Scraper for from https://www.eraktkosh.in/BLDAHIMS/bloodbank/stockAvailability.cnt

bloody_scraper.py

# !usr/bin/env python3
from bs4 import BeautifulSoup  
import sys
import pandas as pd
import argparse


def args():
    parser = argparse.ArgumentParser()
    parser.add_argument('-f','--filename',help='path to input', type=str)
    parser.add_argument('-o','--output',help='Path to store the file', type=str)
    args = parser.parse_args()
    return args

def _row_data(row):
    tds = row.findAll('td')
    data = [td.text if td.text else 'Live' for td in tds]
    return data

def _get_data(soup):
    rows = soup.findAll('tr')
    data = [_row_data(row) for row in rows]
    return data

def table_data(filename):
    file = open(filename)
    soup = BeautifulSoup(file, 'html.parser')
    data = _get_data(soup)
    return data

def generate_csv(list_data, output_file):
    cols = ['Sno','Blood Bank','Category','Availability','Last Updated','Type']
    df = pd.DataFrame(data=list_data, columns=cols).dropna()
    df.to_csv(output_file,index=False)
    print(f'{output_file} Saved!')

def main():
    filename = args().filename
    output = args().output
    table = table_data(filename=filename)
    generate_csv(list_data=table, output_file=output)
    
if __name__ == '__main__':
    main()