requests是python的一个http请求模块,常用的请求方式有GET和POST
GET是向服务器发送请求,服务器返回请求的响应数据;POST是向服务器提交数据,比如向服务器提交的用户登陆表单,就是POST请求,当然为何不用GET提交登陆请求,这是用户信息隐私的问题。
话不多说,直接上代码
# -*- conding:utf-8 -*-
import requests
import re
from bs4 import BeautifulSoup
headers = {"User-Agent:"
"Mozilla/5.0 (Windows NT 6.3;WOW64; rv:41.0)Gecko/20100101 Firefox/42.1"}
for page in range(10):
print("============正在抓取第"+str(page+1)+"页======")
num = page*25
url = "https://movie.douban.com//top250?start=%s&filter="%num
html = requests.get(url)
soup = BeautifulSoup(html.text,"html.parser")
soup = str(soup)
title = re.compile(r'<span class="title">(.*)?</span>')
names = re.findall(title,soup)
for name in names:
if name.find('/'):
print(name)
print("抓取完毕!")