项目地址:
https://github.com/Henryhaohao/Bilibili_video_download
介绍
- 对于单P视频:直接传入B站av号或者视频链接地址(eg: 49842011或者https://www.bilibili.com/video/av49842011)
- 对于多P视频:
1.下载全集:直接传入B站av号或者视频链接地址(eg: 49842011或者https://www.bilibili.com/video/av49842011)
2.下载其中一集:传入那一集的视频链接地址(eg: https://www.bilibili.com/video/av19516333/?p=2)
版本一: bilibili_video_download_v1.py
加密API版,不需要加入cookie,直接即可下载1080p视频
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
|
# !/usr/bin/python
# -*- coding:utf-8 -*-
# time: 2019/04/17--08:12
__author__ = 'Henry'
'''
项目: B站视频下载
版本1: 加密API版,不需要加入cookie,直接即可下载1080p视频
20190422 - 增加多P视频单独下载其中一集的功能
'''
import imageio
imageio.plugins.ffmpeg.download()
import requests, time, hashlib, urllib.request, re, json
from moviepy.editor import *
import os, sys
# 访问API地址
def get_play_list(start_url, cid, quality):
entropy = 'rbMCKn@KuamXWlPMoJGsKcbiJKUfkPF_8dABscJntvqhRSETg'
appkey, sec = ' '.join([chr(ord(i) + 2) for i in entropy[::-1]]).split(' :')
params = 'appkey=%s&cid=%s&otype=json&qn=%s&quality=%s&type=' % (appkey, cid, quality, quality)
chksum = hashlib.md5(bytes(params + sec, 'utf8' )).hexdigest()
url_api = 'https://interface.bilibili.com/v2/playurl?%s&sign=%s' % (params, chksum)
headers = {
'Referer' : start_url, # 注意加上referer
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
# print(url_api)
html = requests.get(url_api, headers = headers).json()
# print(json.dumps(html))
video_list = []
for i in html[ 'durl' ]:
video_list.append(i[ 'url' ])
# print(video_list)
return video_list
# 下载视频
'''
urllib.urlretrieve 的回调函数:
def callbackfunc(blocknum, blocksize, totalsize):
@blocknum: 已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 远程文件的大小
'''
def Schedule_cmd(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
f.write(percent_str.ljust( 8 , ' ' ) + '[' + s + ']' + speed_str)
f.flush()
# time.sleep(0.1)
f.write( '\r' )
def Schedule(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
print (percent_str.ljust( 6 , ' ' ) + '-' + speed_str)
f.flush()
time.sleep( 2 )
# print('\r')
# 字节bytes转化K\M\G
def format_size(bytes):
try :
bytes = float (bytes)
kb = bytes / 1024
except :
print ( "传入的字节格式不对" )
return "Error"
if kb > = 1024 :
M = kb / 1024
if M > = 1024 :
G = M / 1024
return "%.3fG" % (G)
else :
return "%.3fM" % (M)
else :
return "%.3fK" % (kb)
# 下载视频
def down_video(video_list, title, start_url, page):
num = 1
print ( '[正在下载P{}段视频,请稍等...]:' . format (page) + title)
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
for i in video_list:
opener = urllib.request.build_opener()
# 请求头
opener.addheaders = [
# ('Host', 'upos-hz-mirrorks3.acgvideo.com'), #注意修改host,不用也行
( 'User-Agent' , 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0) Gecko/20100101 Firefox/56.0' ),
( 'Accept' , '*/*' ),
( 'Accept-Language' , 'en-US,en;q=0.5' ),
( 'Accept-Encoding' , 'gzip, deflate, br' ),
( 'Range' , 'bytes=0-' ), # Range 的值要为 bytes=0- 才能下载完整视频
( 'Referer' , start_url), # 注意修改referer,必须要加的!
( 'Origin' , 'https://www.bilibili.com' ),
( 'Connection' , 'keep-alive' ),
]
urllib.request.install_opener(opener)
# 创建文件夹存放下载的视频
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
# 开始下载
if len (video_list) > 1 :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}-{}.flv' . format (title, num)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
else :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}.flv' . format (title)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
num + = 1
# 合并视频
def combine_video(video_list, title):
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
if len (video_list) > = 2 :
# 视频大于一段才要合并
print ( '[下载完成,正在合并视频...]:' + title)
# 定义一个数组
L = []
# 访问 video 文件夹 (假设视频都放在这里面)
root_dir = currentVideoPath
# 遍历所有文件
for file in sorted (os.listdir(root_dir), key = lambda x: int (x[x.rindex( "-" ) + 1 :x.rindex( "." )])):
# 如果后缀名为 .mp4/.flv
if os.path.splitext( file )[ 1 ] = = '.flv' :
# 拼接成完整路径
filePath = os.path.join(root_dir, file )
# 载入视频
video = VideoFileClip(filePath)
# 添加到数组
L.append(video)
# 拼接视频
final_clip = concatenate_videoclips(L)
# 生成目标视频文件
final_clip.to_videofile(os.path.join(root_dir, r '{}.mp4' . format (title)), fps = 24 , remove_temp = False )
print ( '[视频合并完成]' + title)
else :
# 视频只有一段则直接打印下载完成
print ( '[视频合并完成]:' + title)
if __name__ = = '__main__' :
# 用户输入av号或者视频链接地址
print ( '*' * 30 + 'B站视频下载小助手' + '*' * 30 )
start = input ( '请输入您要下载的B站av号或者视频链接地址:' )
if start.isdigit() = = True : # 如果输入的是av号
# 获取cid的api, 传入aid即可
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + start
else :
