Python爬虫爬取ts碎片视频+验证码登录功能

import requests
from PIL import Image
 
#用户名-密码-验证码方式，登录
CaptchaUrl = "https://per.enetedu.com/Common/CreateImage" #获取验证码地址
PostUrl = "https://per.enetedu.com/AdminIndex/LoginDo"  #post登录信息地址
 
client = requests.Session()
username = '替换为自己的用户名'
password = '替换为自己的密码'
 
qr_code = client.get(CaptchaUrl)
open('login.jpg', 'wb').write(qr_code.content) #将验证码图片保存至本地
img = Image.open('login.jpg')
img.show()  #打开图片
 
code = input("请输入验证码: \n") #输入验证码
postData = {      #构造POST表单
 'email': username,
 'pwd': password,
 'validateCode': code,
 'x': '22',
 'y': '19'
}
result = client.post(PostUrl,postData) #向PostUrl提交表单

#EXTM3U
#EXT-X-VERSION:3
#EXT-X-ALLOW-CACHE:YES
#EXT-X-TARGETDURATION:10
#EXTINF:10.000000,
start_0-end_765064-record.gv.ts
#EXTINF:10.000000,
start_765064-end_1769567-record.gv.ts
#EXTINF:10.000000,
start_1769567-end_2600798-record.gv.ts
#EXTINF:10.000000,
start_2600798-end_3593502-record.gv.ts
#EXTINF:10.000000,
start_3593502-end_4500784-record.gv.ts
#EXTINF:10.000000,
start_4500784-end_5399861-record.gv.ts
#EXTINF:10.000000,
start_5399861-end_6288622-record.gv.ts
#EXTINF:10.000000,
start_6288622-end_7044459-record.gv.ts
#EXTINF:10.000000,
start_7044459-end_7878487-record.gv.ts
#EXTINF:10.000000,
start_7878487-end_8811793-record.gv.ts
#EXTINF:10.000000,

url = input("请输入m3u8文件地址：")
urlRoot=self.url[0:url.rindex('/')]

client = requests.Session() 
client.post(PostUrl,postData) #登录
 
resp = client.get(download_path) #下载

import requests
from PIL import Image
 
import sys
import m3u8
import time
import os
 
#用户名-密码-验证码方式，登录
CaptchaUrl = "https://per.enetedu.com/Common/CreateImage" #获取验证码地址
PostUrl = "https://per.enetedu.com/AdminIndex/LoginDo"  #post登录信息地址
 
client = requests.Session()
username = '526257482@qq.com'
password = 'dashuju_9514'
 
qr_code = client.get(CaptchaUrl)
open('login.jpg', 'wb').write(qr_code.content) #将验证码图片保存至本地
img = Image.open('login.jpg')
img.show()  #打开图片
 
code = input("请输入验证码: \n") #输入验证码
postData = { #构造POST表单
 'email': username,
 'pwd': password,
 'validateCode': code,
 'x': '56',
 'y': '19'
}
result = client.post(PostUrl,postData) #向PostUrl提交表单
 
#循环下载ts视频
class VideoCrawler():
 
 def __init__(self,url):
 
  super(VideoCrawler, self).__init__()
  self.url=url
  self.final_path=r"D:\Download\Film"
  
 
 #下载并解析m3u8文件
 def get_url_from_m3u8(self,readAdr):
  print("正在解析真实下载地址...")
  with open('temp.m3u8','wb') as file:
   file.write(requests.get(readAdr).content)
  m3u8Obj=m3u8.load('temp.m3u8')
  print("解析完成")
  return m3u8Obj.segments
 
 def run(self):
  print("Start!")
  start_time=time.time()
  realAdr = self.url #m3u8下载地址
  urlList=self.get_url_from_m3u8(realAdr) #解析m3u8文件，获取下载地址
  urlRoot=self.url[0:self.url.rindex('/')]
  i=1
  outputfile=open(os.path.join(self.final_path,'%s.ts'%self.fileName),'wb')#初始创建一个ts文件，之后每次循环将ts片段的文件流写入此文件中从而不需要在去合并ts文件
  
 
  for url in urlList:
   try:    
    download_path = "%s/%s" % (urlRoot, url.uri) #拼接地址
    resp = client.get(download_path) #使用拼接地址去爬取数据
    progess = i/len(urlList)#记录当前的爬取进度
    outputfile.write(resp.content) #将爬取到ts片段的文件流写入刚开始创建的ts文件中
    sys.stdout.write('\r正在下载：{},进度：{:.2%}'.format(self.fileName,progess))#通过百分比显示下载进度
    sys.stdout.flush()#通过此方法将上一行代码刷新，控制台只保留一行
   except Exception as e:
    print("\n出现错误：%s",e.args)
    continue#出现错误跳出当前循环，继续下次循环
   i+=1
  outputfile.close()
  print("下载完成！总共耗时%d s"%(time.time()-start_time))
  print("开始转换视频格式！")
  success = os.system(r'copy /b D:\Download\Film\{0}.ts D:\Download\Film\{0}.mp4'.format(self.fileName)) #ts转成mp4格式
  if (not success):
   print("格式转换成功！")
   os.remove(self.final_path+'\\'+self.fileName+".ts") #删除ts和m3u8临时文件
   os.remove("temp.m3u8")
 
if __name__=='__main__':
 m3u8_addr = input("输入m3u8文件下载地址：\n") 
 crawler=VideoCrawler(m3u8_addr)
 crawler.fileName = input("输入文件名：\n")
 crawler.run()
 quitClick=input("请按Enter键确认退出！")