用python爬取电脑壁纸实例代码

import time
import pinyin
import requests
from lxml import etree    #这是导入xpath模块

type=input("请输入图片的类型：")
type=pinyin.get(f"{type}",format="strip")   #这是将输入的中文转成拼音，format是为了去掉拼音的声标
m=input("请输入图片的页码：")        #图片类型所在网页的页码

url=f"https://pic.netbian.com/4k{type}/index_{m}.html"
header={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36"
}
resp=requests.get(url=url,headers=header)
resp.encoding="gbk"
tree=etree.HTML(resp.text)
tu_links=tree.xpath('//*[@id="main"]/div[3]/ul/li/a/@href')    #小图片的链接
tu_names=tree.xpath('//*[@id="main"]/div[3]/ul/li/a/b/text()')  #图片的名字

    tu_link.split()
    child_url = url.split(f'/4k{type}/')[0] + tu_link       #将小图片的部分链接和主链接拼接起来
    resp1 = requests.get(url=child_url, headers=header)     #打开小图片的网址
    resp1.encoding = 'gbk'
    tree1 = etree.HTML(resp1.text)
    child_tu_link= tree1.xpath('/html/body/div[2]/div[1]/div[2]/div[1]/div[2]/a/img/@src')     #获取大图片的部分链接
    child_tu_link=child_tu_link[0]
    child_tu_link_over=url.split(f'/4k{type}/')[0]+child_tu_link        #将大图片链接拼接起来
    resp2=requests.get(child_tu_link_over,headers=header)       #获取大图片

    with open(f"壁纸图片/{name}.jpg",mode="wb") as f:           #接下来就是下载了
        f.write(resp2.content)

import time
import pinyin
import requests
from lxml import etree    #这是导入xpath模块
type=input("请输入图片的类型：")
type=pinyin.get(f"{type}",format="strip")   #这是将输入的中文转成拼音，format是为了去掉拼音的声标
m=input("请输入图片的页码：")        #图片类型所在网页的页码
url=f"https://pic.netbian.com/4k{type}/index_{m}.html"
header={
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36"
}
resp=requests.get(url=url,headers=header)
resp.encoding="gbk"
tree=etree.HTML(resp.text)
tu_links=tree.xpath('//*[@id="main"]/div[3]/ul/li/a/@href')    #小图片的部分链接
tu_names=tree.xpath('//*[@id="main"]/div[3]/ul/li/a/b/text()')  #图片的名字
n=0
for tu_link in tu_links:
    tu_link.split()
    child_url = url.split(f'/4k{type}/')[0] + tu_link       #将小图片的部分链接和主链接拼接起来
    resp1 = requests.get(url=child_url, headers=header)     #打开小图片的网址
    resp1.encoding = 'gbk'
    tree1 = etree.HTML(resp1.text)
    child_tu_link= tree1.xpath('/html/body/div[2]/div[1]/div[2]/div[1]/div[2]/a/img/@src')     #获取大图片的部分链接
    child_tu_link=child_tu_link[0]
    child_tu_link_over=url.split(f'/4k{type}/')[0]+child_tu_link        #将大图片链接拼接起来
    resp2=requests.get(child_tu_link_over,headers=header)       #获取大图片
    name=tu_names[n]
    with open(f"壁纸图片/{name}.jpg",mode="wb") as f:           #接下来就是下载了
        f.write(resp2.content)
        print(f"{name}          下载完毕！！")
        n+=1        #每下载一张图片n就加1
        time.sleep(1.5)
        resp1.close()
print("全部下载完毕！！")       #over！over！
resp.close()        #最后记得要把所有请求的响应关闭