# https://www.bilibili.com/video/av46958874/?spm_id_from=333.334.b_63686965665f7265636f6d6d656e64.16
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + re.search(r '/av(\d+)/*' , start).group( 1 )
# 视频质量
# <accept_format><![CDATA[flv,flv720,flv480,flv360]]></accept_format>
# <accept_description><![CDATA[高清 1080P,高清 720P,清晰 480P,流畅 360P]]></accept_description>
# <accept_quality><![CDATA[80,64,32,16]]></accept_quality>
quality = input ( '请输入您要下载视频的清晰度(1080p:80;720p:64;480p:32;360p:16)(填写80或64或32或16):' )
# 获取视频的cid,title
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
html = requests.get(start_url, headers = headers).json()
data = html[ 'data' ]
video_title = data[ "title" ].replace( " " , "_" )
cid_list = []
if '?p=' in start:
# 单独下载分P视频中的一集
p = re.search(r '\?p=(\d+)' ,start).group( 1 )
cid_list.append(data[ 'pages' ][ int (p) - 1 ])
else :
# 如果p不存在就是全集下载
cid_list = data[ 'pages' ]
# print(cid_list)
for item in cid_list:
cid = str (item[ 'cid' ])
title = item[ 'part' ]
if not title:
title = video_title
title = re.sub(r '[\/\\:*?"<>|]' , '', title) # 替换为空的
print ( '[下载视频的cid]:' + cid)
print ( '[下载视频的标题]:' + title)
page = str (item[ 'page' ])
start_url = start_url + "/?p=" + page
video_list = get_play_list(start_url, cid, quality)
start_time = time.time()
down_video(video_list, title, start_url, page)
combine_video(video_list, title)
# 如果是windows系统,下载完成后打开下载目录
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 当前目录作为下载目录
if (sys.platform.startswith( 'win' )):
os.startfile(currentVideoPath)
# 分P视频下载测试: https://www.bilibili.com/video/av19516333/
|
版本二:bilibili_video_download_v2.py
1.无加密API版,但是需要加入登录后cookie中的SESSDATA字段,才可下载720p及以上视频
2.如果想下载1080p+视频,需要带入B站大会员的cookie中的SESSDATA才行,普通用户的SESSDATA最多只能下载1080p视频;请定期更换代码31行cookie中的SESSDATA值。跟换方法为:浏览器登录B站,在开发者模式(按F12) --> application --> cookie中找到SESSDATA值替换即可,一个月的有效期
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
# !/usr/bin/python
# -*- coding:utf-8 -*-
# time: 2019/04/16--17:12
__author__ = 'Henry'
'''
项目: B站视频下载
版本2: 无加密API版,但是需要加入登录后cookie中的SESSDATA字段,才可下载720p及以上视频
API:
1.获取cid的api为 https://api.bilibili.com/x/web-interface/view?aid=47476691 aid后面为av号
2.下载链接api为 https://api.bilibili.com/x/player/playurl?avid=44743619&cid=78328965&qn=32 cid为上面获取到的 avid为输入的av号 qn为视频质量
注意:
但是此接口headers需要加上登录后'Cookie': 'SESSDATA=3c5d20cf%2C1556704080%2C7dcd8c41' (30天的有效期)(因为现在只有登录后才能看到720P以上视频了)
不然下载之后都是最低清晰度,哪怕选择了80也是只有480p的分辨率!!
20190422 - 增加多P视频单独下载其中一集的功能
'''
import requests, time, urllib.request, re
from moviepy.editor import *
import os, sys
import imageio
imageio.plugins.ffmpeg.download()
# 访问API地址
def get_play_list(aid, cid, quality):
url_api = 'https://api.bilibili.com/x/player/playurl?cid={}&avid={}&qn={}' . format (cid, aid, quality)
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36' ,
'Cookie' : 'SESSDATA=aa15d6af%2C1560734457%2Ccc8ca251' , # 登录B站后复制一下cookie中的SESSDATA字段,有效期1个月
'Host' : 'api.bilibili.com'
}
html = requests.get(url_api, headers = headers).json()
video_list = []
for i in html[ 'data' ][ 'durl' ]:
video_list.append(i[ 'url' ])
print (video_list)
return video_list
# 下载视频
'''
urllib.urlretrieve 的回调函数:
def callbackfunc(blocknum, blocksize, totalsize):
@blocknum: 已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 远程文件的大小
'''
def Schedule_cmd(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
f.write(percent_str.ljust( 8 , ' ' ) + '[' + s + ']' + speed_str)
f.flush()
# time.sleep(0.1)
f.write( '\r' )
def Schedule(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
print (percent_str.ljust( 6 , ' ' ) + '-' + speed_str)
f.flush()
time.sleep( 2 )
# print('\r')
# 字节bytes转化K\M\G
def format_size(bytes):
try :
bytes = float (bytes)
kb = bytes / 1024
except :
print ( "传入的字节格式不对" )
return "Error"
if kb > = 1024 :
M = kb / 1024
if M > = 1024 :
G = M / 1024
return "%.3fG" % (G)
else :
return "%.3fM" % (M)
else :
return "%.3fK" % (kb)
# 下载视频
def down_video(video_list, title, start_url, page):
num = 1
print ( '[正在下载P{}段视频,请稍等...]:' . format (page) + title)
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
for i in video_list:
opener = urllib.request.build_opener()
# 请求头
opener.addheaders = [
# ('Host', 'upos-hz-mirrorks3.acgvideo.com'), #注意修改host,不用也行
( 'User-Agent' , 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0) Gecko/20100101 Firefox/56.0' ),
( 'Accept' , '*/*' ),
( 'Accept-Language' , 'en-US,en;q=0.5' ),
( 'Accept-Encoding' , 'gzip, deflate, br' ),
( 'Range' , 'bytes=0-' ), # Range 的值要为 bytes=0- 才能下载完整视频
( 'Referer' , start_url), # 注意修改referer,必须要加的!
