爬取豆瓣电影排行榜top250

爬取豆瓣电影top250

平时不知道看什么电影，正好最近学习了爬虫，自己试着把电影排行下载下来，边看边学两不误。
下面直接上代码：

import requests
from bs4 import BeautifulSoup


# 爬取网页源码
def download_page(url):
    headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'
    }
    req = requests.get(url=url, headers=headers)
    return req.content

# 爬取单页电影名返回列表
def get_page_list(html):
    soup = BeautifulSoup(html, 'lxml')
    # find方法返回的是第一个符合条件的元素
    movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'})

    movie_name_list = []
    # find_all 返回所有符合条件的元素
    for movie_li in movie_list_soup.find_all('li'):
        movie_name = movie_li.find('span', attrs={'class': 'title'}).getText()
        movie_num = movie_li.find('em').getText()
        movie_score = movie_li.find('span', attrs={'class': 'rating_num'}).getText()
        movie_name_list.append('%s.%s score: %s分' % (movie_num, movie_name, movie_score))
    return movie_name_list
    
# 保存文件
def write_file(url):
    with open('douban_top_movies.txt', 'a', encoding='utf-8') as f:
        html = download_page(url)
        movies = get_page_list(html)
        for movie in movies:
            f.write(str(movie) + '\n')

def main():
    # 通过分析发现每一页地址的'start='后的数字不同，每页递增25正是每一页所含有的电影数，通过遍历即可爬取每一页
    for n in range(0, 250, 25):
        page_url = 'http://movie.douban.com/top250?start=%d&filter=' % n
        write_file(page_url)


if __name__ == '__main__':
    main()

效果如图：