如果你不在一个盛大的周末款待自己,你怎么能不辜负一周的辛勤工作,对吗?
[En]
If you don’t treat yourself on a big weekend, how can you live up to a week of hard work, right?
那就和我一起攀登你城市的美食吧,。
[En]
Then join me to climb the delicious food of your city, .
基本开发环境
- Python 3.6
- Pycharm
相关模块的使用
爬虫模块使用
import requests
import re
import csv
数据分析模块
import pandas as pd
import numpy as np
from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.globals import ThemeType #引入主题
安装Python并添加到环境变量,pip安装需要的相关模块即可。
兄弟们学习python,有时候不知道怎么学,从哪里开始学。掌握了基本的一些语法或者做了两个案例后,不知道下一步怎么走,不知道如何去学习更加高深的知识。
那么对于这些大兄弟们,我准备了大量的免费视频教程,PDF电子书籍,以及视频源的源代码!
还会有大佬解答!
都在这个群里了
点击蓝色字体(我)获取
欢迎加入,一起讨论 一起学习!
需求数据来源分析
上面某团的数据是可以获取的,当然,商户的电话也是可以获取的。
[En]
The above data of a certain regiment can be obtained, and of course, the phone number of the merchant is also available.
一般来说,在寻找数据时,您会从开发人员的工具中抓取包,复制所需的数据内容,然后进行搜索。
[En]
Generally speaking, when you look for data, you will grab the package from the developer’s tools, copy the desired data content, and then search it.
如果你用这种方式寻找数据,没有问题,但对于美团来说,没有办法爬行多页数据。
[En]
If you look for data in this way, there is no problem, but for Meituan, there is no way to crawl multi-page data.
一个团的数据要从第二页开始查找,这样才能抓取多页数据。
[En]
The data of a regiment should be found from the second page so that multiple pages of data can be crawled.
代码实现
for page in range(0, 1537, 32):
# time.sleep(2)
url = 'https://apimobile.meituan.com/group/v4/poi/pcsearch/30'
data = {
'uuid': '96d0bfc90dfc441b81fb.1630669508.1.0.0',
'userid': '266252179',
'limit': '32',
'offset': page,
'cateId': '-1',
'q': '烤肉',
'token': '你自己的token',
}
headers = {
'Referer': 'https://sz.meituan.com/',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
response = requests.get(url=url, params=data, headers=headers)
result = response.json()['data']['searchResult']
for index in result:
shop_id = index['id']
index_url = f'https://www.meituan.com/meishi/{shop_id}/'
dit = {
'店铺名称': index['title'],
'人均消费': index['avgprice'],
'店铺评分': index['avgscore'],
'评论人数': index['comments'],
'所在商圈': index['areaname'],
'店铺类型': index['backCateName'],
'详情页': index_url,
}
csv_writer.writerow(dit)
print(dit)
f = open('美团烤肉数据.csv', mode='a', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
'店铺名称',
'人均消费',
'店铺评分',
'评论人数',
'所在商圈',
'店铺类型',
'详情页',
])
csv_writer.writeheader()
爬取数据展示
数据分析代码实现及效果
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
plt.rcParams['font.sans-serif'] = ['SimHei'] # 设置加载的字体名
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
fig,axes=plt.subplots(2,1,figsize=(12,12))
sns.regplot(x='人均消费',y='店铺评分',data=df,color='r',marker='+',ax=axes[0])
sns.regplot(x='评论人数',y='店铺评分',data=df,color='g',marker='*',ax=axes[1])
所在商圈烤肉店铺数量top10
df2 = df.groupby('所在商圈')['店铺名称'].count()
df2 = df2.sort_values(ascending=True)[-10:]
df2 = df2.round(2)
c = (
Bar(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add_xaxis(df2.index.to_list())
.add_yaxis("",df2.to_list()).reversal_axis() #X轴与y轴调换顺序
.set_global_opts(title_opts=opts.TitleOpts(title="商圈烤肉店数量top10",subtitle="数据来源:美团",pos_left = 'center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改横坐标字体大小
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改纵坐标字体大小
)
.set_series_opts(label_opts=opts.LabelOpts(font_size=16,position='right'))
