Compare commits

...

9 Commits

Author SHA1 Message Date
34dfc25e87 bump version 2025-01-17 12:00:21 +01:00
dependabot[bot]
0bc6a0ae59 Bump github.com/lmittmann/tint from 1.0.5 to 1.0.6
Bumps [github.com/lmittmann/tint](https://github.com/lmittmann/tint) from 1.0.5 to 1.0.6.
- [Release notes](https://github.com/lmittmann/tint/releases)
- [Commits](https://github.com/lmittmann/tint/compare/v1.0.5...v1.0.6)

---
updated-dependencies:
- dependency-name: github.com/lmittmann/tint
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2025-01-06 18:44:09 +01:00
dependabot[bot]
14c554563a Bump golang.org/x/sync from 0.9.0 to 0.10.0
Bumps [golang.org/x/sync](https://github.com/golang/sync) from 0.9.0 to 0.10.0.
- [Commits](https://github.com/golang/sync/compare/v0.9.0...v0.10.0)

---
updated-dependencies:
- dependency-name: golang.org/x/sync
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2025-01-06 18:43:57 +01:00
475a9a2fd3 add test files in other formats 2025-01-06 18:42:19 +01:00
fbd9a5a621 make clear that this is not the complete filename 2025-01-06 18:42:19 +01:00
7014c97dee added image formats test 2025-01-06 18:42:19 +01:00
91edfeb19a support hashing with all formats 2025-01-06 18:42:19 +01:00
3b3435515c check seek err 2025-01-06 18:42:19 +01:00
2239a83f76 properly check image format for storing and distance hashing 2025-01-06 18:42:19 +01:00
9 changed files with 85 additions and 21 deletions

View File

@@ -34,7 +34,7 @@ import (
)
const (
VERSION string = "0.3.10"
VERSION string = "0.3.12"
Baseuri string = "https://www.kleinanzeigen.de"
Listuri string = "/s-bestandsliste.html"
Defaultdir string = "."

5
go.mod
View File

@@ -13,11 +13,12 @@ require (
github.com/knadh/koanf/providers/file v1.1.2
github.com/knadh/koanf/providers/posflag v0.1.0
github.com/knadh/koanf/v2 v2.1.2
github.com/lmittmann/tint v1.0.5
github.com/lmittmann/tint v1.0.6
github.com/mattn/go-isatty v0.0.20
github.com/spf13/pflag v1.0.5
github.com/tlinden/yadu v0.1.3
golang.org/x/sync v0.9.0
golang.org/x/image v0.23.0
golang.org/x/sync v0.10.0
)
require (

10
go.sum
View File

@@ -39,8 +39,8 @@ github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/lmittmann/tint v1.0.5 h1:NQclAutOfYsqs2F1Lenue6OoWCajs5wJcP3DfWVpePw=
github.com/lmittmann/tint v1.0.5/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE=
github.com/lmittmann/tint v1.0.6 h1:vkkuDAZXc0EFGNzYjWcV0h7eEX+uujH48f/ifSkJWgc=
github.com/lmittmann/tint v1.0.6/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE=
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
@@ -67,14 +67,16 @@ github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXl
github.com/tlinden/yadu v0.1.3 h1:5cRCUmj+l5yvlM2irtpFBIJwVV2DPEgYSaWvF19FtcY=
github.com/tlinden/yadu v0.1.3/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/image v0.23.0 h1:HseQ7c2OpPKTPVzNjG5fwJsOTCiiwS4QdsYi5XU6H68=
golang.org/x/image v0.23.0/go.mod h1:wJJBTdLfCCf3tiHa1fNxpZmUI4mmoZvwMCPP0ddoNKY=
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190606173856-1492cefac77f/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.23.0 h1:7EYJ93RZ9vYSZAIb2x3lnuvqO5zneoD6IvWjuhfxjTs=
golang.org/x/net v0.23.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
golang.org/x/sync v0.9.0 h1:fEo0HyrW1GIgZdpbhCRO0PkJajUS5H9IFUztCgEo2jQ=
golang.org/x/sync v0.9.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
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 v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

