Compare commits

..

24 Commits

Author SHA1 Message Date
T.v.Dein
09948a6b39 add color detail as well (#119)
Co-authored-by: Thomas von Dein <tom@vondein.org>
2025-02-06 20:13:08 +01:00
T.v.Dein
bc01391872 Fix ad condition parsing (#118)
* fix #117: use details slice and pre-set to properly extract condition
* also added the type part of the detail content (original de: "Art")

---------

Co-authored-by: Thomas von Dein <tom@vondein.org>
2025-02-06 13:48:20 +01:00
cd3d00adbe add changelog builder, update release builder 2025-02-05 17:54:47 +01:00
528ecdd43d updated deps 2025-02-01 18:04:25 +01:00
dependabot[bot]
5cb928518d Bump docker/build-push-action from 6.10.0 to 6.13.0
Bumps [docker/build-push-action](https://github.com/docker/build-push-action) from 6.10.0 to 6.13.0.
- [Release notes](https://github.com/docker/build-push-action/releases)
- [Commits](48aba3b46d...ca877d9245)

---
updated-dependencies:
- dependency-name: docker/build-push-action
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2025-02-01 18:03:43 +01:00
dependabot[bot]
d8c7409c7a Bump github.com/lmittmann/tint from 1.0.6 to 1.0.7
Bumps [github.com/lmittmann/tint](https://github.com/lmittmann/tint) from 1.0.6 to 1.0.7.
- [Release notes](https://github.com/lmittmann/tint/releases)
- [Commits](https://github.com/lmittmann/tint/compare/v1.0.6...v1.0.7)

---
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>
2025-02-01 18:03:33 +01:00
dependabot[bot]
1cd6eb5134 Bump github.com/spf13/pflag from 1.0.5 to 1.0.6
Bumps [github.com/spf13/pflag](https://github.com/spf13/pflag) from 1.0.5 to 1.0.6.
- [Release notes](https://github.com/spf13/pflag/releases)
- [Commits](https://github.com/spf13/pflag/compare/v1.0.5...v1.0.6)

---
updated-dependencies:
- dependency-name: github.com/spf13/pflag
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2025-02-01 18:03:11 +01:00
9e2983a85c build release binaries using ci workflow 2025-01-18 10:53:41 +01:00
6eddd08e4a added warning about security update 2025-01-17 12:22:20 +01:00
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
31b27beee5 fix error handling when trying to open files 2024-12-13 11:23:24 +01:00
dependabot[bot]
a4be51f498 Bump docker/build-push-action from 6.9.0 to 6.10.0
Bumps [docker/build-push-action](https://github.com/docker/build-push-action) from 6.9.0 to 6.10.0.
- [Release notes](https://github.com/docker/build-push-action/releases)
- [Commits](4f58ea7922...48aba3b46d)

---
updated-dependencies:
- dependency-name: docker/build-push-action
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-12-13 11:11:31 +01:00
dependabot[bot]
6b5af984cc Bump golang.org/x/sync from 0.8.0 to 0.9.0
Bumps [golang.org/x/sync](https://github.com/golang/sync) from 0.8.0 to 0.9.0.
- [Commits](https://github.com/golang/sync/compare/v0.8.0...v0.9.0)

---
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>
2024-12-13 11:09:28 +01:00
dependabot[bot]
f5d3853388 Bump github.com/knadh/koanf/v2 from 2.1.1 to 2.1.2
Bumps [github.com/knadh/koanf/v2](https://github.com/knadh/koanf) from 2.1.1 to 2.1.2.
- [Release notes](https://github.com/knadh/koanf/releases)
- [Commits](https://github.com/knadh/koanf/compare/v2.1.1...v2.1.2)

---
updated-dependencies:
- dependency-name: github.com/knadh/koanf/v2
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-12-13 11:08:36 +01:00
07ebd7afad bump version 2024-11-01 12:21:04 +01:00
dependabot[bot]
5e82881b69 Bump github.com/knadh/koanf/providers/file from 1.1.0 to 1.1.2
Bumps [github.com/knadh/koanf/providers/file](https://github.com/knadh/koanf) from 1.1.0 to 1.1.2.
- [Release notes](https://github.com/knadh/koanf/releases)
- [Commits](https://github.com/knadh/koanf/compare/v1.1.0...providers/file/v1.1.2)

---
updated-dependencies:
- dependency-name: github.com/knadh/koanf/providers/file
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-11-01 12:20:45 +01:00
20 changed files with 287 additions and 58 deletions