( 'Origin' , 'https://www.bilibili.com' ),
( 'Connection' , 'keep-alive' ),
]
urllib.request.install_opener(opener)
# 创建文件夹存放下载的视频
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
# 开始下载
if len (video_list) > 1 :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}-{}.flv' . format (title, num)),
reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
else :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}.flv' . format (title)),
reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
num + = 1
# 合并视频
def combine_video(video_list, title):
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
if len (video_list) > = 2 :
# 视频大于一段才要合并
print ( '[下载完成,正在合并视频...]:' + title)
# 定义一个数组
L = []
# 访问 video 文件夹 (假设视频都放在这里面)
root_dir = currentVideoPath
# 遍历所有文件
for file in sorted (os.listdir(root_dir), key = lambda x: int (x[x.rindex( "-" ) + 1 :x.rindex( "." )])):
# 如果后缀名为 .mp4/.flv
if os.path.splitext( file )[ 1 ] = = '.flv' :
# 拼接成完整路径
filePath = os.path.join(root_dir, file )
# 载入视频
video = VideoFileClip(filePath)
# 添加到数组
L.append(video)
# 拼接视频
final_clip = concatenate_videoclips(L)
# 生成目标视频文件
final_clip.to_videofile(os.path.join(root_dir, r '{}.mp4' . format (title)), fps = 24 , remove_temp = False )
print ( '[视频合并完成]' + title)
else :
# 视频只有一段则直接打印下载完成
print ( '[视频合并完成]:' + title)
if __name__ = = '__main__' :
# 用户输入av号或者视频链接地址
print ( '*' * 30 + 'B站视频下载小助手' + '*' * 30 )
start = input ( '请输入您要下载的B站av号或者视频链接地址:' )
if start.isdigit() = = True :
# 如果输入的是av号
# 获取cid的api, 传入aid即可
aid = start
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + aid
else :
# 如果输入的是url (eg: https://www.bilibili.com/video/av46958874/)
aid = re.search(r '/av(\d+)/*' , start).group( 1 )
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + aid
# qn参数就是视频清晰度
# 可选值:
# 116: 高清1080P60 (需要带入大会员的cookie中的SESSDATA才行,普通用户的SESSDATA最多只能下载1080p的视频)
# 112: 高清1080P+ (hdflv2) (需要大会员)
# 80: 高清1080P (flv)
# 74: 高清720P60 (需要大会员)
# 64: 高清720P (flv720)
# 32: 清晰480P (flv480)
# 16: 流畅360P (flv360)
print ( '请输入您要下载视频的清晰度(1080p60:116;1080p+:112;1080p:80;720p60:74;720p:64;480p:32;360p:16; **注意:1080p+,1080p60,720p60,720p都需要带入大会员的cookie中的SESSDATA才行,普通用户的SESSDATA最多只能下载1080p的视频):' )
quality = input ( '请填写116或112或80或74或64或32或16:' )
# 获取视频的cid,title
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
html = requests.get(start_url, headers = headers).json()
data = html[ 'data' ]
cid_list = []
if '?p=' in start:
# 单独下载分P视频中的一集
p = re.search(r '\?p=(\d+)' , start).group( 1 )
cid_list.append(data[ 'pages' ][ int (p) - 1 ])
else :
# 如果p不存在就是全集下载
cid_list = data[ 'pages' ]
# print(cid_list)
for item in cid_list:
cid = str (item[ 'cid' ])
title = item[ 'part' ]
title = re.sub(r '[\/\\:*?"<>|]' , '', title) # 替换为空的
print ( '[下载视频的cid]:' + cid)
print ( '[下载视频的标题]:' + title)
page = str (item[ 'page' ])
start_url = start_url + "/?p=" + page
video_list = get_play_list(aid, cid, quality)
start_time = time.time()
down_video(video_list, title, start_url, page)
combine_video(video_list, title)
# 如果是windows系统,下载完成后打开下载目录
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 当前目录作为下载目录
if (sys.platform.startswith( 'win' )):
os.startfile(currentVideoPath)
# 分P视频下载测试: https://www.bilibili.com/video/av19516333/
|
版本三: bilibili_video_download_v3.py
即版本二的升级版,为Threading多线程下载版本,下载速度大幅提升!
