#!/usr/bin/env python

cache_dir = '../raw_data/FAA/TFRs'

import urllib
import sgmllib
import htmllib
import formatter
import string
import re

def get_list():
	TFR_list = urllib.urlopen('http://tfr.faa.gov/tfr/jsp/list.jsp', cache_dir + 'list.html')
	print dir(TFR_list)
	print TFR_list.url
	while 1:
		line = TFR_list.readline()
		print line



def tuples_to_dict(t):
	dict = {}
	for (var, val) in t:
		dict[var] = val

	return(dict)

class mywriter(formatter.NullWriter):
	def __init__(self):
		formatter.NullWriter.__init__(self)

	def send_flowing_data(self, str):
		print str

class myparser(htmllib.HTMLParser):
#class myparser(sgmllib.SGMLParser):
	def __init__(self, fmt, limit=-1):
		self.formatter = fmt
		self.hrefs = []
		htmllib.SGMLParser.__init__(self, fmt)
			
	def anchor_bgn(self, href, name, type):
		self.hrefs.append(href)

def get_hrefs(url):
	fmt = formatter.AbstractFormatter(formatter.NullWriter())
	parser = myparser(fmt=fmt)
	page = urllib.urlopen(url, cache_dir + '/' + url)
	parser.feed(page.read())
	parser.close()
	return parser.hrefs

def get_notam_ids():
	detail_re = re.compile('_([0-9])_([0-9]{4}).html$')
	notam_ids = []
	for href in get_hrefs('http://tfr.faa.gov/tfr/jsp/list.jsp'):
		m = detail_re.search(href)
		if m:
			notam_id = m.groups()
			if not notam_id in notam_ids:
				notam_ids.append(notam_id)

	return(notam_ids)

def parse_notam(notam):
	for (count, sentence) in enumerate(notam.split('. ')):
		print count, sentence

for notam_id in get_notam_ids():
	print notam_id

	page = urllib.urlopen('http://tfr.faa.gov/tfr/jsp/save_pages/detail_%s_%s.html' % notam_id)
	title = 'FDC %s/%s' % notam_id

	m = re.compile('FDC %s/%s (.*)<p>' % notam_id).search(page.read())
	if m:
		parse_notam(m.groups()[0])