python批量发送请求并下载,python 多线程 批量请求 下载视频

import requests

import os

import re

import threading

root = "E://movie//" # 根目录

kv = {'user-agent':'Mozilla/5.0'} # 模拟浏览器请求头

def download(url): # 封装下载器

try:

path = root + url.split('/')[-1] # 文件保存路径

if not os.path.exists(root):

os.mkdir(root)

if not os.path.exists(path):

r = requests.get(url, headers = kv) # requests库的请求信息

r.raise_for_status() # 爬虫时候的异常处理

with open(path, 'wb') as f:

f.write(r.content) # 以二进制形式写

f.close()

else:

print("File already exists")

except:

print("\nVideo crawl failed")

def job1(data1,url):

global url1 # 声明全局变量

for i in range(0,data1):

if i>=1000:

p = re.compile(r'.$') # 正则表达式 最后一位

url1 = re.sub(p, '', url) # 正则表达式删除操作

url = url1 + '%03d' % i + '.ts' # 构造新的url

print('\rdownloaded percent%f' % (((i+1)/data1)*100), end='') # \r属性使指针不指向下一行，指向这一行的行首 end=''使print语句中末尾不添加换行符，直接加一个空字符

download(url) # 下载器 url下载视频资源

def job2(data2,url):

global num1,url1

for i in range(num1,data2):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

def job3(data3,url):

global num2,url1

for i in range(num2,data3):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

def job4(data4,url):

global num3,url1

for i in range(num3,data4):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

def job5(data5,url):

global num4,url1

for i in range(num4,data5):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

def job6(data6,url):

global num5,url1

for i in range(num5,data6):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

def job7(data7,url):

global num6,url1

for i in range(num6,data7):

if i>=1000:

p = re.compile(r'.$')

url1 = re.sub(p, '', url)

url = url1 + '%03d' % i + '.ts'

download(url)

if __name__=='__main__':

url = input('Please enter the url： ')

p = re.compile(r'......$')

url1 = re.sub(p,'',url)

num = int(input('Please enter the number of video: '))

num1 = int(num/7)

num2 = num1*2

num3 = num1*3

num4 = num1*4

num5 = num1*5

num6 = num1*6

num7 = num1*7

t1 = threading.Thread(target=job1,args=(num1,url1)) # 定义线程，并且通过args传参， 需要传一个参数时，可以这样写 num1,

t2 = threading.Thread(target=job2,args=(num2,url1))

t3 = threading.Thread(target=job3,args=(num3,url1))

t4 = threading.Thread(target=job4,args=(num4,url1))

t5 = threading.Thread(target=job5,args=(num5,url1))

t6 = threading.Thread(target=job6,args=(num6,url1))

t7 = threading.Thread(target=job7,args=(num7,url1))

t1.start() # 线程开始

t2.start()

t3.start()

t4.start()

t5.start()

t6.start()

t7.start()

t1.join() # 线程结束以后才开始执行下面的语句

t2.join()

t3.join()

t4.join()

t5.join()

t6.join()

t7.join()

print('\nThe download is complete')

print('press any key to exit')

可以通过解析真实视频地址，来下载ts流文件。 在这里，将代码封装成了一个简单的exe。

以下是百度网盘链接：

链接：https://pan.baidu.com/s/1NcwksIpKuVcrKjOEWAKhSQ

提取码：4vu3