aboutsummaryrefslogtreecommitdiff
path: root/prop_html2md.go
diff options
context:
space:
mode:
authorTong Sun <[email protected]>2020-07-26 11:52:41 -0400
committerTong Sun <[email protected]>2020-07-26 12:10:20 -0400
commitb61a04acfc1e11611019c5c3ac95f38f040d90f3 (patch)
tree3d0cf3d95b2203fadb711e688d9349df34271429 /prop_html2md.go
parent- [*] updated _cli.yaml (diff)
downloadhtml2md-b61a04acfc1e11611019c5c3ac95f38f040d90f3.tar.xz
html2md-b61a04acfc1e11611019c5c3ac95f38f040d90f3.zip
- [*] -d/--domain option functionality implemented
Diffstat (limited to 'prop_html2md.go')
-rw-r--r--prop_html2md.go10
1 files changed, 8 insertions, 2 deletions
diff --git a/prop_html2md.go b/prop_html2md.go
index 3fb64fa..6660909 100644
--- a/prop_html2md.go
+++ b/prop_html2md.go
@@ -8,6 +8,7 @@ package main
import (
"fmt"
+ "regexp"
md "github.com/JohannesKaufmann/html-to-markdown"
"github.com/PuerkitoBio/goquery"
@@ -19,17 +20,22 @@ import (
// root handler
func html2md(ctx *cli.Context) error {
- ctx.JSON(ctx.RootArgv())
rootArgv = ctx.RootArgv().(*rootT)
// https://pkg.go.dev/github.com/mkideal/[email protected]/clis?tab=doc
clis.Setup(progname, rootArgv.Verbose.Value())
+ clis.Verbose(1, "%#v\n", rootArgv)
clis.Verbose(2, "%s\n", rootArgv.Filei.Name())
doc, err := goquery.NewDocumentFromReader(rootArgv.Filei)
clis.AbortOn("Reading file with goquery", err)
content := doc.Find(rootArgv.Sel)
- conv := md.NewConverter(md.DomainFromURL(rootArgv.Filei.Name()), true, nil)
+ domain, url := rootArgv.Domain, rootArgv.Filei.Name()
+ if domain == "" && regexp.MustCompile(`(?i)^http`).MatchString(url) {
+ domain = md.DomainFromURL(url)
+ }
+ clis.Verbose(2, "domain='%s'\n", domain)
+ conv := md.NewConverter(domain, true, nil)
markdown := conv.Convert(content)
fmt.Println(markdown)