Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 275e40d

Browse files
committed
提交代码
1 parent fbf22ef commit 275e40d

File tree

4 files changed

+184
-0
lines changed

4 files changed

+184
-0
lines changed

‎.DS_Store‎

0 Bytes
Binary file not shown.

‎xianhuan/.DS_Store‎

6 KB
Binary file not shown.

‎xianhuan/yanxuanbra/ana.py‎

Lines changed: 124 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,124 @@
1+
#!/usr/bin/env python3
2+
# -*- coding: utf-8 -*-
3+
"""
4+
@author: 闲欢
5+
"""
6+
import json
7+
import pandas as pd
8+
from pyecharts.charts import Bar, Pie
9+
from pyecharts import options as opts
10+
import jieba
11+
from PIL import Image
12+
from wordcloud import WordCloud
13+
from matplotlib import pyplot as plt
14+
import numpy as np
15+
from os import path
16+
17+
size = ['XXL', 'XL', 'XS', 'S', 'M', 'L']
18+
19+
color = []
20+
size1 = []
21+
size2 = []
22+
comments = []
23+
24+
with open("comments.txt", "r", encoding="utf-8") as f:
25+
for line in f:
26+
data_obj = json.loads(line)
27+
comments.append(data_obj['content'])
28+
skuinfo = data_obj['skuInfo']
29+
# skuArr = skuinfo.split(",")
30+
for sku in skuinfo:
31+
if '颜色' in sku and '内裤' not in sku:
32+
color.append(sku.replace("颜色:", "").strip().replace("开扣", "").replace("套头", "").replace("文胸", "").replace("套装", "").replace("(薄杯)", "").replace("(厚杯)", ""))
33+
elif '尺码' in sku:
34+
is_size1 = False
35+
for s in size:
36+
if s in sku:
37+
is_size1 = True
38+
size1.append(s)
39+
break
40+
41+
# 非SML这种定义尺寸的,就是简单罩杯定义的,同时去掉"适合75ABCD"这种定义的
42+
if not is_size1 and '适合' not in sku:
43+
size2.append(sku.replace('尺码:', ""))
44+
45+
# 颜色可视化
46+
df = pd.DataFrame(color, columns=['color'])
47+
analyse_color = df['color'].value_counts()
48+
49+
bar = Bar()
50+
bar.add_xaxis(analyse_color.index.values.tolist())
51+
bar.add_yaxis("", analyse_color.values.tolist())
52+
bar.set_global_opts(
53+
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-90)),
54+
title_opts=opts.TitleOpts(title="颜色分布"),
55+
# datazoom_opts=opts.DataZoomOpts(),
56+
)
57+
# bar.render_notebook()
58+
bar.render('color.html')
59+
60+
61+
# 尺码可视化
62+
df2 = pd.DataFrame(size1, columns=['size'])
63+
analyse_size = df2['size'].value_counts()
64+
65+
bar = Bar()
66+
bar.add_xaxis(analyse_size.index.values.tolist())
67+
bar.add_yaxis("", analyse_size.values.tolist())
68+
bar.set_global_opts(
69+
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=0)),
70+
title_opts=opts.TitleOpts(title="尺寸分布"),
71+
# datazoom_opts=opts.DataZoomOpts(),
72+
)
73+
bar.render('size1.html')
74+
75+
df2 = pd.DataFrame(size2, columns=['size'])
76+
analyse_size = df2['size'].value_counts()
77+
78+
bar = Bar()
79+
bar.add_xaxis(analyse_size.index.values.tolist())
80+
bar.add_yaxis("", analyse_size.values.tolist())
81+
bar.set_global_opts(
82+
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=0)),
83+
title_opts=opts.TitleOpts(title="尺寸分布"),
84+
# datazoom_opts=opts.DataZoomOpts(),
85+
)
86+
bar.render('size2.html')
87+
88+
89+
90+
# 评论可视化
91+
text = " ".join(comments)
92+
def gen_wc_split_text(text='There is no txt', max_words=None, background_color=None,
93+
font_path='/System/Library/Fonts/PingFang.ttc',
94+
output_path='', output_name='',
95+
mask_path=None, mask_name=None,
96+
width=400, height=200, max_font_size=100, axis='off'):
97+
all_seg = jieba.cut(text, cut_all=False)
98+
split_text = ' '
99+
for seg in all_seg:
100+
split_text = split_text + seg + ' '
101+
102+
# 设置一个底图
103+
mask = None
104+
if mask_path is not None:
105+
mask = np.array(Image.open(path.join(mask_path, mask_name)))
106+
107+
wordcloud = WordCloud(background_color=background_color,
108+
mask=mask,
109+
max_words=max_words,
110+
max_font_size=max_font_size,
111+
width=width,
112+
height=height,
113+
# 如果不设置中文字体,可能会出现乱码
114+
font_path=font_path)
115+
myword = wordcloud.generate(str(split_text))
116+
# 展示词云图
117+
plt.imshow(myword)
118+
plt.axis(axis)
119+
plt.show()
120+
121+
# 保存词云图
122+
wordcloud.to_file(path.join(output_path, output_name))
123+
124+
gen_wc_split_text(text, output_name='comments_wc.png', output_path='./')

‎xianhuan/yanxuanbra/bra.py‎

Lines changed: 60 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,60 @@
1+
#!/usr/bin/env python3
2+
# -*- coding: utf-8 -*-
3+
"""
4+
@author: 闲欢
5+
"""
6+
import requests
7+
import time
8+
import json
9+
10+
# 获取产品列表
11+
def search_keyword(keyword):
12+
uri = 'https://you.163.com/xhr/search/search.json'
13+
query = {
14+
"keyword": keyword,
15+
"page": 1
16+
}
17+
try:
18+
res = requests.get(uri, params=query).json()
19+
result = res['data']['directly']['searcherResult']['result']
20+
product_id = []
21+
for r in result:
22+
product_id.append(r['id'])
23+
return product_id
24+
except:
25+
raise
26+
27+
# 获取评论
28+
def details(product_id):
29+
url = 'https://you.163.com/xhr/comment/listByItemByTag.json'
30+
try:
31+
C_list = []
32+
for i in range(1, 100):
33+
query = {
34+
"itemId": product_id,
35+
"page": i,
36+
}
37+
res = requests.get(url, params=query).json()
38+
if not res['data']['commentList']:
39+
break
40+
print("爬取第 %s 页评论" % i)
41+
commentList = res['data']['commentList']
42+
C_list.extend(commentList)
43+
time.sleep(1)
44+
45+
return C_list
46+
except:
47+
raise
48+
49+
50+
product_id = search_keyword('文胸')
51+
r_list = []
52+
for p in product_id:
53+
r_list.extend(details(p))
54+
55+
with open('./comments.txt', 'w') as f:
56+
for r in r_list:
57+
try:
58+
f.write(json.dumps(r, ensure_ascii=False) + '\n')
59+
except:
60+
print('出错啦')

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /