RSS implemented and tested

rss/item.go

@@ -1,7 +1,10 @@
 package rss
 
 import (
+	"fmt"
 	"html"
+	"io/ioutil"
+	"net/http"
 	"regexp"
 	"strings"
 	"time"
@@ -16,6 +19,19 @@ type Item struct {
 	TS      time.Time
 }
 
+func (item *Item) String() string {
+	return fmt.Sprintf("Name %v, Link %v, Content %q, TS %v",
+		item.Name,
+		item.Link,
+		item.Content,
+		item.TS.Local(),
+	)
+}
+
+func (item *Item) ID() string {
+	return strings.Join(regexp.MustCompile("[a-zA-Z0-9]*").FindAllString(item.Link, -1), "_")
+}
+
 func fromGofeedItem(gfitem *gofeed.Item, filter string) *Item {
 	item := &Item{
 		Name:    gfitem.Title,
@@ -23,35 +39,48 @@ func fromGofeedItem(gfitem *gofeed.Item, filter string) *Item {
 		Content: "",
 		TS:      *gofeedItemTS(gfitem),
 	}
-	if filter == "" {
-		item.Content = gfitem.Content
-		return item
+	content := gfitem.Content
+	if content == "" {
+		content = contentFromLink(item.Link)
 	}
-	r := regexp.MustCompile(filter)
-	matches := r.FindAllString(gfitem.Content, -1)
-	content := strings.Join(matches, "\n<br>\n")
-	content = cleanImgTags(content, item.Link)
+	content = strings.Replace(content, "\n", "", -1)
+	if filter != "" {
+		r := regexp.MustCompile(filter)
+		matches := r.FindAllString(content, -1)
+		content = strings.Join(matches, "<br>")
+	}
+	content = cleanImgTags(content)
 	item.Content = content
 	return item
 }
 
-func cleanImgTags(s, url string) string {
-	domain := regexp.MustCompile("(https?://)?(www\\.)?[a-zA-Z0-9]+\\.+[a-z]{2}[a-z]?").FindString(url)
+func contentFromLink(link string) string {
+	resp, err := http.Get(link)
+	if err != nil {
+		return ""
+	}
+	defer resp.Body.Close()
+	b, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		return ""
+	}
+	return string(b)
+}
+
+func cleanImgTags(s string) string {
 	reg := regexp.MustCompile("<img.+?/(img)?>")
 	s = html.UnescapeString(s)
 	matches := reg.FindAllString(s, -1)
 	if len(matches) > 0 {
 		// get img src="..." and build
-		regImgSrc := regexp.MustCompile("src=\"[^\"]+\"")
+		regImgSrc := regexp.MustCompile("src=\".*?\"")
 		for j := range matches {
-			theseMatches := regImgSrc.FindAllString(matches[j], -1)
-			for k := range theseMatches {
-				if strings.HasPrefix(theseMatches[k], "src=\"/") {
-					theseMatches[k] = "src=\"" + domain + theseMatches[k][5:]
-				}
-				theseMatches[k] = "<img " + theseMatches[k] + " />"
+			imgSrc := regImgSrc.FindString(matches[j])
+			replacement := matches[j]
+			if imgSrc != "" {
+				replacement = "<img " + imgSrc + "/>"
 			}
-			s = strings.Replace(s, matches[j], strings.Join(theseMatches, "<br>"), 1)
+			s = strings.Replace(s, matches[j], replacement, 1)
 		}
 	}
 	return s