Initial 423down proxy service

article.go

@@ -0,0 +1,77 @@
+package main
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+
+	"github.com/PuerkitoBio/goquery"
+	"resty.dev/v3"
+)
+
+var (
+	errArticleContentNotFound    = errors.New("无法找到文章内容")
+	errArticleContentParseFailed = errors.New("无法解析文章内容")
+)
+
+// getArticleHTML 优先从缓存读取文章 HTML，缓存未命中时从源站抓取。
+func getArticleHTML(db *DB, client *resty.Client, articleID string) (string, error) {
+	html, err := db.GetArticleHtml(articleID)
+	if err == nil {
+		return html, nil
+	}
+
+	cookies, err := getLoginCookies(db, client)
+	if err != nil {
+		return "", err
+	}
+
+	html, err = fetchRemoteArticleHTML(client, articleID, cookies)
+	if err != nil {
+		return "", err
+	}
+
+	if err := db.SetArticleHtml(articleID, html, articleCacheTTL); err != nil {
+		slog.Warn("failed to cache article", slog.String("article_id", articleID), slog.String("error", err.Error()))
+	}
+
+	return html, nil
+}
+
+// fetchRemoteArticleHTML 从源站下载文章页面并提取正文 HTML。
+func fetchRemoteArticleHTML(client *resty.Client, articleID string, cookies []*http.Cookie) (string, error) {
+	request := client.R()
+	if len(cookies) > 0 {
+		request.SetCookies(cookies)
+	}
+
+	resp, err := request.Get(fmt.Sprintf(articleURLFormat, articleID))
+	if err != nil {
+		return "", err
+	}
+	defer func() { _ = resp.Body.Close() }()
+
+	return extractArticleHTML(resp.Body)
+}
+
+// extractArticleHTML 从源站页面中提取文章正文区域。
+func extractArticleHTML(reader io.Reader) (string, error) {
+	doc, err := goquery.NewDocumentFromReader(reader)
+	if err != nil {
+		return "", err
+	}
+
+	selection := doc.Find("div.entry")
+	if selection.Length() == 0 {
+		return "", errArticleContentNotFound
+	}
+
+	html, err := selection.Html()
+	if err != nil {
+		return "", fmt.Errorf("%w：%v", errArticleContentParseFailed, err)
+	}
+
+	return html, nil
+}