4k图片爬取+中文乱码

4k图片爬取+中文乱码

此案例有三种乱码解决方法，推荐第一种

4k图片爬取其实和普通图片爬取的过程是没有本质区别的

import requests
import os
from lxml import etree

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
}

def work():
    if not os.path.exists("img"):
        os.mkdir("img")
    url="http://pic.netbian.com/4kqiche/"
    res=requests.get(url=url,headers=headers)
    #最推荐方法
    res.encoding=res.apparent_encoding
    #res.encoding="utf8"
    tree=etree.HTML(res.text)
    imgs=tree.xpath("//ul[@class='clearfix']//a")
    for i in imgs:
        img_u=i.xpath("./img/@src")[0]
        img_url="http://pic.netbian.com"+img_u
        img_name=i.xpath("./b/text()")[0]
        # .encode("ISO-8859-1").decode("utf8")
        img_content=requests.get(url=img_url,headers=headers).content
        with open(f"img/{img_name}.jpg","wb")as fw:
            fw.write(img_content)
            print(img_name+"下载成功")
if __name__ == '__main__':
    work()