Merge pull request #15 from kkdai/url_title

implement get title from target url.

ptt.go

@@ -50,6 +50,25 @@ func (p *PTT) GetUrlPhotos(target string) []string {
 	return resultSlice
 }
 
+func (p *PTT) GetUrlTitle(target string) string {
+	// Get https response with setting cookie over18=1
+	resp := getResponseWithCookie(target)
+	doc, err := goquery.NewDocumentFromResponse(resp)
+	if err != nil {
+		log.Println(err)
+		return ""
+	}
+
+	//Title
+	articleTitle := ""
+	doc.Find(".article-metaline").Each(func(i int, s *goquery.Selection) {
+		if strings.Contains(s.Find(".article-meta-tag").Text(), "標題") {
+			articleTitle = s.Find(".article-meta-value").Text()
+		}
+	})
+	return articleTitle
+}
+
 func (p *PTT) Crawler(target string, workerNum int) {
 	// Get https response with setting cookie over18=1
 	resp := getResponseWithCookie(target)

ptt_test.go

@@ -40,16 +40,30 @@ func TestGetNumber(t *testing.T) {
 
 func TestURLPhoto(t *testing.T) {
 	ptt := NewPTT()
+	ptt.ParsePttByNumber(6, 0)
 	title := ptt.GetPostTitleByIndex(5)
 	if CheckTitleWithBeauty(title) {
 		url := ptt.GetPostUrlByIndex(5)
 		ret := ptt.GetUrlPhotos(url)
 		if !ptt.HasValidURL(url) {
-			t.Errorf("URLPhoto: URL is not correct")
+			t.Errorf("TestURLPhoto: URL is not correct")
 		}
 
 		if len(ret) == 0 {
-			t.Errorf("URLPhoto: No result")
+			t.Errorf("TestURLPhoto: No result")
+		}
+	}
+}
+
+func TestURLTitle(t *testing.T) {
+	ptt := NewPTT()
+	ptt.ParsePttByNumber(6, 0)
+	title := ptt.GetPostTitleByIndex(5)
+	if CheckTitleWithBeauty(title) {
+		url := ptt.GetPostUrlByIndex(5)
+		urlTitle := ptt.GetUrlTitle(url)
+		if urlTitle == "" || !CheckTitleWithBeauty(urlTitle) {
+			t.Errorf("TestURLTitle: title is not correct url_title=%s title=%s\n", urlTitle, title)
 		}
 	}
 }