第二个python代码bs4并将数据保存到文本文件

Question

I have managed to write my 2nd python code and I am trying to extract data from a table on a webpage ie www.ksmnet.org. I need the data of the 2nd column of the table which is today's date and I have managed to extract that fine. However I need the data of the 1st column of the data to be saved as a text file containing the data of the 2nd column. So for example if Fajr is 05:00 then I need a text file to be saved as Fajr.txt and inside this text file I need 05:00.

I understand some of the times are not with the ":" symbol and I need to convert them. So for example the ones with 06.00 need to be 06:00.

Here is my code:

# import libraries
import json
import urllib.request
#import soupsieve
from bs4 import BeautifulSoup
import requests

url = 'https://www.ksmnet.org/'
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
html = response.read()
soup = BeautifulSoup(html.decode("utf-8"), "html.parser")
path = '/srv/docker/homeassistant/prayer/'


table = soup.find('div', id={'prayer': 'listing sortable'})
package = '' ; version = ''
for i in table.select('tr'):
    data = i.select('td')
    if data:
        package = data[0].text.strip()
        version = ' '.join(data[1].text.strip().split())
        print(version)

Can anyone please help?

Thanks

Answer 1

Here is the code to write in a text file.

import urllib.request
#import soupsieve
from bs4 import BeautifulSoup
import requests

url = 'https://www.ksmnet.org/'
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
html = response.read()
soup = BeautifulSoup(html.decode("utf-8"), "html.parser")
path = '/srv/docker/homeassistant/prayer/'


table = soup.find('div', id={'prayer': 'listing sortable'})
package = '' ; version = ''
for i in table.select('tr'):
    data = i.select('td')
    if data:
        package = data[0].text.strip()
        file = open(package[:-1] +".txt", "w+")
        version =data[1].text.strip().replace('.',':')
        file.write(version)
        file.close()

---

OR you can use python pandas .

import pandas as pd
url = 'https://www.ksmnet.org/'
df=pd.read_html(url)[0]
for pkg, version in zip(df['Date'],df['06/01']):
    file = open(pkg[:-1] +".txt", "w+")
    version =version.replace('.',':').strip()
    file.write(version)
    file.close()

---

UPDATE checking digits

import urllib.request
#import soupsieve
from bs4 import BeautifulSoup
import requests

url = 'https://www.ksmnet.org/'
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
html = response.read()
soup = BeautifulSoup(html.decode("utf-8"), "html.parser")
path = '/srv/docker/homeassistant/prayer/'


table = soup.find('div', id={'prayer': 'listing sortable'})
package = '' ; version = ''
for i in table.select('tr'):
    data = i.select('td')
    if data:
        package = data[0].text.strip()
        file = open(package[:-1] +".txt", "w+")
        version =data[1].text.strip().replace('.',':')

        #Check hours
        checkHours = version.split(':')[0]
        if len(checkHours) < 2:
            version ="0" + str(checkHours) +':' + version.split(':')[-1]
           # print(version)
        #Check minutes
        checkMinute = version.split(':')[-1]
        if len(checkMinute) < 2:
            version = version.split(':')[0] + ":" + "0" + str(checkMinute)
            print(version)

        file.write(version)
        file.close()