爬取美国各州实时疫情数据 首先选择爬虫网站数据来源，这里选取的是腾讯疫情数据实时更新网站https://news.qq.com/zt2020/page/feiyan.htm选取相关数据接口：https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign #获取数据import requestsimport jsonimport pandas as pd#爬取数据的网址（腾讯新闻网实时更新）America_url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign'headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36','referer': 'https://news.qq.com/'}#获取到json格式数据response = requests.get(url=America_url,headers = headers).json() 保存数据 #将json格式转换成字典data = json.loads(response['data'])#保存数据with open('./美国疫情.json','w') as f: #再将字典改成json格式 f.write(json.dumps(data,indent=2,ensure_ascii=False)) #indent为格式空两格的操作#将数据保存到Excelwith open('./美国疫情.json','r') as f: data = f.read() 整理保存的数据，选取其中需要的数据，重新写入Excel #将json格式保存为字典data = json.loads(data)#获取美国的疫情数据AmericaDict = data['foreignList'][0]#获取美国各州的疫情数据ProvinceList = AmericaDict['children']#保存美国总的疫情数据AmericaCityList = []AmericaTotal = {'更新截止时间':AmericaDict['date'],'province':'北美洲','州':'美国','累计确诊':AmericaDict['confirm'],'治愈':AmericaDict['heal'],'死亡':AmericaDict['dead']}AmericaCityList.append(AmericaTotal)#遍历美国各州for i in range(len(ProvinceList)): date = ProvinceList[i]['date'] province_English = ProvinceList[i]['nameMap'] province = ProvinceList[i]['name'] dead = ProvinceList[i]['dead'] heal = ProvinceList[i]['heal'] confirm = ProvinceList[i]['confirm'] city_list = {'更新截止时间':date,'province':province_English,'州':province,'累计确诊':confirm,'治愈':heal,'死亡':dead} AmericaCityList.append(city_list)#将json格式转换成DataFrameAmericaTotalData = pd.DataFrame(AmericaCityList)#保存至Excel文档AmericaTotalData.to_excel('AmericaData.xlsx',index=False,sheet_name=AmericaDict['date']) 查看数据