Parsing the Arisia HTML schedule for conversion into your favorite calendar format

convert.py

#!/usr/bin/python
#Converts arisia HTML schedule to the following format:
#{name:NAME, start:YYYY-MM-DDTHH:MM:SS.000-05:00, end:(same as start), location:LOCATION, body:TEXT}
#name includes type

import re
from datetime import datetime, timedelta
import dateutil.parser
from sample import main

RFC3339 = '%Y-%m-%dT%H:%M:00.000-05:00'
events = []
thefile = "Schedule"

def parse(thefile):
	with open(thefile) as f:
		for line in f:
			#set time
			time = re.search("<hr /><h3>(.*?)</h3>", line)
			if time:
				TIME = dateutil.parser.parse(time.group(1))
				continue

			#get event title
			#name = re.match("<dl><dt><b>(.*?)</b> <i>\xe2\x80\x94 (.*?)</i> <i>\xe2\x80\x94 (.*?)</i> <i>\xe2\x80\x94 (.*?)</i>( <i>\xe2\x80\x94 (.*?)</i>)?</dt>", line)
			name = re.match("<dl><dt><b>(.*?)</b> <i>\xe2\x80\x94 (.*?)</i> <i>\xe2\x80\x94 (.*?)</i> <i>\xe2\x80\x94 (.*?)</i></dt>", line)
			if name:
				# if name.group(5):
				# 	NAME, TYPE1, TYPE2, DURATION, LOCATION = name.groups()
				# 	TYPE = TYPE1 + TYPE2
				# else:
				NAME, TYPE, DURATION, LOCATION = name.groups()
				TYPE.replace('\xe2\x80\x94', ' ')
				DURATION = re.match("(([0-9])hr)?( ([0-9]{1,2})min)?", DURATION)
				hours = int(DURATION.group(2)) if DURATION.group(1) else 0
				minutes = int(DURATION.group(4)) if DURATION.group(3) else 0
				DURATION = timedelta(hours=hours, minutes=minutes)
				continue

			if '<a href=' in line: continue

			body = re.match("<dd>(.*?)</dd>", line)
			if body:
				BODY = body.group(1)
				events.append({'name': NAME,
							'start': TIME.strftime(RFC3339),
							'end': (TIME + DURATION).strftime(RFC3339),
							'location': LOCATION,
							'body': BODY
						 	})
	return events

if __name__ == '__main__':
parse(thefile)