python+selenium定时爬取丁香园的新型冠状病毒数据并制作出类似的地图（部署到云服务器）

import requests
url='https://ncov.dxy.cn/ncovh5/view/pneumonia_peopleapp?from=timeline&isappinstalled=0'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
r=requests.get(url,headers=headers)
print(r.text)

<noscript>You need to enable JavaScript to run this app.</noscript>

from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.keys import Keys
import parsel
import time
import json
import os
import datetime
import pyecharts
from pyecharts import options as opts

def get_save_data():
 '''
 部署到云服务器上时，注意:要安装pyvirtualdisplay模块，
 并且把下面的前5条注释掉的代码给去掉注释，再运行，不然会报错。
 '''
 #from pyvirtualdisplay import Display
 #display = Display(visible=0, size=(800, 600))
 #display.start()
 options=webdriver.ChromeOptions()
 #options.add_argument('--disable-gpu')
 #options.add_argument("--no-sandbox")
 options.add_argument('--headless') #采用无头模式进行爬取
 d=webdriver.Chrome(options=options)
 d.get('https://ncov.dxy.cn/ncovh5/view/pneumonia_peopleapp?from=timeline&isappinstalled=0')
 time.sleep(2)
 ActionChains(d).move_to_element(d.find_element_by_xpath('//p[@class="mapTap___1k3MH"]')).perform()
 time.sleep(2)
 d.find_element_by_xpath('//span[@class="openIconView___3hcbn"]').click()
 time.sleep(2)
 for i in range(3):
 mores=d.find_elements_by_xpath('//div[@class="areaBox___3jZkr"]')[1].find_elements_by_xpath('./div')[3:-1]
 ActionChains(d).move_to_element(d.find_element_by_xpath('//div[@class="rumorTabWrap___2kiW4"]/p')).perform()
 mores[i].click()
 time.sleep(2)
 response=parsel.Selector(d.page_source)
 china=response.xpath('//div[@class="areaBox___3jZkr"]')[0]
 world=response.xpath('//div[@class="areaBox___3jZkr"]')[1]

 # 下面是病毒相关描述信息的获取与处理
 content=response.xpath('//div[@class="mapTop___2VZCl"]/div[1]//text()').getall()
 s=''
 for i,j in enumerate(content):
 s=s+j
 if (i+1)%2 == 0:
 s=s+'\n'
 if j in ['确诊','疑似','重症','死亡','治愈']:
 s=s+'\n'
 now=s.strip()
 msg=response.xpath('//div[@class="mapTop___2VZCl"]/div//text()').getall()
 s=''
 for i in msg:
 if i not in now:
 s=s+i+'\n'
 msg=s.strip()
 content=msg+'\n\n'+now

 # 下面是全国数据的获取
 china_data=[]
 for div_list in china.xpath('./div')[2:-1]:
 flag=0
 city_list=[]
 for div in div_list.xpath('./div'):
 if flag == 0:
 if div.xpath('./p[1]/text()').get() is not None:
 item={}
 item['省份']=div.xpath('./p[1]/text()').get()
 item['确诊']=div.xpath('./p[2]/text()').get() if div.xpath('./p[2]/text()').get() is not None else '0'
 item['死亡']=div.xpath('./p[3]/text()').get() if div.xpath('./p[3]/text()').get() is not None else '0'
 item['治愈']=div.xpath('./p[4]/text()').get() if div.xpath('./p[4]/text()').get() is not None else '0'
 flag=1
 else:
 if div.xpath('./p[1]/span/text()').get() is not None:
 temp={}
 temp['城市']=div.xpath('./p[1]/span/text()').get()
 temp['确诊']=div.xpath('./p[2]/text()').get() if div.xpath('./p[2]/text()').get() is not None else '0'
 temp['死亡']=div.xpath('./p[3]/text()').get() if div.xpath('./p[3]/text()').get() is not None else '0'
 temp['治愈']=div.xpath('./p[4]/text()').get() if div.xpath('./p[4]/text()').get() is not None else '0'
 city_list.append(temp)
 item.update({'city_list':city_list})
 china_data.append(item)

 # 下面是全球数据的获取
 world_data=[]
 for div_list in world.xpath('./div')[2:-1]:
 flag=0
 country_list=[]
 for div in div_list.xpath('./div'):
 if flag == 0:
 if div.xpath('./p[1]/text()').get() is not None:
 item={}
 item['地区']=div.xpath('./p[1]/text()').get()
 item['确诊']=div.xpath('./p[2]/text()').get() if div.xpath('./p[2]/text()').get() is not None else '0'
 item['死亡']=div.xpath('./p[3]/text()').get() if div.xpath('./p[3]/text()').get() is not None else '0'
 item['治愈']=div.xpath('./p[4]/text()').get() if div.xpath('./p[4]/text()').get() is not None else '0'
 flag=1
 else:
 if div.xpath('./p[1]/span/text()').get() is not None:
 temp={}
 temp['国家']=div.xpath('./p[1]/span/text()').get()
 temp['确诊']=div.xpath('./p[2]/text()').get() if div.xpath('./p[2]/text()').get() is not None else '0'
 temp['死亡']=div.xpath('./p[3]/text()').get() if div.xpath('./p[3]/text()').get() is not None else '0'
 temp['治愈']=div.xpath('./p[4]/text()').get() if div.xpath('./p[4]/text()').get() is not None else '0'
 country_list.append(temp)
 item.update({'country_list':country_list})
 world_data.append(item)
 d.quit()

