版权声明:原创 https://blog.csdn.net/hangvane123/article/details/82937044
使用requests库可以非常简单地爬https协议下的网站:
import requests
url='https://www.baidu.com/'
r = requests.get(url,verify=False)
r.encoding = 'utf-8'
print(r.text)
而当爬取TLSv1或TLSv1.1网站时,这样的代码就会报错
于是我们需要使用HTTPAdapter定制requests参数:
#-*- coding:utf-8 -*-
import re
import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.poolmanager import PoolManager
import ssl
import os
class MyAdapter(HTTPAdapter):
def init_poolmanager(self, connections, maxsize, block=False):
self.poolmanager = PoolManager(num_pools=connections,
maxsize=maxsize,
block=block,
ssl_version=ssl.PROTOCOL_TLSv1)#这里定义了ssl协议版本
s = requests.Session()
s.mount('https://', MyAdapter())
def downloadImage(netPath,localPath,imageName):#netPath=网络全路径,localPath=本地文件夹路径,imageName=图片文件名
#检测当前路径的有效性
if not os.path.isdir(localPath):
os.makedirs(localPath)
ok=0
while(ok==0):
try:
r=s.get(netPath,timeout=10)
ok=1
except:
print("连接超时")
if(r.status_code==200):
fp = open(localPath+'\\'+imageName, 'wb')
fp.write(r.content)
fp.close()
return 1
else:
return 0
这样就可以通过定制HTTPAdapter实现爬取TLSv1或TLSv1.1的网站。