【Python工具】Python实现一款支持各大平台的视频下载器 | 附源码

相关文件

想学Python的小伙伴可以关注小编的公众号【Python日志】
有很多的资源可以白嫖的哈，不定时会更新一下Python的小知识的哈！！
需要源码的小伙伴可以在公众号回复视频下载器

简介

一款简单易用的视频下载器，目前支持的平台如下：

开发环境

Python版本：3.7.8
相关模块：
requests模块；
tqdm模块；
pyfreeproxy模块；
pyecharts模块；
以及一些python自带的模块。

环境搭建

安装Python并添加到环境变量，pip安装需要的相关模块即可。

效果展示

直接输入我们的一个视频链接就可以直接下载到文件夹downloaded中

复制哔哩哔哩视频链接

b站视频链接

https://www.bilibili.com/video/BV1si4y1y76f?spm_id_from=333.999.0.0

然后就可以直接播放我们的视频啦！！

代码实现过程

主代码

import sys
import copy
import json
import click
if __name__ == '__main__':
    from modules import *
    from __init__ import __version__
else:
    from .modules import *
    from .__init__ import __version__


'''basic info'''
BASICINFO = '''************************************************************
Function: 视频下载器 V%s
微信公众号: Python日志
操作帮助:
    输入r: 重新初始化程序(即返回主菜单)
    输入q: 退出程序
视频保存路径:
    当前路径下的%s文件夹内
************************************************************'''


'''视频下载器'''
class videodl():
    def __init__(self, configpath=None, config=None, **kwargs):
        assert configpath or config, 'configpath of config should be given...'
        self.config = loadConfig(configpath) if config is None else config
        self.logger_handle = Logger(self.config['logfilepath'])
        self.supported_sources = self.initializeAllSources()
    '''非开发人员外部调用'''
    def run(self):
        print(BASICINFO % (__version__, self.config.get('savedir')))
        while True:
            # 视频链接输入
            user_input = self.dealInput('请输入视频链接: ')
            # 判断视频链接类型是否支持解析下载
            source = self.findsource(user_input)
            if source is None:
                self.logger_handle.warning('暂不支持解析视频链接: %s...' % user_input)
                continue
            # 实例化
            client = source(self.config, self.logger_handle)
            # 视频链接解析
            videoinfos = client.parse(user_input)
            # 视频下载
            client.download(videoinfos)
    '''判断视频源'''
    def findsource(self, url):
        for key, source in self.supported_sources.items():
            if source.isurlvalid(url): return source
        return None
    '''初始化所有支持的搜索/下载源'''
    def initializeAllSources(self):
        supported_sources = {
            'ted': Ted,
            'cntv': CNTV,
            'mgtv': MGTV,
            'migu': Migu,
            'pipix': Pipix,
            'acfun': AcFun,
            'zhihu': Zhihu,
            'xigua': Xigua,
            'iqiyi': Iqiyi,
            'douyin': Douyin,
            'haokan': Haokan,
            'bilibili': Bilibili,
            'pipigaoxiao': Pipigaoxiao,
        }
        return supported_sources
    '''处理用户输入'''
    def dealInput(self, tip=''):
        user_input = input(tip)
        if user_input.lower() == 'q':
            self.logger_handle.info('ByeBye...')
            sys.exit()
        elif user_input.lower() == 'r':
            self.initializeAllSources()
            self.run()
        else:
            return user_input


'''cmd直接运行'''
@click.command()
@click.option('-i', '--url', default=None, help='想要下载的视频链接, 若不指定, 则进入videodl终端版')
@click.option('-l', '--logfilepath', default='videodl.log', help='日志文件保存的路径')
@click.option('-p', '--proxies', default='{}', help='设置的代理')
@click.option('-s', '--savedir', default='videos', help='视频保存的文件夹')
def videodlcmd(url, logfilepath, proxies, savedir):
    config = {
        'logfilepath': logfilepath,
        'proxies': json.loads(proxies),
        'savedir': savedir,
    }
    dl_client = videodl(config=config)
    if url is None:
        dl_client.run()
    else:
        source = dl_client.findsource(url)
        client = source(dl_client.config, dl_client.logger_handle)
        videoinfos = client.parse(url)
        client.download(videoinfos)


