python爬取百思不得姐視頻

# _*_ coding:utf-8 _*_
from Tkinter import *
from ScrolledText import ScrolledText
import urllib
#import requests
import urllib2
#import pygame
import re
import threading
import time

url_name=[]#放置地址 名稱
a=1#表明頁數
def get():
    global a#改變全局變量
    hd={'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
    url='http://www.budejie.com/video/'+str(a)
    varl.set('已經獲取到第%s的視頻'%a)
    opener=urllib2.build_opener()
    request=urllib2.Request(url,None,hd)
    result=opener.open(request).read()
    url_content=re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)',re.S)#re.S匹配換行符
    url_contents=re.findall(url_content,result)
    # for iterm in url_contents:
    #     print iterm
    url_reg = r'data-mp4="(.*?)">'
    for iterm in url_contents:
        url_items=re.findall(url_reg,iterm)
        #print url_items
        if url_items:#若是有視頻存在，就匹配名字，若是是其餘格式，則跳過
            name_reg=re.compile(r'<a .*?>(.*?)</a>',re.S)
            name_items=re.findall(name_reg,iterm)
            #print name_items
            for name,url in zip(name_items,url_items):
                url_name.append([name,url])
                print name,url
    return url_name
id=1#視頻個數
def write():
    global id
    while id<10:
        url_name=get()#獲取視頻和名字
        for iterm in url_name:
            urllib.urlretrieve(iterm[1],'%s.mp4' % (iterm[0].decode('utf-8').encode('gbk')))#下載
            text.insert(END,str(id)+'.'+iterm[1]+'\n'+iterm[0]+'\n')
            url_name.pop(0)#刪除第一個元素
            id+=1
    varl.set('抓取完成')
def start():
    th=threading.Thread(target=write)
    th.start()#運行線程

root=Tk()
root.title=('視頻下載')
text=ScrolledText(root,font=('微軟雅黑',10))
text.grid()#實現佈局方法
button=Button(root,text='開始爬取',font=('微軟雅黑',10),command=start)
button.grid()
varl=StringVar()#經過tk方法綁定一個變量

label=Label(root,font=('微軟雅黑',10),fg='red',textvariable=varl)
varl.set('熊貓已準備....')
label.grid()
root.mainloop()