ScrapeThemes_irssi.py

#!/usr/bin/env python
#
# Shittiest script to scrape http://irssi.org/themes and fetch the theme
# image screenshots, because frankly, that shit is unviewable.

from os import path, mkdir
import re
import sys
import urllib2
from urlparse import urlsplit, urljoin

from BeautifulSoup import BeautifulSoup

LOCATION = "http://irssi.org/themes"

def parse_url(pageurl):
    """ Parse url, returns soup." """

    try:
        page_handle = urllib2.urlopen(pageurl)
    except urllib2.URLError as e:
        print "Error: Failed to connect to %s: %s" % (pageurl, e.reason)
        sys.exit(1)
    else:
        return BeautifulSoup(page_handle)


def download(url):
    """ Download a file from url to destination """
    try:
        data = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print "Failed to download %s: %s" % (url, e.reason)
        return False
    else:
        filename = path.basename(urlsplit(url)[2])
        try:
            out = open(path.join("out", filename), 'wb')
            out.write(data)
            out.close()
        except IOError as e:
            print "Error occured saving file: %s" % (e)
            return False
        else:
            return True

def main():
    print "Shitty image scraper v1"
    print "(c) Alexandre Gauthier 2010-2011"
    print "--------------------------------------"

    print "Downloading all the themes from %s" % (LOCATION)
    print "Terribly hardcoded output dir is %s" % "out"

    soup = parse_url(LOCATION)

    p = re.compile('^\/themefiles\/.+\.\w+', re.IGNORECASE)

    if path.isdir('out'):
        pass
    elif path.isfile('out'):
        print "A file named 'out' already exists here. Bailing."
        sys.exit(1)
    else:
        # Bah, let it throw an exception, that's enough try/catch
        # bullshit for today, I think.
        mkdir('out')
        print "NOTE: Created directory 'out'"

    for link in soup.findAll('a'):
        if p.match(link['href']):
            print "%s matches pattern, fetching... " % link['href'],
            if download(urljoin(LOCATION,link['href'])):
                print "OK"
            else:
                print "FAILED!"


if __name__ == '__main__':
    main()