相思资源网 Design By www.200059.com
B站原视频爬取,我就不多说直接上代码。直接运行就好。
B站是把视频和音频分开。要把2个合并起来使用。这个需要分析才能看出来。然后就是登陆这块是比较难的。
import os import re import argparse import subprocess import prettytable from DecryptLogin import login '''B站类''' class Bilibili(): def __init__(self, username, password, **kwargs): self.username = username self.password = password self.session = Bilibili.login(username, password) self.headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36' } self.user_info_url = 'http://api.bilibili.com/x/space/acc/info' self.submit_videos_url = 'http://space.bilibili.com/ajax/member/getSubmitVideos' self.view_url = 'http://api.bilibili.com/x/web-interface/view' self.video_player_url = 'http://api.bilibili.com/x/player/playurl' '''运行主程序''' def run(self): while True: userid = input('请输入目标用户ID(例:345993405)(我的一个LOL好友凯撒可以关注他一下 谢谢) ——> ') user_info = self.__getUserInfo(userid) tb = prettytable.PrettyTable() tb.field_names = list(user_info.keys()) tb.add_row(list(user_info.values())) print('获取的用户信息如下:') print(tb) is_download = input('是否下载该用户的所有视频(y/n, 默认: y) ——> ') if is_download == 'y' or is_download == 'yes' or not is_download: self.__downloadVideos(userid) '''根据userid获得该用户基本信息''' def __getUserInfo(self, userid): params = {'mid': userid, 'jsonp': 'jsonp'} res = self.session.get(self.user_info_url, params=params, headers=self.headers) res_json = res.json() user_info = { '用户名': res_json['data']['name'], '性别': res_json['data']['sex'], '个性签名': res_json['data']['sign'], '用户等级': res_json['data']['level'], '生日': res_json['data']['birthday'] } return user_info '''下载目标用户的所有视频''' def __downloadVideos(self, userid): if not os.path.exists(userid): os.mkdir(userid) # 非会员用户只能下载到高清1080P quality = [('16', '流畅 360P'), ('32', '清晰 480P'), ('64', '高清 720P'), ('74', '高清 720P60'), ('80', '高清 1080P'), ('112', '高清 1080P+'), ('116', '高清 1080P60')][-3] # 获得用户的视频基本信息 video_info = {'aids': [], 'cid_parts': [], 'titles': [], 'links': [], 'down_flags': []} params = {'mid': userid, 'pagesize': 30, 'tid': 0, 'page': 1, 'order': 'pubdate'} while True: res = self.session.get(self.submit_videos_url, headers=self.headers, params=params) res_json = res.json() for item in res_json['data']['vlist']: video_info['aids'].append(item['aid']) if len(video_info['aids']) < int(res_json['data']['count']): params['page'] += 1 else: break for aid in video_info['aids']: params = {'aid': aid} res = self.session.get(self.view_url, headers=self.headers, params=params) cid_part = [] for page in res.json()['data']['pages']: cid_part.append([page['cid'], page['part']]) video_info['cid_parts'].append(cid_part) title = res.json()['data']['title'] title = re.sub(r"[‘'\/\\\:\*\"\<\>\|\s']", ' ', title) video_info['titles'].append(title) print('共获取到用户ID<%s>的<%d>个视频...' % (userid, len(video_info['titles']))) for idx in range(len(video_info['titles'])): aid = video_info['aids'][idx] cid_part = video_info['cid_parts'][idx] link = [] down_flag = False for cid, part in cid_part: params = {'avid': aid, 'cid': cid, 'qn': quality, 'otype': 'json', 'fnver': 0, 'fnval': 16} res = self.session.get(self.video_player_url, params=params, headers=self.headers) res_json = res.json() if 'dash' in res_json['data']: down_flag = True v, a = res_json['data']['dash']['video'][0], res_json['data']['dash']['audio'][0] link_v = [v['baseUrl']] link_a = [a['baseUrl']] if v['backup_url']: for item in v['backup_url']: link_v.append(item) if a['backup_url']: for item in a['backup_url']: link_a.append(item) link = [link_v, link_a] else: link = [res_json['data']['durl'][-1]['url']] if res_json['data']['durl'][-1]['backup_url']: for item in res_json['data']['durl'][-1]['backup_url']: link.append(item) video_info['links'].append(link) video_info['down_flags'].append(down_flag) # 开始下载 out_pipe_quiet = subprocess.PIPE out_pipe = None aria2c_path = os.path.join(os.getcwd(), 'tools/aria2c') ffmpeg_path = os.path.join(os.getcwd(), 'tools/ffmpeg') for idx in range(len(video_info['titles'])): title = video_info['titles'][idx] aid = video_info['aids'][idx] down_flag = video_info['down_flags'][idx] print('正在下载视频<%s>...' % title) if down_flag: link_v, link_a = video_info['links'][idx] # --视频 url = '"{}"'.format('" "'.join(link_v)) command = '{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}' command = command.format(aria2c_path, len(link_v), userid, title+'.flv', aid, "", url) print(command) process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True) process.wait() # --音频 url = '"{}"'.format('" "'.join(link_a)) command = '{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}' command = command.format(aria2c_path, len(link_v), userid, title+'.aac', aid, "", url) print(command) process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True) process.wait() # --合并 command = '{} -i "{}" -i "{}" -c copy -f mp4 -y "{}"' command = command.format(ffmpeg_path, os.path.join(userid, title+'.flv'), os.path.join(userid, title+'.aac'), os.path.join(userid, title+'.mp4')) print(command) process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe_quiet, shell=True) process.wait() os.remove(os.path.join(userid, title+'.flv')) os.remove(os.path.join(userid, title+'.aac')) else: link = video_info['links'][idx] url = '"{}"'.format('" "'.join(link)) command = '{} -c -k 1M -x {} -d "{}" -o "{}" --referer="https://www.bilibili.com/video/av{}" {} {}' command = command.format(aria2c_path, len(link), userid, title+'.flv', aid, "", url) process = subprocess.Popen(command, stdout=out_pipe, stderr=out_pipe, shell=True) process.wait() os.rename(os.path.join(userid, title+'.flv'), os.path.join(userid, title+'.mp4')) print('所有视频下载完成, 该用户所有视频保存在<%s>文件夹中...' % (userid)) '''借助大佬开源的库来登录B站''' @staticmethod def login(username, password): _, session = login.Login().bilibili(username, password) return session '''run''' if __name__ == '__main__': parser = argparse.ArgumentParser(description='下载B站指定用户的所有视频(仅支持Windows下使用)') parser.add_argument('--username', dest='username', help='xxx', type=str, required=True) parser.add_argument('--password', dest='password', help='xxxx', type=str, required=True) print(parser) args = parser.parse_args(['--password', 'xxxx','--username', 'xxx']) # args = parser.parse_args(['--password', 'FOO']) print('5') bili = Bilibili(args.username, args.password) bili.run()
把账号密码填上就行。这是我根据一个微信公众号Charles大佬的想法写的。大家可以去关注他一下。
以上就是python 爬取B站原视频的实例代码的详细内容,更多关于python 爬取B站原视频的资料请关注其它相关文章!
相思资源网 Design By www.200059.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
相思资源网 Design By www.200059.com
暂无python 爬取B站原视频的实例代码的评论...