简单的抓图片爬虫

import re,os,sys,bs4,requests,time
def check_url(url,domain_url):
    httpreg = re.compile(r'(https?)://')
    if httpreg.match(url):
        return url
    slashreg = re.compile(r'//')
    if slashreg.match(url):
        return 'http://'+ url[2:]
    return domain_url + url
def replace_filename(filename):
    reg_filename = re.compile(r'(.*)?[\/:*?"<>|].*')
    mo = reg_filename.search(filename)
    if mo:
        return mo.group(1)
    else:
        return filename
def now():
    return int(round(time.time()))
def get_path():
    return os.path.join('c','img')
def download_img(url):
    os.makedirs(get_path(),exist_ok=True)
    if url[-1] == '/':
        url = url[:-1]
    res = requests.get(url)
    res.raise_for_status()
    soup = bs4.BeautifulSoup(res.text)
    tags = soup.select('img')
    print('开始下载图片...')
    for tag in tags:
        if hasattr(tag,'src'):
            img_url = tag.get('src')
            img_url = check_url(img_url,url)
            img_name = os.path.basename(img_url)
            img_name = replace_filename(img_name)
            img_path = os.path.join(get_path(),img_name)
            if os.path.exists(img_path):
                img_name = str(now()) + img_name
                img_path = os.path.join(get_path(),img_name)
            print('开始解析图片地址:',img_url)
            with requests.get(img_url,stream = True) as img_res:
                with open(img_path, 'wb') as fd:
                    for block in img_res.iter_content(8096):
                        fd.write(block)
            print('下载图片完成:',img_name)
    print('Done')



download_img('https://book.douban.com/subject/10779534/')