python爬虫—–Python访问http的几种方式「建议收藏」

import urllib.request
import urllib.parse

import urllib.error
import socket

data = bytes(urllib.parse.urlencode({"hello": "world"}),encoding='utf8')
try:
    response = urllib.request.urlopen('http://httpbin.org/post',data=data,timeout=10)
    print(response.status)
    print(response.read().decode('utf-8'))
except urllib.error.URLError as e:
    if isinstance(e.reason, socket.timeout):
        print("TIMEOUT")

import requests

ico = requests.get("https://github.com/favicon.ico")
with open("favicon.ico", "wb") as file:
    file.write(ico.content)

from requests import Session, Request
url = "https://home.cnblogs.com/u/qiutian-guniang/"
s = Session()
req = Request('GET', url=url, headers=header)
pred = s.prepare_request(req)
r = s.send(pred)
print(r.text)
某些网页会禁止抓取数据  我们可以 通过设置User-Agent来设置  使用cookies来保持登录的访问状态例如：以下的cookie内容可以通过在F12控制台获取  复制粘贴 放入headers中

cookies = "_gat=1"

headers = {
    "Cookie": cookies,
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; '
                  'x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/68.0.3440.106 Safari/537.36'
}