多线程小视频下载

原文作者为:

Donoy 

环境：

python2.7

scrollText

tkinter

1.代码分析：

thread = threading.Thread(target=myThread)
thread.start()

创建一个线程，通过start方法启动

#!/usr/bin/env python
# -*- coding: utf--*-
# coding:utf-8
# @Date    : 6--:8:
# @Author  : Donoy (83@qq.com)
# @Link    : http://www.cnblogs.com/Donoy/
# @Version : $Id$

# 多线程 爬虫
# GUI 界面
import os
import requests
import re
import threading
from   Tkinter import *
from   ScrolledText import ScrolledText  # 文本滚动框
import urllib  # 这个模块中有下载的功能
import sys

# sys 模块的输出编码 格式
reload(sys)
sys.setdefaultencoding('utf-8')
Video_Data = []


def creatWnd():
    global root
    global varl
    global text

    # 创建一个窗口
    root = Tk()  # 窗口

    # 窗口的标题
    root.title('DSpider')
    # 文本滚动窗口
    text = ScrolledText(root, font=('微软雅黑'))
    text.grid()

    # 设置Lable
    varl = StringVar()
    lable = Label(root, font=('微软雅黑'), fg='red', textvariable=varl)
    lable.grid()
    varl.set('Fight......')

    # 设置按钮
    button = Button(root, text='开始爬取', font='黑体', command=begin_Thread)
    button.grid()

    # root.mainloop()     # 显示窗口


def getHtmlData(url):
    # print html.text               # 网站的内容
    # print html.status_code        # 请求的返回值
    RequestHeader = {
        'User-Agent': 'Mozilla/. (Windows NT.3; WOW6) AppleWebKit/3.36 (KHTML, like Gecko) Chrome/..883. Safari/3.36'
    }
    html = requests.get(url, headers=RequestHeader)
    # print html.text
    return html.text


def getVideoUrl(html):
    # re.S 是匹配换行符
    Parse = re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)', re.S)
    context = re.findall(Parse, html)
    Parse = re.compile(r'data-mp4="(.*?)"')
    for item in context:
        VideoUrl = re.findall(Parse, item)
        if VideoUrl:
            Name_Parse = re.compile(r'(<a href="/detail-.{8}.html">(.*?)</a>)', re.S);
            VideoName = re.findall(Name_Parse, item)
            for Name, url in zip(VideoName, VideoUrl):  # zip这个内置函数就是将List重新整合一下
                Video_Data.append([Name, url])
                # Video_Data.append(['123','http://clips.vorwaerts-gmbh.de/big_buck_bunny.mp4'])
                # Video_Data.append(['123','http://mvideo.spriteapp.cn/video/2017/1212/5a2febb81b7cb_wpcco.mp4'])


def begin_Thread():
    try:
        # for i in range(10,12):
        url = 'http://www.budejie.com/video/'
        # url = 'http://clips.vorwaerts-gmbh.de/big_buck_bunny.mp4'
        html = getHtmlData(url)
        getVideoUrl(html)
    except Exception as e:
        raise
    varl.set('一共%s个小视频，现在开始下载......' % (len(Video_Data) / 2))
    thread = threading.Thread(target=myThread)
    thread.start()


def myThread():
    id = 1
    for Data in Video_Data:
        text.insert(END, str(id) + '.' + Data[0][1] + Data[1] + '\n')
        urllib.urlretrieve(Data[1], 'F:\save\\vedio\\' + str(id) + '.mp4')
        Video_Data.pop()
        id += 1
    varl.set('所有的视频都下载完成')