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
|
# !/usr/bin/python
# -*- coding:utf-8 -*-
# time: 2019/07/02--08:12
__author__ = 'Henry'
'''
项目: B站视频下载 - 多线程下载
版本1: 加密API版,不需要加入cookie,直接即可下载1080p视频
20190422 - 增加多P视频单独下载其中一集的功能
20190702 - 增加视频多线程下载 速度大幅提升
'''
import requests, time, hashlib, urllib.request, re, json
from moviepy.editor import *
import os, sys, threading
import imageio
imageio.plugins.ffmpeg.download()
# 访问API地址
def get_play_list(start_url, cid, quality):
entropy = 'rbMCKn@KuamXWlPMoJGsKcbiJKUfkPF_8dABscJntvqhRSETg'
appkey, sec = ' '.join([chr(ord(i) + 2) for i in entropy[::-1]]).split(' :')
params = 'appkey=%s&cid=%s&otype=json&qn=%s&quality=%s&type=' % (appkey, cid, quality, quality)
chksum = hashlib.md5(bytes(params + sec, 'utf8' )).hexdigest()
url_api = 'https://interface.bilibili.com/v2/playurl?%s&sign=%s' % (params, chksum)
headers = {
'Referer' : start_url, # 注意加上referer
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
# print(url_api)
html = requests.get(url_api, headers = headers).json()
# print(json.dumps(html))
video_list = []
for i in html[ 'durl' ]:
video_list.append(i[ 'url' ])
# print(video_list)
return video_list
# 下载视频
'''
urllib.urlretrieve 的回调函数:
def callbackfunc(blocknum, blocksize, totalsize):
@blocknum: 已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 远程文件的大小
'''
def Schedule_cmd(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
f.write(percent_str.ljust( 8 , ' ' ) + '[' + s + ']' + speed_str)
f.flush()
# time.sleep(0.1)
f.write( '\r' )
def Schedule(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
print (percent_str.ljust( 6 , ' ' ) + '-' + speed_str)
f.flush()
time.sleep( 2 )
# print('\r')
# 字节bytes转化K\M\G
def format_size(bytes):
try :
bytes = float (bytes)
kb = bytes / 1024
except :
print ( "传入的字节格式不对" )
return "Error"
if kb > = 1024 :
M = kb / 1024
if M > = 1024 :
G = M / 1024
return "%.3fG" % (G)
else :
return "%.3fM" % (M)
else :
return "%.3fK" % (kb)
# 下载视频
def down_video(video_list, title, start_url, page):
num = 1
print ( '[正在下载P{}段视频,请稍等...]:' . format (page) + title)
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
for i in video_list:
opener = urllib.request.build_opener()
# 请求头
opener.addheaders = [
# ('Host', 'upos-hz-mirrorks3.acgvideo.com'), #注意修改host,不用也行
( 'User-Agent' , 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0) Gecko/20100101 Firefox/56.0' ),
( 'Accept' , '*/*' ),
( 'Accept-Language' , 'en-US,en;q=0.5' ),
( 'Accept-Encoding' , 'gzip, deflate, br' ),
( 'Range' , 'bytes=0-' ), # Range 的值要为 bytes=0- 才能下载完整视频
( 'Referer' , start_url), # 注意修改referer,必须要加的!
( 'Origin' , 'https://www.bilibili.com' ),
( 'Connection' , 'keep-alive' ),
]
urllib.request.install_opener(opener)
# 创建文件夹存放下载的视频
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
# 开始下载
if len (video_list) > 1 :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}-{}.flv' . format (title, num)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
else :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}.flv' . format (title)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
num + = 1
# 合并视频(20190802新版)
def combine_video(title_list):
video_path = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 下载目录
for title in title_list:
current_video_path = os.path.join(video_path ,title)
if len (os.listdir(current_video_path)) > = 2 :
# 视频大于一段才要合并
print ( '[下载完成,正在合并视频...]:' + title)
# 定义一个数组
L = []
# 遍历所有文件
for file in sorted (os.listdir(current_video_path), key = lambda x: int (x[x.rindex( "-" ) + 1 :x.rindex( "." )])):
# 如果后缀名为 .mp4/.flv
if os.path.splitext( file )[ 1 ] = = '.flv' :
# 拼接成完整路径
filePath = os.path.join(current_video_path, file )
# 载入视频
video = VideoFileClip(filePath)
# 添加到数组
L.append(video)
# 拼接视频
final_clip = concatenate_videoclips(L)
# 生成目标视频文件
final_clip.to_videofile(os.path.join(current_video_path, r '{}.mp4' . format (title)), fps = 24 , remove_temp = False )
print ( '[视频合并完成]' + title)
else :
# 视频只有一段则直接打印下载完成
print ( '[视频合并完成]:' + title)
if __name__ = = '__main__' :
start_time = time.time()
# 用户输入av号或者视频链接地址
print ( '*' * 30 + 'B站视频下载小助手' + '*' * 30 )
start = input ( '请输入您要下载的B站av号或者视频链接地址:' )
if start.isdigit() = = True : # 如果输入的是av号
# 获取cid的api, 传入aid即可
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + start
else :
# https://www.bilibili.com/video/av46958874/?spm_id_from=333.334.b_63686965665f7265636f6d6d656e64.16
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + re.search(r '/av(\d+)/*' , start).group( 1 )
