Automatically exported from code.google.com/p/planningalerts
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
 
 
 
 
 
 

71 linhas
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. search_date_format = "%d+%b+%Y"
  11. received_date_format = "%d %b %Y"
  12. class ExmoorParser:
  13. def __init__(self, *args):
  14. self.authority_name = "Exmoor National Park"
  15. self.authority_short_name = "Exmoor"
  16. self.base_url = "http://www.exmoor-nationalpark.gov.uk/planning_weekly_list.htm?weeklylist=%s"
  17. self._results = PlanningAuthorityResults(self.authority_name, self.authority_short_name)
  18. def getResultsByDayMonthYear(self, day, month, year):
  19. search_day = datetime.date(year, month, day)
  20. response = urllib2.urlopen(self.base_url %(search_day.strftime(search_date_format)))
  21. soup = BeautifulSoup(response.read())
  22. # The first <tr> contains headers
  23. trs = soup.table.findAll("tr")[1:]
  24. for tr in trs:
  25. application = PlanningApplication()
  26. tds = tr.findAll("td")
  27. application.date_received = datetime.datetime.strptime(tds[0].string, received_date_format).date()
  28. application.info_url = urllib.unquote(urllib.quote_plus(urlparse.urljoin(self.base_url, tds[1].a['href'])))
  29. application.council_reference = tds[1].a.string.strip()
  30. application.address = tds[2].a.string.strip()
  31. application.postcode = getPostcodeFromText(application.address)
  32. # Now fetch the info url
  33. info_response = urllib.urlopen(application.info_url)
  34. info_soup = BeautifulSoup(info_response.read())
  35. application.description = info_soup.find(text="Proposal:").findNext("td").string.strip()
  36. try:
  37. application.comment_url = urlparse.urljoin(self.base_url, info_soup.find(text="Comment").parent['href'])
  38. except:
  39. application.comment_url = "No Comments"
  40. self._results.addApplication(application)
  41. return self._results
  42. def getResults(self, day, month, year):
  43. return self.getResultsByDayMonthYear(int(day), int(month), int(year)).displayXML()
  44. if __name__ == '__main__':
  45. parser = ExmoorParser()
  46. print parser.getResults(1,8,2008)