实战：使用python爬取新冠疫情国内外最新数据

新型冠状病毒肺炎实时更新地图

完整代码

===============================================================

很久没有写python了= =代码有点冗余

import requests

from lxml import etree

def spiderDemo():

headers = {

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36’}

pre_url = ‘https://user.guancha.cn/app/pneumonia’

html = requests.get(pre_url, headers=headers)

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])

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）

习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！**

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）