# 视频质量
# <accept_format><![CDATA[flv,flv720,flv480,flv360]]></accept_format>
# <accept_description><![CDATA[高清 1080P,高清 720P,清晰 480P,流畅 360P]]></accept_description>
# <accept_quality><![CDATA[80,64,32,16]]></accept_quality>
quality = input ( '请输入您要下载视频的清晰度(1080p:80;720p:64;480p:32;360p:16)(填写80或64或32或16):' )
# 获取视频的cid,title
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
html = requests.get(start_url, headers = headers).json()
data = html[ 'data' ]
cid_list = []
if '?p=' in start:
# 单独下载分P视频中的一集
p = re.search(r '\?p=(\d+)' ,start).group( 1 )
cid_list.append(data[ 'pages' ][ int (p) - 1 ])
else :
# 如果p不存在就是全集下载
cid_list = data[ 'pages' ]
# print(cid_list)
# 创建线程池
threadpool = []
title_list = []
for item in cid_list:
cid = str (item[ 'cid' ])
title = item[ 'part' ]
title = re.sub(r '[\/\\:*?"<>|]' , '', title) # 替换为空的
print ( '[下载视频的cid]:' + cid)
print ( '[下载视频的标题]:' + title)
title_list.append(title)
page = str (item[ 'page' ])
start_url = start_url + "/?p=" + page
video_list = get_play_list(start_url, cid, quality)
start_time = time.time()
# down_video(video_list, title, start_url, page)
# 定义线程
th = threading.Thread(target = down_video, args = (video_list, title, start_url, page))
# 将线程加入线程池
threadpool.append(th)
# 开始线程
for th in threadpool:
th.start()
# 等待所有线程运行完毕
for th in threadpool:
th.join()
# 最后合并视频
print (title_list)
combine_video(title_list)
end_time = time.time() # 结束时间
print ( '下载总耗时%.2f秒,约%.2f分钟' % (end_time - start_time, int (end_time - start_time) / 60 ))
# 如果是windows系统,下载完成后打开下载目录
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 当前目录作为下载目录
if (sys.platform.startswith( 'win' )):
os.startfile(currentVideoPath)
# 分P视频下载测试: https://www.bilibili.com/video/av19516333/
# 下载总耗时14.21秒,约0.23分钟
|
版本四: GUI版本 - bilibili_video_download-GUI.py
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
|
# !/usr/bin/python
# -*- coding:utf-8 -*-
# time: 2019/07/02--08:12
__author__ = 'Henry'
'''
项目: B站视频下载 - GUI版本
版本1: 加密API版,不需要加入cookie,直接即可下载1080p视频
20190422 - 增加多P视频单独下载其中一集的功能
20190702 - 增加视频多线程下载 速度大幅提升
20190711 - 增加GUI版本,可视化界面,操作更加友好
'''
import requests, time, hashlib, urllib.request, re, json
import imageio
imageio.plugins.ffmpeg.download()
from moviepy.editor import *
import os, sys, threading
from tkinter import *
from tkinter import ttk
from tkinter import StringVar
root = Tk()
start_time = time.time()
# 将输出重定向到表格
def print (theText):
msgbox.insert(END,theText + '\n' )
# 访问API地址
def get_play_list(start_url, cid, quality):
entropy = 'rbMCKn@KuamXWlPMoJGsKcbiJKUfkPF_8dABscJntvqhRSETg'
appkey, sec = ' '.join([chr(ord(i) + 2) for i in entropy[::-1]]).split(' :')
params = 'appkey=%s&cid=%s&otype=json&qn=%s&quality=%s&type=' % (appkey, cid, quality, quality)
chksum = hashlib.md5(bytes(params + sec, 'utf8' )).hexdigest()
url_api = 'https://interface.bilibili.com/v2/playurl?%s&sign=%s' % (params, chksum)
headers = {
'Referer' : start_url, # 注意加上referer
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
# print(url_api)
html = requests.get(url_api, headers = headers).json()
# print(json.dumps(html))
video_list = []
for i in html[ 'durl' ]:
video_list.append(i[ 'url' ])
# print(video_list)
return video_list
# 下载视频
'''
urllib.urlretrieve 的回调函数:
def callbackfunc(blocknum, blocksize, totalsize):
@blocknum: 已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 远程文件的大小
'''
def Schedule_cmd(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
download.coords(fill_line1,( 0 , 0 ,pervent * 465 , 23 ))
root.update()
pct. set (percent_str)
def Schedule(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
print (percent_str.ljust( 6 , ' ' ) + '-' + speed_str)
f.flush()
time.sleep( 2 )
# print('\r')
# 字节bytes转化K\M\G
def format_size(bytes):
try :
bytes = float (bytes)
kb = bytes / 1024
except :
print ( "传入的字节格式不对" )
return "Error"
if kb > = 1024 :
M = kb / 1024
if M > = 1024 :
G = M / 1024
return "%.3fG" % (G)
else :
return "%.3fM" % (M)
else :
return "%.3fK" % (kb)
# 下载视频
def down_video(video_list, title, start_url, page):
num = 1
print ( '[正在下载P{}段视频,请稍等...]:' . format (page) + title)
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
for i in video_list:
opener = urllib.request.build_opener()
# 请求头
opener.addheaders = [
# ('Host', 'upos-hz-mirrorks3.acgvideo.com'), #注意修改host,不用也行
( 'User-Agent' , 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0) Gecko/20100101 Firefox/56.0' ),
( 'Accept' , '*/*' ),
( 'Accept-Language' , 'en-US,en;q=0.5' ),
( 'Accept-Encoding' , 'gzip, deflate, br' ),
( 'Range' , 'bytes=0-' ), # Range 的值要为 bytes=0- 才能下载完整视频
( 'Referer' , start_url), # 注意修改referer,必须要加的!
