import requests

from bs4 import BeautifulSoup
url_a='https://movie.douban.com/top250'
def download_page(url):
    data=requests.get(url).content
    return data



def parse_html(html):
    soup=BeautifulSoup(html)
    movie_name_list=[]
    movie_list_soup=soup.find('ol',attrs={'class':"grid_view"})
    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()).encode("utf8")
        movie_name_list.append(movie_name)
        print(movie_name)
    next_page=soup.find('span',attrs={'class':'next'}).find('a')
    if next_page:
        print('ok'+'   '+url_a+next_page['href'])
        return movie_name_list,url_a+next_page['href']
    return movie_name_list,None




def main():
    url_t=url_a
    while(url_t):
        html = (download_page(url_t))
        movies,url_t=parse_html(html)
        print(movies)
    #print(parse_html(html))
if __name__=='__main__':
    main()