2023-12-14 19:00:04 +01:00
|
|
|
/*
|
2024-01-12 13:29:59 +01:00
|
|
|
Copyright © 2023-2024 Thomas von Dein
|
2023-12-14 19:00:04 +01:00
|
|
|
|
|
|
|
|
This program is free software: you can redistribute it and/or modify
|
|
|
|
|
it under the terms of the GNU General Public License as published by
|
|
|
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
|
|
|
(at your option) any later version.
|
|
|
|
|
|
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
GNU General Public License for more details.
|
|
|
|
|
|
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
|
|
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
package main
|
|
|
|
|
|
|
|
|
|
import (
|
2024-01-21 12:38:14 +01:00
|
|
|
"bytes"
|
2023-12-14 19:00:04 +01:00
|
|
|
"errors"
|
|
|
|
|
"fmt"
|
2023-12-15 14:50:40 +01:00
|
|
|
"log/slog"
|
2023-12-18 09:21:26 +01:00
|
|
|
"path/filepath"
|
2023-12-14 19:00:04 +01:00
|
|
|
"strings"
|
|
|
|
|
|
|
|
|
|
"astuart.co/goq"
|
2023-12-19 18:23:41 +01:00
|
|
|
"golang.org/x/sync/errgroup"
|
2023-12-14 19:00:04 +01:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
// extract links from all ad listing pages (that is: use pagination)
|
|
|
|
|
// and scrape every page
|
2024-01-16 19:27:46 +01:00
|
|
|
func ScrapeUser(fetch *Fetcher) error {
|
2023-12-15 14:50:40 +01:00
|
|
|
adlinks := []string{}
|
2023-12-14 19:00:04 +01:00
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
baseuri := fmt.Sprintf("%s%s?userId=%d", Baseuri, Listuri, fetch.Config.User)
|
2023-12-14 19:00:04 +01:00
|
|
|
page := 1
|
|
|
|
|
uri := baseuri
|
|
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
slog.Info("fetching ad pages", "user", fetch.Config.User)
|
2023-12-15 14:50:40 +01:00
|
|
|
|
2023-12-14 19:00:04 +01:00
|
|
|
for {
|
|
|
|
|
var index Index
|
2023-12-15 14:50:40 +01:00
|
|
|
slog.Debug("fetching page", "uri", uri)
|
2024-01-16 19:27:46 +01:00
|
|
|
body, err := fetch.Get(uri)
|
2023-12-14 19:00:04 +01:00
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
defer body.Close()
|
|
|
|
|
|
|
|
|
|
err = goq.NewDecoder(body).Decode(&index)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if len(index.Links) == 0 {
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
|
2023-12-15 14:50:40 +01:00
|
|
|
slog.Debug("extracted ad links", "count", len(index.Links))
|
|
|
|
|
|
2023-12-14 19:00:04 +01:00
|
|
|
for _, href := range index.Links {
|
2023-12-15 14:50:40 +01:00
|
|
|
adlinks = append(adlinks, href)
|
|
|
|
|
slog.Debug("ad link", "href", href)
|
2023-12-14 19:00:04 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
page++
|
|
|
|
|
uri = baseuri + "&pageNum=" + fmt.Sprintf("%d", page)
|
|
|
|
|
}
|
|
|
|
|
|
2023-12-19 18:23:41 +01:00
|
|
|
for i, adlink := range adlinks {
|
2024-01-16 19:27:46 +01:00
|
|
|
err := ScrapeAd(fetch, Baseuri+adlink)
|
2023-12-14 19:00:04 +01:00
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2023-12-19 18:23:41 +01:00
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
if fetch.Config.Limit > 0 && i == fetch.Config.Limit-1 {
|
2023-12-19 18:23:41 +01:00
|
|
|
break
|
|
|
|
|
}
|
2023-12-14 19:00:04 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return nil
|
|
|
|
|
}
|
|
|
|
|
|
2023-12-15 14:50:40 +01:00
|
|
|
// scrape an ad. uri is the full uri of the ad, dir is the basedir
|
2024-01-16 19:27:46 +01:00
|
|
|
func ScrapeAd(fetch *Fetcher, uri string) error {
|
2023-12-15 14:50:40 +01:00
|
|
|
ad := &Ad{}
|
2023-12-14 19:00:04 +01:00
|
|
|
|
2023-12-15 14:50:40 +01:00
|
|
|
// extract slug and id from uri
|
|
|
|
|
uriparts := strings.Split(uri, "/")
|
|
|
|
|
if len(uriparts) < 6 {
|
2023-12-29 13:47:18 +01:00
|
|
|
return errors.New("invalid uri: " + uri)
|
2023-12-15 14:50:40 +01:00
|
|
|
}
|
|
|
|
|
ad.Slug = uriparts[4]
|
|
|
|
|
ad.Id = uriparts[5]
|
|
|
|
|
|
|
|
|
|
// get the ad
|
|
|
|
|
slog.Debug("fetching ad page", "uri", uri)