View File

@@ -22,13 +22,13 @@ jobs:
password: ${{ secrets.GITHUB_TOKEN }} password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push Docker image - name: Build and push Docker image
uses: docker/build-push-action@4f58ea79222b3b9dc2c8bbdd6debcef730109a75 uses: docker/build-push-action@ca877d9245402d1537745e0e356eab47c3520991
with: with:
push: true push: true
tags: ghcr.io/tlinden/kleingebaeck:${{ github.ref_name}} tags: ghcr.io/tlinden/kleingebaeck:${{ github.ref_name}}
- name: Build and push latest Docker image - name: Build and push latest Docker image
uses: docker/build-push-action@4f58ea79222b3b9dc2c8bbdd6debcef730109a75 uses: docker/build-push-action@ca877d9245402d1537745e0e356eab47c3520991
with: with:
push: true push: true
tags: ghcr.io/tlinden/kleingebaeck:latest tags: ghcr.io/tlinden/kleingebaeck:latest

87
.github/workflows/release.yaml vendored Normal file
View File

@@ -0,0 +1,87 @@
name: build-release
on:
push:
tags:
- "v*.*.*"
jobs:
release:
name: Build Release Assets
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.22.11
- name: Build the executables
run: ./mkrel.sh kleingebaeck ${{ github.ref_name}}
- name: List the executables
run: ls -l ./releases
- name: Upload the binaries
uses: svenstaro/upload-release-action@v2
with:
repo_token: ${{ secrets.GITHUB_TOKEN }}
tag: ${{ github.ref_name }}
file: ./releases/*
file_glob: true
- name: Build Changelog
id: github_release
uses: mikepenz/release-changelog-builder-action@v5
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
mode: "PR"
configurationJson: |
{
"template": "#{{CHANGELOG}}\n\n**Full Changelog**: #{{RELEASE_DIFF}}",
"pr_template": "- #{{TITLE}} (##{{NUMBER}}) by #{{AUTHOR}}\n#{{BODY}}",
"empty_template": "- no changes",
"categories": [
{
"title": "## New Features",
"labels": ["add", "feature"]
},
{
"title": "## Bug Fixes",
"labels": ["fix", "bug", "revert"]
},
{
"title": "## Documentation Enhancements",
"labels": ["doc"]
},
{
"title": "## Refactoring Efforts",
"labels": ["refactor"]
},
{
"title": "## Miscellaneus Changes",
"labels": []
}
],
"ignore_labels": [
"duplicate", "good first issue", "help wanted", "invalid", "question", "wontfix"
],
"label_extractor": [
{
"pattern": "(.) (.+)",
"target": "$1"
},
{
"pattern": "(.) (.+)",
"target": "$1",
"on_property": "title"
}
]
}
- name: Create Release
uses: softprops/action-gh-release@v2
with:
body: ${{steps.github_release.outputs.changelog}}

View File

@@ -82,8 +82,8 @@ goupdate:
buildall: buildall:
./mkrel.sh $(tool) $(VERSION) ./mkrel.sh $(tool) $(VERSION)
release: buildall release:
gh release create v$(VERSION) --generate-notes releases/* gh release create v$(VERSION) --generate-notes
show-versions: buildlocal show-versions: buildlocal
@echo "### kleingebaeck version:" @echo "### kleingebaeck version:"

View File

@@ -17,6 +17,15 @@ Anzeige gespeichert werden. In dem Verzeichnis wird eine Datei
`Adlisting.txt` erstellt, in der sich die Inhalte der Anzeige wie `Adlisting.txt` erstellt, in der sich die Inhalte der Anzeige wie
Titel, Preis, Text etc befinden. Bilder werden natürlich auch heruntergeladen. Titel, Preis, Text etc befinden. Bilder werden natürlich auch heruntergeladen.
## ACHTUNG - SICHERHEITS-UPDATE
Fertige vorcompilierte Programme älter als Version `v0.3.12` sind von
Schwachstellen in der Behandlung von HTTP und Zertifikaten
betroffen. Falls Du eine ältere Kleingebäck-Version im Einsatz hast,
bitte update auf Version `v0.3.12` oder höher. Bitte lies auch die [Release Notes für
v0.3.12](https://github.com/TLINDEN/kleingebaeck/releases/tag/v0.3.12)
für mehr Details.
## Screenshots ## Screenshots
Das ist die Hauptseite meines kleinanzeigen.de Accounts: Das ist die Hauptseite meines kleinanzeigen.de Accounts:

View File

@@ -18,6 +18,15 @@ directory, each ad into its own subdirectory. The backup will contain
a textfile `Adlisting.txt` which contains the ad contents as the a textfile `Adlisting.txt` which contains the ad contents as the
title, body, price etc. All images will be downloaded as well. title, body, price etc. All images will be downloaded as well.
## CAUTION - SECURITY UPDATE
Binary releases prior to version `v0.3.11` are affected by
vulnerabilities in HTTP and certificate handling. If you are using
such a binary, please update to `v0.3.12` or higher. Please also refer
to the [Release Notes of
v0.3.12](https://github.com/TLINDEN/kleingebaeck/releases/tag/v0.3.12)
for more details.
## Screenshots ## Screenshots
This is the index of my kleinanzeigen.de Account: This is the index of my kleinanzeigen.de Account:
@@ -195,6 +204,7 @@ Price: 99 € VB
Id: 1919191919 Id: 1919191919
Category: Sachbücher Category: Sachbücher
Condition: Sehr Gut Condition: Sehr Gut
Type: Buch
Created: 10.12.2023 Created: 10.12.2023
This is the description text. This is the description text.

