b站视频下载更新（加入下载进度）_69re

b站视频下载更新（加入下载进度）

一直想加个下载进度进去，最近才搞上
顺便加了个获取视频的AV号
新开一个pa审核过不了
往期相关：
Python爬取b站视频（api真实地址）
selenium模拟登陆b站
参考链接：
【python小工具】requests显示下载速度
requests 中的参数 stream

from lxml import etree
import requests
import os
import re
from sys import stdout
import time

# 正则提取bv号
def bvre(bv):
    bv += '?'
    rx = '(BV[\S]*?)\\?'
    r_bv = re.findall(rx,bv)[0]
    r_bv = r_bv.replace('/','')
    print('\nBV:',r_bv)
    return r_bv
# 获取视频名称
def name(bv,headers):
    url = 'https://www.bilibili.com/video/'+bv
    text = requests.get(url,headers = headers).text
    tree = etree.HTML(text)
    name = tree.xpath('//*[@id="viewbox_report"]/h1/span/text()')[0]
    return name
'''
# =========备用api=========
# 获取(默认第一页的)cid
def cid(bv,headers):
    url = 'https://api.bilibili.com/x/player/pagelist'
    param = {
        'bvid':'%s'%bv,
        'jsonp':'jsonp'
    }
    text = requests.get(url,params = param,headers = headers).json()
    cid = text['data'][0]['cid']
    return cid
'''
# 获取分页信息以及对应的cid
# https://api.bilibili.com/x/web-interface/view/detail?bvid=BV1CX4y1P7M8&aid=713833694&need_operation_card=1&web_rm_repeat=&need_elec=1&out_referer=https%3A%2F%2Fspace.bilibili.com%2F
def page(bv):
    url = 'https://api.bilibili.com/x/web-interface/view/detail'
    param = {
        'bvid':'%s'%bv,
    }
    text = requests.get(url,params = param,headers = headers).json()
    text_pic = text['data']['View']['pic']
    print("\n视频封面链接pic：",text_pic)
    av=text['data']['View']['aid']  # AV号
    print("AV号：","av" + str(av))
    text_cid = text['data']['View']['pages']
    print("\n分页信息以及对应的cid:")
    for page in text_cid:
        if page['page'] == 1:
            f_cid = page['cid']
        print('第 %d 页 cid：%s'%(page['page'],page['cid']))
    cid = input("输入分页或cid值（默认第一页）:")
    for page in text_cid:
        if cid == "":
            cid = f_cid
            num = 1
            break
        else:
            cid = int(cid)
        if page['page'] == cid or page['cid'] == cid:
            cid = page['cid']
            num = page['page']
            break  
    ret = [cid,num]            
    return ret
# 获取视频url
def flv(cid,bv,headers,quality):
    url = 'https://api.bilibili.com/x/player/playurl'
    param = {
        'cid':'%s'%cid,
        'bvid':'%s'%bv,
        'qn':'%s'%quality,
    }
    text = requests.get(url,params = param,headers = headers).json()
    return text
# 请求视频并保存
def get_flv(name,flv_url,headers,page_num):
    def MB(byte):
        return byte / 1024 / 1024
    print("\n等待响应数据（需要的时间较长）...")
    # 当把get函数的stream参数设置成True时，它不会立即开始下载
    # 当你使用iter_content或iter_lines遍历内容或访问内容属性时才开始下载
    response = requests.get(flv_url, stream=True, headers = headers)
    code = response.status_code
    print('\n响应码：',code)
    file_size = int(response.headers['content-length'])  # 文件大小 Byte
    print("文件大小: {:.2f} MB\n".format(file_size/1024/1024))
    if code == 200:
        # 删除标题中的 / 等字符，防止文件路径错误
        name = name.replace('/','').replace('|','')
        down_size = 0  # 已下载字节数
        old_down_size = 0  # 上一次已下载字节数
        interval = 0.5 # 下载输出间隔
        time_ = time.time()
        with open(r"./%s-%d.flv"%(name,page_num),'wb') as fp1:
            for chunk in response.iter_content(chunk_size=512):
                if chunk:
                    fp1.write(chunk)
                    down_size += len(chunk)
                    if time.time() - time_ > interval:
                        # rate = down_size / file_size * 100  # 进度  0.01%
                        speed = (down_size - old_down_size) / interval  # 速率 0.01B/s
                        
                        old_down_size = down_size
                        time_ = time.time()
                        
                        print_params = [MB(speed), MB(down_size), MB(file_size), (file_size - down_size) / speed]
                        # \r 光标回到行首
                        print('\r{:.1f}MB/s - {:.2f}MB，共 {:.2f}MB，还剩 {:.0f} 秒   '.format(*print_params), end='')
                        
            print('\r下载成功' + " "*50)
                    
        with open("./list.txt",'a') as fp2:
            fp2.write(name+"\nhttps://www.bilibili.com/video/"+bv+"?p=%d\n\n"%page_num)
        print("视频获取成功\n(若视频清晰度不符，请及时更新cookie值)")
    else:
        print("视频获取失败")
# main
bv = input("输入BV号(网页链接)：")
bv = bvre(bv)
# 获取本地txt保存的cookie
cookie = ""
if os.path.exists("./cookie.txt"):
    with open('./cookie.txt') as fp:
        cookie = fp.read()
    cookie = cookie.split('\n')[0]
print('\ncookie:',cookie)
headers = {
    'Referer':'https://www.bilibili.com/',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36',
    'cookie':"%s"%cookie,
}
cid_get = page(bv)
cid = cid_get[0]
page_num = cid_get[1]
# cid = cid(bv,headers)
print('\ncid:',cid)
print('page:',page_num) 
print('\n可获取cookie值的链接(需先在浏览器正常登录)\nhttps://api.bilibili.com/x/player/playurl?cid=%s&bvid=%s'%(cid,bv))
name = name(bv,headers)
print('\n标题：',name)
quality = ''
text =flv(cid,bv,headers,quality)
qn = text['data']['support_formats']
print("\n可选择的清晰度(部分清晰度可能获取失败)：")
for qu in qn:
    print(('清晰度：%s'%qu['new_description']).ljust(15)+('视频质量参数:%d'%qu['quality']).ljust(15)+('格式参数:%s'%qu['format']).ljust(15))
quality = input("输入清晰度对应的视频质量参数（默认1080p）：")
if quality == '':
    quality = '80'
text = flv(cid,bv,headers,quality)
flv_url = text['data']['durl'][0]['url']
print('\nflv_url:',flv_url)
get_flv(name,flv_url,headers,page_num)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157