|
2024-01-16 19:27:46 +01:00
|
|
|
body, err := fetch.Get(uri)
|
2023-12-14 19:00:04 +01:00
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
defer body.Close()
|
|
|
|
|
|
2023-12-15 14:50:40 +01:00
|
|
|
// extract ad contents with goquery/goq
|
2023-12-14 19:00:04 +01:00
|
|
|
err = goq.NewDecoder(body).Decode(&ad)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2024-01-12 14:11:02 +01:00
|
|
|
|
|
|
|
|
if len(ad.CategoryTree) > 0 {
|
|
|
|
|
ad.Category = strings.Join(ad.CategoryTree, " => ")
|
2023-12-16 20:32:10 +01:00
|
|
|
}
|
2024-01-01 16:24:07 +01:00
|
|
|
|
|
|
|
|
if ad.Incomplete() {
|
2024-01-12 14:11:02 +01:00
|
|
|
slog.Debug("got ad", "ad", ad)
|
2024-01-01 16:24:07 +01:00
|
|
|
return errors.New("could not extract ad data from page, got empty struct")
|
|
|
|
|
}
|
|
|
|
|
|
2024-01-19 14:41:47 +01:00
|
|
|
ad.CalculateExpire()
|
|
|
|
|
|
2023-12-17 17:32:05 +01:00
|
|
|
// write listing
|
2024-01-16 19:27:46 +01:00
|
|
|
addir, err := WriteAd(fetch.Config, ad)
|
2023-12-15 14:50:40 +01:00
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2023-12-14 19:00:04 +01:00
|
|
|
|
2024-01-21 12:38:14 +01:00
|
|
|
slog.Debug("extracted ad listing", "ad", ad)
|
|
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
fetch.Config.IncrAds()
|
2023-12-19 18:23:41 +01:00
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
return ScrapeImages(fetch, ad, addir)
|
2023-12-16 20:32:10 +01:00
|
|
|
}
|
|
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
func ScrapeImages(fetch *Fetcher, ad *Ad, addir string) error {
|
2023-12-15 14:50:40 +01:00
|
|
|
// fetch images
|
2023-12-14 19:00:04 +01:00
|
|
|
img := 1
|
2024-01-21 12:38:14 +01:00
|
|
|
adpath := filepath.Join(fetch.Config.Outdir, addir)
|
|
|
|
|
|
|
|
|
|
// scan existing images, if any
|
2024-01-22 14:30:54 +01:00
|
|
|
cache, err := ReadImages(adpath, fetch.Config.ForceDownload)
|
2024-01-21 12:38:14 +01:00
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
|
2023-12-19 18:23:41 +01:00
|
|
|
g := new(errgroup.Group)
|
2023-12-16 20:32:10 +01:00
|
|
|
|
2023-12-14 19:00:04 +01:00
|
|
|
for _, imguri := range ad.Images {
|
2023-12-19 18:23:41 +01:00
|
|
|
imguri := imguri
|
2024-01-21 12:38:14 +01:00
|
|
|
file := filepath.Join(adpath, fmt.Sprintf("%d.jpg", img))
|
2023-12-19 18:23:41 +01:00
|
|
|
g.Go(func() error {
|
2024-01-16 19:27:46 +01:00
|
|
|
body, err := fetch.Getimage(imguri)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
|
2024-01-21 12:38:14 +01:00
|
|
|
buf := new(bytes.Buffer)
|
2024-01-22 14:51:26 +01:00
|
|
|
_, err = buf.ReadFrom(body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2024-01-21 12:38:14 +01:00
|
|
|
|
|
|
|
|
buf2 := buf.Bytes() // needed for image writing
|
|
|
|
|
|
|
|
|
|
image := NewImage(buf, "", imguri)
|
|
|
|
|
err = image.CalcHash()
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
|
2024-01-22 14:30:54 +01:00
|
|
|
if !fetch.Config.ForceDownload {
|
|
|
|
|
if image.SimilarExists(cache) {
|
|
|
|
|
slog.Debug("similar image exists, not written", "uri", image.Uri)
|
|
|
|
|
return nil
|
|
|
|
|
}
|
2024-01-21 12:38:14 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
err = WriteImage(file, buf2)
|
2023-12-16 20:32:10 +01:00
|
|
|
if err != nil {
|
2023-12-19 18:23:41 +01:00
|
|
|
return err
|
2023-12-16 20:32:10 +01:00
|
|
|
}
|
2023-12-19 18:23:41 +01:00
|
|
|
|
2024-01-21 12:38:14 +01:00
|
|
|
slog.Debug("wrote image", "image", image, "size", len(buf2))
|
2023-12-19 18:23:41 +01:00
|
|
|
return nil
|
|
|
|
|
})
|
2023-12-14 19:00:04 +01:00
|
|
|
img++
|
|
|
|
|
}
|
|
|
|
|
|
2023-12-19 18:23:41 +01:00
|
|
|
if err := g.Wait(); err != nil {
|
|
|
|
|
return err
|
2023-12-16 20:32:10 +01:00
|
|
|
}
|
|
|
|
|
|
2024-01-16 19:27:46 +01:00
|
|
|
fetch.Config.IncrImgs(len(ad.Images))
|
2023-12-14 19:00:04 +01:00
|
|
|
|
|
|
|
|
return nil
|
|
|
|
|
}
|