12
ad.go
View File

@@ -31,7 +31,10 @@ type Ad struct {
Title string `goquery:"h1"` Title string `goquery:"h1"`
Slug string Slug string
ID string ID string
Condition string `goquery:".addetailslist--detail--value,text"` Details []string `goquery:".addetailslist--detail--value,text"`
Condition string // post processed from details
Type string // post processed from details
Color string // post processed from details
Category string Category string
CategoryTree []string `goquery:".breadcrump-link,text"` CategoryTree []string `goquery:".breadcrump-link,text"`
Price string `goquery:"h2#viewad-price"` Price string `goquery:"h2#viewad-price"`
@@ -56,6 +59,13 @@ func (ad *Ad) LogValue() slog.Value {
) )
} }
// static set of conditions available, used for post processing details
var CONDITIONS = []string{"Neu", "Gut", "Sehr Gut", "In Ordnung"}
var COLORS = []string{"Beige", "Blau", "Braun", "Bunt", "Burgunderrot",
"Creme", "Gelb", "Gold", "Grau", "Grün", "Holz", "Khaki", "Lavelndel",
"Lila", "Orange", "Pink", "Print", "Rot", "Schwarz", "Silber",
"Transparent", "Türkis", "Weiß", "Sonstige"}
// check for completeness. I erected these fields to be mandatory // check for completeness. I erected these fields to be mandatory
// (though I really don't know if they really are). I consider images // (though I really don't know if they really are). I consider images
// and meta optional. So, if either of the checked fields here is // and meta optional. So, if either of the checked fields here is

View File

@@ -34,17 +34,17 @@ import (
) )
const ( const (
VERSION string = "0.3.8" VERSION string = "0.3.15"
Baseuri string = "https://www.kleinanzeigen.de" Baseuri string = "https://www.kleinanzeigen.de"
Listuri string = "/s-bestandsliste.html" Listuri string = "/s-bestandsliste.html"
Defaultdir string = "." Defaultdir string = "."
DefaultTemplate string = "Title: {{.Title}}\nPrice: {{.Price}}\nId: {{.ID}}\n" + DefaultTemplate string = "Title: {{.Title}}\nPrice: {{.Price}}\nId: {{.ID}}\n" +
"Category: {{.Category}}\nCondition: {{.Condition}}\n" + "Category: {{.Category}}\nCondition: {{.Condition}}\nType: {{.Type}}\nColor: {{.Color}}\n" +
"Created: {{.Created}}\nExpire: {{.Expire}}\n\n{{.Text}}\n" "Created: {{.Created}}\nExpire: {{.Expire}}\n\n{{.Text}}\n"
DefaultTemplateWin string = "Title: {{.Title}}\r\nPrice: {{.Price}}\r\nId: {{.ID}}\r\n" + DefaultTemplateWin string = "Title: {{.Title}}\r\nPrice: {{.Price}}\r\nId: {{.ID}}\r\n" +
"Category: {{.Category}}\r\nCondition: {{.Condition}}\r\n" + "Category: {{.Category}}\r\nCondition: {{.Condition}}\r\nType: {{.Type}}\r\nColor: {{.Color}}\r\n" +
"Created: {{.Created}}\r\nExpires: {{.Expire}}\r\n\r\n{{.Text}}\r\n" "Created: {{.Created}}\r\nExpires: {{.Expire}}\r\n\r\n{{.Text}}\r\n"
DefaultUserAgent string = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " + DefaultUserAgent string = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " +
@@ -183,13 +183,22 @@ func InitConfig(output io.Writer) (*Config, error) {
// Load the config file[s] // Load the config file[s]
for _, cfgfile := range configfiles { for _, cfgfile := range configfiles {
if path, err := os.Stat(cfgfile); !os.IsNotExist(err) { path, err := os.Stat(cfgfile)
if !path.IsDir() {
if err := kloader.Load(file.Provider(cfgfile), toml.Parser()); err != nil { if err != nil {
return nil, fmt.Errorf("error loading config file: %w", err) // ignore non-existent files, but bail out on any other errors
} if !os.IsNotExist(err) {
return nil, fmt.Errorf("failed to stat config file: %w", err)
} }
} // else: we ignore the file if it doesn't exists
continue
}
if !path.IsDir() {
if err := kloader.Load(file.Provider(cfgfile), toml.Parser()); err != nil {
return nil, fmt.Errorf("error loading config file: %w", err)
}
}
} }
// env overrides config file // env overrides config file

