豆瓣Top250

 1 """
 2 爬取豆瓣电影top250 - 完整示例代码
 3 """
 4 
 5 import codecs
 6 
 7 import requests
 8 from bs4 import beautifulsoup
 9 
10 download_url = 'http://movie.douban.com/top250/'
11 
12 
13 def download_page(url):
14     return requests.get(url, headers={
15         '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'
16     }).content
17 
18 
19 def parse_html(html):
20     soup = beautifulsoup(html)
21     movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'})
22 
23     movie_name_list = []
24 
25     for movie_li in movie_list_soup.find_all('li'):
26         detail = movie_li.find('div', attrs={'class': 'hd'})
27         movie_name = detail.find('span', attrs={'class': 'title'}).gettext()
28 
29         movie_name_list.append(movie_name)
30 
31     next_page = soup.find('span', attrs={'class': 'next'}).find('a')
32     if next_page:
33         return movie_name_list, download_url + next_page['href']
34     return movie_name_list, none
35 
36 
37 def main():
38     url = download_url
39 
40     with codecs.open('movies', 'wb', encoding='utf-8') as fp:
41         while url:
42             html = download_page(url)
43             movies, url = parse_html(html)
44             fp.write(u'{movies}\n'.format(movies='\n'.join(movies)))
45 
46 
47 if __name__ == '__main__':
48     main()

原文链接：

感谢原po。