'''run'''
if __name__ == '__main__':
    import os
    rootdir = os.path.split(os.path.abspath(__file__))[0]
    dl_client = videodl(os.path.join(rootdir, 'config.json'))
    dl_client.run()

bilibili代码

'''
Function:
    B站视频下载器类
'''
import re
import time
from .base import Base
from ..utils.misc import *


'''B站视频下载器类'''
class Bilibili(Base):
    def __init__(self, config, logger_handle, **kwargs):
        super(Bilibili, self).__init__(config, logger_handle, **kwargs)
        self.source = 'bilibili'
        self.__initialize()
    '''视频解析'''
    def parse(self, url):
        response = self.session.get(url, headers=self.headers)
        bv = re.compile('BV..........').search(url).group()
        response = self.session.get(self.pagelist_url.format(bv), headers=self.headers)
        response_json = response.json()
        cid_list = [item['cid'] for item in response_json['data']]
        titles = [item.get('part', f'视频走丢啦_{time.time()}') for item in response_json['data']]
        download_urls = []
        for cid in cid_list:
            response = self.session.get(self.play_url.format(cid, bv), headers=self.headers)
            response_json = response.json()
            for item in response_json['data']['durl']:
                download_urls.append(item['url'])
        assert len(titles) == len(download_urls)
        videoinfos = []
        for idx, download_url in enumerate(download_urls):
            videoinfo = {
                'source': self.source,
                'download_url': download_url,
                'savedir': self.config['savedir'],
                'savename': '_'.join([self.source, filterBadCharacter(titles[idx])]),
                'ext': 'mp4',
            }
            videoinfos.append(videoinfo)
        return videoinfos
    '''初始化'''
    def __initialize(self):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
        }
        self.pagelist_url = 'https://api.bilibili.com/x/player/pagelist?bvid={}&jsonp=jsonp'
        self.play_url = 'http://api.bilibili.com/x/player/playurl?&cid={}&bvid={}&qn=80&fnval=0&fnver=0&fourk=1'
    '''判断视频链接是否属于该类'''
    @staticmethod
    def isurlvalid(url):
        valid_hosts = ['bilibili.com/video']
        for host in valid_hosts:
            if host in url: return True
        return False

抖音代码

'''
Function:
    抖音视频下载器类
'''
import re
import json
import time
import random
import requests
from .base import Base
from ..utils.misc import *


