'''@author :Eric-chen@contact:809512722@qq.com@time   :2018/1/3 17:55@desc   :通过爬取http://movie.douban.com/top250/得到豆瓣Top 250的电影，并输出到文件movies.txt'''import codecsimport requestsfrom bs4 import BeautifulSoupDOWNLOAD_URL = 'http://movie.douban.com/top250/'def download_page(url):    return requests.get(url).contentdef parse_html(html):    soup = BeautifulSoup(html,"lxml")    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.txt', '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()