前言
大家早好、午好、晚好吖 ❤ ~欢迎光临本文章
开发环境:
模块使用:
安装模块:win + R 输入cmd 输入安装命令 pip install 模块名
如果出现爆红 可能是因为 网络连接超时 切换国内镜像源
基本思路:
一. 数据来源分析
-
明确需求:
-
分析 商品评论相关的信息 请求那个链接可以获取
浏览器自带工具: 开发者工具 <一定要分析清楚采集的数据在什么地方>
二. 代码实现步骤 --> 实现单页数据采集
发送请求, 模拟浏览器对于url地址发送请求
获取数据, 获取服务器返回响应数据 response
解析数据, 提取我们想要的数据内容 --> 评论信息
保存数据, 把评论信息保存表格文件里面
采集评论数据
导入模块
# 导入数据请求模块 --> 需要安装 pip install requests
import requests
# 导入格式化输出模块 --> 内置模块, 不需要安装
from pprint import pprint
# 导入csv模块
import csv
# 导入时间模块
import time
# 导入随机模块
import random
创建文件
f = open('口红20.csv', mode='a', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
'昵称',
'商品',
'评分',
'购买时间',
'评论时间',
'plus会员',
'内容',
])
写入表头
csv_writer.writeheader()
多页采集
for page in range(0, 20):
print(f'正在采集第{page}页的数据内容')
延时操作 random.randint(1, 2) --> 随机生成 1或者2
time.sleep(random.randint(1, 2))
请求链接
url = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=100011323932&score=0&sortType=5&page=3&pageSize=10&isShadowSku=0&rid=0&fold=1'
请求参数 --> 字典数据类型
data = {
'callback': 'fetchJSON_comment98',
'productId': '100011323932',
'score': '0',
'sortType': '5',
'page': page,
'pageSize': '10',
'isShadowSku': '0',
'rid': '0',
'fold': '1',
}
模拟浏览器 headers
headers = {
# user-agent 用户代理 表示浏览器基本上身份信息
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
发送请求
response = requests.get(url=url, params=data, headers=headers)
print(response.text)
break
# # for循环遍历, 一个一个提取列表里面元素
# for index in response.json()['comments']:
# if index['plusAvailable'] == 201:
# Vip = '是'
# else:
# Vip = '不是'
# dit = {
# '昵称': index['nickname'],
# '商品': index['productColor'],
# '评分': index['score'],
# '购买时间': index['referenceTime'],
# '评论时间': index['creationTime'],
# 'plus会员': Vip,
# '内容': index['content'].replace('\n', ''),
# }
# # 写入数据 字典方式进行保存
# csv_writer.writerow(dit)
# print(dit)
评论分析
import pandas as pd
df = pd.read_csv('data.csv', encoding='gbk')
df.head()
VipNum = df['plus会员'].value_counts().to_list()
VipType = df['plus会员'].value_counts().index.to_list()
from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
c = (
Pie()
.add(
'',
[list(z) for z in zip(VipType, VipNum)],
radius=['40%', '55%'],
label_opts=opts.LabelOpts(
position='outside',
formatter='{a|{a}}{abg|}\n{hr|}\n {b|{b}: }{c} {per|{d}%} ',
background_color='#eee',
border_color='#aaa',
border_width=1,
border_radius=4,
rich={
'a': {'color': '#999', 'lineHeight': 22, 'align': 'center'},
'abg': {
'backgroundColor': '#e3e3e3',
'width': '100%',
'align': 'right',
'height': 22,
'borderRadius': [4, 4, 0, 0],
},
'hr': {
'borderColor': '#aaa',
'width': '100%',
'borderWidth': 0.5,
'height': 0,
},
'b': {'fontSize': 16, 'lineHeight': 33},
'per': {
'color': '#eee',
'backgroundColor': '#334455',
'padding': [2, 4],
'borderRadius': 2,
},
},
),
)
.set_global_opts(title_opts=opts.TitleOpts(title='plus会员分布情况'))
# .render('pie_rich_label.html')
)
c.render_notebook()
d = (
Pie()
.add(
series_name='plus会员',
data_pair=[list(z) for z in zip(VipType, VipNum)],
radius=['50%', '70%'],
label_opts=opts.LabelOpts(is_show=False, position='center'),
)
.set_global_opts(legend_opts=opts.LegendOpts(pos_left='legft', orient='vertical'))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(
