当前位置:

首页 > temp > python入门教程 >

Python爬虫+可视化教学：爬取分析宠物猫咪交易数据

网上的数据太多、太杂，而且我也不知道哪个网站的数据比较好。所以，只能找到一个猫咪交易网站的数据来分析了

地址：

http://www.maomijiaoyi.com/

爬虫部分

请求数据

import requests

url = f'http://www.maomijiaoyi.com/index.php?/chanpinliebiao_c_2_1--24.html'
headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
print(response.text)

解析数据

# 把获取到的 html 字符串数据转换成 selector 对象 这样调用
selector = parsel.Selector(response.text)
# css 选择器只要是根据标签属性内容提取数据 编程永远不看过程 只要结果
href = selector.css('.content:nth-child(1) a::attr(href)').getall()
areas = selector.css('.content:nth-child(1) .area .color_333::text').getall()
areas = [i.strip() for i in areas] # 列表推导式

提取标签数据

for index in zip(href, areas):
    # http://www.maomijiaoyi.com/index.php?/chanpinxiangqing_224383.html
    index_url = 'http://www.maomijiaoyi.com' + index[0]
    response_1 = requests.get(url=index_url, headers=headers)
    selector_1 = parsel.Selector(response_1.text)
    area = index[1]
    # getall 取所有 get 取一个
    title = selector_1.css('.detail_text .title::text').get().strip()
    shop = selector_1.css('.dinming::text').get().strip()  # 店名
    price = selector_1.css('.info1 div:nth-child(1) span.red.size_24::text').get()  # 价格
    views = selector_1.css('.info1 div:nth-child(1) span:nth-child(4)::text').get()  # 浏览次数
    # replace() 替换
    promise = selector_1.css('.info1 div:nth-child(2) span::text').get().replace('卖家承诺: ', '')  # 浏览次数
    num = selector_1.css('.info2 div:nth-child(1) div.red::text').get()  # 在售只数
    age = selector_1.css('.info2 div:nth-child(2) div.red::text').get()  # 年龄
    kind = selector_1.css('.info2 div:nth-child(3) div.red::text').get()  # 品种
    prevention = selector_1.css('.info2 div:nth-child(4) div.red::text').get()  # 预防
    person = selector_1.css('div.detail_text .user_info div:nth-child(1) .c333::text').get()  # 联系人
    phone = selector_1.css('div.detail_text .user_info div:nth-child(2) .c333::text').get()  # 联系方式
    postage = selector_1.css('div.detail_text .user_info div:nth-child(3) .c333::text').get().strip()  # 包邮
    purebred = selector_1.css(
        '.xinxi_neirong div:nth-child(1) .item_neirong div:nth-child(1) .c333::text').get().strip()  # 是否纯种
    sex = selector_1.css(
        '.xinxi_neirong div:nth-child(1) .item_neirong div:nth-child(4) .c333::text').get().strip()  # 猫咪性别
    video = selector_1.css(
        '.xinxi_neirong div:nth-child(2) .item_neirong div:nth-child(4) .c333::text').get().strip()  # 能否视频
    worming = selector_1.css(
        '.xinxi_neirong div:nth-child(2) .item_neirong div:nth-child(2) .c333::text').get().strip()  # 是否驱虫
    dit = {
        '地区': area,
        '店名': shop,
        '标题': title,
        '价格': price,
        '浏览次数': views,
        '卖家承诺': promise,
        '在售只数': num,
        '年龄': age,
        '品种': kind,
        '预防': prevention,
        '联系人': person,
        '联系方式': phone,
        '异地运费': postage,
        '是否纯种': purebred,
        '猫咪性别': sex,
        '驱虫情况': worming,
        '能否视频': video,
        '详情页': index_url,
    }

保存数据

import csv # 内置模块

f = open('猫咪1.csv', mode='a', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=['地区', '店名', '标题', '价格', '浏览次数', '卖家承诺', '在售只数',
                                           '年龄', '品种', '预防', '联系人', '联系方式', '异地运费', '是否纯种',
                                           '猫咪性别', '驱虫情况', '能否视频', '详情页'])
csv_writer.writeheader() # 写入表头
csv_writer.writerow(dit)
print(title, area, shop, price, views, promise, num, age,
      kind, prevention, person, phone, postage, purebred, sex, video, worming, index_url, sep=' | ')

得到数据

数据可视化部分

词云图

from pyecharts import options as opts
from pyecharts.charts import WordCloud
from pyecharts.globals import SymbolType
from pyecharts.globals import ThemeType


words = [(i,1) for i in cat_info['品种'].unique()]
c = (
    WordCloud(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    .add("", words,shape=SymbolType.DIAMOND)
    .set_global_opts(title_opts=opts.TitleOpts(title=""))
)
c.render_notebook()

交易品种占比图

from pyecharts import options as opts
from pyecharts.charts import TreeMap

pingzhong = cat_info['品种'].value_counts().reset_index()
data = [{'value':i[1],'name':i[0]} for i in zip(list(pingzhong['index']),list(pingzhong['品种']))]

c = (
    TreeMap(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    .add("", data)
    .set_global_opts(title_opts=opts.TitleOpts(title=""))
    .set_series_opts(label_opts=opts.LabelOpts(position="inside"))
)

c.render_notebook()

均价占比图

from pyecharts import options as opts
from pyecharts.charts import PictorialBar
from pyecharts.globals import SymbolType

location = list(price['品种'])
values = list(price['价格'])

c = (
    PictorialBar(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    .add_xaxis(location)
    .add_yaxis(
        "",
        values,
        label_opts=opts.LabelOpts(is_show=False),
        symbol_size=18,
        symbol_repeat="fixed",
        symbol_offset=[0, 0],
        is_symbol_clip=True,
        symbol=SymbolType.ROUND_RECT,
    )
    .reversal_axis()
    .set_global_opts(
        title_opts=opts.TitleOpts(title="均价排名"),
        xaxis_opts=opts.AxisOpts(is_show=False),
        yaxis_opts=opts.AxisOpts(
            axistick_opts=opts.AxisTickOpts(is_show=False),
            axisline_opts=opts.AxisLineOpts(
                linestyle_opts=opts.LineStyleOpts(opacity=0),
            
            ),
        ),
    )
    .set_series_opts(
        label_opts=opts.LabelOpts(position='insideRight')
    )
)

c.render_notebook()

猫龄柱状图

from pyecharts import options as opts
from pyecharts.charts import Bar
from pyecharts.faker import Faker

x = ['1-3个月','3-6个月','6-9个月','9-12个月','1年以上']
y = [69343,115288,18239,4139,5]

c = (
    Bar(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    .add_xaxis(x)
    .add_yaxis('', y)
    .set_global_opts(title_opts=opts.TitleOpts(title="猫龄分布"))
)

c.render_notebook()