import re
          

          from urllib.request import urlopen
          

          

          def getPage(url):
          

              response = urlopen(url)
          

              return response.read().decode('utf-8')
          

          

          def parsePage(s):
          

              ret = re.findall(
          

                  '
          

            .*?
            

              .*?
              
                (?P
                
                  \d+).*?
                  
                    (?P
                  
                  '
                  

                         '.*?
                  
                    (?P
                    
                      .*?)
                    
                  
                  .*?
                  
                    (?P
                    
                      .*?)評價
                    
                  
                  ',s,re.S)
                  

                      return ret
                  

                  

                  def main(num):
                  

                      url = 'https://movie.douban.com/top250?start=%s&filter=' % num
                  

                      response_html = getPage(url)
                  

                      ret = parsePage(response_html)
                  

                      print(ret)
                  

                  

                  count = 0
                  

                  for i in range(10):   # 10頁
                  

                      main(count)
                  

                      count += 25
                  

                  

                  # url從網(wǎng)頁上把代碼搞下來
                  

                  # bytes decode ——> utf-8 網(wǎng)頁內(nèi)容就是我的待匹配字符串
                  

                  # ret = re.findall(正則，帶匹配的字符串)  #ret是所有匹配到的內(nèi)容組成的列表