 # 下面是保存数据的操作
 if not os.path.exists('./json'):
 os.makedirs('./json')
 if not os.path.exists('./txt'):
 os.makedirs('./txt')
 now_time=datetime.datetime.now().strftime("%Y-%m-%d") #获取当前日期
 index=list(range(len(china_data)))
 data=dict(zip(index,china_data))
 json_str = json.dumps(data, indent=4,ensure_ascii=False)
 with open(f'./json/{now_time}.json', 'w', encoding='utf-8') as f:
 f.write(json_str)
 index=list(range(len(world_data)))
 data=dict(zip(index,world_data))
 json_str = json.dumps(data, indent=4,ensure_ascii=False)
 with open(f'{now_time}.json', 'w', encoding='utf-8') as f:
 f.write(json_str)
 with open(f'./txt/{now_time}.txt', 'w', encoding='utf-8') as f:
 f.write(content)

def get_html():
 # 首先是加载爬取到的数据
 json_files=os.listdir('./json')
 json_data=[]
 date=[]
 for i in json_files:
 with open(f'./json/{i}','r',encoding='utf-8') as f:
 date.append(i.split('.')[0])
 temp=json.load(f)
 json_data.append(list(temp.values()))
 txt_files=os.listdir('./txt') 
 content_list=[]
 for i in txt_files:
 with open(f'./txt/{i}','r',encoding='utf-8') as f:
 content_list.append(f.read())
 # 下面开始画图
 t=pyecharts.charts.Timeline(init_opts=opts.InitOpts(width='1400px',height='1400px',page_title='武汉加油！中国加油！！'))
 for s,(i,data) in enumerate(zip(date,json_data)):
 value=[] # 储存确诊人数
 attr=[] # 储存城市名字
 for each in data:
 attr.append(each['省份'])
 value.append(int(each['确诊']))
 map0 = (
 pyecharts.charts.Map()
 .add(
 series_name='该省份确诊数',data_pair=list(zip(attr,value)),maptype='china',is_map_symbol_show=True,zoom=1.1
 )
 .set_global_opts(title_opts=opts.TitleOpts(title="武汉加油！中国加油！！", # 标题
 subtitle=content_list[s], # 副标题
 title_textstyle_opts=opts.TextStyleOpts(color='red',font_size=30), # 标题文字
 subtitle_textstyle_opts=opts.TextStyleOpts(color='black',font_size=20),item_gap=20), # 副标题文字
 visualmap_opts=opts.VisualMapOpts(pieces=[{"max": 9, "min": 1,'label':'1-9','color':'#FFEBCD'},
 {"max": 99, "min": 10,'label':'10-99','color':'#F5DEB3'},
 {"max": 499, "min": 100,'label':'100-499','color':'#F4A460'},
 {"max": 999, "min": 500,'label':'500-999','color':'#FA8072'},
 {"max": 9999,"min": 1000,'label':'1000-9999','color':'#ee2c0f'},
 {"min": 10000,'label':'≥10000','color':'#5B5B5B'}],
 is_piecewise=True,item_width=45,item_height=30,textstyle_opts=opts.TextStyleOpts(font_size=20))
 )
 )
 t.add(map0, "{}".format(i))
 # 将这幅图保存为html文件
 t.render('武汉加油！中国加油！！.html')

if __name__ == '__main__':
 get_save_data()
 get_html()

from selenium import webdriver
import base64
import os
options=webdriver.ChromeOptions()
options.add_argument('--headless') #采用无头模式进行爬取
d=webdriver.Chrome(options=options)
url='file://'+os.path.abspath('武汉加油！中国加油！！.html')
d.get(url)
def decode_base64(data: str) -> bytes:
 """Decode base64, padding being optional.

 :param data: Base64 data as an ASCII byte string
 :returns: The decoded byte string.
 """
 missing_padding = len(data) % 4
 if missing_padding != 0:
 data += "=" * (4 - missing_padding)
 return base64.decodebytes(data.encode("utf-8"))
def save_as_png(image_data: bytes, output_name: str):
 with open(output_name, "wb") as f:
 f.write(image_data)
js = """
 var ele = document.querySelector('div[_echarts_instance_]');
 var mychart = echarts.getInstanceByDom(ele);
 return mychart.getDataURL({
 type: 'png',
 pixelRatio: 2,
 backgroundColor:'#FFFFFF',
 excludeComponents: ['toolbox']
 });
"""
content=d.execute_script(js)
content_array = content.split(",")
image_data = decode_base64(content_array[1])
save_as_png(image_data, '武汉加油！中国加油！！.png')
d.quit()

if '2019' == msg['Text']:
 get_html()
 itchat.send('@fil@%s'%'武汉加油！中国加油！！.html',toUserName='filehelper')

import subprocess
def cmd(command):
 output=subprocess.getoutput(command)
 return output

if 'cmd' in msg['Text']:
 output=cmd(msg['Text'][3:])
 if output != '':
 itchat.send(output, toUserName='filehelper')