我用Python爬取美食网站3032个菜谱并分析，真香！

 1# 主函数
 2def main(x):
 3    url = 'https://www.douguo.com/caipu/{}/0/{}'.format(caipu,x*20)
 4    print(url)
 5    html = get_page(url)
 6    parse_page(html,caipu)
 7
 8if __name__ == '__main__':
 9    caipu_list = ['川菜', '湘菜','粤菜','东北菜','鲁菜','浙菜','湖北菜','清真菜'] #中国菜系
10    start = time.time()  # 计时
11    for caipu in caipu_list:
12        for i in range(22):
13            # 爬取多页
14            main(x=i)
15            time.sleep(random.uniform(1, 2))
16            print(caipu,"第" + str(i+1) + "页提取完成")
17    end = time.time()
18    print('共用时',round((end - start) / 60, 2), '分钟')

 1from pyecharts import options as opts
 2from pyecharts.charts import Page, Pie
 3cut = lambda x : '4分以下' if x < 4 else ('4.1-4.5分' if x <= 4.5 else('4.6-4.9分' if x <= 4.9 else '5分'))
 4df['评分分布'] = df['评分'].map(cut)
 5df2 = df.groupby('评分分布')['评分'].count()
 6df2 = df2.sort_values(ascending=False)
 7df2 = df2.round(2)
 8print(df2)
 9c = (
10        Pie()
11        .add(
12            "",
13            [list(z) for z in zip(df2.index.to_list(),df2.to_list())],
14            radius=["20%", "80%"],# 圆环的粗细和大小
15            rosetype='area' #玫瑰图
16        )
17        .set_global_opts(
18            title_opts=opts.TitleOpts(title="菜谱评分分布"
19                                     ),
20            legend_opts=opts.LegendOpts(
21                orient="vertical", pos_top="5%", pos_left="2%" ,textstyle_opts=opts.TextStyleOpts(font_size=14)# 左面比例尺
22            ),
23
24
25        )
26        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%",font_size=18),
27                      )
28    )
29c.render_notebook()

 1from pyecharts import options as opts
 2from pyecharts.charts import Page, Pie 
 3df2 = df.groupby('菜系')['评分'].count() #按菜系分组，对评分计数
 4df2 = df2.sort_values(ascending=False) #降序
 5print(df2)
 6c = (
 7        Pie()
 8        .add("", [list(z) for z in zip(df2.index.to_list(),df2.to_list())])
 9        .set_global_opts(title_opts=opts.TitleOpts(title="各菜系菜谱数量占比",subtitle="数据来源：豆果美食"))
10        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
11    )
12c.render_notebook()

 1from pyecharts import options as opts
 2from pyecharts.charts import Page, Pie
 3df2 = df.groupby('菜系')['评分'].mean()
 4df2 = df2.sort_values(ascending=False)
 5df2 = df2.round(2)
 6print(df2)
 7c = (
 8        Pie()
 9        .add(
10            "",
11            [list(z) for z in zip(df2.index.to_list(),df2.to_list())],
12            radius=["40%", "75%"],   # 圆环的粗细和大小
13        )
14        .set_global_opts(
15            title_opts=opts.TitleOpts(title="各菜系平均评分"),
16            legend_opts=opts.LegendOpts(
17                orient="vertical", pos_top="5%", pos_left="2%"  # 左面比例尺
18            ),
19        )
20        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{c}"))
21    )
22c.render_notebook()

 1from pyecharts.charts import Bar,Pie
 2from pyecharts import options as opts
 3df1 = df.groupby('菜系')['用料数'].mean() #按菜系分组，对评分计数
 4df1 = df1.sort_values(ascending=False) #降序
 5df1 = df1.round(0)
 6print(df1)
 7bar = Bar()
 8bar.add_xaxis(df1.index.to_list())
 9bar.add_yaxis("用料数量",df1.to_list())
10bar.set_global_opts(title_opts=opts.TitleOpts(title="各菜系用料数量",subtitle="数据来源：豆果美食"))
11bar.render_notebook()

1# 绘制词云图
2text1 = get_cut_words(content_series=df[df['菜系']=='川菜']['用料'])
3stylecloud.gen_stylecloud(text=' '.join(text1), max_words=1000,
4                          collocations=False,
5                          font_path='字酷堂清楷体.ttf',
6                          icon_name='fas fa-thumbs-up',
7                          size=653,
8                          output_name='./川菜.png')
9Image(filename='./川菜.png')