def scrape_logos(): local("mkdir -p data/logos") base_uri = "http://www.sportslogos.net/league.php?id={0}" for url in [base_uri.format(page_id) for page_id in xrange(30, 36)]: resp = requests.get(url) if not resp.ok: print "Error retrieving {0}".format(url) continue tree = HTML(resp.content) for thumb in tree.findall(".//div[@class='thumbHolder']"): link = thumb.find("a") logo = link.find("img") title = link.attrib["title"].lower().replace("Logos", "") title = title.replace(" ", "_").strip() filename = "data/logos/{0}.gif".format(title) urllib.urlretrieve(logo.attrib["src"], filename)