爬虫爬取数据保存到mysql

import pymysql
from pyquery import PyQuery as pq
import requests

def Get_HTML(url):
    headers = {'User-Agent': 'Mozilla/5.0'}
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print("Error!")

def parse_page(html):
    doc=pq(html)
    title=doc('.li03 a').text().split(' ')  #名称
    actor=doc('.li04 span').text().split(' ')  #演员表
    index=doc('.li01 b').text().split(' ')     #序号
    href=[]  #链接
    for i in doc('.li03 a').items():  #遍历
        href.append(i.attr('href'))
    score=doc('.li05 span').text().split(' ')  #评分
#保存为字典
    Result={}
    for i in range(100):
        result={
            '序号':index[i],
            '名称':title[i],
            '链接':href[i],
            '演员':actor[i],
            '评分':score[i]
        }
        Result[index[i]]=result
    return Result

def write_to_mysql(dict):
    db=pymysql.connect(host='*******',user='root',password='******',passwd='3306',db='*******')
    cursor=db.cursor()
    table='movie'  #表名
    keys=','.join(dict.keys())
    values=','.join(['%s']*len(dict))
    sql='insert into {table}({keys}) values ({values})'.format(table=table,keys=keys,values=values)
    try:
        if cursor.execute(sql,tuple(dict.values())):
            print("successful")
            db.commit()
    except:
        print("failed")
        db.rollback()
    db.close()

#若主键存在,进行更新操作;否则进行插入数据
def update_data(dict):
    db = pymysql.connect(host='*******',user='root',password='******',passwd='3306',db='*******')
    cursor=db.cursor()
    table='movie'    #表名
    keys=','.join(dict.keys())
    values=','.join(['%s']*len(dict))
    sql='insert into {table}({keys}) values ({values}) ON DUPLICATE KEY UPDATE'.format(table=table,keys=keys,values=values)
    update=','.join([' {key}=%s'.format(key=key) for key in dict])
    sql+=update
    try:
        if cursor.execute(sql,tuple(dict.values())*2):
            print("successful")
            db.commit()
    except:
        print("failed")
        db.rollback()
    db.close()

#查询
def search():
    db = pymysql.connect(host='*******',user='root',password='******',passwd='3306',db='*******')
    cursor = db.cursor()
    sql = 'select * from movie'
    try:
        cursor.execute(sql)
        print(cursor.rowcount)
        row = cursor.fetchone()
        while row:
            print('Row:', row)
            row = cursor.fetchone()
    except:
        print("Error")
    db.close()

def main():
    url = 'https://www.1905.com/vod/top/lst/'
    html = Get_HTML(url)
    item=parse_page(html)
    for i in range(len(item)):
        write_to_mysql(item[str(i+1)])
main()

国内疫情可视化

import requests
import json
import re
import pandas as pd
import time
from pyecharts.components import Table
from pyecharts import options as opts
from pyecharts.charts import Bar, Page,Pie,Line,Timeline,Map
from pyecharts.commons.utils import JsCode
from pyecharts.options import DataZoomOpts,ComponentTitleOpts





def Get_HTML():
    headers = {'User-Agent': 'Mozilla/5.0'}
    url = 'https://m.look.360.cn/events/feiyan?sv=&version=&market=&device=2&net=4&stype=&scene=&sub_scene=&refer_scene=&refer_subscene=&f=jsonp&location=true&sort=2&_=1649252949072&callback=jsonp2'
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        re = r.text[7:-2]
        response = json.loads(re)
        return response
    except:
        print("error!")
def China_data_Total():
    url='http://m.look.360.cn/subject/400?sign=360_6aa05217'
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0'}
    html = requests.get(url, headers=headers).text
    pattern=re.compile('"qcmsint1":"0"},"feiyanTrend":(.*),"local":',re.S)
    item=re.findall(pattern,html)
    response=json.loads(item[0])
    data = {
        "截止日期":response['total']['modifyTime'],
        "现存确诊":response['total']['currentConfirmed'],
        "境外输入":response['total']['overseasInput'],
        "现存无症状":response['total']['asymptom'],
        "累计确诊":response['total']['diagnosed'],
        "累计治愈":response['total']['cured'],
        "累计死亡":response['total']['died'],
        "现存_较昨日":response['newDiff']['currentConfirmed'],
        "境外输入_较昨日":response['newDiff']['overseasInput'],
        "无症状_较昨日":response['newDiff']['asymptom'],
        "累计_较昨日":response['newDiff']['diagnosed'],
        "治愈_较昨日":response['newDiff']['cured'],
        "死亡_较昨日":response['newDiff']['died']
    }
    return data
# 国内数据
def China_data(response):
    P_name, P_Ljqz, P_Cured, P_Died, P_Xcqz, P_Xzqz = [], [], [], [], [], []    #省数据
    C_name, C_Ljqz, C_Cured, C_Died, C_Xcqz, C_Xzqz = [], [], [], [], [], []    #市数据
    for i in range(34):
        P_name.append(response['data'][i]['cityShortName'])  # 城市名称
        P_Ljqz.append(response['data'][i]['diagnosed'])  # 累计确诊
        P_Cured.append(response['data'][i]['cured'])  # 治愈
        P_Died.append(response['data'][i]['died'])  # 死亡
        P_Xcqz.append(response['data'][i]['currentConfirmed'])  # 现存确诊
        P_Xzqz.append(response['data'][i]['diffDiagnosed'])  # 新增确诊
    data = {
        "地区": P_name,
        "新增确诊": P_Xzqz,
        "现存确诊": P_Xcqz,
        "累计确诊": P_Ljqz,
        "治愈人数": P_Cured,
        "死亡人数": P_Died,
    }
    return data

