go-extractor/sites/duckduckgo/weather.go

package duckduckgo

import (
	"context"
	"fmt"
	"log/slog"
	"strings"
	"time"

	"gitea.stevedudenhoeffer.com/steve/go-extractor"
	"gitea.stevedudenhoeffer.com/steve/go-extractor/sites/internal/parse"
)

// WeatherData holds structured weather information extracted from DuckDuckGo.
type WeatherData struct {
	Location    string
	CurrentTemp float64
	Condition   string
	HighTemp    float64
	LowTemp     float64
	Humidity    string
	Wind        string
	Forecast    []DayForecast
	Hourly      []HourlyForecast
}

// DayForecast holds a single day's forecast.
type DayForecast struct {
	Day           string
	HighTemp      float64
	LowTemp       float64
	Condition     string
	Precipitation int    // percentage 0-100, -1 if unavailable
	IconHint      string // icon type from element attributes (e.g. "PartlyCloudy", "Snow")
}

// HourlyForecast holds a single hour's forecast.
type HourlyForecast struct {
	Time          string
	Temp          float64
	Condition     string
	Precipitation int    // percentage 0-100, -1 if unavailable
	IconHint      string // icon type from element attributes (e.g. "MostlyCloudy", "Rain")
}

// GetWeather extracts weather data from DuckDuckGo's weather widget.
func (c Config) GetWeather(ctx context.Context, b extractor.Browser, city string) (*WeatherData, error) {
	c = c.validate()

	u := c.ToSearchURL("weather " + city)

	slog.Info("fetching weather", "url", u, "city", city)
	doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
	if err != nil {
		return nil, fmt.Errorf("failed to open weather page: %w", err)
	}
	defer extractor.DeferClose(doc)

	timeout := 10 * time.Second
	if err := doc.WaitForNetworkIdle(&timeout); err != nil {
		slog.Warn("WaitForNetworkIdle failed", "err", err)
	}

	return extractWeather(doc)
}

// GetWeather is a convenience function using DefaultConfig.
func GetWeather(ctx context.Context, b extractor.Browser, city string) (*WeatherData, error) {
	return DefaultConfig.GetWeather(ctx, b, city)
}

func extractWeather(doc extractor.Node) (*WeatherData, error) {
	var data WeatherData

	// DuckDuckGo's weather widget uses randomized CSS class names (CSS modules),
	// so we identify elements by structural selectors and image src attributes.
	// The widget is an article element containing weatherkit icon images.
	widget := doc.SelectFirst("article:has(img[src*='weatherkit'])")
	if widget == nil {
		return &data, nil
	}

	section := widget.SelectFirst("section")
	if section == nil {
		return &data, nil
	}

	// Header: condition and location
	// Structure: section > div > [div(toggle), p(condition), p(location)]
	// Use :not(:has(ul)) to skip the hourly container div and avoid breaking
	// when advisory banners (e.g. wind advisory) insert extra divs.
	header := section.SelectFirst("div:not(:has(ul))")
	if header != nil {
		ps := header.Select("p")
		if len(ps) >= 2 {
			data.Condition, _ = ps[0].Text()
			data.Location, _ = ps[1].Text()
		} else if len(ps) == 1 {
			data.Condition, _ = ps[0].Text()
		}
	}

	// Hourly forecast and details
	// Structure: section > div > [ul(hourly items), div(humidity/wind)]
	// Use :has(> ul) to find the div containing the hourly list, regardless of
	// position. This avoids breaking when advisory banners insert extra divs.
	hourlyContainer := section.SelectFirst("div:has(> ul)")
	if hourlyContainer != nil {
		_ = hourlyContainer.ForEach("ul > li", func(n extractor.Node) error {
			var hour HourlyForecast
			hour.Precipitation = -1

			// Each li contains: p(time), img(icon), [span(precip)], p(temp)
			ps := n.Select("p")
			if len(ps) >= 2 {
				hour.Time, _ = ps[0].Text()
				txt, _ := ps[len(ps)-1].Text()
				hour.Temp = parse.NumericOnly(txt)
			}

			// Icon hint and condition from the weather icon's alt attribute
			icons := n.Select("img[src*='weatherkit']:not([src*='Precipitation'])")
			hour.IconHint = extractIconHint(icons)
			hour.Condition = hour.IconHint

			// Precipitation percentage is in a span > span structure
			if precip := n.SelectFirst("span > span"); precip != nil {
				txt, _ := precip.Text()
				hour.Precipitation = int(parse.NumericOnly(txt))
			}

			data.Hourly = append(data.Hourly, hour)
			return nil
		})

		// Use first hourly temperature as current temp (no standalone current temp element)
		if len(data.Hourly) > 0 {
			data.CurrentTemp = data.Hourly[0].Temp
		}

		// Humidity and wind from the details div (after the hourly ul)
		details := hourlyContainer.Select("div > p")
		for _, p := range details {
			txt, _ := p.Text()
			if strings.Contains(txt, "Humidity") {
				if strong := p.SelectFirst("strong"); strong != nil {
					data.Humidity, _ = strong.Text()
				}
			} else if strings.Contains(txt, "Wind") {
				if strong := p.SelectFirst("strong"); strong != nil {
					data.Wind, _ = strong.Text()
				}
			}
		}
	}

	// Daily forecast
	// Structure: section > ul > div (each day)
	// The daily ul has div children; the hourly ul has li children, so ul > div is unambiguous.
	_ = section.ForEach("ul > div", func(n extractor.Node) error {
		var day DayForecast
		day.Precipitation = -1

		// Day name from first p
		if d := n.SelectFirst("p:first-child"); d != nil {
			day.Day, _ = d.Text()
		}

		// Icon hint and condition from the weather icon's alt attribute
		icons := n.Select("img[src*='weatherkit']:not([src*='Precipitation'])")
		day.IconHint = extractIconHint(icons)
		day.Condition = day.IconHint

		// High/low temps from last p's spans
		if temps := n.SelectFirst("p:last-of-type"); temps != nil {
			spans := temps.Select("span")
			if len(spans) >= 2 {
				highTxt, _ := spans[0].Text()
				day.HighTemp = parse.NumericOnly(highTxt)
				lowTxt, _ := spans[1].Text()
				day.LowTemp = parse.NumericOnly(lowTxt)
			}
		}

		// Precipitation percentage is in a span > span structure
		if precip := n.SelectFirst("span > span"); precip != nil {
			txt, _ := precip.Text()
			day.Precipitation = int(parse.NumericOnly(txt))
		}

		data.Forecast = append(data.Forecast, day)
		return nil
	})

	// Today's high/low from first daily forecast entry
	if len(data.Forecast) > 0 {
		data.HighTemp = data.Forecast[0].HighTemp
		data.LowTemp = data.Forecast[0].LowTemp
	}

	return &data, nil
}

// extractIconHint reads the icon type from an element's aria-label, title, or alt attribute.
func extractIconHint(nodes extractor.Nodes) string {
	if len(nodes) == 0 {
		return ""
	}
	n := nodes[0]
	for _, attr := range []string{"aria-label", "title", "alt"} {
		v, _ := n.Attr(attr)
		if v != "" {
			return v
		}
	}
	return ""
}