下面是代码,刚开始的时候能爬一点图片,过几秒就报错,不知道是怎么回事,求大佬指点!
import requests
import re
for i in range(0,200):
base_url = ("https://www.buxiuse.com/?page={}".format(i))
headers = {
'headers':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36'
}
response = requests.get(base_url,headers=headers)
page_urls = re.findall('<div class=".*?"> <span class=".*?"> <a href="(.*?)" class=".*?">',response.text)
for urls in page_urls:
response = requests.get(urls,headers=headers)
jpg_urls = re.findall('<img src="(.*?)" width=".*?" referrerpolicy=".*?">',response.text)
for jpg in jpg_urls:
jpg_name = jpg.split('/')[-1]
response = requests.get(jpg,headers=headers)
with open('IMG\\' + jpg_name,'wb') as f:
f.write(response.content)
print("下载完成=======>",jpg_name)