#河南省数据
def Henan_data():
    url = 'https://m.look.360.cn/events/feiyanCityInfo?sv=&version=&market=&device=2&net=4&stype=&scene=&sub_scene=&refer_scene=&refer_subscene=&f=jsonp&ename=henan&_=1650426134574&callback=jsonp4'
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0'}
    html = requests.get(url, headers=headers).text[7:-2]
    response=json.loads(html)
    # print(response['data']['cityInfo'])
    C_name, C_Ljqz, C_Cured, C_Died, C_Xcqz, C_Xzqz = [], [], [], [], [], []  # 市数据
    for i in range(len(response['data']['cityInfo'])):
        C_name.append(response['data']['cityInfo'][i]['cityName'])   #名称
        C_Ljqz.append(response['data']['cityInfo'][i]['diagnosed'])  # 累计确诊
        C_Cured.append(response['data']['cityInfo'][i]['cured'])  # 治愈
        C_Died.append(response['data']['cityInfo'][i]['died'])  # 死亡
        C_Xzqz.append(response['data']['cityInfo'][i]['diffDiagnosed'])  # 新增确诊
    data = {
        "地区": C_name,
        "新增确诊": C_Xzqz,
        "累计确诊": C_Ljqz,
        "治愈人数": C_Cured,
        "死亡人数": C_Died
    }
    return data

def Abroad_data(response):  # 国外数据
    C_name, Ljqz, Cured, Died, Xcqz, Xzqz = [], [], [], [], [], []
    for i in range(196):
        c_name = response['country'][i]['provinceName']  # 城市名称
        ljqz = response['country'][i]['diagnosed']  # 累计确诊
        cured = response['country'][i]['cured']  # 治愈
        died = response['country'][i]['died']  # 死亡
        xzqz = response['country'][i]['diffDiagnosed']  # 新增确诊
        C_name.append(c_name)
        Ljqz.append(ljqz)
        Cured.append(cured)
        Died.append(died)
        Xzqz.append(xzqz)
    data = {
        "地区": C_name,
        "新增确诊": Xzqz,
        "累计确诊": Ljqz,
        "治愈人数": Cured,
        "死亡人数": Died
    }
    return data

def TimeLine():
    headers = {'User-Agent': 'Mozilla/5.0'}
    url = 'https://api.look.360.cn/events/feiyanHomeMulTrend?sv=&version=&market=&device=2&net=4&stype=&scene=&sub_scene=&refer_scene=&refer_subscene=&f=jsonp&_=1650032782170&callback=jsonp3'
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        re = r.text[7:-2]
        response = json.loads(re)
    except:
        print("error!")
    time,Ljqz, Cured, Died, Xcqz, Xzqz, Xz_Died, Xz_Cured= [], [], [], [], [], [], [], []
    for i in range(len(response['data']['timeline_n1'])):
        time.append(response['data']['timeline_n1'][i]['time'])         #时间
        Xzqz.append(response['data']['timeline_n1'][i]['diagnosed'])    #新增确诊
        Xcqz.append(response['data']['timeline_n2'][i]['total_currentConfirmed']) #现存确诊
        Ljqz.append(response['data']['timeline_n2'][i]['total_diagnosed'])   #累计确诊
        Cured.append(response['data']['timeline_n3'][i]['total_cured'])      #累计治愈
        Died.append(response['data']['timeline_n3'][i]['total_died'])      #累计死亡
        Xz_Died.append(response['data']['timeline_n4'][i]['died'])        #新增死亡
        Xz_Cured.append(response['data']['timeline_n4'][i]['cured'])      #新增治愈
    data={
        "时间":time,
        "新增确诊":Xzqz,
        "现存确诊":Xcqz,
        "累计确诊":Ljqz,
        "累计治愈":Cured,
        "累计死亡":Died,
        "新增死亡":Xz_Died,
        "新增治愈":Xz_Cured
    }
    return data

