42. application.postcode = getPostcodeFromText(application.address)
  43. # This just gets us an initial segment of the description.
  44. # We are going to have to download the info page...
  45. #application.description = tds[2].string.strip()
  46. info_response = urllib.urlopen(application.info_url)
  47. info_soup = BeautifulSoup(info_response.read())
  48. application.description = info_soup.find(text="Proposal:").findNext("td").string.strip()
  49. application.comment_url = urlparse.urljoin(self.base_url, info_soup.find("a", title="Link to Planning Application Comment page")['href'])
  50. self._results.addApplication(application)
  51. return self._results
  52. def getResults(self, day, month, year):
  53. return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
  54. if __name__ == '__main__':
  55. parser = HerefordshireParser()
  56. print parser.getResults(31,8,2008)