chore: rename http getter package (#1349)

This commit is contained in:
boojack
2023-03-14 08:38:54 +08:00
committed by GitHub
parent 89053e86b3
commit 8d88477538
7 changed files with 1 additions and 1 deletions

View File

@@ -0,0 +1,98 @@
package getter
import (
"fmt"
"io"
"net/http"
"net/url"
"golang.org/x/net/html"
"golang.org/x/net/html/atom"
)
type HTMLMeta struct {
Title string `json:"title"`
Description string `json:"description"`
Image string `json:"image"`
}
func GetHTMLMeta(urlStr string) (*HTMLMeta, error) {
if _, err := url.Parse(urlStr); err != nil {
return nil, err
}
response, err := http.Get(urlStr)
if err != nil {
return nil, err
}
defer response.Body.Close()
mediatype, err := getMediatype(response)
if err != nil {
return nil, err
}
if mediatype != "text/html" {
return nil, fmt.Errorf("Wrong website mediatype")
}
htmlMeta := extractHTMLMeta(response.Body)
return htmlMeta, nil
}
func extractHTMLMeta(resp io.Reader) *HTMLMeta {
tokenizer := html.NewTokenizer(resp)
htmlMeta := new(HTMLMeta)
for {
tokenType := tokenizer.Next()
if tokenType == html.ErrorToken {
break
} else if tokenType == html.StartTagToken || tokenType == html.SelfClosingTagToken {
token := tokenizer.Token()
if token.DataAtom == atom.Body {
break
}
if token.DataAtom == atom.Title {
tokenizer.Next()
token := tokenizer.Token()
htmlMeta.Title = token.Data
} else if token.DataAtom == atom.Meta {
description, ok := extractMetaProperty(token, "description")
if ok {
htmlMeta.Description = description
}
ogTitle, ok := extractMetaProperty(token, "og:title")
if ok {
htmlMeta.Title = ogTitle
}
ogDescription, ok := extractMetaProperty(token, "og:description")
if ok {
htmlMeta.Description = ogDescription
}
ogImage, ok := extractMetaProperty(token, "og:image")
if ok {
htmlMeta.Image = ogImage
}
}
}
}
return htmlMeta
}
func extractMetaProperty(token html.Token, prop string) (content string, ok bool) {
content, ok = "", false
for _, attr := range token.Attr {
if attr.Key == "property" && attr.Val == prop {
ok = true
}
if attr.Key == "content" {
content = attr.Val
}
}
return content, ok
}

View File

@@ -0,0 +1,28 @@
package getter
import (
"testing"
"github.com/stretchr/testify/require"
)
func TestGetHTMLMeta(t *testing.T) {
tests := []struct {
urlStr string
htmlMeta HTMLMeta
}{
{
urlStr: "https://www.bytebase.com/blog/sql-review-tool-for-devs",
htmlMeta: HTMLMeta{
Title: "The SQL Review Tool for Developers",
Description: "Reviewing SQL can be somewhat tedious, yet is essential to keep your database fleet reliable. At Bytebase, we are building a developer-first SQL review tool to empower the DevOps system.",
Image: "https://www.bytebase.com/static/blog/sql-review-tool-for-devs/dev-fighting-dba.webp",
},
},
}
for _, test := range tests {
metadata, err := GetHTMLMeta(test.urlStr)
require.NoError(t, err)
require.Equal(t, test.htmlMeta, *metadata)
}
}

View File

@@ -0,0 +1,4 @@
// Package getter is using to get resources from url.
// * Get metadata for website;
// * Get image blob to avoid CORS;
package getter

View File

@@ -0,0 +1,45 @@
package getter
import (
"fmt"
"io"
"net/http"
"net/url"
"strings"
)
type Image struct {
Blob []byte
Mediatype string
}
func GetImage(urlStr string) (*Image, error) {
if _, err := url.Parse(urlStr); err != nil {
return nil, err
}
response, err := http.Get(urlStr)
if err != nil {
return nil, err
}
defer response.Body.Close()
mediatype, err := getMediatype(response)
if err != nil {
return nil, err
}
if !strings.HasPrefix(mediatype, "image/") {
return nil, fmt.Errorf("Wrong image mediatype")
}
bodyBytes, err := io.ReadAll(response.Body)
if err != nil {
return nil, err
}
image := &Image{
Blob: bodyBytes,
Mediatype: mediatype,
}
return image, nil
}

View File

@@ -0,0 +1,21 @@
package getter
import (
"testing"
"github.com/stretchr/testify/require"
)
func TestGetImage(t *testing.T) {
tests := []struct {
urlStr string
}{
{
urlStr: "https://star-history.com/bytebase.webp",
},
}
for _, test := range tests {
_, err := GetImage(test.urlStr)
require.NoError(t, err)
}
}

View File

@@ -0,0 +1,15 @@
package getter
import (
"mime"
"net/http"
)
func getMediatype(response *http.Response) (string, error) {
contentType := response.Header.Get("content-type")
mediatype, _, err := mime.ParseMediaType(contentType)
if err != nil {
return "", err
}
return mediatype, nil
}