第一个爬虫：爬取豆瓣Top250电影名字

import requests
from bs4 import BeautifulSoup


def get_movies():
    headers = {
        'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Mobile Safari/537.36',
        'Host': 'movie.douban.com'

        }
    movie_list = []
    for i in range(0, 10):
        link = 'https://movie.douban.com/top250?start='+str(i * 25)+"&filter="
        print(link)
        r = requests.get(link, headers=headers, timeout=100)
        print(str(i + 1), "页响应码", r.status_code)
        soup = BeautifulSoup(r.text, "lxml")
        div_list = soup.find_all('div', class_='hd')
        for each in div_list:
            movie = each.a.span.text.strip()
            print(movie)
            movie_list.append(movie)
    return movie_list


movies = get_movies()
print(movies)