爬取肺炎疫情最新动态

leoqs

看楼主装X

Kate_M

回复看代码

yellow_rain

学习一下

supergzx

学习学习

wt9503

1

DavidCT

想看代码，支持楼主

Carry2020

python

云犀

新小白，来看看

人间洪荒镜

厉害

python-yjl

高大上，好好学习下。

蒙哥-斧王

爬取肺炎疫情最新动态

windsboy

学习

暗冬序曲

666

PhycoCycle

我想看看

MichaelBach

666

ski_magicboy

1. from selenium import webdriver
   
2. import re
   
3. import pandas as pd
   
4. import openpyxl as op
   
5. import time
   
6. class feiyan():
   
7.     def __init__(self,html=None,source=None,confirmed=None,suspected=None,cure=None,died=None,timess=None):
   
8.         self.html = html
   
9.         self.source = source
   
10.         self.confirmed = confirmed
    
11.         self.suspected = suspected
    
12.         self.cure = cure
    
13.         self.died = died
    
14.         self.timess = timess
    
15.     def FindWeb(self,html):
    
16.         option = webdriver.ChromeOptions()
    
17.         option.add_argument('--headless')
    
18.         driver = webdriver.Chrome(options=option)
    
19.         driver.get(html)
    
20.         time.sleep(5)
    
21.         #source = driver.page_source
    
22.         self.source = driver.execute_script('return document.documentElement.outerHTML') #执行JS后得到整个HTML
    
23.         return self.source
    
24.     def FindData(self):
    
25.         confir = re.search(r'number.*\S\s*.*累计确诊',self.source)
    
26.         self.confirmed = re.search(r'\d+',confir.group())
    
27.         suspect = re.search(r'number.*\S\s*.*现有疑似',self.source)
    
28.         self.suspected = re.search(r'\d+',suspect.group())
    
29.         cur = re.search(r'number.*\S\s*.*治愈人数',self.source)
    
30.         self.cure = re.search(r'\d+',cur.group())
    
31.         die = re.search(r'number.*\S\s*.*死亡人数',self.source)
    
32.         self.died = re.search(r'\d+',die.group())
    
33.         times = re.search(r'统计截至.*?</span>',self.source)
    
34.         self.timess = re.search(r'\d+-\d+-\d+\s+\d+:\d+:\d+',times.group())
    
35.         print('截止{}:\n全国确诊人数为：{}人\n'.format(self.timess.group(),self.confirmed.group()))
    
36.         print('疑似病例为：{}人\n'.format(self.suspected.group()))
    
37.         print('治愈人数为：{}人\n'.format(self.cure.group()))
    
38.         print('死亡人数为：{}人\n'.format(self.died.group()))
    
39.     def save(self):
    
40.         target = r'E:\Python\肺炎数据\肺炎数据.xlsx'  #读取前一天数据，合并生成本日数据并保存
    
41.         excel = pd.read_excel(target)
    
42.         num = len(excel.loc[:,'时间'])
    
43.         excel.loc[num,'时间'] = self.timess.group()
    
44.         excel.loc[num,'确诊人数'] = self.confirmed.group()
    
45.         excel.loc[num,'死亡人数'] = self.died.group()
    
46.         excel.loc[num,'治愈人数'] = self.cure.group()
    
47.         excel.loc[num,'疑似病例'] = self.suspected.group()
    
48.         book = op.load_workbook(target)
    
49.         write = pd.ExcelWriter(target,engine = 'openpyxl')
    
50.         write.book = book
    
51.         excel.to_excel(write,sheet_name='alldata')
    
52.         write.save()
    
53.         write.close()
    
54. if __name__ == '__main__':
    
55.     f = feiyan()
    
56.     f.FindWeb(html='https://news.qq.com//zt2020/page/feiyan.htm')
    
57.     f.FindData()
    
58.     f.save()

复制代码

Spx12138

爬取

jmfsw

武汉加油！

挣扎起飞

牛逼

0404

6