View File

@@ -23,6 +23,7 @@ outdir = "test"
#Id: {{.Id}} #Id: {{.Id}}
#Category: {{.Category}} #Category: {{.Category}}
#Condition: {{.Condition}} #Condition: {{.Condition}}
#Type: {{.Type}}
#Created: {{.Created}} #Created: {{.Created}}
#{{.Text}} #{{.Text}}

18
go.mod
View File

@@ -10,30 +10,32 @@ require (
github.com/knadh/koanf/parsers/toml v0.1.0 github.com/knadh/koanf/parsers/toml v0.1.0
github.com/knadh/koanf/providers/confmap v0.1.0 github.com/knadh/koanf/providers/confmap v0.1.0
github.com/knadh/koanf/providers/env v1.0.0 github.com/knadh/koanf/providers/env v1.0.0
github.com/knadh/koanf/providers/file v1.1.0 github.com/knadh/koanf/providers/file v1.1.2
github.com/knadh/koanf/providers/posflag v0.1.0 github.com/knadh/koanf/providers/posflag v0.1.0
github.com/knadh/koanf/v2 v2.1.1 github.com/knadh/koanf/v2 v2.1.2
github.com/lmittmann/tint v1.0.5 github.com/lmittmann/tint v1.0.7
github.com/mattn/go-isatty v0.0.20 github.com/mattn/go-isatty v0.0.20
github.com/spf13/pflag v1.0.5 github.com/spf13/pflag v1.0.6
github.com/tlinden/yadu v0.1.3 github.com/tlinden/yadu v0.1.3
golang.org/x/sync v0.8.0 golang.org/x/image v0.23.0
golang.org/x/sync v0.10.0
) )
require ( require (
github.com/PuerkitoBio/goquery v1.5.1 // indirect github.com/PuerkitoBio/goquery v1.5.1 // indirect
github.com/alecthomas/repr v0.4.0 // indirect
github.com/andybalholm/cascadia v1.1.0 // indirect github.com/andybalholm/cascadia v1.1.0 // indirect
github.com/fatih/color v1.16.0 // indirect github.com/fatih/color v1.16.0 // indirect
github.com/fsnotify/fsnotify v1.7.0 // indirect github.com/fsnotify/fsnotify v1.7.0 // indirect
github.com/go-viper/mapstructure/v2 v2.0.0-alpha.1 // indirect github.com/go-viper/mapstructure/v2 v2.2.1 // indirect
github.com/knadh/koanf/maps v0.1.1 // indirect github.com/knadh/koanf/maps v0.1.1 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect github.com/mattn/go-colorable v0.1.14 // indirect
github.com/mitchellh/copystructure v1.2.0 // indirect github.com/mitchellh/copystructure v1.2.0 // indirect
github.com/mitchellh/reflectwalk v1.0.2 // indirect github.com/mitchellh/reflectwalk v1.0.2 // indirect
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
github.com/pelletier/go-toml v1.9.5 // indirect github.com/pelletier/go-toml v1.9.5 // indirect
golang.org/x/net v0.23.0 // indirect golang.org/x/net v0.23.0 // indirect
golang.org/x/sys v0.21.0 // indirect golang.org/x/sys v0.29.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect gopkg.in/yaml.v3 v3.0.1 // indirect
) )