def View(data_1,data_2,data_3,data_4):
    #柱状图
    c_1 = Timeline(init_opts=opts.InitOpts(chart_id='1'))
    c_1.add_schema(play_interval=1000,
                   label_opts=opts.series_options.LabelOpts(color='#cfe2f3'),is_auto_play = True)
    for i in range(3):
        #全国累计详情柱状图
        C_1 = (
            Bar()
                .add_xaxis(data_1['地区'][i*11:(i+1)*11])
                .add_yaxis("累计确诊", data_1['累计确诊'][i*11:(i+1)*11],stack='stack1',label_opts=opts.LabelOpts(is_show=False))
                .add_yaxis("新增确诊", data_1['新增确诊'][i*11:(i+1)*11],stack='stack1',label_opts=opts.LabelOpts(is_show=False))
                .add_yaxis("死亡人数", data_1['死亡人数'][i * 11:(i + 1) * 11],stack='stack1',label_opts=opts.LabelOpts(is_show=False))
                .add_yaxis("治愈人数", data_1['治愈人数'][i * 11:(i + 1) * 11],stack='stack1',label_opts=opts.LabelOpts(is_show=False))
                .add_yaxis("现存确诊", data_1['现存确诊'][i * 11:(i + 1) * 11],stack='stack1',label_opts=opts.LabelOpts(is_show=False))
                .reversal_axis()
                # .set_global_opts(legend_opts=opts.LegendOpts(selected_mode='single'))  # 单选模式
            .set_global_opts(xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white')),#调整x轴字体颜色
                                yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white')),
                             legend_opts=opts.LegendOpts(selected_mode='single'),
                             title_opts=opts.TitleOpts("国内疫情详情",pos_right=0,pos_top=20,title_textstyle_opts=opts.TextStyleOpts(font_size=13,color="#cfe2f3")))
        )
        c_1.add(C_1, "第{}页".format(i+1))
        # 全国地图
    c_2 = (
            Map(init_opts=opts.InitOpts(chart_id='2'))
                # .add("死亡人数", [list(z) for z in zip(data_1['地区'], data_1['死亡人数'])], "china",is_selected=False)        #默认关闭该标签
                .add("累计确诊",[list(z) for z in zip(data_1['地区'], data_1['累计确诊'])], "china")
                .add("死亡人数", [list(z) for z in zip(data_1['地区'], data_1['死亡人数'])], "china")
                .add("治愈人数", [list(z) for z in zip(data_1['地区'], data_1['治愈人数'])], "china")
                .add("新增确诊", [list(z) for z in zip(data_1['地区'], data_1['新增确诊'])], "china")
                .add("现存确诊", [list(z) for z in zip(data_1['地区'], data_1['现存确诊'])], "china")
                .set_global_opts(
                title_opts=opts.TitleOpts(""),
                visualmap_opts=opts.VisualMapOpts(max_=10000),
                legend_opts=opts.LegendOpts(selected_mode='single')    #单选模式
            )
        )
        #时间线折线图
    c_3 = (
            Line(init_opts=opts.InitOpts(chart_id='3'))
                .add_xaxis(data_3['时间'])
                .add_yaxis("新增确诊",data_3['新增确诊'],label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#DC143C'))
                .add_yaxis("现存确诊",data_3['现存确诊'],label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#a98175'))
                .add_yaxis("累计确诊",data_3['累计确诊'], label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#60281e'))
                .add_yaxis("累计治愈",data_3['累计治愈'], label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#2add9c'))
                .add_yaxis("累计死亡",data_3['累计死亡'], label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='black'))
                .add_yaxis("新增死亡",data_3['新增死亡'], label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#758a99'))
                .add_yaxis("新增治愈",data_3['新增治愈'], label_opts=opts.LabelOpts(is_show=False),linestyle_opts=opts.LabelOpts(color='#1bd1a5'))
                .set_global_opts(
                title_opts=opts.TitleOpts(title="疫情汇总时间线",pos_top=20,title_textstyle_opts=opts.TextStyleOpts(font_size=13,color="#cfe2f3")),
                tooltip_opts=opts.TooltipOpts(trigger="axis"),
                xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white')),  # 调整x轴字体颜色
                yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white')),
                legend_opts=opts.LegendOpts(selected_mode='single')
            )
        )
        #河南省地图
    c_4 = (
            Map(init_opts=opts.InitOpts(chart_id='4'))
                # .add("死亡人数", [list(z) for z in zip(data_1['地区'], data_1['死亡人数'])], "china",is_selected=False)        #默认关闭该标签
                .add("累计确诊", [list(z) for z in zip(data_4['地区'], data_4['累计确诊'])], "河南")
                .add("死亡人数", [list(z) for z in zip(data_4['地区'], data_4['死亡人数'])], "河南")
                .add("治愈人数", [list(z) for z in zip(data_4['地区'], data_4['治愈人数'])], "河南")
                .add("新增确诊", [list(z) for z in zip(data_4['地区'], data_4['新增确诊'])], "河南")

