今天尝试准备写个爬虫,在网上找了些图片网站,发现这个网站页面规则简单,就决定用他做处女作吧。该网站图片命名规则就是xxx1.jgp-xxx100.jpg:
import requests
import time
import os
from bs4 import BeautifulSoup
tp = 'E:\\tp'
if not os.path.exists(tp):
os.mkdir(tp)
headers = {'User-Agent':' Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}
for h in range(1,100):
if h <10:
h = str('00') + str(h)
else:
h = str('0') + str(h)
resp = requests.get('http://img.ivsky.com/img/bizhi/pre/201910/08/zhaoze-'+str(h)+'.jpg',headers)
if resp.status_code != 200:
break
#状态码非200时结束循环
time_file = int(time.time())
#加入时间戳
with open('E:\\tp\\'+str(h)+'_'+str(time_file)+'.jpg','wb') as f:
f.write(resp.content)
time.sleep(3)
print('下载完毕,第 %d 张图片' % int(h))
)