32
go.sum
View File

@@ -3,6 +3,8 @@ astuart.co/goq v1.0.0/go.mod h1:+fokcnFrO8Pw2fj8drdStJvzoMFebJH69rw8IC21rno=
github.com/PuerkitoBio/goquery v1.5.0/go.mod h1:qD2PgZ9lccMbQlc7eEOjaeRlFQON7xY8kdmcsrnKqMg= github.com/PuerkitoBio/goquery v1.5.0/go.mod h1:qD2PgZ9lccMbQlc7eEOjaeRlFQON7xY8kdmcsrnKqMg=
github.com/PuerkitoBio/goquery v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE= github.com/PuerkitoBio/goquery v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE=
github.com/PuerkitoBio/goquery v1.5.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc= github.com/PuerkitoBio/goquery v1.5.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc=
github.com/alecthomas/repr v0.4.0 h1:GhI2A8MACjfegCPVq9f1FLvIBS+DrQ2KQBFZP1iFzXc=
github.com/alecthomas/repr v0.4.0/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y= github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo= github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y= github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
@@ -15,8 +17,8 @@ github.com/fatih/color v1.16.0 h1:zmkK9Ngbjj+K0yRhTVONQh1p/HknKYSlNT+vZCzyokM=
github.com/fatih/color v1.16.0/go.mod h1:fL2Sau1YI5c0pdGEVCbKQbLXB6edEj1ZgiY4NijnWvE= github.com/fatih/color v1.16.0/go.mod h1:fL2Sau1YI5c0pdGEVCbKQbLXB6edEj1ZgiY4NijnWvE=
github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA= github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM= github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
github.com/go-viper/mapstructure/v2 v2.0.0-alpha.1 h1:TQcrn6Wq+sKGkpyPvppOz99zsMBaUOKXq6HSv655U1c= github.com/go-viper/mapstructure/v2 v2.2.1 h1:ZAaOCxANMuZx5RCeg0mBdEZk7DZasvvZIxtHqx8aGss=
github.com/go-viper/mapstructure/v2 v2.0.0-alpha.1/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM= github.com/go-viper/mapstructure/v2 v2.2.1/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8= github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
github.com/jarcoal/httpmock v1.3.1 h1:iUx3whfZWVf3jT01hQTO/Eo5sAYtB2/rqaUuOtpInww= github.com/jarcoal/httpmock v1.3.1 h1:iUx3whfZWVf3jT01hQTO/Eo5sAYtB2/rqaUuOtpInww=
@@ -29,20 +31,22 @@ github.com/knadh/koanf/providers/confmap v0.1.0 h1:gOkxhHkemwG4LezxxN8DMOFopOPgh
github.com/knadh/koanf/providers/confmap v0.1.0/go.mod h1:2uLhxQzJnyHKfxG927awZC7+fyHFdQkd697K4MdLnIU= github.com/knadh/koanf/providers/confmap v0.1.0/go.mod h1:2uLhxQzJnyHKfxG927awZC7+fyHFdQkd697K4MdLnIU=
github.com/knadh/koanf/providers/env v1.0.0 h1:ufePaI9BnWH+ajuxGGiJ8pdTG0uLEUWC7/HDDPGLah0= github.com/knadh/koanf/providers/env v1.0.0 h1:ufePaI9BnWH+ajuxGGiJ8pdTG0uLEUWC7/HDDPGLah0=
github.com/knadh/koanf/providers/env v1.0.0/go.mod h1:mzFyRZueYhb37oPmC1HAv/oGEEuyvJDA98r3XAa8Gak= github.com/knadh/koanf/providers/env v1.0.0/go.mod h1:mzFyRZueYhb37oPmC1HAv/oGEEuyvJDA98r3XAa8Gak=
github.com/knadh/koanf/providers/file v1.1.0 h1:MTjA+gRrVl1zqgetEAIaXHqYje0XSosxSiMD4/7kz0o= github.com/knadh/koanf/providers/file v1.1.2 h1:aCC36YGOgV5lTtAFz2qkgtWdeQsgfxUkxDOe+2nQY3w=
github.com/knadh/koanf/providers/file v1.1.0/go.mod h1:/faSBcv2mxPVjFrXck95qeoyoZ5myJ6uxN8OOVNJJCI= github.com/knadh/koanf/providers/file v1.1.2/go.mod h1:/faSBcv2mxPVjFrXck95qeoyoZ5myJ6uxN8OOVNJJCI=
github.com/knadh/koanf/providers/posflag v0.1.0 h1:mKJlLrKPcAP7Ootf4pBZWJ6J+4wHYujwipe7Ie3qW6U= github.com/knadh/koanf/providers/posflag v0.1.0 h1:mKJlLrKPcAP7Ootf4pBZWJ6J+4wHYujwipe7Ie3qW6U=
github.com/knadh/koanf/providers/posflag v0.1.0/go.mod h1:SYg03v/t8ISBNrMBRMlojH8OsKowbkXV7giIbBVgbz0= github.com/knadh/koanf/providers/posflag v0.1.0/go.mod h1:SYg03v/t8ISBNrMBRMlojH8OsKowbkXV7giIbBVgbz0=
github.com/knadh/koanf/v2 v2.1.1 h1:/R8eXqasSTsmDCsAyYj+81Wteg8AqrV9CP6gvsTsOmM= github.com/knadh/koanf/v2 v2.1.2 h1:I2rtLRqXRy1p01m/utEtpZSSA6dcJbgGVuE27kW2PzQ=
github.com/knadh/koanf/v2 v2.1.1/go.mod h1:4mnTRbZCK+ALuBXHZMjDfG9y714L7TykVnZkXbMU3Es= github.com/knadh/koanf/v2 v2.1.2/go.mod h1:Gphfaen0q1Fc1HTgJgSTC4oRX9R2R5ErYMZJy8fLJBo=
github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI= 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/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 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= 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 v1.0.7 h1:D/0OqWZ0YOGZ6AyC+5Y2kD8PBEzBk6rFHVSfOqCkF9Y=
github.com/lmittmann/tint v1.0.5/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE= github.com/lmittmann/tint v1.0.7/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE=
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA= 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-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=
github.com/mattn/go-colorable v0.1.14/go.mod h1:6LmQG8QLFO4G5z1gPvYEzlUgJ2wF+stgPZH1UqBm1s8=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM= github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY= github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y= github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
@@ -58,8 +62,8 @@ github.com/pelletier/go-toml v1.9.5 h1:4yBQzkHv+7BHq2PQUZF3Mx0IYxG7LsP222s7Agd3v
github.com/pelletier/go-toml v1.9.5/go.mod h1:u1nR/EPcESfeI/szUZKdtJ0xRNbUoANCkoOuaOx1Y+c= github.com/pelletier/go-toml v1.9.5/go.mod h1:u1nR/EPcESfeI/szUZKdtJ0xRNbUoANCkoOuaOx1Y+c=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA= github.com/spf13/pflag v1.0.6 h1:jFzHGLGAlb3ruxLB8MhbI6A8+AQX/2eW4qeyNZXNp2o=
github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk= github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
@@ -67,19 +71,23 @@ 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 h1:5cRCUmj+l5yvlM2irtpFBIJwVV2DPEgYSaWvF19FtcY=
github.com/tlinden/yadu v0.1.3/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA= 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/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 v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= golang.org/x/net v0.0.0-20181114220301-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 v0.0.0-20190606173856-1492cefac77f/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 v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.23.0 h1:7EYJ93RZ9vYSZAIb2x3lnuvqO5zneoD6IvWjuhfxjTs= golang.org/x/net v0.23.0 h1:7EYJ93RZ9vYSZAIb2x3lnuvqO5zneoD6IvWjuhfxjTs=
golang.org/x/net v0.23.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg= golang.org/x/net v0.23.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ= golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
golang.org/x/sync v0.8.0/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 v0.0.0-20190215142949-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 v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws= golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.29.0 h1:TPYlXGxvx1MGTn2GiZDhnjPA9wZzZeGKHHmKhHYvgaU=
golang.org/x/sys v0.29.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo= gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=

