爬 meizi 图
本帖最后由 aa1448176630 于 2020-6-8 22:54 编辑import re
import requests as r
import time
import os
def open_url(url):
head={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36 Edg/83.0.478.37'}
p=r.get(url,headers=head)
#print(p.status_code)
return p
def find(p):
html=p.text
r_link='<a href="//(img2.[^"]+)'
link=re.findall(r_link,html)
if not link:
r_link=r'<img src="https://([^"]+)'
link=re.findall(r_link,html)
#print(link)
return link
def save(link):
#print("ceshi")
if not os.path.exists(r'C:\Users\Administrator\Desktop\image'):
#print("ceshi")
os.mkdir(r'C:\Users\Administrator\Desktop\image')
os.chdir(r'C:\Users\Administrator\Desktop\image')
i=0
for each in link:
#print(each)
each='https://'+each
print(each)
p=open_url(each)
html=p.content
path=r'C:\Users\Administrator\Desktop\image'+'\\'+each.split('/')[-1]
with open(path,'wb+') as f:
f.write(html)
i=i+1
print("写入第"+ str(i) + "张图片成功")
#print(html)
if __name__=='__main__':
url='https://www.woyaogexing.com/touxiang/nv/2020/1005194.html'
#url='https://www.qqtn.com/article/article_296117_1.html'#链接自行更换 这两个链接仅用于测试
p=open_url(url)
link=find(p)
save(link)
爬虫新手，仅为交作业大佬绕道 小超超
页:
[1]