Lambda function to send an email

import json
import requests
import PyPDF2 # for the parsing of the pdf
import boto3 # for the email service
import datetime
import io

ses = boto3.client('ses') # simple email service, needs further configuration on the AWS console

# function to send an email
def sendEmail(subject='testmail',body='testmail'):

    ses.send_email(
	    Source = 'your@email.com',
	    Destination = {
		    'ToAddresses': [
			    'your@email.com'
		    ]
	    },
	    Message = {
		    'Subject': {
			    'Data': subject,
			    'Charset': 'UTF-8'
		    },
		    'Body': {
			    'Text':{
				    'Data': body,
				    'Charset': 'UTF-8'
			    }
		    }
	    }
    )

# lets setup some useful functions
def download_pdf(pdf_url):
    response = requests.get(pdf_url)
    return io.BytesIO(response.content)  # Return a BytesIO object to avoid saving to disk

def extract_text_from_pdf(pdf_bytes):
    reader = PyPDF2.PdfReader(pdf_bytes)
    text = ''
    for page in reader.pages:
        text += page.extract_text()
    return text
    
# i  need this cause the text will be sent per email, and i basically need to format a string
def format_search_results(search_results):
    result_str = ""
    for keyword, details in search_results.items():
        # Add the keyword and occurrences
        result_str += f"Keyword: '{keyword}', Occurrences: {details['count']}\n"
        result_str += "Snippets:\n"
        
        # Add each snippet with a new line
        for snippet in details['snippets']:
            result_str += f"- {snippet}\n"
        
        # Add a newline for better separation between keywords
        result_str += "\n"
    
    return result_str

# Fixed-date public holidays in Italy. On these dates, the Gazzetta Ufficiale is not published.
def is_fixed_holiday(date_to_check):
    year = date_to_check.year
    fixed_holidays = {
        datetime.date(year, 1, 1),   # New Year's Day
        datetime.date(year, 1, 6),   # Epiphany
        datetime.date(year, 4, 25),  # Liberation Day
        datetime.date(year, 5, 1),   # Labor Day
        datetime.date(year, 6, 2),   # Republic Day
        datetime.date(year, 8, 15),  # Assumption Day (Ferragosto)
        datetime.date(year, 11, 1),  # All Saints' Day
        datetime.date(year, 12, 8),  # Feast of the Immaculate Conception
        datetime.date(year, 12, 25), # Christmas Day
        datetime.date(year, 12, 26)  # St. Stephen's Day
    }
    
    # Check if the date is in the set of fixed holidays
    return date_to_check in fixed_holidays

# the function to count the number of tuesdays and fridays from the beginning of the year
# this is needed because the gazzetta number is the sum of the two
def count_fridays_and_tuesdays(start_date, end_date):
    # Initialize counters
    friday_count = 0
    tuesday_count = 0

    # Iterate over each date between start_date and end_date
    current_date = start_date
    while current_date <= end_date:
        if is_fixed_holiday(current_date): # Skip fixed holidays
            pass
        elif current_date.weekday() == 1:  # Tuesday (weekday() == 1)
            tuesday_count += 1
        elif current_date.weekday() == 4:  # Friday (weekday() == 4)
            friday_count += 1
        
        # Move to the next day
        current_date += datetime.timedelta(days=1)

    return friday_count, tuesday_count

# function to search for keywords in the text
def search_keywords(text, keywords, snippet_radius=50):
    # Convert the entire text to lowercase for case-insensitive search
    lower_text = text.lower()
    
    # Store results for each keyword
    results = {}

    for keyword in keywords:
        # Initialize list to hold snippets for this keyword
        snippets = []
        
        # Convert keyword to lowercase for case-insensitive search
        lower_keyword = keyword.lower()

        # Find occurrences of the keyword in the text
        start = 0
        while True:
            # Find the next occurrence of the keyword
            index = lower_text.find(lower_keyword, start)
            if index == -1:
                break  # No more occurrences

            # Determine snippet boundaries
            start_index = max(index - snippet_radius, 0)
            end_index = min(index + len(keyword) + snippet_radius, len(text))

            # Extract the snippet from the original text (not the lowercase version)
            snippet = (
                text[start_index:index] + "[" + text[index:index + len(keyword)] + "]" + text[index + len(keyword):end_index]
            )
            
            snippets.append(snippet)

            # Update start position to continue searching after the current keyword
            start = index + len(keyword)

        # Store the snippets and the total count of occurrences for each keyword
        results[keyword] = {
            'count': len(snippets),
            'snippets': snippets
        }
    
    return results

# this is the main function
def lambda_handler(event, context):
    # create url for the pdf
    # get year month day and gazzetta number from the actual date 
    today = datetime.date.today()
    # today = datetime.date(2024, 9, 3)
    year = today.year
    month = today.month
    day = today.day

    # the variable gazzetta, is the number of the gazzetta, counted as the number of tuesdays and friday from the beginning of the year
    start_date = datetime.date(year, 1, 1)

    end_date = today
    friday_count, tuesday_count = count_fridays_and_tuesdays(start_date, end_date)
    gazzetta = friday_count + tuesday_count 

    # in my case i can alogrithmically create the url. I want the lambda to get the pdf from the correct url at the give time of the month
    pdf_url = 'https://www.gazzettaufficiale.it/do/gazzetta/downloadPdf?dataPubblicazioneGazzetta=' +f"{year:04}{month:02}{day:02}"+'&numeroGazzetta='+str(gazzetta)+'&tipoSerie=S4&tipoSupplemento=GU&numeroSupplemento=0&progressivo=0&estensione=pdf&edizione=0'

    # the keywords I am looking for
    keywords = ['PHYS-01','ISTITUTO NAZIONALE DI ASTROFISICA','ISTUTUTO NAZIONALE DI FISICA NUCLEARE','AGENZIA SPAZIALE ITALIANA','ENEA','AGENZIA NAZIONALE PER LE NUOVE TECNOLOGIE']

    response = ''

    # Download PDF and extract text
    try:
        pdf_bytes = download_pdf(pdf_url)
        pdf_text = extract_text_from_pdf(pdf_bytes)

        # Search keywords
        search_results = search_keywords(pdf_text, keywords)

        # format the response
        response = "Gazzetta URL: " + pdf_url + "\n\n"
        response += format_search_results(search_results)
        sendEmail('Recap da Gazzetta Ufficiale',response)

        
    except Exception as e:
        return {
            'statusCode': 500,
            'body': json.dumps({
                'message': 'An error occurred.',
                'error': str(e)
            })
        }