                .set_global_opts(
                title_opts=opts.TitleOpts(title='省内详细信息',pos_top=30,title_textstyle_opts=opts.TextStyleOpts(font_size=13, color="#cfe2f3")),
                visualmap_opts=opts.VisualMapOpts(max_=500),
                legend_opts=opts.LegendOpts(selected_mode='single')  # 单选模式
            )
        )
        #省内死亡详情饼图
    c_5 = (
            Pie(init_opts=opts.InitOpts(chart_id='5'))
                .add("死亡人数", [list(z) for z in zip(data_4['地区'], data_4['死亡人数'])])
                .set_global_opts(title_opts=opts.TitleOpts('市死亡人数',title_textstyle_opts=opts.TextStyleOpts(font_size=13, color="gray"),),
                                 legend_opts=opts.LegendOpts(is_show=False))
                # .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"),)
        )
    # 汇总数据与昨日相比
    data = China_data_Total()
    c_7 = (
        Pie(init_opts=opts.InitOpts(chart_id='7'))
        .set_global_opts(
                    title_opts=opts.TitleOpts(
                        title="现存确诊" + " " * 17 + "境外输入" + " " * 17 + "现存无症状", title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="white"), ))
        )
    c_8 = (
        Pie(init_opts=opts.InitOpts(chart_id='8'))
        .set_global_opts(
                    title_opts=opts.TitleOpts(
                        title="累计确诊"+ " " * 17 + "累计治愈"+ " " * 17 + "累计死亡", title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="white"), ))
        )
    c_9 = (
        Pie(init_opts=opts.InitOpts(chart_id='9'))
        .set_global_opts(
                    title_opts=opts.TitleOpts(
                        title=str(data['现存_较昨日']) + " " * 25 + str(data['境外输入_较昨日']) + " " * 25  + str(data['无症状_较昨日']), title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="#e9e7ef"), ))
        )
    c_10 = (
        Pie(init_opts=opts.InitOpts(chart_id='10'))
        .set_global_opts(
                    title_opts=opts.TitleOpts(
                        title=str(data['累计_较昨日']) + " " * 25 + str(data['治愈_较昨日']) + " " * 25+ str(data['死亡_较昨日']), title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="#e9e7ef")))
        )
    #数字
    c_11 = (
        Pie(init_opts=opts.InitOpts(chart_id='16'))
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title=str(data['现存确诊']) + " " * 3 + str(data['境外输入']) + " " * 3 + str(data['现存无症状']),
                title_textstyle_opts=opts.TextStyleOpts(font_size=23, color="#CD3700")))
    )
    c_12 = (
        Pie(init_opts=opts.InitOpts(chart_id='17'))
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title=str(data['累计确诊']) + " " * 3 + str(data['累计治愈']) + " " * 3 + str(data['累计死亡']),
                title_textstyle_opts=opts.TextStyleOpts(font_size=23, color="#7F7F7F")))
    )

    tu_1 = (
        Line(init_opts=opts.InitOpts(width="1500px",
                                     height="850px",
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"},
                                     chart_id='11'))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            title_opts=opts.TitleOpts(),
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )

    tu_1.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_body.jpg';

        """
    )
    tu_2 = (
        Line(init_opts=opts.InitOpts(
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"},
                                     chart_id='12'))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_2.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_box5.png';

        """
    )
    tu_3 = (
        Line(init_opts=opts.InitOpts(chart_id='13',
            bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"},
        ))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_3.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_box5.png';

        """
    )
    tu_4 = (
        Line(init_opts=opts.InitOpts(chart_id='14',
            bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"},
        ))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_4.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_box4.png';

        """
    )
    tu_5 = (
        Line(init_opts=opts.InitOpts(width="1500px",
                                     height="200px",
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"},
                                     chart_id='15'))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            title_opts=opts.TitleOpts(title="全球疫情信息 截至" + data['截止日期'],
                                      pos_left='center',
                                      title_textstyle_opts=opts.TextStyleOpts(font_size=21, color='#51c2d5'),
                                      pos_top='23%'),
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_5.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_title.png';

        """
    )
    page = Page(layout=Page.DraggablePageLayout, page_title="可视化大屏")
    page.add(tu_1,tu_2,tu_3,tu_4,c_1,c_2,c_3,c_4,c_5,c_7,c_8,c_9,c_10,tu_5,c_11,c_12)
    page.render('国内疫情信息.html')

def Style():
    # 固定样式
    Page.save_resize_html(source="./国内疫情信息.html",  # 上面的HTML文件名称
                          cfg_file="chart_config_3.json",  # 保存的json配置文件
                          dest="new_国内疫情信息可视化大屏.html"  # 新HTML文件名称,可以空缺,默认resize_render.html
                          )
def main():
    a=0
    while True:
        data_1 = China_data(Get_HTML())
        data_2 = Abroad_data(Get_HTML())
        data_3 = TimeLine()
        data_4=Henan_data()
        date=China_data_Total()['截止日期']
        if date!=a:
            View(data_1, data_2, data_3,data_4)
            Style()
            a=date

main()

