最新实战：使用python爬取新冠疫情国内外最新数据

selector = etree.HTML(html.text)

china_list = selector.xpath(“//*[@id=‘table1’]/div[4]/div”)

china_result = {}

china_detail = []

for province in china_list:

province_name = (province.xpath(“div[1]/div[1]/text()”)[0])

province_confirm = int((province.xpath(“div[1]/div[2]/text()”)[0]))

province_died = int((province.xpath(“div[1]/div[3]/text()”)[0]))

province_cure = int((province.xpath(“div[1]/div[3]/text()”)[0]))

province_city = province.xpath(“div[2]/div”)

province_city_result = []

for city in province_city:

city_name = city.xpath(“div[1]/text()”)[0]

city_confirm = int(city.xpath(“div[2]/text()”)[0])

city_died = int(city.xpath(“div[3]/text()”)[0])

city_cure = int(city.xpath(“div[4]/text()”)[0])

province_city_result.append({

“城市名”: city_name,

“确诊数”: city_confirm,

“死亡数”: city_died,

“治愈数”: city_cure

})

item = {

“省份名”: province_name,

“确诊数”: province_confirm,

“死亡数”: province_died,

“治愈数”: province_cure,

“下属城市”: province_city_result

}

china_detail.append(item)

china_result[“详细数据”] = china_detail

china_today_confirm = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[1]/p[1]/text()”)[0])

china_today_suspect = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[2]/p[1]/text()”)[0])

china_today_cure = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[3]/p[1]/text()”)[0])

china_today_death = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[4]/p[1]/text()”)[0])

china_total_confirm = int(selector.xpath(“/html/body/div[1]/div[3]/div[2]/div[2]/div/div[1]/p[1]/text()”)[0])

china_total_suspect = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[2]/p[1]/text()”)[0])

china_total_cure = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[3]/p[1]/text()”)[0])

china_total_death = int(selector.xpath(“/html/body/div[1]/div[3]/div[1]/div[2]/div/div[4]/p[1]/text()”)[0])

china_result[“今日数据”] = {“新增确诊”: china_today_confirm, “新增疑似”: china_today_suspect, “新增治愈”: china_today_cure,

“新增死亡”: china_today_death, }

china_result[“累计病例”] = {“确诊病例”: china_total_confirm, “疑似病例”: china_total_suspect, “治愈病例”: china_total_cure,

“死亡病例”: china_total_death, }

world_list = selector.xpath(“//*[@id=‘table2’]/div[4]/div/div/div”)

world_result = {}

world_detail = []

for country in world_list:

country_name = (country.xpath(“div[1]/text()”)[0])

country_confirm = (country.xpath(“div[2]/text()”)[0])

country_cure = (country.xpath(“div[3]/text()”)[0])

country_death = (country.xpath(“div[4]/text()”)[0])

item = {

“国家名”: country_name,

“确诊数”: country_confirm,

“死亡数”: country_cure,

“治愈数”: country_death

}

world_detail.append(item)

world_result[“详细数据”] = world_detail

world_today_confirm = int(selector.xpath(“/html/body/div[1]/div[4]/div[1]/div[2]/div/div[1]/p[1]/text()”)[0])

感谢每一个认真阅读我文章的人，看着粉丝一路的上涨和关注，礼尚往来总是要有的：

①　2000多本Python电子书（主流和经典的书籍应该都有了）

②　Python标准库资料（最全中文版）

③　项目源码（四五十个有趣且经典的练手项目及源码）

④　Python基础入门、爬虫、web开发、大数据分析方面的视频（适合小白学习）

⑤ Python学习路线图（告别不入流的学习）

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

需要这份系统化学习资料的朋友，可以戳这里无偿获取

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！