爬取每日疫情通报

最新推荐文章于 2023-01-02 20:56:53 发布

许武

最新推荐文章于 2023-01-02 20:56:53 发布

阅读量371

点赞数

文章标签： python

本文链接：https://blog.csdn.net/vs_hero_2019/article/details/108515286

版权

爬取每日疫情通报

知识点

https://blog.csdn.net/qq_35531549/article/details/87983243 定义日期，数字或字符转日期
https://blog.csdn.net/HoWaterSuper/article/details/82891278 日期比较

源代码


from fake_useragent import UserAgent
import requests
from lxml import etree
import datetime
import time

class Yqtb(object):
    def __init__(self):
        self.ua = UserAgent()
        self.url = r'http://wjw.gz.gov.cn/ztzl/xxfyyqfk/yqtb/index.html'
        self.content = ''



    def parse_url(self,url):
        headers = {"User-Agent":self.ua.random}
        respose = requests.get(url,headers=headers).content.decode()
        return respose
    def get_url_list(self):
        res=self.parse_url(self.url)
        html = etree.HTML(res)
        #print(type(html))
        url_list = html.xpath("//div[@class='cont_list']/ul/li[2]//a/@href")
        date_list = html.xpath("//div[@class='cont_list']/ul/li[2]//a/text()")
        date_str = date_list[0]
        date_y = int(date_str[0:date_str.rfind("月")])
        date_r = int(date_str[date_str.rfind("月")+1:date_str.rfind("日")])
        # date_time_str = '2020-' + date_y + "-" + date_r
        # date_time = datetime.datetime.strptime(date_time_str , "%Y-%m-%d")
        date_time = datetime.datetime(2020,date_y,date_r)
        return url_list[0],date_time

    def valid_date(self,date_time):
        # 获取时间与当前时间对比
        now_time = datetime.datetime.now().strftime('%Y-%m-%d')
        e_time = date_time.strftime('%Y-%m-%d') #转换成字符串格式
        # 将日期转化为秒，
        s_now_time = time.mktime(time.strptime(now_time, "%Y-%m-%d"))
        s_e_time = time.mktime(time.strptime(e_time, "%Y-%m-%d"))
        diff = int(s_now_time) - int(s_e_time)
        if diff == 86400 :
            return True
        else:
            return False




    def get_content(self,url):
        res = self.parse_url(url)
        html = etree.HTML(res)
        content_list = html.xpath("//div[@class='zoom_box']/p//text()")
        content = '\n'.join(content_list)
        return content



    def run(self):

        content_url,date_time = self.get_url_list()
        content = self.get_content(content_url)
        print(date_time,content)
        if self.valid_date(date_time) :
            print("时间相同")
        else:
            print("时间不同")
        #1、获取URL列表
        #2、遍历列表，获取数据
        #3、保存数据



if __name__ == '__main__':
    yqtb = Yqtb()
    yqtb.run()