( 'Origin' , 'https://www.bilibili.com' ),
( 'Connection' , 'keep-alive' ),
]
urllib.request.install_opener(opener)
# 创建文件夹存放下载的视频
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
# 开始下载
if len (video_list) > 1 :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}-{}.flv' . format (title, num)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
else :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}.flv' . format (title)),reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
num + = 1
# 合并视频(20190802新版)
def combine_video(title_list):
video_path = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 下载目录
for title in title_list:
current_video_path = os.path.join(video_path ,title)
if len (os.listdir(current_video_path)) > = 2 :
# 视频大于一段才要合并
print ( '[下载完成,正在合并视频...]:' + title)
# 定义一个数组
L = []
# 遍历所有文件
for file in sorted (os.listdir(current_video_path), key = lambda x: int (x[x.rindex( "-" ) + 1 :x.rindex( "." )])):
# 如果后缀名为 .mp4/.flv
if os.path.splitext( file )[ 1 ] = = '.flv' :
# 拼接成完整路径
filePath = os.path.join(current_video_path, file )
# 载入视频
video = VideoFileClip(filePath)
# 添加到数组
L.append(video)
# 拼接视频
final_clip = concatenate_videoclips(L)
# 生成目标视频文件
final_clip.to_videofile(os.path.join(current_video_path, r '{}.mp4' . format (title)), fps = 24 , remove_temp = False )
print ( '[视频合并完成]' + title)
else :
# 视频只有一段则直接打印下载完成
print ( '[视频合并完成]:' + title)
def do_prepare(inputStart,inputQuality):
# 清空进度条
download.coords(fill_line1,( 0 , 0 , 0 , 23 ))
pct. set ( '0.00%' )
root.update()
# 清空文本栏
msgbox.delete( '1.0' , 'end' )
start_time = time.time()
# 用户输入av号或者视频链接地址
print ( '*' * 30 + 'B站视频下载小助手' + '*' * 30 )
start = inputStart
if start.isdigit() = = True : # 如果输入的是av号
# 获取cid的api, 传入aid即可
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + start
else :
# https://www.bilibili.com/video/av46958874/?spm_id_from=333.334.b_63686965665f7265636f6d6d656e64.16
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + re.search(r '/av(\d+)/*' , start).group( 1 )
# 视频质量
# <accept_format><![CDATA[flv,flv720,flv480,flv360]]></accept_format>
# <accept_description><![CDATA[高清 1080P,高清 720P,清晰 480P,流畅 360P]]></accept_description>
# <accept_quality><![CDATA[80,64,32,16]]></accept_quality>
quality = inputQuality
# 获取视频的cid,title
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
html = requests.get(start_url, headers = headers).json()
data = html[ 'data' ]
cid_list = []
if '?p=' in start:
# 单独下载分P视频中的一集
p = re.search(r '\?p=(\d+)' ,start).group( 1 )
cid_list.append(data[ 'pages' ][ int (p) - 1 ])
else :
# 如果p不存在就是全集下载
cid_list = data[ 'pages' ]
# print(cid_list)
# 创建线程池
threadpool = []
title_list = []
for item in cid_list:
cid = str (item[ 'cid' ])
title = item[ 'part' ]
title = re.sub(r '[\/\\:*?"<>|]' , '', title) # 替换为空的
print ( '[下载视频的cid]:' + cid)
print ( '[下载视频的标题]:' + title)
title_list.append(title)
page = str (item[ 'page' ])
start_url = start_url + "/?p=" + page
video_list = get_play_list(start_url, cid, quality)
start_time = time.time()
# down_video(video_list, title, start_url, page)
# 定义线程
th = threading.Thread(target = down_video, args = (video_list, title, start_url, page))
# 将线程加入线程池
threadpool.append(th)
# 开始线程
for th in threadpool:
th.start()
# 等待所有线程运行完毕
for th in threadpool:
th.join()
# 最后合并视频
combine_video(title_list)
end_time = time.time() # 结束时间
print ( '下载总耗时%.2f秒,约%.2f分钟' % (end_time - start_time, int (end_time - start_time) / 60 ))
# 如果是windows系统,下载完成后打开下载目录
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 当前目录作为下载目录
if (sys.platform.startswith( 'win' )):
os.startfile(currentVideoPath)
def thread_it(func, * args):
'''将函数打包进线程'''
# 创建
t = threading.Thread(target = func, args = args)
# 守护 !!!
t.setDaemon( True )
# 启动
t.start()
if __name__ = = "__main__" :
# 设置标题
root.title( 'B站视频下载小助手-GUI' )
# 设置ico
root.iconbitmap( './Pic/favicon.ico' )
# 设置Logo
photo = PhotoImage( file = './Pic/logo.png' )
logo = Label(root,image = photo)
logo.pack()
# 各项输入栏和选择框
inputStart = Entry(root,bd = 4 ,width = 600 )
labelStart = Label(root,text = "请输入您要下载的B站av号或者视频链接地址:" ) # 地址输入
labelStart.pack(anchor = "w" )
inputStart.pack()
labelQual = Label(root,text = "请选择您要下载视频的清晰度" ) # 清晰度选择
labelQual.pack(anchor = "w" )
inputQual = ttk.Combobox(root,state = "readonly" )
# 可供选择的表
inputQual[ 'value' ] = ( '1080P' , '720p' , '480p' , '360p' )
# 对应的转换字典
keyTrans = dict ()
keyTrans[ '1080P' ] = '80'
keyTrans[ '720p' ] = '64'
keyTrans[ '480p' ] = '32'
keyTrans[ '360p' ] = '16'
# 初始值为720p
inputQual.current( 1 )
inputQual.pack()
confirm = Button(root,text = "开始下载" ,command = lambda :thread_it(do_prepare,inputStart.get(), keyTrans[inputQual.get()] ))
msgbox = Text(root)
msgbox.insert( '1.0' , "对于单P视频:直接传入B站av号或者视频链接地址\n(eg: 49842011或者https://www.bilibili.com/video/av49842011)\n对于多P视频:\n1.下载全集:直接传入B站av号或者视频链接地址\n(eg: 49842011或者https://www.bilibili.com/video/av49842011)\n2.下载其中一集:传入那一集的视频链接地址\n(eg: https://www.bilibili.com/video/av19516333/?p=2)" )
msgbox.pack()
download = Canvas(root,width = 465 ,height = 23 ,bg = "white" )
# 进度条的设置
labelDownload = Label(root,text = "下载进度" )
labelDownload.pack(anchor = "w" )
download.pack()
fill_line1 = download.create_rectangle( 0 , 0 , 0 , 23 , width = 0 , fill = "green" )
pct = StringVar()
pct. set ( '0.0%' )
pctLabel = Label(root,textvariable = pct)
pctLabel.pack()
root.geometry( "600x800" )
confirm.pack()
# GUI主循环
root.mainloop()
|
版本五: bilibili_video_download_bangumi.py
在版本一,三基础上增加下载B站番剧视频(eg: https://www.bilibili.com/bangumi/play/ep269835)
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
# !/usr/bin/python
# -*- coding:utf-8 -*-
# time: 2019/07/21--20:12
__author__ = 'Henry'
'''
项目: B站动漫番剧(bangumi)下载
版本2: 无加密API版,但是需要加入登录后cookie中的SESSDATA字段,才可下载720p及以上视频
API:
1.获取cid的api为 https://api.bilibili.com/x/web-interface/view?aid=47476691 aid后面为av号
2.下载链接api为 https://api.bilibili.com/x/player/playurl?avid=44743619&cid=78328965&qn=32 cid为上面获取到的 avid为输入的av号 qn为视频质量
注意:
但是此接口headers需要加上登录后'Cookie': 'SESSDATA=3c5d20cf%2C1556704080%2C7dcd8c41' (30天的有效期)(因为现在只有登录后才能看到720P以上视频了)
不然下载之后都是最低清晰度,哪怕选择了80也是只有480p的分辨率!!
