python百行代码实现汉服圈图片爬取

def get_menu(url, heades):
    """
    根据每一页的网址
    获得每个链接对应的子网址
    params: url 网址
    """
    r = requests.get(url, headers=headers)
    if r.status_code == 200:
        r.encoding = r.apparent_encoding
        html = etree.HTML(r.text)
        html = etree.tostring(html)
        html = etree.fromstring(html)
        # 查找每个子网址对应的链接, 然后返回
        children_url = html.xpath('//div[@class="news_list"]//article/figure/a/@href')
        for _ in children_url:
            yield _

def get_page(url, headers):
    """
    根据子页链接，获得图片地址，然后打包下载
    params: url 子网址
    """
    r = requests.get(url, headers=headers)
    if r.status_code == 200:
        r.encoding = r.apparent_encoding
        html = etree.HTML(r.text)
        html = etree.tostring(html)
        html = etree.fromstring(html)
        # 获得标题
        title = html.xpath(r'/汉服/'
    if not os.path.exists(path):
        os.mkdir(path)
        os.chdir(path)
    else:
        os.chdir(path)
    # url = 'Http://www.aihanfu.com/zixun/tushang-1/'
    headers = {'User-Agent': 'Mozilla/5.0 (windows NT 10.0; Win64; x64)'
                             ' AppleWEBKit/537.36 (KHTML, like Gecko)'
                             ' Chrome/81.0.4044.129 Safari/537.36'}
    for _ in range(1, 50):
        url = 'http://www.aihanfu.com/zixun/tushang-{}/'.fORMat(_)
        for _ in get_menu(url, headers):
            get_page(_, headers)  # 获得一页