根据html提取资源链接

This commit is contained in:
Yun
2024-08-23 15:09:37 +08:00
parent 6800ac9fbc
commit 868a5106e6
5 changed files with 190 additions and 38 deletions
+7
View File
@@ -1,3 +1,10 @@
module code.yun.ink/pkg/mailx
go 1.20
require github.com/PuerkitoBio/goquery v1.9.2
require (
github.com/andybalholm/cascadia v1.3.2 // indirect
golang.org/x/net v0.24.0 // indirect
)
+40
View File
@@ -0,0 +1,40 @@
github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE=
github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
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/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 v0.24.0 h1:1PcaxkF854Fu3+lvBIx5SYn9wRlBzzcnHZSiaFFAb0w=
golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=
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=
+77
View File
@@ -0,0 +1,77 @@
package mailx
import (
"bytes"
"github.com/PuerkitoBio/goquery"
)
// 解析HTML资源,响应资源链接
func ParseHtmlResource(html string) ([]string, error) {
resp := []string{}
b := bytes.NewBufferString(html)
doc, err := goquery.NewDocumentFromReader(b)
if err != nil {
return nil, err
}
// 找到所有的 css 标签,并且打印它们的 href 属性
doc.Find("link").Each(func(i int, s *goquery.Selection) {
// 忽略dns预请求
r, ok := s.Attr("rel")
if ok && r == "dns-prefetch" {
return
}
href, ok := s.Attr("href")
if ok && href != "" {
resp = append(resp, href)
}
})
// 找到所有的 script 标签,并且打印它们的 src 属性
doc.Find("script").Each(func(i int, s *goquery.Selection) {
src, ok := s.Attr("src")
if ok && src != "" {
resp = append(resp, src)
}
})
// 找到所有的 img 标签,并且打印它们的 src 属性
doc.Find("img").Each(func(i int, s *goquery.Selection) {
src, ok := s.Attr("src")
if ok && src != "" {
resp = append(resp, src)
}
data_src, ok := s.Attr("data-src")
if ok && data_src != "" {
resp = append(resp, data_src)
}
})
// 找到所有的 video 标签,并且打印它们的 src 属性
doc.Find("video").Each(func(i int, s *goquery.Selection) {
src, ok := s.Attr("src")
if ok && src != "" {
resp = append(resp, src)
}
data_src, ok := s.Attr("data-src")
if ok && data_src != "" {
resp = append(resp, data_src)
}
})
// 找到所有的 audio 标签,并且打印它们的 src 属性
doc.Find("audio").Each(func(i int, s *goquery.Selection) {
src, ok := s.Attr("src")
if ok && src != "" {
resp = append(resp, src)
}
})
return resp, nil
}
+60
View File
@@ -0,0 +1,60 @@
package mailx_test
import (
"testing"
"code.yun.ink/pkg/mailx"
)
func TestParseHtmlResource(t *testing.T) {
html := `<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Document</title>
<link rel="stylesheet" href="./assets/css/index.css" />
</head>
<body>
<header class="header flex-center">
<img src="./assets/img/ab-pay-logo.png" alt="" class="logo" />
</header>
<main class="code-main">
<div class="exception-title">您的收款方式审核失败</div>
<div class="exception-content">
尊敬的ABpay用户,您好!
您的收款方式审核失败,失败原因人脸识别失败,请检查您的面部是否被遮挡或处于模糊状态,并再次尝试。
如非本人操作,请立即修改密码或联系客服。
</div>
<div class="exception-ignore">这是一条自动发送的消息,请勿回复</div>
<li class="exception-team-tips">ABpay开发者团队服务</li>
<section class="contact-us">
<div class="contact-us-info">
本邮件由系统自动发出请勿回复,如需要了解更多服务,欢迎访问ABpay官方网
还可以通以下方式联系我们
</div>
<img src="./assets/img/contact-us-qrcode.png" alt="" class="qr-code" />
<div class="contact-tel">
客服电话:<span class="contact-tel-number">400-278-2890</span>
</div>
<div class="contact-created-version">2024 ABpay.com.cn . All rightes reserved</div>
</section>
</main>
</body>
</html>
`
res, err := mailx.ParseHtmlResource(html)
if err != nil {
t.Fatal(err)
}
t.Log(res)
}
+6 -38
View File
@@ -15,42 +15,6 @@ import (
// 1. 支持文本
// 2. 支持文件
func simple_test() {
// mail_driver := "smtp"
// mail_host := "smtpdm-ap-southeast-1.aliyun.com"
// mail_port := ""
// mail_username := ""
// mail_password := ""
// mail_From_address := ""
// mail_from_name := ""
// mail_reply_to := ""
// user := "tech@email.blueoceantech.co"
// password := "SupporT2017"
// host := "smtpdm-ap-southeast-1.aliyun.com"
// port := "80" // 80或smtp
// auth := smtp.PlainAuth("", user, password, host)
// toEmial := []string{
// "995116474@qq.com",
// "yun@blueoceanpay.com",
// }
// // split := strings.Split()
// emailHeader := "Header"
// subject := "邮件的主题"
// contentType := "Content-Type: text/html; charset=UTF-8"
// // contentType := "Content-Type: text/plain; charset=UTF-8"
// body := `<html><body> <h1>黄新云</h1> <span>666</span></body></html>`
// msg := []byte(contentType + "\r\nTo: " + strings.Join(toEmial, ",") + "\r\nFrom: " + emailHeader + "<" + user + ">\r\nSubject: " + subject + "\r\nBcc: yun@blueoceanpay.com \r\nReply-To: yun@blueoceanpay.com" + "\r\n\r\n" + body)
// err := smtp.SendMail(host+":"+port, auth, user, toEmial, msg)
// fmt.Println(err)
}
// type Mail interface {
// Auth()
// Send(message Message) error
// }
type Mailx struct {
user string
password string
@@ -66,7 +30,7 @@ type Attachment struct {
}
type Message struct {
// Form string
Form string
To []string
Cc []string
Bcc []string
@@ -173,9 +137,13 @@ func (m *Mailx) Send(message Message) error {
buffer.WriteString(newBuf.String())
}
if message.Form == "" {
message.Form = m.user
}
buffer.WriteString("\r\n--" + boundary + "--\r\n")
b := buffer.Bytes()
err := smtp.SendMail(m.host+":"+m.port, m.auth, m.user, message.To, b)
err := smtp.SendMail(m.host+":"+m.port, m.auth, message.Form, message.To, b)
fmt.Println("发送结束:", err)
fmt.Println(string(b))
return err