add extension - xhtml fetch

http/x/README.md

@@ -0,0 +1,7 @@
+# gurl http extensions
+
+## awsapi
+Enables AWS Signature V4 for HTTP I/O. Allows to use AWS API Gateway with IAM authentication.  
+
+## xhtml
+Enables fetching and parsing xHTML content.

http/x/xhtml/go.mod

@@ -0,0 +1,16 @@
+module github.com/fogfish/gurl/http/x/xhtml
+
+go 1.21.0
+
+require (
+	github.com/PuerkitoBio/goquery v1.9.1
+	github.com/fogfish/gurl/v2 v2.9.0
+	github.com/fogfish/it/v2 v2.0.1
+)
+
+require (
+	github.com/ajg/form v1.5.2-0.20200323032839-9aeb3cf462e1 // indirect
+	github.com/andybalholm/cascadia v1.3.2 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
+	golang.org/x/net v0.21.0 // indirect
+)

http/x/xhtml/go.sum

@@ -0,0 +1,48 @@
+github.com/PuerkitoBio/goquery v1.9.1 h1:mTL6XjbJTZdpfL+Gwl5U2h1l9yEkJjhmlTeV9VPW7UI=
+github.com/PuerkitoBio/goquery v1.9.1/go.mod h1:cW1n6TmIMDoORQU5IU/P1T3tGFunOeXEpGP2WHRwkbY=
+github.com/ajg/form v1.5.2-0.20200323032839-9aeb3cf462e1 h1:8Qzi+0Uch1VJvdrOhJ8U8FqoPLbUdETPgMqGJ6DSMSQ=
+github.com/ajg/form v1.5.2-0.20200323032839-9aeb3cf462e1/go.mod h1:uL1WgH+h2mgNtvBq0339dVnzXdBETtL2LeUXaIv25UY=
+github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
+github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
+github.com/fogfish/gurl/v2 v2.9.0 h1:IZlOxZte9y+NFgKHkPYw5jS0VCNG9avu2Ywrm2c3S6k=
+github.com/fogfish/gurl/v2 v2.9.0/go.mod h1:vBqw+SCrfOPNllWDCwPnuotrNeuuyTsYZ28iP13qF3Y=
+github.com/fogfish/it/v2 v2.0.1 h1:vu3kV2xzYDPHoMHMABxXeu5CoMcTfRc4gkWkzOUkRJY=
+github.com/fogfish/it/v2 v2.0.1/go.mod h1:h5FdKaEQT4sUEykiVkB8VV4jX27XabFVeWhoDZaRZtE=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
+golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
+golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
+golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

http/x/xhtml/xhtml.go

@@ -0,0 +1,72 @@
+//
+// Copyright (C) 2019 - 2024 Dmitry Kolesnikov
+//
+// This file may be modified and distributed under the terms
+// of the MIT license.  See the LICENSE file for details.
+// https://github.com/fogfish/gurl
+//
+
+// Package xhtml is an extension to gurl library for fetching and parsing
+// html using query selectors.
+package xhtml
+
+import (
+	"bytes"
+	"context"
+
+	"github.com/PuerkitoBio/goquery"
+	"github.com/fogfish/gurl/v2/http"
+	ø "github.com/fogfish/gurl/v2/http/recv"
+	ƒ "github.com/fogfish/gurl/v2/http/send"
+)
+
+// HTTP Arrow receive and parses HTML content
+func Content(content **goquery.Selection) http.Arrow {
+	b := &bytes.Buffer{}
+
+	return http.Join(
+		ø.Bytes(b),
+		func(ctx *http.Context) error {
+			doc, err := goquery.NewDocumentFromReader(b)
+			if err != nil {
+				return err
+			}
+
+			c := doc.Selection
+			*content = c
+
+			return nil
+		},
+	)
+}
+
+// HTTP Client tailored for fetching HTML content from public resources
+type Client struct {
+	http.Stack
+}
+
+// Create new instance of HTTP Client tailored for fetching HTML content
+// from public resources.
+func New(opts ...http.Config) Client {
+	return Client{Stack: http.New(opts...)}
+}
+
+// Fetches HTML content behind url, parser HTML.
+func (site Client) Fetch(ctx context.Context, url string) (*goquery.Selection, error) {
+	var content *goquery.Selection
+
+	err := site.Stack.IO(context.Background(),
+		http.GET(
+			ƒ.URI(url),
+			ƒ.Accept.HTML,
+
+			ø.Status.OK,
+			Content(&content),
+		),
+	)
+	if err != nil {
+		return nil, err
+	}
+
+	return content, nil
+}

http/x/xhtml/xhtml_test.go

@@ -0,0 +1,33 @@
+//
+// Copyright (C) 2019 - 2024 Dmitry Kolesnikov
+//
+// This file may be modified and distributed under the terms
+// of the MIT license.  See the LICENSE file for details.
+// https://github.com/fogfish/gurl
+//
+
+package xhtml_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/fogfish/gurl/http/x/xhtml"
+	"github.com/fogfish/gurl/v2/http/mock"
+	"github.com/fogfish/it/v2"
+)
+
+func TestFetch(t *testing.T) {
+	web := mock.New(
+		mock.Header("Content-Type", "text/html"),
+		mock.Body([]byte("<html><body><div>Hello World</div></body></html>")),
+	)
+
+	cli := xhtml.New(web)
+	c, err := cli.Fetch(context.Background(), "http://example.com/")
+
+	it.Then(t).Should(
+		it.Nil(err),
+		it.Equal(c.Find("div").Text(), "Hello World"),
+	)
+}