image.png

    3. import requests
    4. import re
    5. import json
    6. import os
    7. from fake_useragent import UserAgent
    8. class LiVideo:
    9.     def __init__(self,cate_id):
    10.         self.base_url = 'https://www.pearvideo.com/'  # 主域名
    11.         self.url = self.base_url + 'category_' + cate_id  # 首页的请求地址
    12.         self.file_path = 'category_' + cate_id + 'page.html'     # 保存页面文件
    13.         self.videoDir = './video-' + cate_id  # 视频分类目录地址
    14.         self.pre_video = self.base_url + 'videoStatus.jsp?contId=' # 单个视频请求地址
    15.         self.checkDir(self.videoDir)
    16.         self.checkDir(self.videoDir)
    18.     # 创建视频目录
    19.     def checkDir(self,dirPath):
    20.         if  not os.path.exists(dirPath):
    21.             os.mkdir(dirPath)
    23.     # 获取用户信息
    24.     def getVideo(self):
    25.         if os.path.exists(self.file_path):
    26.             self.getVideoInfo()
    27.         else:
    28.             self.savePageHtml()
    30.     # 保存页面
    31.     def savePageHtml(self):
    32.         response = requests.get(self.url)
    33.         if response.status_code == 200:
    34.             with open(self.file_path,'w',encoding='utf-8') as file:
    35.                 file.write(response.text)
    36.         # 获取页面视频信息
    37.         self.getVideoInfo()
    39.     # 保存数据
    40.     def getVideoInfo(self):
    41.         videoes = []
    42.         with open(self.file_path,'r',encoding='utf-8') as file:
    43.             html = file.read()
    44.             images = re.findall(r'<div class="verimg-view">.*? url\((.*?)\);">',html)
    45.             titles = re.findall(r'<div class="vervideo-title">(.*?)</div>',html)
    46.             videoIds = re.findall(r'<a href="video_(.*?)" class="vervideo-lilink actplay">',html)
    47.             authos = re.findall(r'<a href=".*?" class="column">(.*?)</a>',html);
    48.             for i in range(0,len(videoIds)):
    49.                 videoInfo = {'title':titles[i],'author':authos[i],'image':images[i],'videoId':videoIds[i]}
    50.                 videoes.append(videoInfo)
    52.         if videoes:
    53.             print('开始下载视频...')
    54.             for video in videoes:
    55.                 requestVideoUrl = self.pre_video + video['videoId']
    56.                 headers = {
    57.                     'User-Agent': UserAgent().random,
    58.                     'Referer': self.base_url + 'video_' + video['videoId']
    59.                 }
    60.                 response = requests.get(requestVideoUrl, headers=headers)
    61.                 if response.status_code == 200:
    62.                     result = json.loads(response.text)
    63.                     # 得到视频url：https://video.pearvideo.com/mp4/third/20211229/1641655664960-10054243-161801-hd.mp4
    64.                     # 实际播放地址：url: https://video.pearvideo.com/mp4/third/20220113/cont-1749919-10054243-151326-hd.mp4
    65.                     videoUrl = result['videoInfo']['videos']['srcUrl']
    66.                     newVideoUrl = re.sub(r'/(\d+)-', f'/cont-{video["videoId"]}-', videoUrl)
    67.                     try:
    68.                         videoContent = requests.get(newVideoUrl)
    69.                         if response.status_code == 200:
    70.                             print(f'下载视频:{video["title"]}中')
    71.                             with open(f'{self.videoDir}/{video["title"]}.mp4', 'wb') as file:
    72.                                 file.write(videoContent.content)
    73.                     except Exception as error:
    74.                         print(error)
    75.                 else:
    76.                     print(response.status_code)
    77.             print('下载完毕!!!')
    78.         else:
    79.             print('该页面不存在')
    81. cate_id = input('请输入分类id')
    82. video = LiVideo(cate_id)
    83. video.getVideo()

    地址: https://www.pearvideo.com/category_6 输入category_后的值
    image.png