trigger='item', formatter='{a} <br/>{b}: {c} ({d}%)'
),
# label_opts=opts.LabelOpts(formatter='{b}: {c}')
)
)
d.render_notebook()
scoreNum = df['评分'].value_counts().to_list()
scoreType = df['评分'].value_counts().index.to_list()
from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
score = (
Pie()
.add(
'',
[list(z) for z in zip(scoreType, scoreNum)],
center=['35%', '50%'],
)
.set_global_opts(
title_opts=opts.TitleOpts(title='评分分布情况'),
legend_opts=opts.LegendOpts(pos_left='15%'),
)
.set_series_opts(label_opts=opts.LabelOpts(formatter='{b}: {c}'))
)
score.render_notebook()
# df['购买时间'] = df['购买时间'].str[:-6]
# BuyDateNum = df['购买时间'].value_counts().to_list()
# BuyDateType = df['购买时间'].value_counts().index.to_list()
BuyDateNum = df['购买时间'].str[:-6].value_counts().to_list()
BuyDateType = df['购买时间'].str[:-6].value_counts().index.to_list()
from pyecharts.charts import Bar
from pyecharts.faker import Faker
from pyecharts.globals import ThemeType
BuyDate = (
Bar({'theme': ThemeType.MACARONS})
.add_xaxis(BuyDateType)
.add_yaxis('购买时间', BuyDateNum)
.set_global_opts(
title_opts={'text': '商品购买时间', 'subtext': '2023年'}
)
# .render('bar_base_dict_config.html')
)
BuyDate.render_notebook()
import jieba
string = ' '.join([i for i in df['评论']])
words = jieba.lcut(string)
# 统计词频
word_count = {}
for word in words:
if word not in word_count:
word_count[word] = 1
else:
word_count[word] += 1
word_list = list(zip(word_count.keys(),word_count.values()))
word_list
df['商品'] = df['商品'].replace(regex='【.*?】', value='')
ShopNum = df['商品'].value_counts().to_list()[:7]
ShopType = df['商品'].value_counts().index.to_list()[:7]
ShopType
from pyecharts import options as opts
from pyecharts.charts import Bar
from pyecharts.commons.utils import JsCode
from pyecharts.faker import Faker
c = (
Bar()
.add_xaxis(ShopType)
.add_yaxis('商品', ShopNum, category_gap='60%')
.set_series_opts(
itemstyle_opts={
'normal': {
'color': JsCode(
'''new echarts.graphic.LinearGradient(0, 0, 0, 1, [{
offset: 0,
color: 'rgba(0, 244, 255, 1)'
}, {
offset: 1,
color: 'rgba(0, 77, 167, 1)'
}], false)'''
),
'barBorderRadius': [30, 30, 30, 30],
'shadowColor': 'rgb(0, 160, 221)',
}
}
)
.set_global_opts(
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
title_opts=opts.TitleOpts(title='口红款式', subtitle='DIRO'),
)
)
c.render_notebook()
import pyecharts.options as opts
from pyecharts.charts import WordCloud
wc = (
WordCloud()
.add(series_name='词云分析', data_pair=word_list, word_size_range=[6, 66])
.set_global_opts(
title_opts=opts.TitleOpts(
title='词云分析', title_textstyle_opts=opts.TextStyleOpts(font_size=23)
),
tooltip_opts=opts.TooltipOpts(is_show=True),
)
# .render('basic_wordcloud.html')
)
wc.render_notebook()
from pyecharts import options as opts
from pyecharts.charts import WordCloud
from pyecharts.globals import SymbolType
c = (
WordCloud()
.add('', word_list, word_size_range=[20, 100], shape=SymbolType.DIAMOND)
.set_global_opts(title_opts=opts.TitleOpts(title='WordCloud-shape-diamond'))
# .render('wordcloud_diamond.html')
)
c.render_notebook()