clx-browser

commit 75a224627c528b830a5cf92be938214db98a2760
parent 6e7af3f2eea3c3fce7bd7439e00c9d1217075e26
Author: FIGBERT <figbert@figbert.com>
Date:   Sat, 30 Jul 2022 13:16:06 -0700

Clean URLs of excess query components

Diffstat:
M
go.mod
 | 
3
++-
M
go.sum
 | 
2
++
M
reader.go
 | 
30
++++++++++++++++++++++++++++++

3 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/go.mod b/go.mod
@@ -4,13 +4,14 @@ go 1.18
 
 require (
 	github.com/JohannesKaufmann/html-to-markdown v1.3.5
+	github.com/PuerkitoBio/goquery v1.8.0
 	github.com/charmbracelet/glamour v0.5.0
 	github.com/charmbracelet/lipgloss v0.5.0
 	github.com/go-shiori/go-readability v0.0.0-20220215145315-dd6828d2f09b
+	github.com/kozmos/clean-url v0.0.0-20171106101704-be7f9d853a5e
 )
 
 require (
-	github.com/PuerkitoBio/goquery v1.8.0 // indirect
 	github.com/alecthomas/chroma v0.10.0 // indirect
 	github.com/andybalholm/cascadia v1.3.1 // indirect
 	github.com/aymerick/douceur v0.2.0 // indirect
diff --git a/go.sum b/go.sum
@@ -72,6 +72,8 @@ github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7V
 github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/kozmos/clean-url v0.0.0-20171106101704-be7f9d853a5e h1:OBbESkCZyg5JmX+cOu90az48Eiw0n5vB5IcwIsv6G6M=
+github.com/kozmos/clean-url v0.0.0-20171106101704-be7f9d853a5e/go.mod h1:MNjZeAQSFsNlu7wGmb3uIzR99mMVR/JUmr4IaDvh4z8=
 github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
diff --git a/reader.go b/reader.go
@@ -1,14 +1,20 @@
 package main
 
 import (
+	"fmt"
 	"net/http"
 	"net/url"
+	"strings"
 	"time"
 
 	md "github.com/JohannesKaufmann/html-to-markdown"
 	"github.com/JohannesKaufmann/html-to-markdown/plugin"
 
 	"github.com/go-shiori/go-readability"
+
+	"github.com/PuerkitoBio/goquery"
+
+	"github.com/kozmos/clean-url"
 )
 
 func getArticle(URL string) (string, string) {
@@ -29,8 +35,32 @@ func getArticle(URL string) (string, string) {
 		panic(err)
 	}
 
+	href := md.Rule{
+		Filter: []string{"a"},
+		Replacement: func(content string, selec *goquery.Selection, opt *md.Options) *string {
+			href, ok := selec.Attr("href")
+			if !ok {
+				return md.String(strings.TrimSpace(content))
+			}
+
+			parsedURL, err := url.Parse(href)
+			if err != nil {
+				panic(err)
+			}
+
+			return md.String(
+				fmt.Sprintf(
+					"[%s](%s://%s)",
+					strings.TrimSpace(content), parsedURL.Scheme,
+					cleanurl.Clean(opt.GetAbsoluteURL(selec, href, pageURL.Host)),
+				),
+			)
+		},
+	}
+
 	opt := &md.Options{}
 	converter := md.NewConverter(URL, true, opt)
+	converter.AddRules(href)
 	converter.Use(plugin.Table())
 	markdown, err := converter.ConvertString(art.Content)
 	if err != nil {