Python 文档解析lxml库的使用详解【python爬虫】

目录

• 1.lxml库简介
• 2.lxml库方法介绍
• 3.代码实例

pip install lxml

from lxml import etree

from lxml import etree
parse_html = etree.HTML(html)

from lxml import etree
html_str = """

    

        
Python
        
Java
        
CSDN
    

"""

html = etree.HTML(html_str)
# tostring()将标签元素转换为字符串输出，注意：result为字节类型
result = etree.tostring(html)
print(result.decode("utf-8"))

    

        
Python
        
Java
        
CSDN
    

from lxml import etree

html_str = """

    

        
Python
        
Java
        
CSDN
    

"""

html=etree.HTML(html_str)

xpath_bds="//@href"

r_list = html.xpath(xpath_bds)

print(r_list)

import os
import sys
import requests
from lxml import etree

x = requests.get("https://www.csdn.net/")


html = etree.HTML(x.text)

xpath_bds = "//img/@src"

img_list = html.xpath(xpath_bds)

# 创建img文件夹
os.chdir(os.path.dirname(sys.argv[0]))

if not os.path.exists("img"):
    os.mkdir("img")
    print("创建文件夹成功")
else:
    print("文件夹已存在")

# 下载图片
for i in range(len(img_list)):
    img = requests.get(img_list[i]).content
    if img_list[i].endswith(".jpg"):
        with open(f"./img/{i}.jpg", "wb") as f:
            f.write(img)
    elif img_list[i].endswith(".jpeg"):
        with open(f"./img/{i}.jpeg", "wb") as f:
            f.write(img)
    elif img_list[i].endswith(".png"):
        with open(f"./img/{i}.png", "wb") as f:
            f.write(img)
    else:
        print(f"第{i + 1}张图片格式不正确")
        continue
    print(f"第{i + 1}张图片下载成功")