Steve Dudenhoeffer
9947cae947
Adjusted HTML selectors for improved compatibility and updated price parsing logic to handle additional formats. Added logging to provide better debugging insights during price extraction.
82 lines
1.5 KiB
Go
82 lines
1.5 KiB
Go
package aislegopher
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"net/url"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/go-extractor"
|
|
)
|
|
|
|
type Config struct {
|
|
}
|
|
|
|
var DefaultConfig = Config{}
|
|
|
|
var (
|
|
ErrInvalidURL = errors.New("invalid url")
|
|
)
|
|
|
|
type Item struct {
|
|
ID int
|
|
Name string
|
|
Price float64
|
|
}
|
|
|
|
func deferClose(cl io.Closer) {
|
|
if cl != nil {
|
|
_ = cl.Close()
|
|
}
|
|
}
|
|
func GetItemFromURL(ctx context.Context, b extractor.Browser, u *url.URL) (Item, error) {
|
|
return DefaultConfig.GetItemFromURL(ctx, b, u)
|
|
}
|
|
|
|
func (c Config) GetItemFromURL(ctx context.Context, b extractor.Browser, u *url.URL) (Item, error) {
|
|
res := Item{}
|
|
|
|
// the url will be in the format of aislegopher.com/p/slug/id
|
|
// we need to parse the slug and id from the url
|
|
a := strings.Split(u.Path, "/")
|
|
if len(a) != 4 {
|
|
return res, ErrInvalidURL
|
|
}
|
|
|
|
if a[1] != "p" {
|
|
return res, ErrInvalidURL
|
|
}
|
|
|
|
if u.Host != "aislegopher.com" && u.Host != "www.aislegopher.com" {
|
|
return res, ErrInvalidURL
|
|
}
|
|
|
|
res.ID, _ = strconv.Atoi(a[3])
|
|
|
|
doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
|
|
defer deferClose(doc)
|
|
if err != nil {
|
|
return res, fmt.Errorf("failed to open page: %w", err)
|
|
}
|
|
|
|
names := doc.Select(".h4")
|
|
|
|
if len(names) > 0 {
|
|
res.Name, _ = names[0].Text()
|
|
}
|
|
|
|
prices := doc.Select(".h2")
|
|
|
|
if len(prices) > 0 {
|
|
priceStr, _ := prices[0].Text()
|
|
priceStr = strings.ReplaceAll(priceStr, "$", "")
|
|
priceStr = strings.TrimSpace(priceStr)
|
|
res.Price, _ = strconv.ParseFloat(priceStr, 64)
|
|
}
|
|
|
|
return res, nil
|
|
}
|