forked from lanbinshijie/bili2text
-
Notifications
You must be signed in to change notification settings - Fork 0
/
downBili.py
206 lines (180 loc) · 7.42 KB
/
downBili.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
# 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
def bv2av(bv):
table = 'fZodR9XQDSUm21yCkr6zBqiveYah8bt4xsWpHnJE7jL5VG3guMTKNPAwcF'
tr = {}
for i in range(58):
tr[table[i]] = i
s = [11,10,3,8,4,6]
xor = 177451812
add = 8728348608
r=0
for i in range(6):
r+=tr[bv[s[i]]]*58**i
return (r-add)^xor
def Schedule_cmd(blocknum, blocksize, totalsize):
pass
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)
start_time = 0
def download_video(avnum=None, quality_=16) -> str:
global start_time
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 not avnum else avnum
start_url = 'https://api.bilibili.com/x/web-interface/view?aid=' + start
# 视频质量
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):') if quality_ != 16 else quality_
# 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']
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)
print('[下载完成]')
return video_title