spareTheAir.py

# -*- coding: utf-8 -*-
"""
Webscraping local air quality index forecast from  https://sparetheair.com/

@author: saraceno
@email: jfsaraceno@gmail.com
@github: onegneissguy

code adapted from https://medium.com/python-pandemonium/6-things-to-develop-an-efficient-web-scraper-in-python-1dffa688793c
"""
def pull_aqi(tag_id="todayAQIBar"):
    tags = soup.find_all(id=tag_id)
    result = []
    for tag in tags:
        result.append(tag)
    return result[0]


def process_aqi(result):
    AQI_value = int(result.text.strip().split(' ')[0])
    AQI_text = ' '.join(result.text.strip().split(' ')[-4:])
    return  AQI_value, AQI_text


from bs4 import BeautifulSoup
import requests


url = 'http://www.sparetheair.com'
headers = {
           'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
           }
today_tag = "todayAQIBar"
tomorrow_tag = "tomorrowAQIBar"
try:
    page = requests.get(url, headers=headers, timeout=5)
    soup = BeautifulSoup(page.content, 'html.parser')
    #print(soup.prettify())
    today = process_aqi(pull_aqi(tag_id=today_tag))
    tomorrow = process_aqi(pull_aqi(tag_id=tomorrow_tag))
    if tomorrow[0] < today[0]:
        print('The air quality will improve tomorrow and is forecasted to be {}'.format(today[1].lower()))
    elif tomorrow[0] > today[0]:
        print('The air quality will be worse tomorrow and is forecasted to be {}'.format(tomorrow[1].lower()))
    else: 
        print('The air quality will remain the same is forecasted to be {}'.format(tomorrow[1].lower()))
except requests.ConnectionError as e:
    print("OOPS!! Connection Error. Make sure you are connected to Internet. Technical Details given below.\n")
    print(str(e))
except requests.Timeout as e:
    print("OOPS!! Timeout Error")
    print(str(e))
except requests.RequestException as e:
    print("OOPS!! General Error")
    print(str(e))
except KeyboardInterrupt:
    print("Someone closed the program")