爬取全球疫情数据并使用pyecharts可视化

# -*- coding:utf-8 -*-
import requests
import json
import re
import pandas as pd
import time
from pyecharts import options as opts
from pyecharts.charts import Bar, Page,Pie,Line,Timeline,Grid,Map
from pyecharts.commons.utils import JsCode


def sleeptime(hour, min, sec):  # 时间转换
    return hour * 3600 + min * 60 + sec


def Get_HTML():
    headers = {'User-Agent': 'Mozilla/5.0'}
    url = 'https://m.look.360.cn/events/feiyan?sv=&version=&market=&device=2&net=4&stype=&scene=&sub_scene=&refer_scene=&refer_subscene=&f=jsonp&location=true&sort=2&_=1649252949072&callback=jsonp2'
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        re = r.text[7:-2]
        response = json.loads(re)
        return response
    except:
        print("error!")

def China_data_Total():
    url='http://m.look.360.cn/subject/400?sign=360_6aa05217'
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0'}
    html = requests.get(url, headers=headers).text
    pattern=re.compile('"qcmsint1":"0"},"feiyanTrend":(.*),"local":',re.S)
    item=re.findall(pattern,html)
    response=json.loads(item[0])
    data = {
        "截止日期":response['total']['modifyTime'],
        "现存确诊":response['total']['currentConfirmed'],
        "境外输入":response['total']['overseasInput'],
        "现存无症状":response['total']['asymptom'],
        "累计确诊":response['total']['diagnosed'],
        "累计治愈":response['total']['cured'],
        "累计死亡":response['total']['died'],
        "现存_较昨日":response['newDiff']['currentConfirmed'],
        "境外输入_较昨日":response['newDiff']['overseasInput'],
        "无症状_较昨日":response['newDiff']['asymptom'],
        "累计_较昨日":response['newDiff']['diagnosed'],
        "治愈_较昨日":response['newDiff']['cured'],
        "死亡_较昨日":response['newDiff']['died']
    }
    return data

def China_data(response):  # 国内数据
    C_name, Ljqz, Cured, Died, Xcqz, Xzqz = [], [], [], [], [], []
    for i in range(34):
        c_name = response['data'][i]['city']  # 城市名称
        ljqz = response['data'][i]['diagnosed']  # 累计确诊
        cured = response['data'][i]['cured']  # 治愈
        died = response['data'][i]['died']  # 死亡
        xcqz = response['data'][i]['currentConfirmed']  # 现存确诊
        xzqz = response['data'][i]['diffDiagnosed']  # 新增确诊
        C_name.append(c_name)
        Ljqz.append(ljqz)
        Cured.append(cured)
        Died.append(died)
        Xcqz.append(xcqz)
        Xzqz.append(xzqz)
    data = {
        "地区": C_name,
        "新增确诊": Xzqz,
        "现存确诊": Xcqz,
        "累计确诊": Ljqz,
        "治愈人数": Cured,
        "死亡人数": Died
    }
    return data


def Abroad_data(response):  # 国外数据
    C_name, Ljqz, Cured, Died, Xcqz, Xzqz = [], [], [], [], [], []
    for i in range(196):
        c_name = response['country'][i]['provinceName']  # 城市名称
        ljqz = response['country'][i]['diagnosed']  # 累计确诊
        cured = response['country'][i]['cured']  # 治愈
        died = response['country'][i]['died']  # 死亡
        xzqz = response['country'][i]['diffDiagnosed']  # 新增确诊
        C_name.append(c_name)
        Ljqz.append(ljqz)
        Cured.append(cured)
        Died.append(died)
        Xzqz.append(xzqz)
    data = {
        "地区": C_name,
        "新增确诊": Xzqz,
        "累计确诊": Ljqz,
        "治愈人数": Cured,
        "死亡人数": Died
    }
    return data


def View(data_1, data_2):  # 可视化
    # 柱状图
    area_color_js = (
        "new echarts.graphic.LinearGradient(0, 0, 0, 1, "
        "[{offset: 0, color: '#7bbfea'}, {offset: 1, color: '#3fbbff0d'}], false)"
    )

    t_1 = Timeline()
    t_1.add_schema(play_interval=1000,
                  label_opts=opts.series_options.LabelOpts( color='#cfe2f3'))

