Python Daily National Weather Report Generator

weather_report_generator.py

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import pytz
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch
from reportlab.platypus import Paragraph, Frame
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from io import BytesIO
from PIL import Image
import logging
from reportlab.lib.utils import ImageReader
import os
import re

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Suppress InsecureRequestWarning
import urllib3

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)


def scrape_weather_gov():
    url = "https://www.weather.gov/"
    response = requests.get(url, verify=False)
    soup = BeautifulSoup(response.text, 'html.parser')

    eastern = pytz.timezone('US/Eastern')
    date = datetime.now(eastern)
    formatted_date = date.strftime("%Y-%m-%d %H:%M:%S")

    topnews = soup.find('div', id='topnews')
    if topnews:
        headline = topnews.find('h1')
        paragraph = topnews.find('p')

        if headline and paragraph:
            headline_text = headline.text.strip()
            paragraph_text = paragraph.text.strip()
            return formatted_date, headline_text, paragraph_text
        else:
            return formatted_date, "Headline not found", "Paragraph not found"
    else:
        return formatted_date, "Top news section not found", "Top news section not found"


def get_map_urls():
    surface_map_url = "https://www.wpc.ncep.noaa.gov/sfc/usfntsfcwbg.gif"

    # Calculate the 500mb map URL based on the current date
    current_date = datetime.now().strftime("%Y%m%d")
    mb500_map_url = f"https://weather.uwyo.edu/upperair/maps/{current_date}00.500a.naconf.gif"
    # mb500_map_url = f"https://weather.uwyo.edu/upperair/maps/{current_date}00.500a.naconf.gif"

    return surface_map_url, mb500_map_url


def download_image(url):
    try:
        response = requests.get(url, verify=False)
        response.raise_for_status()  # Raise an exception for bad status codes
        image = Image.open(BytesIO(response.content))
        return image
    except requests.RequestException as e:
        logging.error(f"Error downloading image from {url}: {str(e)}")
        return None
    except IOError as e:
        logging.error(f"Error opening image from {url}: {str(e)}")
        return None


def scrape_discussion():
    url = "https://www.wpc.ncep.noaa.gov/discussions/hpcdiscussions.php?disc=pmdspd"
    response = requests.get(url, verify=False)
    soup = BeautifulSoup(response.text, 'html.parser')

    # Find the pre tag containing the discussion
    discussion_tag = soup.find('pre')

    if discussion_tag:
        # Extract the text and remove any leading/trailing whitespace
        discussion_text = discussion_tag.text.strip()

        # Split the text into paragraphs
        paragraphs = discussion_text.split('\n\n')

        # Remove line breaks within each paragraph
        formatted_paragraphs = [re.sub(r'\s+', ' ', p.strip()) for p in paragraphs]

        # Join the paragraphs back together with double newlines
        formatted_discussion = '\n\n'.join(formatted_paragraphs)

        return formatted_discussion
    else:
        return "Discussion not found"


def create_weather_pdf(filename, date, headline, paragraph, surface_map_url, mb500_map_url, discussion):
    print(headline, "Headline in create PDF")
    c = canvas.Canvas(filename, pagesize=letter)
    width, height = letter

    # Set up styles
    styles = getSampleStyleSheet()
    title_style = ParagraphStyle(
        'Title',
        parent=styles['Heading1'],
        fontSize=14,
        leading=16,
        spaceAfter=2
    )
    body_style = ParagraphStyle(
        'Body',
        parent=styles['BodyText'],
        fontSize=10,
        leading=12,
        spaceAfter=2
    )
    discussion_style = ParagraphStyle(
        'Discussion',
        parent=styles['BodyText'],
        fontSize=9,
        leading=12,
        spaceAfter=3
    )

    # Add title and date
    c.setFont("Helvetica-Bold", 16)
    c.drawString(0.5 * inch, height - 0.5 * inch, "Daily Weather Report")
    c.setFont("Helvetica", 10)
    c.drawString(0.5 * inch, height - 0.75 * inch, f"Date: {date}")

    #Add headline to canvas
    c.setFont("Helvetica-Bold", 12)
    c.drawString(0.5 * inch, height -  inch, headline)

    # Add headline and paragraph
    content_width = width - inch
    # headline_frame = Frame(0.5 * inch, height - 1.5 * inch, content_width, 0.5 * inch, showBoundary=0)
    # headline_paragraph = Paragraph(headline, title_style)
    # headline_frame.addFromList([headline_paragraph], c)



    paragraph_frame = Frame(0.5 * inch, height - 1.75 * inch, content_width, 0.75 * inch, showBoundary=0)
    body_paragraph = Paragraph(paragraph, body_style)
    paragraph_frame.addFromList([body_paragraph], c)

    # Download and add images
    surface_map = download_image(surface_map_url)
    mb500_map = download_image(mb500_map_url)

    # Calculate image sizes
    img_width = (width - 1.5 * inch) / 2
    img_height = 2.75 * inch

    if surface_map:
        c.drawImage(ImageReader(surface_map), 0.5 * inch, height - 4.75 * inch, width=img_width, height=img_height,
                    preserveAspectRatio=True)
        c.setFont("Helvetica-Bold", 10)
        c.drawString(0.5 * inch, height - 1.95 * inch, "Surface Map")
    else:
        c.setFont("Helvetica", 10)
        c.drawString(0.5 * inch, height - 3.5 * inch, f"Error loading Surface Map")

    if mb500_map:
        c.drawImage(ImageReader(mb500_map), 0.75 * inch + img_width, height - 4.75 * inch, width=img_width,
                    height=img_height, preserveAspectRatio=True)
        c.setFont("Helvetica-Bold", 10)
        c.drawString(0.75 * inch + img_width, height - 1.95 * inch, "500mb Map")
    else:
        c.setFont("Helvetica", 10)
        c.drawString(0.75 * inch + img_width, height - 3.5 * inch, f"Error loading 500mb Map")

    # Add discussion
    c.setFont("Helvetica-Bold", 12)
    c.drawString(0.5 * inch, height - 5.25 * inch, "Weather Discussion")

    discussion_frame = Frame(
        0.5 * inch,
        0.5 * inch,
        content_width,
        5 * inch,  # Reduced height to accommodate the space after the headline
        leftPadding=0,
        bottomPadding=0,
        rightPadding=0,
        topPadding=0
    )

    discussion_paragraphs = [Paragraph(p.strip(), discussion_style) for p in discussion.split('\n\n') if p.strip()]
    discussion_frame.addFromList(discussion_paragraphs, c)

    # Add footer
    c.setFont("Helvetica", 10)
    c.drawString(0.5 * inch, 0.25 * inch, f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")

    c.save()


if __name__ == "__main__":
    # Scrape weather data
    date, headline, paragraph = scrape_weather_gov()

    # Get map URLs
    surface_map_url, mb500_map_url = get_map_urls()

    # Scrape discussion
    discussion = scrape_discussion()

    # Create reports directory if it doesn't exist
    reports_dir = "reports"
    os.makedirs(reports_dir, exist_ok=True)

    # Generate filename
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    filename = os.path.join(reports_dir, f"weather_report_{timestamp}.pdf")

    # Create PDF
    create_weather_pdf(filename, date, headline, paragraph, surface_map_url, mb500_map_url, discussion)

    print(f"Weather report PDF created: {filename}")
    print(f"Date: {date}")
    print(f"Headline: {headline}")
    print(f"Paragraph: {paragraph}")
    print(f"Surface Map URL: {surface_map_url}")
    print(f"500mb Map URL: {mb500_map_url}")
    print(f"Discussion length: {len(discussion)} characters")