爬取某内培训班vip课程并保存

# auther:xiaomge
# 达内视频下载(此代码用于学习)
import time
import shutil

import lxml.etree as etree
import requests
from Crypto.Cipher import AES
import os

header3 = dict()
header3[
    'User-Agent'] = 
header3['Referer'] = 
header3['Origin'] = 
header3['Host'] = 
header3['Accept'] = 
header3['Accept-Encoding'] =
header3['Sec-Fetch-Dest'] = 
header3['Sec-Fetch-Mode'] =
header3['Sec-Fetch-Site'] = 


class DaNei:
    def __init__(self):
        self.headers2 = {
            'User-Agent': ,
            'Cookie': ,
        }
        self.studentscenter_url = 'https://tts.tmooc.cn/studentCenter/toMyttsPage'
        self.verify = False
        self.dow_lowd_path = './tes'
        self.dow_hb_path = './hb'

    def dow_lowd(self, key_url_pipei, menu_id):
        if os.path.exists('./tes'):
            print('exist')
        else:
            os.mkdir('./tes')  # 创建
        if os.path.exists('./hb'):
            print('exist')
        else:
            os.mkdir('./hb')
        for i in range(0, 500):
            try:
                # 这两个是变化的 nsd21050727am 下面两个要换 网页中自动获取就行了
                key_url = 'https://c.it211.com.cn/{}/static.key'.format(key_url_pipei)
                ts_url = 'https://c.it211.com.cn/{}/{}-{}.ts'.format(key_url_pipei, key_url_pipei, i)
                header3['Referer'] = header3['Referer'].format(menu_id)
                key = requests.get(key_url, headers=header3, verify=self.verify).content
                res_ts = requests.get(ts_url, headers=header3, verify=self.verify).content
                # 下载ts文件
                down_path = self.dow_lowd_path + '/{}.ts'.format(i)
                with open(down_path, 'wb') as ts:
                    # 解密
                    cryptor = AES.new(key, AES.MODE_CBC, key)
                    ts.write(cryptor.decrypt(res_ts))
                    print('第{}个下载完成'.format(i))
            except Exception as e:
                print('错误:', e)
                break
        print('{}视频下载完成了，马上去合并'.format(key_url_pipei))
        return True

    def has_id(self):
        one_page_html = requests.get(self.studentscenter_url, headers=self.headers2, verify=self.verify).content.decode(
            'utf-8')
        selector = etree.HTML(one_page_html)
        course_list = selector.xpath('.//div[@class="course-menu"]//li[@class="sp"]//@href')
        for one_url in course_list:
            menu_id = one_url.split('?')[1].split('&')[0]
            one_page_html2 = requests.get(one_url, headers=self.headers2, verify=self.verify).content.decode('utf-8')
            selector2 = etree.HTML(one_page_html2)
            data_time = selector2.xpath('.//div[@class="video-list"]//p//@id')
            course_title = str(selector2.xpath('.//div[@id="video_stage_lty"]//text()')[0])
            # print(course_title)
            print('*' * 10)
            for one_pa_am in data_time:
                true_time_contents = one_pa_am.split('_')[1].split('.')[0]
                if self.dow_lowd(true_time_contents, menu_id) is True:
                    # 开始合并视频
                    all_ts = os.listdir('./tes')
                    save_path = self.dow_hb_path + '/' + course_title + str(true_time_contents) + '.mp4'
                    with open(save_path, 'wb+') as f:
                        for i in range(len(all_ts)):
                            ts_video_path = os.path.join('./tes', all_ts[i])
                            f.write(open(ts_video_path, 'rb').read())
                    print("合并完成！！删除所有")
                    try:
                        shutil.rmtree('./tes')
                    except Exception as e:
                        print(e)
                        pass
                print('{}的视频下载合并完成了，下一个开始了!休息一分钟'.format(true_time_contents))
                time.sleep(60)
            print('*' * 10)


if __name__ == '__main__':
    D = DaNei()
    D.has_id()