find("标签", 属性:id class) 
find("p", id="sdq")

find("标签", 属性:id class).find_all("标签")
find("p", id="sdq").find_all("a")

# 导入requests和bs4库
import requests
from bs4 import BeautifulSoup
import time

url = "https://www.umei.cc/bizhitupian/weimeibizhi/"
resp = requests.get(url)
resp.encoding = 'utf-8'  # 处理乱码

# print(resp.text)
# 把源代码交给bs
main_page = BeautifulSoup(resp.text, "html.parser")
alist = main_page.find("div", class_="TypeList").find_all("a")
# print(alist)
for a in alist:
    href = a.get('href')  # 直接通过get就可以拿到属性的值
    # 子页面的源代码
    child_resp = requests.get(href)
    child_resp.encoding = 'utf-8'
    child_text = child_resp.text
    # 从子页面中拿到图片的下载路径
    child = BeautifulSoup(child_text, "html.parser")
    p = child.find("p", align="center")
    img = p.find("img")
    src = img.get("src")
    # 下载图片
    img_resp = requests.get(src)
    # img_resp.content  # 这里拿到的是字节
    img_name = src.split("/")[-1]  # 拿到url中的最后一个 / 以后的内容-1代表最后一个
    with open("img/"+img_name, mode="wb") as f:
        f.write(img_resp.content)  # 图片内容写入文件

    print("正在下载", img_name)
    time.sleep(1) #停1秒


print("下载完了")

from lxml import etree

html = etree.HTML(text)     # text为文本内容
ret_list = html.xpath("xpath语法规则字符串")     # 用xpath来解析

from lxml import etree

html_str = ''' <div><ul>
                <li class="itrm-1"><a href=";link1.html">first item</a></li>
                <li class="itrm-1"><a href=";link2.html">second item</a></li>
                <li class="itrm-inactive"><a href=";link3.html">third item</a></li>
                <li class="itrm-1"><a href=";link1.html">fourth item</a></li>
                <li class="itrm-0"><a href=";link5.html">fifth item</a></li>
                <ul><div> '''         
# 将html源码转换成element对象   etree.HTML()能够自动补全html缺失的标签
html = etree.HTML(html_str)
# 转换成String类型的数据        
handeled_html_str = etree.toString(html).decode()
print(handeled_html_str)