Quick and dirty snippet for checking new releases in Gohlke repository

get_gohlke

#Check http://www.lfd.uci.edu/~gohlke/pythonlibs/ for new releases
#works for Python 3.2

from urllib import request
from html.parser import HTMLParser
import re
import datetime
from collections import defaultdict

months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
          'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

class MyParser(HTMLParser):
    def __init__(self, checkversion):
        HTMLParser.__init__(self)
        self.hitpy = None
        self.pack = None
        self.checkversion = checkversion
        self.col = defaultdict(list)
        
    def handle_starttag(self, tag, attrs):
        if tag == 'a':
            for a, b in attrs:
                if a == 'id':
                    self.pack = b
                    self.hitpy = False
                    
    def handle_data(self, data):
        "handle all text not in html tags"
        if self.checkversion in data:
            self.hitpy = True
        if self.hitpy:
            hitdate = re.search('\[(\D\D\D \d\d), 2011\]', data)
            if hitdate:
                self.hitpy = False
                self.col[self.pack].append(hitdate.group(1))
    
    def output(self, n):
        "printa los cambios de menos de n dias"
        today = datetime.date.today()
        today = today.toordinal()
        for key, dates in self.col.items():
            dates = set(dates)
            for date in dates:
                (month, day) = date.split()
                num_month = months.index(month) + 1
                time_published = datetime.date(2011, num_month, int(day))
                time_published = time_published.toordinal()
                if (today - time_published) < n:
                    txt = '%-10s %s' %(key, date)
                    print(txt)
        
        
if __name__ == "__main__":

    url = "http://www.lfd.uci.edu/~gohlke/pythonlibs/"
    checkversion = 'Python 3.2'
    days_old = 7
    
    with request.urlopen(url) as sock:
        html = sock.read()
        
    htmldec = html.decode('utf8')
    myparser = MyParser(checkversion)
    myparser.feed(htmldec)
    myparser.output(days_old)