使用python抓取豆瓣电影信息

来源：互联网发布：caffe loss值不变编辑：程序博客网时间：2024/04/29 18:44

#!/usr/bin/env python2.7# encoding=utf-8"""爬取豆瓣电影TOP250 - 完整示例代码"""import codecsimport requestsfrom bs4 import BeautifulSoupDOWNLOAD_URL = 'http://movie.douban.com/top250/'def download_page(url):    return requests.get(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'    }).contentdef parse_html(html):    soup = BeautifulSoup(html)    movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'})    movie_name_list = []    for movie_li in movie_list_soup.find_all('li'):        detail = movie_li.find('div', attrs={'class': 'hd'})        movie_name = detail.find('span', attrs={'class': 'title'}).getText()        movie_name_list.append(movie_name)    next_page = soup.find('span', attrs={'class': 'next'}).find('a')    if next_page:        return movie_name_list, DOWNLOAD_URL + next_page['href']    return movie_name_list, Nonedef main():    url = DOWNLOAD_URL    with codecs.open('movies', 'wb', encoding='utf-8') as fp:        while url:            html = download_page(url)            movies, url = parse_html(html)            fp.write(u'{movies}\n'.format(movies='\n'.join(movies)))if __name__ == '__main__':    main()

简单说明下，在目录下会生成一个文档存放电影名。python2

0 0