使用Python下载pear视频网站中的小视频

qq_50310664

已于 2022-11-04 21:37:49 修改

阅读量709

点赞数

文章标签： python 音视频开发语言

于 2022-11-04 21:27:22 首次发布

本文链接：https://blog.csdn.net/qq_50310664/article/details/127696803

版权

示例代码如下所示：

import random
import os
import requests
from lxml import etree
import time
from multiprocessing.dummy import Pool

url = 'https://www.pearvideo.com/category_1'
header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.52'
}
response = requests.get(url, headers=header).text
tree = etree.HTML(response)
li_list = tree.xpath('/html/body/div[2]/div[1]/div/ul/li')
videos = []
for li in li_list:
    detial = 'https://www.pearvideo.com/' + li.xpath('.//a[@class="vervideo-lilink actplay"]/@href')[0]
    name = li.xpath('.//a[@class="vervideo-lilink actplay"]/div[2]/text()')[0] + '.mp4'
    id = li.xpath('.//a[@class="vervideo-lilink actplay"]/@href')[0].split('_')[1]
    ram = random.Random()
    address = f'https://www.pearvideo.com/videoStatus.jsp?contId={id}&mrd={ram}'
    ajax_header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.52',
        'Referer': detial
    }
    content = requests.get(address, headers=ajax_header).json()
    _url = content['videoInfo']['videos']['srcUrl']
    password = content['systemTime']
    # 虚拟地址_url =https://video.pearvideo.com/mp4/adshort/20190205/1667563305982-13557057_adpkg-ad_hd.mp4
    # 真实地址video_url =https://video.pearvideo.com/mp4/adshort/20190205/cont-1514702-13557057_adpkg-ad_hd.mp4
    video_url = _url.replace(password, f'cont-{id}')
    videos.append({'name': name, 'video_url': video_url})


def download(_dict):
    video_name = _dict['name']
    video_url = _dict['video_url']
    print(f'正在下载【{video_name}】')
    video_data = requests.get(video_url, headers=header).content
    with open(f'./videos/{video_name}', 'wb') as wfile:
        wfile.write(video_data)
    print(f'【{video_name}】已下载完成')


if __name__ == '__main__':
    start_time = time.time()
    if not os.path.exists('./videos'):
        os.mkdir('./videos')

    # 单线程下载
    # for video in videos:
    #     download(video)

    # 多线程下载
    pool = Pool(4)
    pool.map(download, videos)
    end_time = time.time()
    pool.close()
    pool.join()
    print(f'视频全部下载完成，共耗时：{end_time - start_time}s')

本次示例代码为pear视频中人物分类