爬取豆瓣电影网页的电影的电影名称连接和作者
import requests
from bs4 import BeautifulSoup
# 1、获取网页的html源代码
url = 'https://movie.douban.com/top250?start'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.7 Safari/537.36'
}
response = requests.get(url, headers=headers) # 发送请求
html = response.text # 获取html源代码
soup = BeautifulSoup(html, 'html.parser')
movie_list = soup.find_all('ol', class_="grid_view")
for i in movie_list[0].find_all('li'):
#电影名称
movies = i.find('span', class_='title').text
#电影导演
actors = i.find('p', class_='').text
#电影链接
link = i.find('a')['href']
print('电影名称:' + movies + '\n 链接:' + link + ' \n作者:' + actors)