Update links to Spinnerette comics to current format

fix-spinny.py

import sys
from datetime import datetime
import re
import urllib2
from bs4 import BeautifulSoup

wayback_prefix = 'https://web.archive.org/web/20160824022930/'
newformat_prefix = 'http://www.spinnyverse.com/comic/'

cachef = open('spinny-cache', 'a+')
cachef.seek(0, 0)
cache = {}
for l in cachef:
    (id, new_suffix) = l.split()
    cache[id] = new_suffix

def update_url(m):
    org_uri = m.group(0)
    id = m.group(1)
    try:
        new_suffix = cache[id]
    except KeyError:
        print >>sys.stderr, 'Fetching page for ' + id
        wayback_page = urllib2.urlopen(wayback_prefix + org_uri)
        soup = BeautifulSoup(wayback_page, 'html.parser')
        img = soup.find('img', attrs={'id': 'cc-comic'})
        if img <> None:
            new_suffix = img['title'].lower().replace(' ', '-')
            new_suffix = re.sub('-+', '-', new_suffix)
        else:
            img = soup.find('img', attrs={'id': 'comic'})
            m = re.match('/web/\d+im_/http://www.spinnyverse.com:80/comics/(.+).jpg', img['src'])
            comicdate = datetime.strptime(m.group(1), '%Y-%m-%d')
            new_suffix = comicdate.strftime('%m-%d-%Y')
        cache[id] = new_suffix
        cachef.write(id + ' ' + new_suffix + '\n')
    return (newformat_prefix + new_suffix).encode('ascii')

def update_format2(m):
    year = m.group(2)
    month = m.group(3)
    day = m.group(4)
    month2 = m.group(5)
    day2 = m.group(6)
    year2 = m.group(7)
    assert year == year2 and month == month2 and day == day2
    return '{0}{1}-{2}-{3}'.format(newformat_prefix, month, day, year)

with open(sys.argv[1], 'r') as f:
    cnt = f.read()

newcnt = re.sub('http://www\.spinnyverse\.com/index\.php\?id=(\d+)', update_url, cnt)
newcnt = re.sub('http://www\.(spinnyverse\.com|krakowstudios\.com/spinnerette)/(\d\d\d\d)/(\d\d)/(\d\d)/(\d\d)(\d\d)(\d\d\d\d)/?', update_format2, newcnt)

cachef.close()
print newcnt