草民网单线程爬取好莱坞大片：草民网单线程爬取好莱坞大片

草民网单线程爬取好莱坞大片：草民网单线程爬取好莱坞大片import socketfrom time import sleep最后贴上代码from urllib import requestimport urllib

兵人 https://www.cmdy5.com/play/21669.html?21669-1-1

打开该界面进行分析

然后F12

发现很多ts文件，我们要得就是他

最后贴上代码

from urllib import request

import urllib

from time import sleep

import socket

import random

class Video():

def __init__(self):

self.headers = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3704.400 QQBrowser/10.4.3615.400"

self.url = ""

def set_url(self i):

if i < 1000:

self.url = "https://zy.baidu-360-yyy-kubo.com/20180705/mBlJPrWZ/800kb/hls/FF9QaL5935d.ts" % i

else:

self.url = "https://zy.baidu-360-yyy-kubo.com/20180705/mBlJPrWZ/800kb/hls/FF9QaL5935d.ts" % i

# 获取并下载ts文件

def download_ts(self i):

rq = request.Request(self.url)

rq.add_header('User-Agent' self.headers)

response = request.urlopen(rq)

res= response.read()

#保存文件路径

with open('./HW/' str(i) ".ts" "wb") as f:

f.write(res)

response.close() # 关闭urlopen方法

def start(self):

for i in range(0 2001):

self.set_url(i)

try:

self.download_ts(i)

print('第' str(i) ".ts" '已下载')

sleep(1)

except urllib.error.URLError as e:

print(e.reason)

break

except socket.timeout as e2:

print(e2.reason)

self.download_ts(i)

if __name__ == '__main__':

Video = Video()

#设置随机请求超时时间

socket.setdefaulttimeout(random.randint(5 10))

video.start()