# encoding = utf-8

 import codecs

 import requests

 from bs4 import BeautifulSoup

 # 爬取豆瓣电影TOP250

 DOWNLOADURL = 'https://movie.douban.com/top250'

 def download_page(url): # 向服务器发送请求下载得到html

     headers = {'User-Agent': 'Mozilla/4.0(compatibel; MSIE 5.5; Windows NT)'} # 伪装成浏览器

     data = requests.get(url, headers=headers).content

     return data # 返回得到的html代码

 def parse_html(html): # 解析网页

     soup = BeautifulSoup(html, 'lxml') # 创建一个BeautifulSoup对象

     movie_list_soup = soup.find('ol', attrs={'class': 'grid_view'}) # 定位

     name_list = []

     for movie_li in movie_list_soup.find_all('li'): # 找到电影名字

         detail = movie_li.find('div', attrs={'class', 'hd'})

         movie_name = detail.find('span', attrs={'class', 'title'}).getText()

         name_list.append(movie_name) # 放到一个list里面

     have_next = soup.find('span', attrs={'class': 'next'}).find('a') # 找下一页的链接

     if have_next: # 如果有下一页的链接不为空

         return name_list, DOWNLOADURL + have_next['href'] # 返回名字列表还有下一页的URL

     else:

         return name_list, None # 找不到返回None

 def main():

     url = DOWNLOADURL

     # with xxx.open as f 打开xxx之后finally关闭xxx

     # codecs方便处理中文编码

     with codecs.open('douban_movies', 'wb', encoding='utf-8') as fp:

         while url:

             html = download_page(url)

             name_list, url = parse_html(html)

             #'\n'.join(name_list) : 以'\n'为分隔符将name_list所有元素合并成一个新的字符串

             #'{movies}'.format(movies='xxxxx') : 即movies = 'xxxxx',将xxxxx按照格式输出

             fp.write(u'{movies}\n'.format(movies='\n'.join(name_list)))

 if __name__ == '__main__':

     main()