前言

2023年的中秋节和国庆节即将来临，好消息是，它们将连休8天！这个长假为许多人提供了绝佳的休闲机会，让许多人都迫不及待地想要释放他们被压抑已久的旅游热情，所以很多朋友已经开始着手规划他们的旅游行程。

今天我们来分析下去哪儿的旅游攻略数据，看看吃、住、游玩在价位合适的情况下，怎样才能玩的开心

环境使用

Python 3.8
Pycharm

模块使用

requests
parsel
csv

数据来源分析

1. 明确需求

这次选的月份为10 ~ 12月，游玩费用为1000 ~ 2999这个价位

2. 抓包分析

按F12，打开开发者工具，点击搜索，输入你想要的数据

找到数据链接

https://travel.qunar.com/travelbook/list.htm?page=1&order=hot_heat&&month=10_11_12&avgPrice=2

代码实现

导入模块

import requests
import parsel
import csv

请求数据

模拟浏览器: <可以直接复制>
response.text 获取响应文本数据
response.json() 获取响应json数据
response.content 获取响应二进制数据
我们使用requests.get()方法向指定的URL发送GET请求，并获取到响应的内容

url = f'https://travel.qunar.com/travelbook/list.htm?page=1&order=hot_heat&&month=10_11_12&&avgPrice=2'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
}
response = requests.get(url, headers=headers)

解析

先取响应文本数据

selector = parsel.Selector(response.text)

css选择器:：根据标签属性提取数据内容，看元素面板, 为了帮助找到数据标签,

lis = selector.css('.list_item')
for li in lis:
    title = li.css('.tit a::text').get()
    user_name = li.css('.user_name a::text').get()
    date = li.css('.date::text').get()
    days = li.css('.days::text').get()
    photo_nums = li.css('.photo_nums::text').get()
    fee = li.css('.fee::text').get()
    people = li.css('.people::text').get()
    trip = li.css('.trip::text').get()
    places = ''.join(li.css('.places ::text').getall()).split('行程')
    place_1 = places[0].replace('途经：', '')
    place_2 = places[-1].replace('：', '')
    href = li.css('.tit a::attr(href)').get().split('/')[-1]
    link = f'https://travel.qunar.com/travelbook/note/{href}'
    dit = {
        '标题': title,
        '昵称': user_name,
        '日期': date,
        '耗时': days,
        '照片': photo_nums,
        '费用': fee,
        '人员': people,
        '标签': trip,
        '途径': place_1,
        '行程': place_2,
        '详情页': link,
    }
    print(title, user_name, date, days, photo_nums, fee, people, trip, place_1, place_2, link, sep=' | ')

保存

f = open('data.csv', mode='w', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
    '标题',
    '昵称',
    '日期',
    '耗时',
    '照片',
    '费用',
    '人员',
    '标签',
    '途径',
    '行程',
    '详情页',
])
csv_writer.writeheader()

数据可视化

导入模块、数据

import pandas as pd

df = pd.read_csv('data.csv')
df.head()

年份分布情况

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
num = df['年份'].value_counts().to_list()
info = df['年份'].value_counts().index.to_list()
c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                info,
                num,
            )
        ],
        center=["40%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="年份分布情况"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
#     .render("pie_scroll_legend.html")
)
c.render_notebook()

月份分布情况

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
num = df['月份'].value_counts().to_list()
info = df['月份'].value_counts().index.to_list()
c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                info,
                num,
            )
        ],
        center=["40%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="月份分布情况"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
#     .render("pie_scroll_legend.html")
)
c.render_notebook()

出行时间情况

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
num = df['耗时'].value_counts().to_list()
info = df['耗时'].value_counts().index.to_list()
c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                info,
                num,
            )
        ],
        center=["40%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="出行时间情况"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
#     .render("pie_scroll_legend.html")
)
c.render_notebook()

费用分布情况

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
num = df['费用'].value_counts().to_list()
info = df['费用'].value_counts().index.to_list()
c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                info,
                num,
            )
        ],
        center=["40%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="费用分布情况"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
#     .render("pie_scroll_legend.html")
)
c.render_notebook()

人员分布情况

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
num = df['人员'].value_counts().to_list()
info = df['人员'].value_counts().index.to_list()
c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                info,
                num,
            )
        ],
        center=["40%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="人员分布情况"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
#     .render("pie_scroll_legend.html")
)
c.render_notebook()