Search/images-imgur.go

package main

import (
	"fmt"
	"net/http"
	"net/url"
	"strconv"
	"strings"
	"time"

	"github.com/PuerkitoBio/goquery"
)

// PerformImgurImageSearch performs an image search on Imgur and returns the results
func PerformImgurImageSearch(query, safe, lang string, page int) ([]ImageSearchResult, time.Duration, error) {
	startTime := time.Now() // Start the timer

	var results []ImageSearchResult
	searchURL := buildImgurSearchURL(query, page)

	resp, err := http.Get(searchURL)
	if err != nil {
		return nil, 0, fmt.Errorf("making request: %v", err)
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return nil, 0, fmt.Errorf("unexpected status code: %d", resp.StatusCode)
	}

	doc, err := goquery.NewDocumentFromReader(resp.Body)
	if err != nil {
		return nil, 0, fmt.Errorf("loading HTML document: %v", err)
	}

	doc.Find("div.cards div.post").Each(func(i int, s *goquery.Selection) {
		thumbnailSrc, exists := s.Find("a img").Attr("src")
		if !exists || len(thumbnailSrc) < 25 {
			return
		}
		imgSrc := strings.Replace(thumbnailSrc, "b.", ".", 1)

		// Ensure the URLs have the correct protocol
		if !strings.HasPrefix(thumbnailSrc, "http") {
			thumbnailSrc = "https:" + thumbnailSrc
		}
		if !strings.HasPrefix(imgSrc, "http") {
			imgSrc = "https:" + imgSrc
		}

		urlPath, exists := s.Find("a").Attr("href")
		if !exists {
			return
		}

		// Scrape the image directly from the Imgur page
		imgSrc = scrapeImageFromImgurPage("https://imgur.com" + urlPath)

		// Remove any query parameters from the URL
		imgSrc = removeQueryParameters(imgSrc)

		title, _ := s.Find("a img").Attr("alt")

		width, _ := strconv.Atoi(s.Find("a img").AttrOr("width", "0"))
		height, _ := strconv.Atoi(s.Find("a img").AttrOr("height", "0"))

		results = append(results, ImageSearchResult{
			Thumbnail:  thumbnailSrc,
			Title:      strings.TrimSpace(title),
			Media:      imgSrc,
			Width:      width,
			Height:     height,
			Source:     "https://imgur.com" + urlPath,
			ThumbProxy: imgSrc, //"/img_proxy?url=" + url.QueryEscape(imgSrc)
		})
	})

	duration := time.Since(startTime) // Calculate the duration

	return results, duration, nil
}

// scrapeImageFromImgurPage scrapes the image source from the Imgur page
func scrapeImageFromImgurPage(pageURL string) string {
	resp, err := http.Get(pageURL)
	if err != nil {
		fmt.Printf("Error fetching page: %v\n", err)
		return ""
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		fmt.Printf("Unexpected status code: %d\n", resp.StatusCode)
		return ""
	}

	doc, err := goquery.NewDocumentFromReader(resp.Body)
	if err != nil {
		fmt.Printf("Error loading HTML document: %v\n", err)
		return ""
	}

	imgSrc, exists := doc.Find("meta[property='og:image']").Attr("content")
	if !exists {
		fmt.Printf("Image not found on page: %s\n", pageURL)
		return ""
	}

	// Ensure the URL has the correct protocol
	if !strings.HasPrefix(imgSrc, "http") {
		imgSrc = "https:" + imgSrc
	}

	return imgSrc
}

// removeQueryParameters removes query parameters from a URL
func removeQueryParameters(rawURL string) string {
	parsedURL, err := url.Parse(rawURL)
	if err != nil {
		fmt.Printf("Error parsing URL: %v\n", err)
		return rawURL
	}
	parsedURL.RawQuery = ""
	return parsedURL.String()
}

func buildImgurSearchURL(query string, page int) string {
	baseURL := "https://imgur.com/search/score/all"
	params := url.Values{}
	params.Add("q", query)
	params.Add("qs", "thumbs")
	params.Add("p", fmt.Sprintf("%d", page-1))
	return fmt.Sprintf("%s?%s", baseURL, params.Encode())
}

// func main() {
// 	results, duration, err := PerformImgurImageSearch("cats", "true", "en", 1)
// 	if err != nil {
// 		fmt.Println("Error:", err)
// 		return
// 	}

// 	fmt.Printf("Search took: %v\n", duration)
// 	for _, result := range results {
// 		fmt.Printf("Title: %s\nSource: %s\nMedia: %s\nThumbnail: %s\nThumbProxy: %s\nWidth: %d\nHeight: %d\n\n",
// 			result.Title, result.Source, result.Media, result.Thumbnail, result.ThumbProxy, result.Width, result.Height)
// 	}
// }