python爬虫下载网页图片简例

默然

[Python] 纯文本查看 复制代码

import requests
import urllib3
import re
from bs4 import BeautifulSoup as bsp
img_list=[] #存储所有的图片的超链接
file_list=[]
url=r'https://www.mlito.com/photo/girl/g_model/121112.html'
headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0"}
xiangying=requests.get(url=url, headers=headers)
soup=bsp(xiangying.content.decode('utf-8'), 'lxml')
imgs=soup.find_all('img')
 
def xiazai(img):
    print("开始下载图片: %s"% img.split(r'/')[-1])
    try:
        pic=requests.get(img, timeout =100)
    except requests.exceptions.InvalidURL:
        print("无法下载")
    fp=open(img.split(r'/')[-1], 'wb')
    fp.write(pic.content)
    fp.close()
    print("下载成功")
     
for i in imgs:
    i=str(i)
    if "alignnone" in i:
        kaishi= i.find("src")+5 #  src=" 一共5个字符
        jieshu= i.find("jpg")+3 #  jpg  一共3个字符
        img= i[kaishi:jieshu]
        xiazai(img.replace('///', '//'))

qazmlp

谢谢大牛

Jonathan

多谢楼主分享

18920733351

6666

xuehuang58

谢谢@Thanks！

136930216@qq.co

先收藏了，万一用到呢

mlj2003318

谢谢大佬分享