【无标题】

叹！

已于 2022-05-18 16:54:30 修改

阅读量85

点赞数

分类专栏：爬虫文章标签： python

于 2022-05-17 14:09:18 首次发布

本文链接：https://blog.csdn.net/qq_44721518/article/details/124807868

版权

爬虫专栏收录该内容

4 篇文章 0 订阅

订阅专栏

第一个简单爬虫代码

import requests
from bs4 import BeautifulSoup

link = "http://www.santostang.com/"
headers = {'User-Agent':"Mozilla/5.0(Windows;U;Windows NT6.1;en-US;rv:1.9.1.6)Gecko/20091201 Firefox/3.5.6"}
r = requests.get(link,headers = headers)

soup = BeautifulSoup(r.text,'lxml')
title = soup.find("h1",class_="post-title").a.text.strip()#strip()函数去除首尾空格
print(title)

with open("title.txt","a+")as f:
    f.write(title)
    f.close()

截图：路径（C:\Users\asus\title.txt）
在这里插入图片描述

import requests
headers = {
    'Host': 'www.santostang.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}

r = requests.get("http://www.santostang.com/",headers = headers)*第一参数是url 第二个参数是请求头
print("响应状态码：",r.status_code)

在这里插入图片描述

import requests
from bs4 import BeautifulSoup

def get_movies():
    headers={
       'Host': 'movie.douban.com',
       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
    }
    movie = []
    for i in range(0,10):
        link = "https://movie.douban.com/top250?start=" + str(i*25) + "&filter="
        r = requests.get(link,headers = headers,timeout=10)
        print(str(i+1),"页响应状态码：",r.status_code)
       
        soup = BeautifulSoup(r.text,"lxml")
        list1 = soup.find_all('div',class_="hd")*注意class_不是class
        for each in list1:
            temp = each.a.span.text.strip()
            movie.append(temp)
    return movie
        
        
movies = get_movies()
print(movies)
``![
![\](https://img-blog.csdnimg.cn/a5ae7a0112ba4b1eb5d51d4bdce6092c.png)

```python
import requests
from bs4 import BeautifulSoup

headers = {
   'Host': 'movie.douban.com',
   'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
date = []
list = {}
link = 'https://movie.douban.com/top250'
r = requests.get(link,headers = headers)
soup = BeautifulSoup(r.text,"lxml")
for i in range(0,25):
    
    title = soup.find_all('div',class_="item")[i]
    t = title.find_all("span")
    for j in range(0,len(t)):
        
        date.append(t[j].text)
#         print(date)
#         print(t[j].text,end="    ")
    list[i]=date
    date = []
print(list)
```获取电影信息
![在这里插入图片描述](https://img-blog.csdnimg.cn/ed3cf8f9240145f091bd9dfdbe90e598.png)