)
c.render_notebook()
商圈烤肉店铺评分top10
df4 = df.groupby('评分类型')['店铺名称'].count()
df4 = df4.sort_values(ascending=False)
regions = df4.index.to_list()
values = df4.to_list()
c = (
Pie(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add("", zip(regions,values))
.set_global_opts(title_opts=opts.TitleOpts(title="不同评分类型店铺数量",subtitle="数据来源:美团",pos_top="-1%",pos_left = 'center'))
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%",font_size=18))
)
c.render_notebook()
不同评分类型店铺数量
df4 = df.groupby('评分类型')['店铺名称'].count()
df4 = df4.sort_values(ascending=False)
regions = df4.index.to_list()
values = df4.to_list()
c = (
Pie(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add("", zip(regions,values))
.set_global_opts(title_opts=opts.TitleOpts(title="不同评分类型店铺数量",subtitle="数据来源:美团",pos_top="-1%",pos_left = 'center'))
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%",font_size=18))
)
c.render_notebook()
不同店铺类型店铺数量
df6 = df.groupby('店铺类型')['店铺名称'].count()
df6 = df6.sort_values(ascending=False)[:10]
df6 = df6.round(2)
regions = df6.index.to_list()
values = df6.to_list()
c = (
Pie(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add("", zip(regions,values),radius=["40%", "75%"])
.set_global_opts(title_opts=opts.TitleOpts(title="不同店铺类型店铺数量",pos_top="-1%",pos_left = 'center'))
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}",font_size=18))
)
c.render_notebook()
不同店铺类型店铺评分
df6 = df.groupby('店铺类型')['店铺评分'].mean()
df6 = df6.sort_values(ascending=True)
df6 = df6.round(2)
df6 = df6.tail(10)
c = (
Bar(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add_xaxis(df6.index.to_list())
.add_yaxis("",df6.to_list()).reversal_axis() #X轴与y轴调换顺序
.set_global_opts(title_opts=opts.TitleOpts(title="不同店铺类型评分",subtitle="数据来源:美团",pos_left = 'center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改横坐标字体大小
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改纵坐标字体大小
)
.set_series_opts(label_opts=opts.LabelOpts(font_size=16,position='right'))
)
c.render_notebook()
不同类型商店的店铺评论数量
[En]
Number of shop reviews for different types of stores
df7 = df.groupby('店铺类型')['评论人数'].sum()
df7 = df7.sort_values(ascending=True)
df7 = df7.tail(10)
c = (
Bar(init_opts=opts.InitOpts(theme=ThemeType.WONDERLAND))
.add_xaxis(df7.index.to_list())
.add_yaxis("",df7.to_list()).reversal_axis() #X轴与y轴调换顺序
.set_global_opts(title_opts=opts.TitleOpts(title="不同店铺类型评论人数",subtitle="数据来源:美团",pos_left = 'center'),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改横坐标字体大小
yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(font_size=16)), #更改纵坐标字体大小
)
.set_series_opts(label_opts=opts.LabelOpts(font_size=16,position='right'))
)
c.render_notebook()
将Place改到您对应的地方,找到您喜欢吃的地方,并带上您的女朋友和伴侣来打卡。
[En]
Change the place to your corresponding place, find the place you like to eat, and bring your girlfriend and partner to sign in.
如果你觉得它有帮助,记得喜欢它,并将其转发到。
[En]
If you find it helpful, remember to like it and forward it to .
小编的动力来自于你的爱。
[En]
The editor’s motivation comes from your love.
Original: https://www.cnblogs.com/hahaa/p/15448883.html
Author: 轻松学Python
Title: 周末福利!用Python爬取美团美食信息,吃货们走起来!
原创文章受到原创版权保护。转载请注明出处:https://www.johngo689.com/511016/
转载文章受原作者版权保护。转载请注明原作者出处!