Watercress Top250

1  "" " 
2  crawling IMDb TOP250 - the complete sample code
 . 3  " " ' 
. 4  
. 5  Import the codecs
 . 6  
. 7  Import Requests
 . 8  from BS4 Import the BeautifulSoup
 . 9  
10 DOWNLOAD_URL = ' http://movie.douban.com/top250/ ' 
. 11  
12 is  
13 is  DEF download_page (URL):
 14      return requests.get (URL, headers = {
 15          ' the 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()

Original link:

https://zhuanlan.zhihu.com/p/20423182

Thanks to the original po.