Python 爬蟲教學

import urllib.request as req

url="http://fhy.wra.gov.tw/ReservoirPage_2011/Statistics.aspx"

with req.urlopen(url)as response:

    data=response.read().decode("utf-8")

import bs4

root= bs4.BeautifulSoup((data.replace('<br>','')).replace('<br/>',''),"html.parser")

//把文件裡的空格替換掉

up=root.find("th", string="水庫名稱")

print(up.string) 

up2=root.find("th", string="水位(公尺)")

print(up2.string) 

up3=root.find("th", string="蓄水百分比(%)")

print(up3.string) 

with open ("haha.html", mode="w", encoding='UTF-8')as f:            

    f.write(up.string+"&nbsp;&nbsp;&nbsp;&nbsp;"+up2.string+"&nbsp;&nbsp;&nbsp;&nbsp;"+up3.string+"<br />"+"==============================<br />")

i=0

k=0

z=0

td =root.find_all("td" ,align="right")

a = root.find_all('a', target="chart")

  

for row in td:

                

    i=i+1 

    

    if(i==12):

        z=0

        i=0

        k=k+1

    for title in a:            

        with open ("haha.html", mode="a", encoding='UTF-8')as f:     

            z=z+1

            if(z==k+1):

                f.write(title.string+"&nbsp;&nbsp;&nbsp;&nbsp;")  

                break    

    if i==3 or i==6:

        with open ("haha.html", mode="a", encoding='UTF-8')as f:            

            f.write(row.string+"&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;")

    if(i==6):

        with open ("haha.html", mode="a", encoding='UTF-8')as f:            

            f.write("<br />")