    for i in range(len(data_1['地区'])):
        c_1 = (
            Bar(init_opts=opts.InitOpts(width="300px",height='300px'))
                .add_xaxis(['新增确诊','现存确诊','累计确诊','治愈人数','死亡人数'],)
                .add_yaxis("",[data_1['新增确诊'][i],data_1['现存确诊'][i],data_1['累计确诊'][i],data_1['治愈人数'][i],data_1['死亡人数'][i]],
                          color='#44cef6',)
                .reversal_axis()
                .set_global_opts(
                title_opts=opts.TitleOpts(" (地区: {} )".format(data_1['地区'][i]),title_textstyle_opts=opts.TextStyleOpts(color="#cfe2f3")),
                xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white')),#调整x轴字体颜色
                yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white'))
            )
        )
        t_1.add(c_1, "{}".format(data_1['地区'][i]))
    # 柱状图
    t_2 = Timeline()
    t_2.add_schema(play_interval=1000,
                   label_opts=opts.series_options.LabelOpts(color='#cfe2f3'))
    for i in range(len(data_2['地区'])):
        c_2 = (
            Bar()
                .add_xaxis(['新增确诊', '累计确诊', '治愈人数', '死亡人数'], )
                .add_yaxis("", [data_2['新增确诊'][i], data_2['累计确诊'][i], data_2['治愈人数'][i],data_2['死亡人数'][i]],
                           label_opts=opts.LabelOpts(position="right"),
                           color='#44cef6', )
                .reversal_axis()
                .set_global_opts(
                title_opts=opts.TitleOpts(" (国家: {} )".format(data_2['地区'][i]),pos_right='0',title_textstyle_opts=opts.TextStyleOpts(color="#cfe2f3")),
                xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white',)),  # 调整x轴字体颜色
                yaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white'),position='right')
            )
        )
        t_2.add(c_2, "{}".format(data_2['地区'][i]))
    # 饼图
    # 转换数据为类型,#转换后数据为['美国', 1010774]
    # data_pair = [list(z) for z in zip(x_data, y_data)]  # 转换后数据为['美国', 1010774]
    c_3 = (
        Line()
        .add_xaxis(data_2['地区'])
        .add_yaxis(
            series_name="新增确诊",
            y_axis=data_2['新增确诊'],
            label_opts=opts.LabelOpts(is_show=False,),
        )
        .add_yaxis(
            series_name="累计确诊",
            y_axis=data_2['累计确诊'],
            label_opts=opts.LabelOpts(is_show=False,),
        )
        .add_yaxis(
            series_name="治愈人数",
            y_axis=data_2['治愈人数'],
            label_opts=opts.LabelOpts(is_show=False,),
        )
            .add_yaxis(
            series_name="死亡人数",
            y_axis=data_2['死亡人数'],
            label_opts=opts.LabelOpts(is_show=False,),
        )

        .set_global_opts(
            title_opts=opts.TitleOpts(title="国外疫情数据",pos_right='0',title_textstyle_opts=opts.TextStyleOpts(color="#cfe2f3")),
            datazoom_opts=opts.DataZoomOpts(),
            tooltip_opts=opts.TooltipOpts(trigger="axis"),
             xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(color='white', )),  # 调整x轴字体颜色
            yaxis_opts=opts.AxisOpts(
                position='right',
                axistick_opts=opts.AxisTickOpts(is_show=True,),
                splitline_opts=opts.SplitLineOpts(is_show=True),
                axislabel_opts=opts.LabelOpts(color='white')
            ),
        )
    )
    c_5 = (      #地图
        Map()
            .add("累计确诊", [['河南', 2840], ['香港', 308175], ['吉林', 37712] , ['台湾', 27410], ['上海', 11366], ['浙江', 2819], ['福建', 2905],['山东', 2646], ['黑龙江', 2505], ['广东', 6681], ['四川', 1948], ['辽宁', 1604], ['河北', 1981], ['江苏', 2083], ['广西', 1518], ['北京', 1821], ['海南', 243], ['山西', 350], ['陕西', 3247], ['天津', 1798], ['云南', 2079], ['安徽', 1054], ['江西', 1063], ['湖南', 1335], ['青海', 43], ['内蒙古', 1687],['重庆',2423], ['贵州', 178], ['湖北', 68392], ['甘肃', 681], ['新疆', 999], ['宁夏', 122], ['澳门', 82], ['西藏', 1]], "china")
            .set_global_opts(
            title_opts=opts.TitleOpts(title="国内现存确诊",title_textstyle_opts=opts.TextStyleOpts(color="#cfe2f3")),visualmap_opts=opts.VisualMapOpts(max_=10000))

    )

