import requestsfrom bs4 import BeautifulSoupresponse = requests.get('https://ncov.dxy.cn/ncovh5/view/pneumonia')home_page = response.content.decode()soup = BeautifulSoup(home_page, 'lxml')print(soup)

import requestsfrom bs4 import BeautifulSoupimport reimport jsonimport pandas as pdimport matplotlib.pyplot as plt# 采集最近一日疫情数据class ChinaCoronaVirusSpider():    def __init__(self):        self.home_url = 'https://ncov.dxy.cn/ncovh5/view/pneumonia'    # 获取数据函数    def get_content_from_url(self, url):        response = requests.get(url)  # 发送请求，获取疫情首页        return response.content.decode()  # 提取最近一日全国各省疫情数据    # 解析数据函数    def parse_home_page(self, home_page):        soup = BeautifulSoup(home_page, 'lxml')  # 从HTML或XML文件中提取数据        script = soup.find(id="getAreaStat")        text = script.text        json_str = re.findall(r'\[.+\]', text)[0]  # 正则表达式提取json字符串        python_str = json.loads(json_str)  # json字符串转化为python类型数据        return python_str    # 保存数据函数    def save(self, data, path):        with open(path, 'w') as fp:            json.dump(data, fp, ensure_ascii=False)    # 爬虫函数    def crawl_china_last_day_corona_virus(self):        home_page = self.get_content_from_url(self.home_url)  # 调用获取数据函数        data = self.parse_home_page(home_page)  # 调用解析数据函数        self.save(data, 'china_last_day_corona_virus.py')  # 调用保存数据函数        # 数据可视化        china_data_set = []        for i in data:            china_data_dict = {}            china_data_dict['省份'] = i['provinceShortName']            china_data_dict['现存确诊数'] = i['currentConfirmedCount']            china_data_dict['累计确诊数'] = i['confirmedCount']            china_data_dict['死亡数'] = i['deadCount']            china_data_dict['治愈数'] = i['curedCount']            china_data_set.append(china_data_dict)        china_df = pd.DataFrame(china_data_set)        china_df1 = china_df[china_df['现存确诊数']>10]        plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']        china_df1.plot.bar(x='省份', y='现存确诊数')        plt.show()        shanxi_data_set = []        for i in data:            if i['provinceShortName'] == '广东':                for k, v in i.items():                    if k == 'cities':                        for i in v:                            guangdong_data_dict = {}                            guangdong_data_dict['城市'] = i['cityName']                            guangdong_data_dict['现存确诊数'] = i['currentConfirmedCount']                            guangdong_data_dict['累计确诊数'] = i['confirmedCount']                            guangdong_data_dict['死亡数'] = i['deadCount']                            guangdong_data_dict['治愈数'] = i['curedCount']                            guangdong_data_set.append(shanxi_data_dict)        guangdong_df = pd.DataFrame(guangdong_data_set)        guangdong_df1 = guangdong_df[guangdong_df['现存确诊数']>0]        # 设置matplotlib中文字体(mac系统)        # plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']          # 设置matplotlib中文字体(windows系统)        # from matplotlib.pylab import style        # style.use('ggplot')        # plt.rcParams['font.sans-serif'] = ['SimHei']        # plt.rcParams['axes.unicode_minus'] = False        # 如果未设置，matplotlib所绘制的图无法显示中文        guangdong_df1.plot.bar(x='城市', y='现存确诊数')        plt.show()    def run(self):        self.crawl_china_last_day_corona_virus()  # 调用爬虫函数
if __name__ == '__main__':    spider = ChinaCoronaVirusSpider()    spider.run()

import requestsfrom bs4 import BeautifulSoupimport reimport jsonfrom tqdm import tqdm# 采集记录以来疫情数据class ChinaCoronaVirusSpider():    def __init__(self):        self.home_url = 'https://ncov.dxy.cn/ncovh5/view/pneumonia'    # 获取数据函数    def get_content_from_url(self, url):        response = requests.get(url)  # 发送请求，获取疫情首页        return response.content.decode()  # 提取最近一日全国各省疫情数据    # 解析数据函数    def parse_home_page(self, home_page):        soup = BeautifulSoup(home_page, 'lxml')  # 从HTML或XML文件中提取数据        script = soup.find(id="getAreaStat")        text = script.text        json_str = re.findall(r'\[.+\]', text)[0]  # 正则表达式提取json字符串        python_str = json.loads(json_str)  # json字符串转化为python类型数据        return python_str    # 保存数据函数    def save(self, data, path):        with open(path, 'w') as fp:            json.dump(data, fp, ensure_ascii=False)    # 爬虫函数    def crawl_china_corona_virus(self):        # 加载最近一日全国各省数据        with open('china_last_day_corona_virus.py') as fp:            last_day_china_corona_virus = json.load(fp)        china_corona_virus = []        for province in last_day_china_corona_virus:            statistics_url = province['statisticsData']  # 遍历已经保存的最近一日全国各省数据，获取各省记录以来疫情数据的url            statistics_json_str = self.get_content_from_url(statistics_url)  # 调用获取数据函数            statistics_python_str = json.loads(statistics_json_str)['data']  # json字符串转化为python类型数据(只获取其中的'data')            for one_day in tqdm(statistics_python_str, '采集丁香园开始记录疫情以来全国各省疫情数据'):                one_day['provinceName'] = province['provinceName']            china_corona_virus.extend(statistics_python_str)            self.save(china_corona_virus, 'china_corona_virus.py')  # 调用保存数据函数    def run(self):        self.crawl_china_corona_virus()  # 调用爬虫函数
if __name__ == '__main__':    spider = ChinaCoronaVirusSpider()    spider.run()