FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
python_scripts/utils.py at patch-1 · ApacheAde/python_scripts · GitHub
ApacheAde
python_scripts
Repository navigation
Code
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
python_scripts
/
utils.py
Copy path
More file actions
More file actions
Latest commit
History
History
History
128 lines (102 loc) · 3.21 KB
Breadcrumbs
python_scripts
/
utils.py
Copy path
File metadata and controls
128 lines (102 loc) · 3.21 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
import
json
import
matplotlib
.
pyplot
as
plt
from
imageio
import
imread
from
wordcloud
import
WordCloud
import
jieba
.
analyse
print
(
__file__
)
def
word_segment
(
text
):
# 分词处理
jieba
.
analyse
.
set_stop_words
(
"./stopwords.txt"
)
words
=
jieba
.
cut
(
text
)
for
w
in
words
:
print
(
w
)
from
collections
import
Counter
result
=
Counter
(
words
).
most_common
(
20
)
tags
=
jieba
.
analyse
.
extract_tags
(
text
,
topK
=
20
)
# yield " ".join(tags)
if
__name__
==
'__main__'
:
#text = open("text.txt", encoding="utf-8").read()
data
=
json
.
load
(
open
(
'title.json'
))
text
=
""
.
join
([
d
.
get
(
"标题"
)
for
d
in
data
])
print
(
text
)
# word_segment(text)
from
wordcloud
import
ImageColorGenerator
back_img
=
imread
(
"./wuhan.jpeg"
)
img_colors
=
ImageColorGenerator
(
back_img
)
jieba
.
analyse
.
set_stop_words
(
'./stopwords.txt'
)
# 设置止词列表
tags
=
jieba
.
analyse
.
extract_tags
(
text
,
1000
,
withWeight
=
True
)
data
=
{
item
[
0
]:
item
[
1
]
for
item
in
tags
}
word_cloud
=
WordCloud
(
font_path
=
"/Library/Fonts/SimHei.ttf"
,
background_color
=
"white"
,
max_words
=
1000
,
max_font_size
=
100
,
width
=
1920
,
mask
=
back_img
,
height
=
1080
).
generate_from_frequencies
(
data
)
word_cloud
.
recolor
(
color_func
=
img_colors
)
# 替换默认的字体颜色
plt
.
figure
()
# 创建一个图形实例
plt
.
imshow
(
word_cloud
,
interpolation
=
'bilinear'
)
plt
.
axis
(
"off"
)
# 不显示坐标尺寸
plt
.
savefig
(
'./wordcloud.jpg'
,
dpi
=
600
)
plt
.
show
()
pass
def
word_cloud
(
texts
):
"""
根据文本生成词云图片
"""
data
=
""
.
join
(
text
for
text
in
texts
)
mask_img
=
imread
(
'./python-lo'
,
flatten
=
True
)
wordcloud
=
WordCloud
(
font_path
=
'/Library/Fonts//华文黑体.ttf'
,
background_color
=
'white'
,
mask
=
mask_img
).
generate
(
data
)
plt
.
imshow
(
wordcloud
)
plt
.
axis
(
'off'
)
plt
.
savefig
(
'./wordcloud.jpg'
,
dpi
=
600
)
# 分词处理
jieba
.
analyse
.
set_stop_words
(
"./stopwords.txt"
)
words
=
jieba
.
cut
(
text
)
from
collections
import
Counter
result
=
Counter
(
words
).
most_common
(
20
)
print
(
result
)
tags
=
jieba
.
analyse
.
extract_tags
(
text
,
topK
=
20
)
print
(
tags
)
if
__name__
==
'__main__'
:
text
=
open
(
"text.txt"
,
encoding
=
"utf-8"
).
read
()
word_segment
(
text
)
pass
def
word_cloud
(
texts
):
"""
根据文本生成词云图片
"""
data
=
" "
.
join
(
text
for
text
in
texts
)
mask_img
=
imread
(
'./python-logo.png'
,
flatten
=
True
)
wordcloud
=
WordCloud
(
font_path
=
'/Library/Fonts//华文黑体.ttf'
,
background_color
=
'white'
,
mask
=
mask_img
).
generate
(
data
)
plt
.
imshow
(
wordcloud
)
plt
.
axis
(
'off'
)
plt
.
savefig
(
'./wordcloud.jpg'
,
dpi
=
600
)
def
cookie
(
s
):
from
http
.
cookies
import
SimpleCookie
rawdata
=
s
cookie
=
SimpleCookie
()
cookie
.
load
(
rawdata
)
# Even though SimpleCookie is dictionary-like, it internally uses a Morsel object
# which is incompatible with requests. Manually construct a dictionary instead.
cookies
=
{}
for
key
,
morsel
in
cookie
.
items
():
cookies
[
key
]
=
morsel
.
value
return
cookie
def
format_duration
(
duration
):
"""
格式化时长
:param duration 毫秒
"""
total_seconds
=
int
(
duration
/
1000
)
minute
=
total_seconds
//
60
seconds
=
total_seconds
%
60
return
f'
{
minute
:02
}
:
{
seconds
:02
}
'
Back
|
FazBrowse Home
|
New Git URL