吾爱破解 - 52pojie.cn

 找回密码
 注册[Register]

QQ登录

只需一步,快速开始

查看: 1344|回复: 3
收起左侧

[Python 转载] 抓指定UP主更新的视频

[复制链接]
黑夜太美 发表于 2021-11-19 10:01
import json
import os
import re
import shutil
import ssl
import time
import requests
from concurrent.futures import ThreadPoolExecutor
from random import choice
from lxml import etree
import ffmpeg


#设置请求头等参数,防止被反爬
headers = {
   'Accept': '*/*',
   'Accept-Language': 'en-US,en;q=0.5',
   'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
}
def get_user_agent():
   '''获取随机用户代{过}{滤}理'''
   user_agents = [
       "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
       "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
       "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
       "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
       "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
       "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
       "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
       "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
       "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
       "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
       "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
       "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
       "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
       "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
       "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
       "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
       "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
       "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
       "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
       "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
       "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
       "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
       "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
       "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
       "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
       "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
       "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
       "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
       "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
       "Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
       "Mozilla/5.0 (Linux; Android 5.1.1; Nexus 6 Build/LYZ28E) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.23 Mobile Safari/537.36",
       "Mozilla/5.0 (iPod; U; CPU iPhone OS 2_1 like Mac OS X; ja-jp) AppleWebKit/525.18.1 (KHTML, like Gecko) Version/3.1.1 Mobile/5F137 Safari/525.20",
       "Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
       "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html"
   ]
   # user_agent列表中随机产生一个代{过}{滤}理,作为模拟的浏览器
   user_agent = choice(user_agents)
   return user_agent
def re_video_info(text,pattern):
    match =re.search(pattern,text)
    print(match.group(1))
    print()
    return json.loads(match.group(1))
def get_video_info():  #  host_uid=1436161751 修改需要抓取视频的UPID
    url = 'https://api.vc.bilibili.com/dynamic_svr/v1/dynamic_svr/space_history?host_uid=1436161751&need_top=1'
    res = requests.get(url, headers=headers)
    html = json.loads(res.text)
    for item in html['data']['cards']:
        card = json.loads(item['card'])
        url = card['short_link_v2'].rsplit('tv/')[1]
        my_file = "C:\\inetpub\\wwwroot\\jack100_g4Yp\\web\\video\\temp\\"+card['title'].split('')[1]+'.mp4'
        print(my_file)
        if os.path.exists(my_file):
            print("跳过这个", card['title'])
        else:
            single_download(url, 0)



def single_download(aid, acc_quality):
    '''单个视频实现下载'''
    # 请求视频链接,获取信息
    origin_video_url = 'https://www.bilibili.com/video/' + aid
    res = requests.get(origin_video_url, headers=headers)
    html = etree.HTML(res.text)
    titles = html.xpath('//*[@id="viewbox_report"]/h1/span/text()')[0].split('')
    title = titles[1]
    print('您当前正在下载:', title)

    video_info_temp = re_video_info(res.text, '__playinfo__=(.*?)</script><script>')
    video_info = {}
    # 获取视频质量
    quality = video_info_temp['data']['accept_description'][acc_quality]
    # 获取视频时长
    video_info['duration'] = video_info_temp['data']['dash']['duration']
    # 获取视频链接
    video_url = video_info_temp['data']['dash']['video'][acc_quality]['baseUrl']
    # 获取音频链接
    audio_url = video_info_temp['data']['dash']['audio'][acc_quality]['baseUrl']
    # 计算视频时长
    video_time = int(video_info.get('duration', 0))
    video_minute = video_time // 60
    video_second = video_time % 60
    print('当前视频清晰度为{},时长{}{}'.format(quality, video_minute, video_second))
    # 调用函数下载保存视频
    download_video_single(origin_video_url, video_url, audio_url, title)
    #print(origin_video_url, video_url, audio_url, title)
def download_video_single(referer_url, video_url, audio_url, video_name):
    '''单个视频下载'''
    # 更新请求头
    headers.update({"Referer": referer_url})
    print("视频下载开始:%s" % video_name)
    # 下载并保存视频
    video_content = requests.get(video_url, headers=headers)
    print('%s\t视频大小:' % video_name, round(int(video_content.headers.get('content-length', 0)) / 1024 / 1024, 2), '\tMB')

    received_video = 0
    with open('%s_video.mp4' % video_name, 'ab') as output:
        headers['Range'] = 'bytes=' + str(received_video) + '-'
        response = requests.get(video_url, headers=headers)
        output.write('temp\\'+response.content)
    # 下载并保存音频
    audio_content = requests.get(audio_url, headers=headers)
    print('%s\t音频大小:' % video_name, round(int(audio_content.headers.get('content-length', 0)) / 1024 / 1024, 2), '\tMB')
    received_audio = 0
    with open('%s_audio.mp4' % video_name, 'ab') as output:
        headers['Range'] = 'bytes=' + str(received_audio) + '-'
        response = requests.get(audio_url, headers=headers)
        output.write('temp\\'+response.content)
        received_audio += len(response.content)
    print("视频下载结束:%s" % video_name)
    video_audio_merge_single(video_name)
def video_audio_merge_single(video_name):
    '''使用ffmpeg单个视频音频合并'''
    print("视频合成开始:%s" % video_name)
    import subprocess
    command = f'D:\\Python\\Lib\\FFmpeg\\bin\\ffmpeg -i %s_video.mp4 -i %s_audio.mp4 -acodec copy -vcodec copy %s.mp4'%(video_name, video_name, video_name)
    subprocess.call(command, shell=True)
    print("视频合成结束:%s" % video_name)
    import os
    os.remove(video_name+"_video.mp4")
    os.remove(video_name + "_audio.mp4")
get_video_info()
# single_download('BV1yQ4y1y74s',0)

bilibili.zip

3.21 KB, 下载次数: 18, 下载积分: 吾爱币 -1 CB

免费评分

参与人数 1吾爱币 +1 收起 理由
kiopc + 1 感谢发布原创作品,吾爱破解论坛因你更精彩!

查看全部评分

发帖前要善用论坛搜索功能,那里可能会有你要找的答案或者已经有人发布过相同内容了,请勿重复发帖。

正己 发表于 2021-11-19 10:17
随机请求头可以用这个库,fake_useragent,减少代码冗余
另外,代码建议用代码块包裹起来会比较直观,精美
Galaxy2010 发表于 2021-11-19 10:19
cwl 发表于 2021-11-19 11:19
如果用百度的爬虫请求头,这算不算违法啊,非法利用别人的数据来入侵他人系统
您需要登录后才可以回帖 登录 | 注册[Register]

本版积分规则

返回列表

RSS订阅|小黑屋|处罚记录|联系我们|吾爱破解 - LCG - LSG ( 京ICP备16042023号 | 京公网安备 11010502030087号 )

GMT+8, 2024-11-25 11:39

Powered by Discuz!

Copyright © 2001-2020, Tencent Cloud.

快速回复 返回顶部 返回列表