Python实现--【简易】视频爬虫

  1 #!/usr/bin/env python
  2 # -*- coding: utf-8 -*-
  3 #coding:utf-8
  4 # @Date    : 2016-12-28 11:18:40
  5 # @Author  : Donoy (172829352@qq.com)
  6 # @Link    : http://www.cnblogs.com/Donoy/
  7 # @Version : $Id$
  8 
  9 #多线程 爬虫 
 10 #GUI 界面
 11 
 12 import os
 13 import requests
 14 import re
 15 import threading
 16 from   Tkinter import *
 17 from   ScrolledText import ScrolledText #文本滚动框
 18 import urllib #这个模块中有下载的功能
 19 import sys
 20 #sys 模块的输出编码 格式
 21 reload(sys)
 22 sys.setdefaultencoding(‘utf-8‘)
 23 Video_Data = []
 24 
 25  
 26 def creatWnd():
 27     global root 
 28     global varl 
 29     global text
 30 
 31     #创建一个窗口
 32     root = Tk() # 窗口
 33 
 34     #窗口的标题
 35     root.title(‘DSpider‘)
 36     #文本滚动窗口
 37     text = ScrolledText(root,font=(‘微软雅黑‘))
 38     text.grid()
 39 
 40     #设置Lable
 41     varl = StringVar()
 42     lable = Label(root,font=(‘微软雅黑‘),fg=‘red‘,textvariable=varl)
 43     lable.grid()
 44     varl.set(‘Fight......‘)
 45 
 46     #设置按钮
 47     button = Button(root,text=‘开始爬取‘,font=‘黑体‘,command=begin_Thread)
 48     button.grid()
 49 
 50     #root.mainloop()     # 显示窗口
 51 
 52 def getHtmlData(url):
 53     #print html.text               # 网站的内容
 54     #print html.status_code        # 请求的返回值
 55     RequestHeader = { 
 56            ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36‘
 57     }
 58     html  =  requests.get(url,headers=RequestHeader)
 59     #print html.text
 60     return html.text
 61 
 62 
 63 def getVideoUrl(html):
 64     #re.S 是匹配换行符 
 65     Parse   = re.compile(r‘(<div class="j-r-list-c">.*?</div>.*?</div>)‘,re.S)
 66     context = re.findall(Parse,html)
 67     Parse   = re.compile(r‘data-mp4="(.*?)"‘)
 68     for item in context:
 69         VideoUrl  = re.findall(Parse,item)
 70         if VideoUrl:
 71             Name_Parse = re.compile(r‘(<a href="/detail-.{8}.html">(.*?)</a>)‘,re.S);
 72             VideoName  = re.findall(Name_Parse,item) 
 73             for Name,url in zip(VideoName,VideoUrl): #zip这个内置函数就是将List重新整合一下
 74                 Video_Data.append([Name,url])
 75                 
 76 
 77 def begin_Thread():
 78     try:
 79         for i in range(10,12):
 80             url = ‘http://www.budejie.com/%d‘%i
 81             html = getHtmlData(url)
 82             getVideoUrl(html)    
 83     except Exception as e:
 84         raise
 85     varl.set(‘一共%s个小视频，现在开始下载......‘%(len(Video_Data)/2))
 86     thread = threading.Thread(target= myThread)
 87     thread.start()
 88 
 89 
 90 def myThread():
 91     id = 1
 92     for Data in Video_Data:
 93         text.insert(END,str(id)+‘.‘+Data[0][1]+Data[1]+‘\n‘)
 94         urllib.urlretrieve(Data[1],‘%s.mp4‘%Data[0][1].decode(‘utf-8‘).encode(‘gbk‘))
 95         Video_Data.pop(0)
 96         id += 1
 97     varl.set(‘所有的视频都下载完成‘)    
 98         
 99 
100 
101 def main():
102     creatWnd()
103     root.mainloop()
104 
105 
106 if __name__ == ‘__main__‘:
107     main()
108     
109 
110