def scraper(url,downloadDirectory):
    start = time.time()

    baseUrl = r"{some_url}"


    html = urlopen(url)
    bsObj = BeautifulSoup(html.read())
    table = bsObj.findAll("table")[0]
    links = table.findAll("a")

    count = 0
    broken_links = []
    for link in links:
        try:
            count += 1
            link = str(link).split(""")
            if len(link) > 1:
                print(link)
                link = link[1]
                linkBreak = link.split("_")
            else:
                if link[0] == "<a></a>":
                    print("Skipping")
                    continue
                else:
                    print(link)
                    linkBreak = link.split("_")

            title = re.findall(r"[w']+",str(linkBreak))[9].strip("'")
            if title == "nyc":
                title = re.findall(r"[w']+",str(linkBreak))[10].strip("'")
            print("# " + str(count), "Title: " + str(title))
            dir_path = os.path.join(downloadDirectory,title)
            if os.path.isdir(dir_path) == False:
                print("Creating directory: " + str(os.path.join(downloadDirectory,title)))
                os.mkdir(dir_path)

            file_path = urllib.parse.urljoin(baseUrl,link)
            print("File Path: " + str(file_path), "n" + "Directory Path: " + str(dir_path))
            print("Split array and length: ", linkBreak, len(linkBreak))
            if len(linkBreak) == 1:
                if os.path.isfile(os.path.join(dir_path,str(linkBreak[0]).split("/")[7])):
                    print("Skipping")
                    continue
                else:
                    print("Result: " + str(os.path.join(dir_path,str(linkBreak[0]).split("/")[7])))
                    urlretrieve(file_path,os.path.join(dir_path,str(linkBreak[0]).split("/")[7]))
            elif len(linkBreak) == 2:
                if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[1])):
                    print("Skipping")
                    continue
                elif str(os.path.join(dir_path,title + "_" + linkBreak[1])).endswith(".zip") == False:
                    if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[1] + ".zip")):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[1] + ".zip")))
                        urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[1] + ".zip"))
                else:
                    print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[1])))
                    urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[1]))
            elif len(linkBreak) == 3:
                if "?" in linkBreak[2]:
                    linkBreak[2] = linkBreak[2].split("?", 1)[0]
                    if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[2])):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[2])))
                        urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[2]))
                if title == "sidewalkcafe":
                    linkBreak[2] = str(linkBreak[1]) + str(linkBreak[2])
                    if os.path.isfile(os.path.join(dir_path,title + linkBreak[2])):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + linkBreak[2])))
                        urlretrieve(file_path,os.path.join(dir_path,title + linkBreak[2]))
                else:
                    if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[2])):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[2])))
                        urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[2]))
            elif len(linkBreak) == 4:
                if "?" in linkBreak[3]:
                    linkBreak[3] = linkBreak[3].split("?",1)[0]
                    linkBreak[2] = str(linkBreak[2]) + "_" + str(linkBreak[3])
                    if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[2])):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[2])))
                        urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[2]))
                else:
                    if os.path.isfile(os.path.join(dir_path,title + "_" + linkBreak[2])):
                        print("Skipping")
                        continue
                    else:
                        print("Result: " + str(os.path.join(dir_path,title + "_" + linkBreak[2])))
                        urlretrieve(file_path,os.path.join(dir_path,title + "_" + linkBreak[2]))
        except HTTPError as e:
            if e.code == 404:
                print(e)
                print(count,"__________")
                broken_links.append([count,title,link])
                continue
            else:
                raise

    end = time.time()
    fp = os.path.join(downloadDirectory,"BrokenLinks.txt")
    file = open(fp,"w+")
    for link in broken_links:
        file.write(str(link) + "n")
    file.write(str(datetime.now()))
    file.close()

    return("Script completed in: " + str(end - start) + " seconds.")

archURL = {some_url}
archDownloadDirectory = {some_localpath}

scraper(archURL,archDownloadDirectory)