1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
#!/usr/bin/env python
from __future__ import print_function
import sys
import urllib,re
import sqlite3
#con = sqlite3.connect('ais.db3')
#cx = sqlite3.connect('test.db3')
#cu = cx.cursor()
######################################################################
# MMSI Prefix handling
def mmsi_codes(filename=None):
'''Create a table of 3 digit MMSI codes
@return: code lookup table
@rtype: dict
'''
entry_re_str = r'''\<tr\>\<td\>(?P<prefixes>[0-9 ,]*)\</td\>\<td\>(?P<country>[^<]*)\</td\>\</tr\>'''
entry_re = re.compile(entry_re_str)
if not filename:
html = urllib.urlopen('http://www.itu.int/cgi-bin/htsh/glad/cga_mids.sh?lng=E')
else:
html = file(filename)
# Lame parser. Would be better to use BeautifulSoup or html5lib
last_country = None
codes = {}
for line in html:
if '<tr>' != line[0:4]: continue
matches = entry_re.search(line)
if not matches: continue
prefixes = matches.group('prefixes')
country = matches.group('country')
if chr(244) in country:
country = country.replace(chr(244),'o')
if ' - ' == country:
country = last_country
for prefix in prefixes.split(','):
codes[int(prefix)] = country
last_country = country
return codes
if __name__=='__main__':
codes = mmsi_codes('mid.html')
for code in codes:
print ('%s,"%s"' % (code,codes[code]))
|
