poj_parse.py

import os, re, datetime

class CST_tzinfo(datetime.tzinfo):
  def utcoffset(self, dt):
    return datetime.timedelta(hours=+8) + self.dst(dt)

  def dst(self, dt):
    return datetime.timedelta(0)

  def tzname(self, dt):
    return 'CST'

class JST_tzinfo(datetime.tzinfo):
  def utcoffset(self, dt):
    return datetime.timedelta(hours=+9) + self.dst(dt)

  def dst(self, dt):
    return datetime.timedelta(0)

  def tzname(self, dt):
    return 'JST'

def parse_problems():
  rex = re.compile('^<tr align=center><td>(?P<problem>\d+)</td>'
      '<td align=left><a lang=".*" href=problem\?id=\d+>(?P<title>.+?)</a>')

  for line in open(os.path.expanduser("~/Volume 1.html")).readlines():
    matches = rex.match(line)
    if matches:
      problem = matches.group('problem')
      title = matches.group('title')

def parse_status_list():
  rex = re.compile('^<tr align=center><td>(?P<runid>\d+)</td>' # runid
      '<td><a href=userstatus\?user_id=.*>(?P<userid>.*)</a></td>' # userid
      '<td><a href=problem\?id=\d+>(?P<problem>\d+)</a></td>' # problem
      '<td>.*<font color=.*>(?P<status>.+)</font>.*</td>' # status
      '<td>(?P<memory>.*)</td><td>(?P<runtime>.*)</td>' # memory and runtime
      '<td>(?P<language>.+)</td><td>(?P<size>.+)</td>' # language and size
      '<td>(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2}) ' # date
      '(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})</td></tr>')

  for line in open(os.path.expanduser("~/Problem Status List.html")).readlines():
    matches = rex.match(line)
    if matches:
      rundate = datetime.datetime(
          int(matches.group('year')),
          int(matches.group('month')),
          int(matches.group('day')),
          int(matches.group('hour')),
          int(matches.group('minute')),
          int(matches.group('second')),
          0, CST_tzinfo())
      runid = int(matches.group('runid'))
      userid = matches.group('userid')
      problem = matches.group('problem')
      status = matches.group('status')
      memory = matches.group('memory')
      runtime = matches.group('runtime')
      language = matches.group('language')
      size = int(matches.group('size').strip('B'))

parse_problems()
parse_status_list()