《python网络爬虫从入门到实践》读书笔记 chp2 第一个简单的爬虫

环境：win10
ide：pycharm

1.获取页面

import requests as requests

link = "http://www.santostang.com"
r = requests.get(link)
print(r)
print(r.text)

2.提取需要的数据

import requests as requests
from bs4 import BeautifulSoup

link = "http://www.santostang.com"
r = requests.get(link)
soup = BeautifulSoup(r.text, "html.parser")
title=soup.find("h1",class_="post-title").a.text.strip() #取决于前端知识了
print(title)

3.存储数据

import requests as requests
from bs4 import BeautifulSoup

link = "http://www.santostang.com"
r = requests.get(link)
soup = BeautifulSoup(r.text, "html.parser")
title=soup.find("h1",class_="post-title").a.text.strip() #取决于前端知识了
print(title)
with open("crawlertest.txt","a+") as f:
    f.write(title)