python爬虫---抓取优酷的电影

最近在学习爬虫，用的BeautifulSoup4这个库，设想是把优酷上面的电影的名字及链接爬到，然后存到一个文本文档中。比较简单的需求，第一次写爬虫。贴上代码供参考：

 # coding:utf-8

 import requests
 import os
 from bs4 import BeautifulSoup
 import re
 import time

 '''抓优酷网站的电影：http://www.youku.com/ '''

 url = "http://list.youku.com/category/show/c_96_s_1_d_1_u_1.html"
 h = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0"}

 #存到movie文件夹的文本文件中
 def write_movie():
     currentPath = os.path.dirname(os.path.realpath(__file__))
     #print(currentPath)
     moviePath = currentPath + "\\" + "movie"+"\\" + "youku_movie_address.text"
     #print(moviePath)
     fp = open(moviePath ,encoding="utf-8",mode="a")

     for x in list_a:
         text = x.get_text()
         if text == "":
             try:
                 fp.write(x["title"] + ":    " + x["href"]+"\n")
             except IOError as msg:
                 print(msg)

     fp.write("-------------------------------over-----------------------------" + "\n")
     fp.close()

 #第一页
 res = requests.get(url,headers = h)
 print(res.url)
 soup = BeautifulSoup(res.content,'html.parser')
 list_a = soup.find_all(href = re.compile("==.html"),target="_blank")
 write_movie()

 for num in range(2,1000):

     #获取“下一页”的href属性
     fanye_a = soup.find(charset="-4-1-999" )
     fanye_href = fanye_a["href"]
     print(fanye_href)
     #请求页面
     ee = requests.get("http:" + fanye_href,headers = h)
     time.sleep(3)
     print(ee.url)

     soup = BeautifulSoup(ee.content,'html.parser')
     list_a = soup.find_all(href = re.compile("==.html"),target="_blank")

     #调用写入的方法
     write_movie()
     time.sleep(6)

运行后的txt内的文本内容：