Add flexible CSS selector extraction

Replace hardcoded title extraction with user-defined CSS selectors using goquery. Users specify selector in job JSON to extract any HTML elements. Worker extracts text content plus src/href attributes. Webhook payload includes extracted content and URL.
This commit is contained in:
Soldier 2025-11-16 08:33:19 +00:00
parent 1ce45cfe97
commit 405f9ca173
5 changed files with 128 additions and 38 deletions

View File

@ -32,12 +32,13 @@ func main() {
var req struct {
WebhookURL string `json:"webhook_url"`
URL string `json:"url"`
Selector string `json:"selector"`
}
body, _ := io.ReadAll(r.Body)
json.Unmarshal(body, &req)
id, err := db.CreateJob(database, req.WebhookURL, req.URL)
id, err := db.CreateJob(database, req.WebhookURL, req.URL, req.Selector)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return

2
go.mod
View File

@ -3,6 +3,8 @@ module alpenqueue
go 1.25.4
require (
github.com/PuerkitoBio/goquery v1.10.3 // indirect
github.com/andybalholm/cascadia v1.3.3 // indirect
github.com/mattn/go-sqlite3 v1.14.32 // indirect
github.com/temoto/robotstxt v1.1.2 // indirect
golang.org/x/net v0.47.0 // indirect

69
go.sum
View File

@ -1,4 +1,9 @@
github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo=
github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y=
github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs=
github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@ -6,5 +11,69 @@ github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg=
github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
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/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
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/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
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 v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY=
golang.org/x/net v0.47.0/go.mod h1:/jNxtkgq5yWUGYkaZGqo27cfGZ1c5Nen03aYrrKpVRU=
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/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
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 v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
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 v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
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/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
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/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

View File

@ -13,7 +13,8 @@ type Job struct {
CreatedAt time.Time
WebhookURL string
URL string
Title string
Selector string
ExtractedContent string
}
func Init(dbPath string) (*sql.DB, error) {
@ -29,7 +30,8 @@ func Init(dbPath string) (*sql.DB, error) {
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
webhook_url TEXT,
url TEXT,
title TEXT
selector TEXT,
extracted_content TEXT
);`
_, err = db.Exec(schema)
@ -40,8 +42,8 @@ func Init(dbPath string) (*sql.DB, error) {
return db, nil
}
func CreateJob(db *sql.DB, webhookURL, url string) (int64, error) {
result, err := db.Exec("INSERT INTO jobs (status, webhook_url, url) VALUES ('pending', ?, ?)", webhookURL, url)
func CreateJob(db *sql.DB, webhookURL, url, selector string) (int64, error) {
result, err := db.Exec("INSERT INTO jobs (status, webhook_url, url, selector) VALUES ('pending', ?, ?, ?)", webhookURL, url, selector)
if err != nil {
return 0, err
}
@ -49,7 +51,7 @@ func CreateJob(db *sql.DB, webhookURL, url string) (int64, error) {
}
func GetPendingJobs(db *sql.DB) ([]Job, error) {
rows, err := db.Query("SELECT id, status, created_at, webhook_url, url, title FROM jobs WHERE status = 'pending'")
rows, err := db.Query("SELECT id, status, created_at, webhook_url, url, selector, extracted_content FROM jobs WHERE status = 'pending'")
if err != nil {
return nil, err
}
@ -58,20 +60,21 @@ func GetPendingJobs(db *sql.DB) ([]Job, error) {
var jobs []Job
for rows.Next() {
var job Job
var webhookURL, url, title sql.NullString
if err := rows.Scan(&job.ID, &job.Status, &job.CreatedAt, &webhookURL, &url, &title); err != nil {
var webhookURL, url, selector, extractedContent sql.NullString
if err := rows.Scan(&job.ID, &job.Status, &job.CreatedAt, &webhookURL, &url, &selector, &extractedContent); err != nil {
return nil, err
}
job.WebhookURL = webhookURL.String
job.URL = url.String
job.Title = title.String
job.Selector = selector.String
job.ExtractedContent = extractedContent.String
jobs = append(jobs, job)
}
return jobs, nil
}
func UpdateJobTitle(db *sql.DB, id int, title string) error {
_, err := db.Exec("UPDATE jobs SET title = ? WHERE id = ?", title, id)
func UpdateJobContent(db *sql.DB, id int, content string) error {
_, err := db.Exec("UPDATE jobs SET extracted_content = ? WHERE id = ?", content, id)
return err
}

View File

@ -13,25 +13,39 @@ import (
"strings"
"time"
"github.com/PuerkitoBio/goquery"
"github.com/temoto/robotstxt"
"golang.org/x/net/html"
)
const userAgent = "AlpenQueue/1.0 (+https://github.com/yourusername/alpenqueue)"
func extractTitle(body io.Reader) string {
tokenizer := html.NewTokenizer(body)
for {
tokenType := tokenizer.Next()
if tokenType == html.ErrorToken {
func extractContent(body io.Reader, selector string) string {
if selector == "" {
selector = "title"
}
doc, err := goquery.NewDocumentFromReader(body)
if err != nil {
return ""
}
token := tokenizer.Token()
if tokenType == html.StartTagToken && token.Data == "title" {
tokenizer.Next()
return strings.TrimSpace(tokenizer.Token().Data)
var results []string
doc.Find(selector).Each(func(i int, s *goquery.Selection) {
text := strings.TrimSpace(s.Text())
if text != "" {
results = append(results, text)
}
if src, exists := s.Attr("src"); exists {
results = append(results, src)
}
if href, exists := s.Attr("href"); exists {
results = append(results, href)
}
})
return strings.Join(results, "\n")
}
func checkRobotsTxt(targetURL string) bool {
@ -79,10 +93,10 @@ func Start(database *sql.DB) {
}
for _, job := range jobs {
log.Printf("Processing job %d: %s", job.ID, job.URL)
log.Printf("Processing job %d: %s (selector: %s)", job.ID, job.URL, job.Selector)
start := time.Now()
title := ""
content := ""
status := "ok"
if job.URL != "" {
@ -104,11 +118,11 @@ func Start(database *sql.DB) {
status = "error"
} else {
defer resp.Body.Close()
title = extractTitle(resp.Body)
log.Printf("Job %d: Extracted title: %s", job.ID, title)
content = extractContent(resp.Body, job.Selector)
log.Printf("Job %d: Extracted content (%d chars)", job.ID, len(content))
if err := db.UpdateJobTitle(database, job.ID, title); err != nil {
log.Printf("Job %d: Error updating title: %v", job.ID, err)
if err := db.UpdateJobContent(database, job.ID, content); err != nil {
log.Printf("Job %d: Error updating content: %v", job.ID, err)
}
}
}
@ -121,7 +135,8 @@ func Start(database *sql.DB) {
payload := map[string]string{
"status": status,
"took": fmt.Sprintf("%.1fs", duration.Seconds()),
"title": title,
"url": job.URL,
"content": content,
}
jsonData, _ := json.Marshal(payload)