    data = China_data_Total()
    c_6 = (
        Pie(init_opts=opts.InitOpts())
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title="现存确诊:" + str(data['现存确诊']) + " " * 5 + "境外输入:" + str(data['境外输入']) + " " * 5 + "现存无症状:" + str(
                    data['现存无症状']), title_textstyle_opts=opts.TextStyleOpts(font_size=15, color="#ffb3a7"), ))
    )
    c_7 = (
        Pie(init_opts=opts.InitOpts())
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title="累计确诊:" + str(data['累计确诊']) + " " * 5 + "累计治愈:" + str(data['累计治愈']) + " " * 5 + "累计死亡:" + str(
                    data['累计死亡']), title_textstyle_opts=opts.TextStyleOpts(font_size=15, color="#ffb3a7"), ))
    )
    c_8 = (
        Pie(init_opts=opts.InitOpts())
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title="较昨日:" + str(data['现存_较昨日']) + " " * 25 + "较昨日:" + str(data['境外输入_较昨日']) + " " * 25 + "较昨日:" + str(
                    data['无症状_较昨日']), title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="#e9e7ef"), ))
    )
    c_9 = (
        Pie(init_opts=opts.InitOpts())
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title="较昨日:" + str(data['累计_较昨日']) + " " * 25 + "较昨日:" + str(data['治愈_较昨日']) + " " * 25 + "较昨日:" + str(
                    data['死亡_较昨日']), title_textstyle_opts=opts.TextStyleOpts(font_size=10, color="#e9e7ef"), ))
    )
    c_10 = (  # 地图
        Map()
            .add("死亡人数",[['河南', 22], ['香港', 8827], ['吉林', 5], ['台湾', 854], ['上海', 7], ['浙江', 1], ['福建', 1], ['山东', 7], ['广东', 8], ['黑龙江', 13], ['四川', 3], ['江苏', 0], ['河北', 7], ['辽宁', 2], ['广西', 2], ['北京', 9], ['海南', 6], ['山西', 0], ['陕西', 3], ['云南', 2], ['安徽', 6], ['湖南', 4], ['江西', 1], ['天津', 3], ['青海', 0], ['内蒙古', 1], ['重庆', 6], ['贵州', 2], ['湖北', 4512], ['甘肃', 2], ['新疆', 3], ['宁夏', 0], ['澳门', 0], ['西藏', 0]], "china")
            .set_global_opts(
            title_opts=opts.TitleOpts(title="国内各地死亡人数", title_textstyle_opts=opts.TextStyleOpts(color="#cfe2f3")),
            visualmap_opts=opts.VisualMapOpts(max_=10000))

    )

    tu_1 = (
        Line(init_opts=opts.InitOpts(width="1500px",
                                     height="850px",
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"}))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            title_opts=opts.TitleOpts(),
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )

    tu_1.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_body.jpg';

        """
    )
    tu_2 = (
        Line(init_opts=opts.InitOpts(width="600px",
                                     height="700px",
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"}))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            title_opts=opts.TitleOpts(
                                      pos_left='center',
                                      title_textstyle_opts=opts.TextStyleOpts(font_size=25, color='#51c2d5'),
                                      pos_top='5%'),
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_2.add_js_funcs(
        """
        var img = new Image(); img.src = './images/data_icon.png';

        """
    )
    tu_3 = (
        Line(init_opts=opts.InitOpts(width="1500px",
                                     height="200px",
                                     bg_color={"type": "pattern", "image": JsCode("img"), "repeat": "no-repeat"}))
            .add_xaxis([None])
            .add_yaxis("", [None])
            .set_global_opts(
            title_opts=opts.TitleOpts(title="全球疫情信息 截至"+data['截止日期'],
                pos_left='center',
                title_textstyle_opts=opts.TextStyleOpts(font_size=21, color='#51c2d5'),
                pos_top='5%'),
            yaxis_opts=opts.AxisOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(is_show=False))
    )
    tu_3.add_js_funcs(
        """
        var img = new Image(); img.src = './images/bg_title.png';

        """
    )

    # page = Page(layout=Page.DraggablePageLayout, page_title="模拟")
    # page.add(tu_1,t_1, t_2, c_3,c_5,c_6,c_7,c_8,c_9,tu_2,tu_3,c_10)
    # page.render('全球疫情信息.html')

    # 固定样式
    Page.save_resize_html(source="全球疫情信息.html",  # 上面的HTML文件名称
                          cfg_file="chart_config.json",  # 保存的json配置文件
                          dest="new_全球疫情信息.html"  # 新HTML文件名称,可以空缺,默认resize_render.html
                          )

def main():
    second = sleeptime(5, 0, 0)  # 设置时间
    data_1 = China_data(Get_HTML())  # 国内数据
    data_2 = Abroad_data(Get_HTML())  # 国外数据
    data_11 = pd.DataFrame(data_1)
    data_22 = pd.DataFrame(data_2)
    while True:
        data_11.to_csv('./国内疫情数据.csv')
        data_22.to_csv('./国外疫情数据.csv')
        View(data_1, data_2)
        time.sleep(second)


# main()

data_1 = China_data(Get_HTML())  # 国内数据
data_2 = Abroad_data(Get_HTML())  # 国外数据
data_11 = pd.DataFrame(data_1)
data_22 = pd.DataFrame(data_2)
# data_11
# data_22
View(data_1,data_2)
# print(data_1)