View File

@@ -20,11 +20,16 @@ package main
import ( import (
"bytes" "bytes"
"fmt" "fmt"
"image/jpeg" "image"
_ "image/gif"
_ "image/jpeg"
_ "image/png"
"log/slog" "log/slog"
"os" "os"
"path/filepath" "path/filepath"
_ "golang.org/x/image/webp"
"github.com/corona10/goimagehash" "github.com/corona10/goimagehash"
) )
@@ -35,6 +40,7 @@ type Image struct {
Hash *goimagehash.ImageHash Hash *goimagehash.ImageHash
Data *bytes.Reader Data *bytes.Reader
URI string URI string
Mime string
} }
// used for logging to avoid printing Data // used for logging to avoid printing Data
@@ -49,21 +55,52 @@ func (img *Image) LogValue() slog.Value {
// holds all images of an ad // holds all images of an ad
type Cache []*goimagehash.ImageHash 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{ img := &Image{
Filename: filename, Filename: filename,
URI: uri, URI: uri,
Data: buf, Data: buf,
Mime: imgconfig,
} }
return img slog.Debug("image MIME", "mime", img.Mime)
return img, nil
} }
// Calculate diff hash of the image // Calculate diff hash of the image
func (img *Image) CalcHash() error { func (img *Image) CalcHash() error {
jpgdata, err := jpeg.Decode(img.Data) jpgdata, format, err := image.Decode(img.Data)
if err != nil { 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) hash1, err := goimagehash.DifferenceHash(jpgdata)
@@ -133,12 +170,19 @@ func ReadImages(addir string, dont bool) (Cache, error) {
reader := bytes.NewReader(data.Bytes()) 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 { if err := img.CalcHash(); err != nil {
return nil, err return nil, err
} }
slog.Debug("Caching image from file system", "image", img, "hash", img.Hash.ToString()) if img.Hash != nil {
slog.Debug("Caching image from file system", "image", img, "hash", img.Hash.ToString())
}
cache = append(cache, img.Hash) cache = append(cache, img.Hash)
} }
} }