'''
import requests, time, urllib.request, re
from moviepy.editor import *
import os, sys, threading, json
import imageio
imageio.plugins.ffmpeg.download()
# 访问API地址
def get_play_list(aid, cid, quality):
url_api = 'https://api.bilibili.com/x/player/playurl?cid={}&avid={}&qn={}' . format (cid, aid, quality)
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36' ,
'Cookie' : 'SESSDATA=75a75cf2%2C1564669876%2Cb7c7b171' , # 登录B站后复制一下cookie中的SESSDATA字段,有效期1个月
'Host' : 'api.bilibili.com'
}
html = requests.get(url_api, headers = headers).json()
# print(html)
# 当下载会员视频时,如果cookie中传入的不是大会员的SESSDATA时就会返回: {'code': -404, 'message': '啥都木有', 'ttl': 1, 'data': None}
if html[ 'code' ] ! = 0 :
print ( '注意!当前集数为B站大会员专享,若想下载,Cookie中请传入大会员的SESSDATA' )
return 'NoVIP'
video_list = []
for i in html[ 'data' ][ 'durl' ]:
video_list.append(i[ 'url' ])
print (video_list)
return video_list
# 下载视频
'''
urllib.urlretrieve 的回调函数:
def callbackfunc(blocknum, blocksize, totalsize):
@blocknum: 已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 远程文件的大小
'''
def Schedule_cmd(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
f.write(percent_str.ljust( 8 , ' ' ) + '[' + s + ']' + speed_str)
f.flush()
# time.sleep(0.1)
f.write( '\r' )
def Schedule(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
# speed_str = " Speed: %.2f" % speed
speed_str = " Speed: %s" % format_size(speed)
recv_size = blocknum * blocksize
# 设置下载进度条
f = sys.stdout
pervent = recv_size / totalsize
percent_str = "%.2f%%" % (pervent * 100 )
n = round (pervent * 50 )
s = ( '#' * n).ljust( 50 , '-' )
print (percent_str.ljust( 6 , ' ' ) + '-' + speed_str)
f.flush()
time.sleep( 2 )
# print('\r')
# 字节bytes转化K\M\G
def format_size(bytes):
try :
bytes = float (bytes)
kb = bytes / 1024
except :
print ( "传入的字节格式不对" )
return "Error"
if kb > = 1024 :
M = kb / 1024
if M > = 1024 :
G = M / 1024
return "%.3fG" % (G)
else :
return "%.3fM" % (M)
else :
return "%.3fK" % (kb)
# 下载视频
def down_video(video_list, title, start_url, page):
num = 1
print ( '[正在下载第{}话视频,请稍等...]:' . format (page) + title)
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' , title) # 当前目录作为下载目录
for i in video_list:
opener = urllib.request.build_opener()
# 请求头
opener.addheaders = [
# ('Host', 'upos-hz-mirrorks3.acgvideo.com'), #注意修改host,不用也行
( 'User-Agent' , 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0) Gecko/20100101 Firefox/56.0' ),
( 'Accept' , '*/*' ),
( 'Accept-Language' , 'en-US,en;q=0.5' ),
( 'Accept-Encoding' , 'gzip, deflate, br' ),
( 'Range' , 'bytes=0-' ), # Range 的值要为 bytes=0- 才能下载完整视频
( 'Referer' , start_url), # 注意修改referer,必须要加的!
