FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
python-spider/douyin.py at master · jackcoolpython/python-spider · GitHub
jackcoolpython
python-spider
Repository navigation
Code
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
python-spider
/
douyin.py
Copy path
More file actions
More file actions
Latest commit
History
History
History
134 lines (122 loc) · 4.03 KB
Breadcrumbs
python-spider
/
douyin.py
Copy path
File metadata and controls
134 lines (122 loc) · 4.03 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
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
# -*- coding:utf-8 -*-
from
bs4
import
BeautifulSoup
from
contextlib
import
closing
import
requests
,
json
,
time
,
re
,
os
,
sys
,
time
class
DouYin
(
object
):
def
__init__
(
self
):
"""
抖音App视频下载
"""
#SSL认证
pass
def
get_video_urls
(
self
,
user_id
):
"""
获得视频播放地址
Parameters:
nickname：查询的用户名
Returns:
video_names: 视频名字列表
video_urls: 视频链接列表
aweme_count: 视频数量
"""
video_names
=
[]
video_urls
=
[]
unique_id
=
''
while
unique_id
!=
user_id
:
search_url
=
'https://api.amemv.com/aweme/v1/discover/search/?cursor=0&keyword=%s&count=10&type=1&retry_type=no_retry&iid=17900846586&device_id=34692364855&ac=wifi&channel=xiaomi&aid=1128&app_name=aweme&version_code=162&version_name=1.6.2&device_platform=android&ssmix=a&device_type=MI+5&device_brand=Xiaomi&os_api=24&os_version=7.0&uuid=861945034132187&openudid=dc451556fc0eeadb&manifest_version_code=162&resolution=1080*1920&dpi=480&update_version_code=1622'
%
user_id
req
=
requests
.
get
(
url
=
search_url
,
verify
=
False
)
html
=
json
.
loads
(
req
.
text
)
aweme_count
=
html
[
'user_list'
][
0
][
'user_info'
][
'aweme_count'
]
uid
=
html
[
'user_list'
][
0
][
'user_info'
][
'uid'
]
nickname
=
html
[
'user_list'
][
0
][
'user_info'
][
'nickname'
]
unique_id
=
html
[
'user_list'
][
0
][
'user_info'
][
'unique_id'
]
user_url
=
'https://www.douyin.com/aweme/v1/aweme/post/?user_id=%s&max_cursor=0&count=%s'
%
(
uid
,
aweme_count
)
req
=
requests
.
get
(
url
=
user_url
,
verify
=
False
)
html
=
json
.
loads
(
req
.
text
)
i
=
1
for
each
in
html
[
'aweme_list'
]:
share_desc
=
each
[
'share_info'
][
'share_desc'
]
if
'抖音-原创音乐短视频社区'
==
share_desc
:
video_names
.
append
(
str
(
i
)
+
'.mp4'
)
i
+=
1
else
:
video_names
.
append
(
share_desc
+
'.mp4'
)
video_urls
.
append
(
each
[
'share_info'
][
'share_url'
])
return
video_names
,
video_urls
,
nickname
def
get_download_url
(
self
,
video_url
):
"""
获得视频播放地址
Parameters:
video_url：视频播放地址
Returns:
download_url: 视频下载地址
"""
req
=
requests
.
get
(
url
=
video_url
,
verify
=
False
)
bf
=
BeautifulSoup
(
req
.
text
,
'lxml'
)
script
=
bf
.
find_all
(
'script'
)[
-
1
]
video_url_js
=
re
.
findall
(
'var data = \[(.+)\];'
,
str
(
script
))[
0
]
video_html
=
json
.
loads
(
video_url_js
)
download_url
=
video_html
[
'video'
][
'play_addr'
][
'url_list'
][
0
]
return
download_url
def
video_downloader
(
self
,
video_url
,
video_name
):
"""
视频下载
Parameters:
None
Returns:
None
"""
size
=
0
with
closing
(
requests
.
get
(
video_url
,
stream
=
True
,
verify
=
False
))
as
response
:
chunk_size
=
1024
content_size
=
int
(
response
.
headers
[
'content-length'
])
if
response
.
status_code
==
200
:
sys
.
stdout
.
write
(
' [文件大小]:%0.2f MB
\n
'
%
(
content_size
/
chunk_size
/
1024
))
with
open
(
video_name
,
"wb"
)
as
file
:
for
data
in
response
.
iter_content
(
chunk_size
=
chunk_size
):
file
.
write
(
data
)
size
+=
len
(
data
)
file
.
flush
()
sys
.
stdout
.
write
(
' [下载进度]:%.2f%%'
%
float
(
size
/
content_size
*
100
))
sys
.
stdout
.
flush
()
time
.
sleep
(
1
)
def
run
(
self
):
"""
运行函数
Parameters:
None
Returns:
None
"""
self
.
hello
()
# user_id = input('请输入ID(例如13978338):')
user_id
=
'sm666888'
video_names
,
video_urls
,
nickname
=
self
.
get_video_urls
(
user_id
)
if
nickname
not
in
os
.
listdir
():
os
.
mkdir
(
nickname
)
sys
.
stdout
.
write
(
'视频下载中:
\n
'
)
for
num
in
range
(
len
(
video_urls
)):
print
(
' %s
\n
'
%
video_urls
[
num
])
video_url
=
self
.
get_download_url
(
video_urls
[
num
])
if
'
\\
'
in
video_names
[
num
]:
video_name
=
video_names
[
num
].
replace
(
'
\\
'
,
''
)
elif
'/'
in
video_names
[
num
]:
video_name
=
video_names
[
num
].
replace
(
'/'
,
''
)
else
:
video_name
=
video_names
[
num
]
self
.
video_downloader
(
video_url
,
os
.
path
.
join
(
nickname
,
video_name
))
print
(
''
)
def
hello
(
self
):
"""
打印欢迎界面
Parameters:
None
Returns:
None
"""
print
(
'*'
*
100
)
print
(
'
\t
\t
\t
\t
抖音App视频下载小助手'
)
print
(
'*'
*
100
)
if
__name__
==
'__main__'
:
douyin
=
DouYin
()
douyin
.
run
()
Back
|
FazBrowse Home
|
New Git URL