View File

@@ -133,7 +133,7 @@
.\" ======================================================================== .\" ========================================================================
.\" .\"
.IX Title "KLEINGEBAECK 1" .IX Title "KLEINGEBAECK 1"
.TH KLEINGEBAECK 1 "2024-02-10" "1" "User Commands" .TH KLEINGEBAECK 1 "2025-02-06" "1" "User Commands"
.\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" For nroff, turn off justification. Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents. .\" way too many mistakes in technical documents.
.if n .ad l .if n .ad l
@@ -174,7 +174,7 @@ well. We use \s-1TOML\s0 as our configuration language. See
.PP .PP
Format is pretty simple: Format is pretty simple:
.PP .PP
.Vb 11 .Vb 10
\& user = 1010101 \& user = 1010101
\& loglevel = verbose \& loglevel = verbose
\& outdir = "test" \& outdir = "test"
@@ -185,6 +185,8 @@ Format is pretty simple:
\& Id: {{.ID}} \& Id: {{.ID}}
\& Category: {{.Category}} \& Category: {{.Category}}
\& Condition: {{.Condition}} \& Condition: {{.Condition}}
\& Type: {{.Type}}
\& Color: {{.Color}}
\& Created: {{.Created}} \& Created: {{.Created}}
\& \&
\& {{.Text}} \& {{.Text}}
@@ -267,12 +269,13 @@ variables as the ad name template above.
.PP .PP
This is the default template: This is the default template:
.PP .PP
.Vb 7 .Vb 8
\& Title: {{.Title}} \& Title: {{.Title}}
\& Price: {{.Price}} \& Price: {{.Price}}
\& Id: {{.ID}} \& Id: {{.ID}}
\& Category: {{.Category}} \& Category: {{.Category}}
\& Condition: {{.Condition}} \& Condition: {{.Condition}}
\& Type: {{.Type}}
\& Created: {{.Created}} \& Created: {{.Created}}
\& Expire: {{.Expire}} \& Expire: {{.Expire}}
\& \&

View File

@@ -46,6 +46,8 @@ CONFIGURATION
Id: {{.ID}} Id: {{.ID}}
Category: {{.Category}} Category: {{.Category}}
Condition: {{.Condition}} Condition: {{.Condition}}
Type: {{.Type}}
Color: {{.Color}}
Created: {{.Created}} Created: {{.Created}}
{{.Text}} {{.Text}}
@@ -111,6 +113,7 @@ TEMPLATES
Id: {{.ID}} Id: {{.ID}}
Category: {{.Category}} Category: {{.Category}}
Condition: {{.Condition}} Condition: {{.Condition}}
Type: {{.Type}}
Created: {{.Created}} Created: {{.Created}}
Expire: {{.Expire}} Expire: {{.Expire}}

View File

@@ -46,6 +46,8 @@ Format is pretty simple:
Id: {{.ID}} Id: {{.ID}}
Category: {{.Category}} Category: {{.Category}}
Condition: {{.Condition}} Condition: {{.Condition}}
Type: {{.Type}}
Color: {{.Color}}
Created: {{.Created}} Created: {{.Created}}
{{.Text}} {{.Text}}
@@ -131,6 +133,7 @@ This is the default template:
Id: {{.ID}} Id: {{.ID}}
Category: {{.Category}} Category: {{.Category}}
Condition: {{.Condition}} Condition: {{.Condition}}
Type: {{.Type}}
Created: {{.Created}} Created: {{.Created}}
Expire: {{.Expire}} Expire: {{.Expire}}