爬取国内疫情数据并可视化

import requests
import json
from lxml import etree
import pandas as pd
import time
from pyecharts import options as opts
from pyecharts.charts import Bar

def sleeptime(hour, min, sec):   #时间转换
    return hour * 3600 + min * 60 + sec

def Get_HTML(url):
    headers={'User-Agent':'Mozilla/5.0'}
    try:
        r=requests.get(url,headers=headers)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        print("error!")
def Parse_page():
    C_name,Ljqz,Cured,Died,Xcqz,Xzqz=[],[],[],[],[],[]
    url='https://m.look.360.cn/events/feiyan?sv=&version=&market=&device=2&net=4&stype=&scene=&sub_scene=&refer_scene=&refer_subscene=&f=jsonp&location=true&sort=2&_=1649252949072&callback=jsonp2'
    re=Get_HTML(url)
    re=re[7:-2]
    response=json.loads(re)
    for i in range(34):
        c_name=response['data'][i]['data']['provinceName']  #城市名称
        ljqz=response['data'][i]['diagnosed']               #累计确诊
        cured=response['data'][i]['cured']           #治愈
        died=response['data'][i]['died']             #死亡
        xcqz=response['data'][i]['currentConfirmed']   #现存确诊
        xzqz=response['data'][i]['diffDiagnosed']      #新增确诊
        C_name.append(c_name)
        Ljqz.append(ljqz)
        Cured.append(cured)
        Died.append(died)
        Xcqz.append(xcqz)
        Xzqz.append(xzqz)
#     columns=['新增确诊','现存确诊','累计确诊','治愈人数','死亡人数']
#     index=C_name
    data={
        "地区":C_name,
        "新增确诊":Xzqz,
        "现存确诊":Xcqz,
        "累计确诊":Ljqz,
        "治愈人数":Cured,
        "死亡人数":Died
    }
#     print(data)
    return data
def View():
    data=Parse_page()
    c = (
        Bar()
        .add_xaxis(data['地区'])
        .add_yaxis("新增确诊",data['新增确诊'], stack="stack1")
        .add_yaxis("现存确诊",data['现存确诊'] , stack="stack1")
        .add_yaxis("累计确诊",data['累计确诊'] , stack="stack1")
        .add_yaxis("治愈人数",data['治愈人数'] , stack="stack1")
        .add_yaxis("死亡人数",data['死亡人数'] , stack="stack1")
        .set_global_opts(
            title_opts=opts.TitleOpts(title="国内疫情数据数据(全部)"),
            datazoom_opts=opts.DataZoomOpts(type_="inside"),
            )
        .render("国内疫情数据数据.html")
    )
def main():
    data=Parse_page()
    data=pd.DataFrame(data)
    second = sleeptime(24,0,0)
    while True:
#         print(data)
        data.to_csv('./国内疫情数据.csv')
        View()
        time.sleep(second)
# main()

data=Parse_page()
data=pd.DataFrame(data)
data

爬取百度翻译接口

import requests
def BaiDu_fanyi(url):
    kw = input('请输入待翻译的英文/中文单词:')
    data={'kw':kw}
    headers = {
    'User_Agent':'Mozilla/5.0',
    'content-length': str(len(data)),
    'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'referer': 'https://fanyi.baidu.com/',
    'x-requested-with': 'XMLHttpRequest'
    }
    response=requests.post(url,headers=headers,data=data)
#     print(response.json())
# 请输入待翻译的英文/中文单词:word
# {'errno': 0, 'data': [{'k': 'word', 'v': 'n. 单词; 话语; 诺言; 消息 vt. 措辞,用词; 用言语表达 vi. 讲话'}, 
# {'k': 'Word', 'v': '微软公司生产的文字处理软件。; [人名] 沃德'}, {'k': 'words', 'v': 'n. 字( word的名词复数 );
# (说的)话; 诺言; 口令'}, {'k': 'Words', 'v': '[医]言语'}, {'k': 'WORDS', 'v': 'abbr. Western Operational Research Discussion Soci'}]}
    result=''
    for i in response.json()['data']:
        result+=i['v']+'\n'
    print("{}的翻译结果为:".format(kw))
    print(result)
url='https://fanyi.baidu.com/sug'
BaiDu_fanyi(url)

爬取QQ音乐流行指数榜

import requests
import re
def Get_HTML(url):
    headers={'User-Agent':'Mozilla/5.0'}
    try:
        r=requests.get(url,headers=headers)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        print("error!")
def ParsePage(html):
    pattern=re.compile('<div class="songlist__songname">.?<a title="(.?)" href.?>.?</a>.?<div class="songlist__artist">.?<a class.?>(.?)</a>',re.S)
    items=re.findall(pattern,html)
    return items
def Print(items):
    name=[]
    tplt="{0:^10}{1:^25}{2:^25}"
    print("{0:^10}{1:^25}{2:^18}".format("排名","歌名","歌手",chr(12288)))
    for i in range(20):
        print(tplt.format(i+1,itemsi,itemsi),chr(12288))
def main():
    url='https://y.qq.com/n/ryqq/toplist/4';
    html=Get_HTML(url)
    items=ParsePage(html)
    Print(items)
main()