Crawling State and their Codes for Weather forecast

app.py

@@ -381,7 +381,7 @@ with gr.Blocks(title='KKMS-KSSW Demo') as demo:
             with gr.Tab(label='Weather Forecast for next 5 days'):
                 # Select the State
                 state = gr.Dropdown(
-                    constants_utils.WEATHER_FORECAST_STATES,
+                    list(constants_utils.WEATHER_FORECAST_STATE_CODES.keys()),
                     label="Select state"
                 )
 

src/constants.py

@@ -124,47 +124,7 @@ MANDI_PRICE_STATES = [
 
 # State list used in the Weather forecast widget dropdown list
 weather_utils_obj = weather_utils.WEATHER()
-WEATHER_FORECAST_STATES = weather_utils_obj.get_state_names()
-
-WEATHER_FORECAST_STATE_CODES = {
-    'Andaman-Nicobar': '01',
-    'Andhra-Pradesh': '02',
-    'Arunachal-Pradesh': '03',
-    'Assam': '04',
-    'Bihar': '05',
-    'Chandigarh': '06',
-    'Chhattisgarh': '07',
-    'Dadra-and-Nagar-Haveli': '08',
-    'Daman-and-Diu': '09',
-    'Delhi': '10',
-    'Goa': '11',
-    'Gujarat': '12',
-    'Haryana': '13',
-    # 14
-    'Himachal-Pradesh': '15',
-    'Jammu-Kashmir': '16',
-    'Jharkhand': '17',
-    'Karnataka': '18',
-    'Kerala': '19',
-    'Lakshadweep': '20',
-    'Madhya-Pradesh': '21',
-    'Maharashtra': '22',
-    'Manipur': '23',
-    'Meghalaya': '24',
-    'Mizoram': '25',
-    'Nagaland': '26',
-    'Odisha': '27',
-    'Pondicherry': '28',
-    'Punjab': '29',
-    'Rajasthan': '30',
-    'Sikkim': '31',
-    'Tamilnadu': '32',
-    'Telangana': '33',
-    'Tripura': '34',
-    'Uttar-Pradesh': '35',
-    'Uttarakhand': '36',
-    'West-Bengal': '37',
-}
+WEATHER_FORECAST_STATE_CODES = weather_utils_obj.get_state_names_codes()
 
 # LIST OF  PESTICIDES WHICH ARE BANNED AND RESTRICTED USE (List created from: https://pib.gov.in/PressReleaseIframePage.aspx?PRID=1896140)
 BANNED_PESTICIDES_FORMULATIONS = [

src/weather.py

@@ -6,18 +6,15 @@ import src.constants as constants_utils
 class WEATHER:
     def __init__(self):
         self.base_url = 'https://nwp.imd.gov.in/blf/blf_temp'
-
-        self.states = []
-        self.districts = []
-        self.states_districts = dict(
-                (ds, None) for ds in list(constants_utils.DATA_SOURCES.values()))
-        
         self.headers = {
             'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
         }
 
+        self.state_names_codes = {}
+        self.districts = []
+
 
-    def get_state_names(
+    def get_state_names_codes(
         self
     ):
         response = requests.get(
@@ -26,9 +23,12 @@ class WEATHER:
         )
 
         soup = bs(response.text, 'html.parser')
-        self.states = soup.findAll('select', {'onchange': 'window.location.href=this.value'}, limit=None)
-        self.states = [state.strip() for state in self.states[0].text.split('\n') if state and state != 'Select']
-        return self.states
+        for option in soup.find_all('option'):
+            if option.text.strip() == 'Select':
+                continue
+            self.state_names_codes[option.text.strip()] = str(option['value'].split('=')[-1][:2])
+        
+        return self.state_names_codes
 
 
     def get_district_names(
@@ -44,7 +44,6 @@ class WEATHER:
         soup = bs(response.text, 'html.parser')
         self.districts = soup.findAll('select', {'name': 'dis'}, limit=None)
         self.districts = [district.strip() for district in self.districts[0].text.split('\n') if district and district != 'Select']
-        # self.districts = [district for district in self.districts[0].text.split('\n\n') if district]
         return self.districts