( 'Origin' , 'https://www.bilibili.com' ),
( 'Connection' , 'keep-alive' ),
]
urllib.request.install_opener(opener)
# 创建文件夹存放下载的视频
if not os.path.exists(currentVideoPath):
os.makedirs(currentVideoPath)
# 开始下载
if len (video_list) > 1 :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}-{}.flv' . format (title, num)),
reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
else :
urllib.request.urlretrieve(url = i, filename = os.path.join(currentVideoPath, r '{}.flv' . format (title)),
reporthook = Schedule_cmd) # 写成mp4也行 title + '-' + num + '.flv'
num + = 1
# 合并视频(20190802新版)
def combine_video(title_list):
video_path = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 下载目录
for title in title_list:
current_video_path = os.path.join(video_path ,title)
if len (os.listdir(current_video_path)) > = 2 :
# 视频大于一段才要合并
print ( '[下载完成,正在合并视频...]:' + title)
# 定义一个数组
L = []
# 遍历所有文件
for file in sorted (os.listdir(current_video_path), key = lambda x: int (x[x.rindex( "-" ) + 1 :x.rindex( "." )])):
# 如果后缀名为 .mp4/.flv
if os.path.splitext( file )[ 1 ] = = '.flv' :
# 拼接成完整路径
filePath = os.path.join(current_video_path, file )
# 载入视频
video = VideoFileClip(filePath)
# 添加到数组
L.append(video)
# 拼接视频
final_clip = concatenate_videoclips(L)
# 生成目标视频文件
final_clip.to_videofile(os.path.join(current_video_path, r '{}.mp4' . format (title)), fps = 24 , remove_temp = False )
print ( '[视频合并完成]' + title)
else :
# 视频只有一段则直接打印下载完成
print ( '[视频合并完成]:' + title)
if __name__ = = '__main__' :
start_time = time.time()
# 用户输入番剧完整链接地址
# 1. https://www.bilibili.com/bangumi/play/ep267692 (用带ep链接)
# 2. https://www.bilibili.com/bangumi/play/ss26878 (不要用这个ss链接,epinfo的aid会变成'-1')
print ( '*' * 30 + 'B站番剧视频下载小助手' + '*' * 30 )
print ( '[提示]: 1.如果您想下载720P60,1080p+,1080p60质量的视频,请将35行代码中的SESSDATA改成你登录大会员后得到的SESSDATA,普通用户的SESSDATA最多只能下载1080p的视频' )
print ( ' 2.若发现下载的视频质量在720p以下,请将35行代码中的SESSDATA改成你登录后得到的SESSDATA(有效期一个月),而失效的SESSDATA就只能下载480p的视频' )
start = input ( '请输入您要下载的B站番剧的完整链接地址(例如:https://www.bilibili.com/bangumi/play/ep267692):' )
ep_url = start
headers = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
html = requests.get(ep_url,headers = headers).text
ep_info = re.search(r 'INITIAL_STATE__=(.*?"]});' , html).group( 1 )
# print(ep_info)
ep_info = json.loads(ep_info)
# print('您将要下载的番剧名为:' + ep_info['mediaInfo']['title']) # 字段格式太不统一了
y = input ( '请输入1或2 - 1.只下载当前一集 2.下载此番剧的全集:' )
# 1.如果只下载当前ep
id_list = []
if y = = '1' :
try :
id_list.append([ep_info[ 'epInfo' ][ 'aid' ], ep_info[ 'epInfo' ][ 'cid' ],
ep_info[ 'epInfo' ][ 'titleFormat' ] + ' ' + ep_info[ 'epInfo' ][ 'longTitle' ]])
except :
id_list.append([ep_info[ 'epInfo' ][ 'aid' ], ep_info[ 'epInfo' ][ 'cid' ],
'第' + str (ep_info[ 'epInfo' ][ 'index' ]) + '话 ' + ep_info[ 'epInfo' ][ 'index_title' ]])
# 2.下载此番剧全部ep
else :
for i in ep_info[ 'epList' ]:
# if i['badge'] == '': # 当badge字段为'会员'时,接口返回404
try :
id_list.append([i[ 'aid' ], i[ 'cid' ],
i[ 'titleFormat' ] + ' ' + i[ 'longTitle' ]])
except :
id_list.append([i[ 'aid' ], i[ 'cid' ], '第' + str (i[ 'index' ]) + '话 ' + i[ 'index_title' ]])
# qn参数就是视频清晰度
# 可选值:
# 116: 高清1080P60 (需要带入大会员的cookie中的SESSDATA才行,普通用户的SESSDATA最多只能下载1080p的视频,不带入SESSDATA就只能下载480p的)
# 112: 高清1080P+ (hdflv2) (需要大会员)
# 80: 高清1080P (flv)
# 74: 高清720P60 (需要大会员)
# 64: 高清720P (flv720)
# 32: 清晰480P (flv480)
# 16: 流畅360P (flv360)
print ( '请输入您要下载视频的清晰度(1080p60:116;1080p+:112;1080p:80;720p60:74;720p:64;480p:32;360p:16; **注意:1080p+,1080p60,720p60都需要带入大会员的cookie中的SESSDATA才行,普通用户的SESSDATA最多只能下载1080p的视频):' )
quality = input ( '请输入116或112或80或74或64或32或16:' )
threadpool = []
title_list = []
page = 1
print (id_list)
for item in id_list:
aid = str (item[ 0 ])
cid = str (item[ 1 ])
title = item[ 2 ]
title = re.sub(r '[\/\\:*?"<>|]' , '', title) # 替换为空的
print ( '[下载番剧标题]:' + title)
title_list.append(title)
start_url = ep_url
video_list = get_play_list(aid, cid, quality)
start_time = time.time()
# down_video(video_list, title, start_url, page)
# 定义线程
if video_list ! = 'NoVIP' :
th = threading.Thread(target = down_video, args = (video_list, title, start_url, page))
# 将线程加入线程池
threadpool.append(th)
page + = 1
# 开始线程
for th in threadpool:
th.start()
# 等待所有线程运行完毕
for th in threadpool:
th.join()
# 最后合并视频
print (title_list)
combine_video(title_list)
end_time = time.time() # 结束时间
print ( '下载总耗时%.2f秒,约%.2f分钟' % (end_time - start_time, int (end_time - start_time) / 60 ))
# 如果是windows系统,下载完成后打开下载目录
currentVideoPath = os.path.join(sys.path[ 0 ], 'bilibili_video' ) # 当前目录作为下载目录
if (sys.platform.startswith( 'win' )):
os.startfile(currentVideoPath)
# 番剧视频下载测试: https://www.bilibili.com/bangumi/play/ep269828
|
以上就是python b站视频下载的五种版本的详细内容,更多关于python b站视频下载的资料请关注服务器之家其它相关文章!
原文链接:https://github.com/Henryhaohao/Bilibili_video_download