python爬取河北省疫情通报

河北省卫生健康委员会关于疫情的通报格式一般为如下格式：因此可以通过改变爬取地址去爬取所有疫情数据。

 

代码如下：

from lxml import etree
import re
import requests


def info(url):
    strhtml = requests.get(url)  # Get方式获取网页数据
    tree = etree.HTML(strhtml.text)
    text=tree.xpath('//p//text()')
    text[0] = re.sub(r'\u3000', '', text[0])
    date=re.findall(r"(.+?日)", text[0])
    print("时间",date)
    xin_que_num=re.findall(r"新增确诊病例(.+?例)", text[0])
    mid = text[0].split("其中", 1)[1]
    num=len(mid.split("其中", 1))
    if num>1:
        mid=mid.split("其中", 1)[0]
    xin_shi_num=re.findall(r"[，,、](.+?市)(.+?例)", mid)
    xin_chu_num = re.findall(r"新增治愈出院病例(.+?例)", text[0])
    xin_yi_num = re.findall(r"新增疑似病例(.+?例)", text[0])
    print("新增确诊病例",xin_que_num)
    print("详细新增确诊病例",xin_shi_num)
    print("新增治愈出院病例",xin_chu_num)
    print("新增疑似病例",xin_yi_num)

    que_num=re.findall(r"累计报告确诊病例(.+?例)", text[1])
    si_num=re.findall(r"例，其中死亡(.+?例)", text[1])
    zhong_num=re.findall(r"，现有重症病例(.+?例)", text[1])
    yu_num=re.findall(r"，累计治愈出院(.+?例)", text[1])
    print("累计确诊病例",que_num)
    print("死亡病例",si_num)
    print("重症病例",zhong_num)
    print("出院病例",yu_num)

    que_xi_num=[]
    si_xi_num=[]
    zhong_xi_num=[]
    chu_xi_num=[]
    num=len(text[1].split("确诊病例中",1))
    if num>1:
        mid = text[1].split("确诊病例中", 1)[1]
        num = len(mid.split("死亡病例中",1))
        if num > 1:
            que=mid.split("死亡病例中",1)[0]
            que_xi_num = re.findall(r"[，、](.+?市)(.+?例)", que)
            si=mid.split("死亡病例中",1)[1]
            mid=si
            num = len(mid.split("重症病例中", 1))
            if num > 1:
                si=mid.split("重症病例中",1)[0]
                si_xi_num = re.findall(r"[，、](.+?市)(.+?例)", si)
                zhong=mid.split("重症病例中",1)[1]
                mid=zhong
                num = len(mid.split("出院病例中", 1))
                if num > 1:
                    zhong=mid.split("出院病例中",1)[0]
                    zhong_xi_num = re.findall(r"[，、](.+?市)(.+?例)", zhong)
                    chu=mid.split("出院病例中",1)[1]
                    chu_xi_num = re.findall(r"[，、](.+?市)(.+?例)", chu)
                else:
                    zhong_xi_num = re.findall(r"[，、](.+?市)(.+?例)", zhong)
            else:
                si_xi_num = re.findall(r"[，、](.+?市)(.+?例)", si)
    print("详细确诊病例",que_xi_num)
    print("详细死亡病例",si_xi_num)
    print("详细重症病例",zhong_xi_num)
    print("详细出院病例",chu_xi_num)

    yisi_num=re.findall(r"疑似病例(.+?例)", text[1])
    print("疑似病例",yisi_num)

    miqie_num=re.findall(r"密切接触者(.+?人)", text[2])
    jie_num=re.findall(r"解除隔离医学观察(.+?人)", text[2])
    guan_num=re.findall(r"现有(.+?人)", text[2])
    print("密切接触者",miqie_num)
    print("接触医学观察",jie_num)
    print("现有医学观察人数",guan_num)


def get_url(url):
    strhtml = requests.get(url)  # Get方式获取网页数据
    tree = etree.HTML(strhtml.text)
    return tree


if __name__ == '__main__':
    url = 'http://www.hebwst.gov.cn/index.do?cid=326&templet=list'
    list_url = get_url(url)
    tltle_ = list_url.xpath('//tr/td/a//text()')
    url_ = list_url.xpath('//tr/td/a/@href')
    l = []
    url_tltles = [] #疫情标提列表
    url_list = [] #疫情详情页列表
    for i in tltle_:
        if i == '\r\n\t\t\t\t\t\t':
            pass
        else:
            l.append(i)

    for index,i in enumerate(l):
        if '河北省新型冠状病毒' not in i :
            pass
        else:
            url_list.append(url_[index])
            url_tltles.append(i)
    for index,i in enumerate(url_list):
        url = 'http://www.hebwst.gov.cn/'+i
        print(url_tltles[index])
        print(url)
        info(url)