View File

@@ -20,11 +20,16 @@ package main
import (
"bytes"
"fmt"
"image/jpeg"
"image"
_ "image/gif"
_ "image/jpeg"
_ "image/png"
"log/slog"
"os"
"path/filepath"
_ "golang.org/x/image/webp"
"github.com/corona10/goimagehash"
)
@@ -35,6 +40,7 @@ type Image struct {
Hash *goimagehash.ImageHash
Data *bytes.Reader
URI string
Mime string
}
// used for logging to avoid printing Data
@@ -49,21 +55,52 @@ func (img *Image) LogValue() slog.Value {
// holds all images of an ad
type Cache []*goimagehash.ImageHash
func NewImage(buf *bytes.Reader, filename, uri string) *Image {
// filename comes from the scraper, it contains directory/base w/o suffix
func NewImage(buf *bytes.Reader, filename, uri string) (*Image, error) {
_, imgconfig, err := image.DecodeConfig(buf)
if err != nil {
return nil, fmt.Errorf("failed to decode image: %w", err)
}
_, err = buf.Seek(0, 0)
if err != nil {
return nil, fmt.Errorf("failed to seek(0) on image buffer: %w", err)
}
if imgconfig == "jpeg" {
// we're using the format as file extension, but have used
// "jpg" in the past, so to be backwards compatible, stay with
// it.
imgconfig = "jpg"
}
if imgconfig == "" {
return nil, fmt.Errorf("failed to process image: unknown or unsupported image format (supported: jpg,png,gif,webp)")
}
filename += "." + imgconfig
img := &Image{
Filename: filename,
URI: uri,
Data: buf,
Mime: imgconfig,
}
return img
slog.Debug("image MIME", "mime", img.Mime)
return img, nil
}
// Calculate diff hash of the image
func (img *Image) CalcHash() error {
jpgdata, err := jpeg.Decode(img.Data)
jpgdata, format, err := image.Decode(img.Data)
if err != nil {
return fmt.Errorf("failed to decode JPEG image: %w", err)
return fmt.Errorf("failed to decode image: %w", err)
}
if format == "" {
return fmt.Errorf("failed to decode image: unknown or unsupported image format (supported: jpg,png,gif,webp)")
}
hash1, err := goimagehash.DifferenceHash(jpgdata)
@@ -133,12 +170,19 @@ func ReadImages(addir string, dont bool) (Cache, error) {
reader := bytes.NewReader(data.Bytes())
img := NewImage(reader, filename, "")
img, err := NewImage(reader, filename, "")
if err != nil {
return nil, err
}
if err := img.CalcHash(); err != nil {
return nil, err
}
if img.Hash != nil {
slog.Debug("Caching image from file system", "image", img, "hash", img.Hash.ToString())
}
cache = append(cache, img.Hash)
}
}

View File

@@ -182,13 +182,13 @@ var tests = []Tests{
{
name: "download-all-ads",
args: base + " -o t/out -u 1",
expect: "Successfully downloaded 6 ads with 12 images to t/out",
expect: "Successfully downloaded 7 ads with 16 images to t/out",
exitcode: 0,
},
{
name: "download-all-ads-using-config",
args: "kleingebaeck -c t/fullconfig.conf",
expect: "Successfully downloaded 6 ads with 12 images to t/out",
expect: "Successfully downloaded 7 ads with 16 images to t/out",
exitcode: 0,
},
}
@@ -321,6 +321,17 @@ var adsrc = []AdConfig{
Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"},
},
{
Title: "Ad with multiple img formats",
ID: "7",
Price: "5€",
Category: "Klunker",
Text: "Thing to sale",
Slug: "seventh-ad",
Condition: "works",
Created: "Yesterday",
Images: []string{"t/1.png", "t/1.gif", "t/1.webp", "t/1.jpg"},
},
}
// An Adsource is used to construct a httpmock responder for a
@@ -363,7 +374,7 @@ func InitValidSources() []Adsource {
// valid ad listing page 2
list2 := []AdConfig{
adsrc[3], adsrc[4], adsrc[5],
adsrc[3], adsrc[4], adsrc[5], adsrc[6],
}
// valid ad listing page 3, which is empty
@@ -459,7 +470,7 @@ func SetIntercept(ads []Adsource) {
}
// we just use 2 images, put this here
for _, image := range []string{"t/1.jpg", "t/2.jpg"} {
for _, image := range []string{"t/1.jpg", "t/2.jpg", "t/1.png", "t/1.gif", "t/1.webp"} {
httpmock.RegisterResponder("GET", image,
httpmock.NewBytesResponder(200, GetImage(image)).HeaderAdd(headers))
}

View File

@@ -170,7 +170,9 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
for _, imguri := range advertisement.Images {
imguri := imguri
file := filepath.Join(adpath, fmt.Sprintf("%d.jpg", img))
// we append the suffix later in NewImage() based on image format
basefilename := filepath.Join(adpath, fmt.Sprintf("%d", img))
egroup.Go(func() error {
// wait a little
@@ -192,7 +194,11 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
reader := bytes.NewReader(buf.Bytes())
image := NewImage(reader, file, imguri)
image, err := NewImage(reader, basefilename, imguri)
if err != nil {
return err
}
err = image.CalcHash()
if err != nil {
return err
@@ -211,7 +217,7 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
return fmt.Errorf("failed to seek(0) on image reader: %w", err)
}
err = WriteImage(file, reader)
err = WriteImage(image.Filename, reader)
if err != nil {
return err
}

BIN
t/1.gif Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 62 B

BIN
t/1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 4.2 KiB

BIN
t/1.webp Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 4.3 KiB