import re
import os.path
import requests
import hashlib
import time
respose=requests.get('http://www.xiaohuar.com/hua/')
print(respose.status_code)# 响应的状态码
# print(respose.content) #返回字节信息
# print(respose.text) #返回文本内容
urls=re.findall(r'class="item masonry_brick".*?src="(.*?)"',respose.text,re.S) #re.S 把文本信息转换成1行匹配
print(urls)
for url in urls:
if not url.startswith('http'):
url='http://www.xiaohuar.com%s' %url
img = requests.get(url)
if img.status_code==200:
m=hashlib.md5()
m.update(url.encode('utf-8'))
m.update(str(time.time()).encode('utf-8'))
# 后缀名
ext = os.path.splitext(url)[1]
filename=r"%s%s"% (m.hexdigest(),ext)
filepath=r'F:\\xiaocao/%s'%filename
print(filepath)
with open(filepath, 'wb') as f:
f.write(img.content)
python爬取校花网的图片
猜你喜欢
转载自blog.csdn.net/jerryyang_2017/article/details/82259560
今日推荐
周排行