'''抖音视频下载器类'''
class Douyin(Base):
    def __init__(self, config, logger_handle, **kwargs):
        super(Douyin, self).__init__(config, logger_handle, **kwargs)
        self.source = 'douyin'
        self.__initialize()
    '''视频解析'''
    def parse(self, url):
        url = re.findall(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', url)[0]
        response = self.session.get(url)
        if response.url[:28] == 'https://www.douyin.com/user/':
            videoinfos = self.multiparse(response)
        else:
            videoinfos = self.singleparse(response)
        return videoinfos
    '''批量下载用户的视频'''
    def multiparse(self, response):
        videoinfos = []
        key = re.findall(r'/user/(.*?)\?', str(response.url))[0]
        if not key: key = response.url[28: 83]
        page_count, max_cursor = 35, 0
        while True:
            url = self.uid_url.format('post', key, page_count, max_cursor)
            response = self.session.get(url, headers=self.headers)
            response_json = json.loads(response.content.decode())
            max_cursor, aweme_list = response_json['max_cursor'], response_json['aweme_list']
            if max_cursor == 0: break
            for idx in range(min(page_count, len(aweme_list))):
                download_url = str(aweme_list[idx].get('video', {}).get('play_addr', {}).get('url_list', [''])[0])
                videoinfo = {
                    'source': self.source,
                    'aweme_id': aweme_list[idx].get('aweme_id', None),
                    'download_url': download_url,
                    'savedir': self.config['savedir'],
                    'savename': '_'.join([self.source, filterBadCharacter(str(aweme_list[idx].get('desc', f'视频走丢啦_{time.time()}')))]),
                    'ext': 'mp4',
                }
                if videoinfo['download_url']: videoinfos.append(videoinfo)
            time.sleep(random.random() + 0.2)
        return videoinfos
    '''下载单个视频'''
    def singleparse(self, response):
        url = self.iteminfo_url.format(re.findall(r'video/(\d+)?', str(response.url))[0])
        response_json = json.loads(self.session.get(url, headers=self.headers).text)
        try: download_url = str(response_json['item_list'][0]['video']['play_addr']['url_list'][0]).replace('playwm','play')
        except: return []
        videoinfo = {
            'source': self.source,
            'download_url': download_url,
            'savedir': self.config['savedir'],
            'savename': '_'.join([self.source, filterBadCharacter(str(response_json.get('item_list', [{}])[0].get('desc', f'视频走丢啦_{time.time()}')))]),
            'ext': 'mp4',
        }
        return [videoinfo]
    '''初始化'''
    def __initialize(self):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66',
        }
        self.iteminfo_url = 'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={}'
        self.uid_url = 'https://www.iesdouyin.com/web/api/v2/aweme/{}/?sec_uid={}&count={}&max_cursor={}&aid=1128&_signature=PDHVOQAAXMfFyj02QEpGaDwx1S&dytk='
    '''判断视频链接是否属于该类'''
    @staticmethod
    def isurlvalid(url):
        valid_hosts = ['v.douyin.com']
        for host in valid_hosts:
            if host in url: return True
        return False

皮皮搞笑视频

import re
import json
from .base import Base
from ..utils.misc import *


'''皮皮搞笑视频下载器类'''
class Pipigaoxiao(Base):
    def __init__(self, config, logger_handle, **kwargs):
        super(Pipigaoxiao, self).__init__(config, logger_handle, **kwargs)
        self.source = 'pipigaoxiao'
        self.__initialize()
    '''视频解析'''
    def parse(self, url):
        pattern = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', re.S)
        url = re.findall(pattern, url)[0]
        self.headers['Referer'] = url
        try:
            mid = re.findall('mid=(\d+)', url, re.S)[0]
            pid = re.findall('pid=(\d+)', url, re.S)[0]
        except:
            mid = ''
            pid = url.split('/')[-1]
        data = {
            'mid': int(mid) if mid else 'null',
            'pid': int(pid),
            'type': 'post',
        }
        response = self.session.post(self.content_url, data=json.dumps(data), headers=self.headers)
        response_json = response.json()
        download_url = response_json['data']['post']['videos'][str(response_json['data']['post']['imgs'][0]['id'])]['url']
        title = response_json['data']['post']['content'].replace('\n', '')
        videoinfo = {
            'source': self.source,
            'download_url': download_url,
            'savedir': self.config['savedir'],
            'savename': '_'.join([self.source, filterBadCharacter(title)]),
            'ext': 'mp4',
        }
        return [videoinfo]
    '''初始化'''
    def __initialize(self):
        self.headers = {
            'Host': 'share.ippzone.com',
            'Origin': 'http://share.ippzone.com',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36',
        }
        self.content_url = 'https://h5.ippzone.com/ppapi/share/fetch_content'
    '''判断视频链接是否属于该类'''
    @staticmethod
    def isurlvalid(url):
        valid_hosts = ['h5.ippzone.com', 'share.ippzone.com']
        for host in valid_hosts:
            if host in url: return True
        return False

代码量太多，小编就不全部展示啦
代码获取可以关注小编公众号：Python日志
在公众号中回复：视频下载器就可以领取啦