[Python知识库]python爬取B站视频和弹幕文件(demo)

首先对B站的动态加载做了解析找到了他放置Bv号的方法然后再使用了you-get，ffmpeg的组合来下载视频
效果如下:

谁能拒绝会举重的小姐姐呢，珍珍的b站账号:https://space.bilibili.com/2146116262

代码如下：

#author:zac
import requests
import json
import os
from tqdm import tqdm
from bs4 import BeautifulSoup

headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36"}
#避免重复使用
def get_resp_text(url):
    rsp = requests.get(url,headers=headers)
    rsp.encoding = 'utf-8'
    return rsp.text
#把up的名字返回一下
def get_upname(mid):
        rsp = requests.get('https://space.bilibili.com/'+mid)
        rsp.encoding = 'utf-8'
        html = rsp.text
        bss = BeautifulSoup(html, 'lxml')
        return (bss.find('title').text[:-len('的个人空间_哔哩哔哩_Bilibili')])
#获取up主的全部视频BV号
def get_bvid(mid):
        i = 1
        bvid = []
        while i != 0:
                url0 = 'https://api.bilibili.com/x/space/arc/search?mid='+str(mid)+'&ps=30&tid=0&pn=&keyword=&order=pubdate&jsonp=jsonp'
                url0 = url0[:-len('&keyword=&order=pubdate&jsonp=jsonp')] + str(
                        i) + '&keyword=&order=pubdate&jsonp=jsonp'
                i += 1
                html = get_resp_text(url0)
                dict = json.loads(html.replace('\n', ''))
                datadict = dict['data']
                listdict = datadict['list']
                vlist = listdict['vlist']
                if len(vlist) == 0:
                        i = 0
                elif len(vlist) != 0:
                        for _ in range(len(vlist)):
                                bvid.insert(0, vlist[_]['bvid'])
        return bvid,get_upname(mid)
#you-get下载视频
def download_vedio(bvid):
        command='you-get --format=dash-flv360 https://www.bilibili.com/video/'+bvid
        os.system(command)
def get_xml(bvid):
        url0 = 'https://api.bilibili.com/x/player/pagelist?bvid='+bvid+'&jsonp=jsonp'


if __name__=='__main__':
        bvid, upname = get_bvid(input("输入你想要爬取的up主的id号: "))
        print("up主:" + str(upname) + "共有" + str(len(bvid)) + "条视频")
        # 下载试试
        for vid in tqdm(bvid):
                download_vedio(vid)