View File

@@ -93,6 +93,10 @@ const ADTPL string = `DOCTYPE html>
<li class="addetailslist--detail"> <li class="addetailslist--detail">
Zustand<span class="addetailslist--detail--value" > Zustand<span class="addetailslist--detail--value" >
{{ .Condition }}</span> {{ .Condition }}</span>
Farbe<span class="addetailslist--detail--value" >
{{ .Color }}</span>
Art<span class="addetailslist--detail--value" >
{{ .Type }}</span>
</li> </li>
</ul> </ul>
</div> </div>
@@ -182,13 +186,13 @@ var tests = []Tests{
{ {
name: "download-all-ads", name: "download-all-ads",
args: base + " -o t/out -u 1", 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, exitcode: 0,
}, },
{ {
name: "download-all-ads-using-config", name: "download-all-ads-using-config",
args: "kleingebaeck -c t/fullconfig.conf", 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, exitcode: 0,
}, },
} }
@@ -251,11 +255,14 @@ type AdConfig struct {
Price string Price string
Category string Category string
Condition string Condition string
Type string
Color string
Created string Created string
Text string Text string
Images []string // files in ./t/ Images []string // files in ./t/
} }
// used to generate ad listings returned by httpmock using templates
var adsrc = []AdConfig{ var adsrc = []AdConfig{
{ {
Title: "First Ad", Title: "First Ad",
@@ -263,7 +270,9 @@ var adsrc = []AdConfig{
Category: "Klimbim", Category: "Klimbim",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "first-ad", Slug: "first-ad",
Condition: "works", Condition: "Sehr Gut",
Color: "Grün",
Type: "Ball",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, Images: []string{"t/1.jpg", "t/2.jpg"},
}, },
@@ -273,7 +282,7 @@ var adsrc = []AdConfig{
Category: "Kram", Category: "Kram",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "second-ad", Slug: "second-ad",
Condition: "works", Condition: "Gut",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, Images: []string{"t/1.jpg", "t/2.jpg"},
}, },
@@ -284,7 +293,7 @@ var adsrc = []AdConfig{
Category: "Kuddelmuddel", Category: "Kuddelmuddel",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "third-ad", Slug: "third-ad",
Condition: "works", Condition: "In Ordnung",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, Images: []string{"t/1.jpg", "t/2.jpg"},
}, },
@@ -295,7 +304,7 @@ var adsrc = []AdConfig{
Category: "Krempel", Category: "Krempel",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "fourth-ad", Slug: "fourth-ad",
Condition: "works", Condition: "Neu",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, Images: []string{"t/1.jpg", "t/2.jpg"},
}, },
@@ -306,7 +315,7 @@ var adsrc = []AdConfig{
Category: "Kladderadatsch", Category: "Kladderadatsch",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "fifth-ad", Slug: "fifth-ad",
Condition: "works", Condition: "Sehr Gut",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, Images: []string{"t/1.jpg", "t/2.jpg"},
}, },
@@ -317,10 +326,21 @@ var adsrc = []AdConfig{
Category: "Klunker", Category: "Klunker",
Text: "Thing to sale", Text: "Thing to sale",
Slug: "sixth-ad", Slug: "sixth-ad",
Condition: "works", Condition: "Sehr Gut",
Created: "Yesterday", Created: "Yesterday",
Images: []string{"t/1.jpg", "t/2.jpg"}, 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: "Sehr Gut",
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 // An Adsource is used to construct a httpmock responder for a
@@ -363,7 +383,7 @@ func InitValidSources() []Adsource {
// valid ad listing page 2 // valid ad listing page 2
list2 := []AdConfig{ list2 := []AdConfig{
adsrc[3], adsrc[4], adsrc[5], adsrc[3], adsrc[4], adsrc[5], adsrc[6],
} }
// valid ad listing page 3, which is empty // valid ad listing page 3, which is empty
@@ -459,7 +479,7 @@ func SetIntercept(ads []Adsource) {
} }
// we just use 2 images, put this here // 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.RegisterResponder("GET", image,
httpmock.NewBytesResponder(200, GetImage(image)).HeaderAdd(headers)) httpmock.NewBytesResponder(200, GetImage(image)).HeaderAdd(headers))
} }

View File

@@ -22,6 +22,7 @@ import (
"fmt" "fmt"
"log/slog" "log/slog"
"path/filepath" "path/filepath"
"slices"
"strconv" "strconv"
"strings" "strings"
"time" "time"
@@ -124,6 +125,17 @@ func ScrapeAd(fetch *Fetcher, uri string) error {
return fmt.Errorf("could not extract ad data from page, got empty struct") return fmt.Errorf("could not extract ad data from page, got empty struct")
} }
for _, detail := range advertisement.Details {
switch {
case slices.Contains(CONDITIONS, detail):
advertisement.Condition = detail
case slices.Contains(COLORS, detail):
advertisement.Color = detail
default:
advertisement.Type = detail
}
}
advertisement.CalculateExpire() advertisement.CalculateExpire()
// prepare ad dir name // prepare ad dir name
@@ -170,7 +182,9 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
for _, imguri := range advertisement.Images { for _, imguri := range advertisement.Images {
imguri := imguri 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 { egroup.Go(func() error {
// wait a little // wait a little
@@ -192,7 +206,11 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
reader := bytes.NewReader(buf.Bytes()) reader := bytes.NewReader(buf.Bytes())
image := NewImage(reader, file, imguri) image, err := NewImage(reader, basefilename, imguri)
if err != nil {
return err
}
err = image.CalcHash() err = image.CalcHash()
if err != nil { if err != nil {
return err return err
@@ -211,7 +229,7 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
return fmt.Errorf("failed to seek(0) on image reader: %w", err) return fmt.Errorf("failed to seek(0) on image reader: %w", err)
} }
err = WriteImage(file, reader) err = WriteImage(image.Filename, reader)
if err != nil { if err != nil {
return err return err
} }

View File

@@ -149,7 +149,9 @@ func ReadImage(filename string) (*bytes.Buffer, error) {
func fileExists(filename string) bool { func fileExists(filename string) bool {
info, err := os.Stat(filename) info, err := os.Stat(filename)
if os.IsNotExist(err) {
if err != nil {
// return false on any error
return false return false
} }

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