Add year,month,day support to Adnametemplate (#123)

* add year, month and day to adnametemplate as well

.github/workflows/pushimage.yaml

@@ -22,13 +22,13 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build and push Docker image
-        uses: docker/build-push-action@48aba3b46d1b1fec4febb7c5d0c644b249a11355
+        uses: docker/build-push-action@ca877d9245402d1537745e0e356eab47c3520991
         with:
           push: true
           tags: ghcr.io/tlinden/kleingebaeck:${{ github.ref_name}}
 
       - name: Build and push latest Docker image
-        uses: docker/build-push-action@48aba3b46d1b1fec4febb7c5d0c644b249a11355
+        uses: docker/build-push-action@ca877d9245402d1537745e0e356eab47c3520991
         with:
           push: true
           tags: ghcr.io/tlinden/kleingebaeck:latest

.github/workflows/release.yaml

@@ -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}}

Makefile

@@ -82,8 +82,8 @@ goupdate:
 buildall:
 	./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
 	@echo "### kleingebaeck version:"

README-de.md

@@ -17,6 +17,15 @@ Anzeige gespeichert werden. In dem Verzeichnis wird eine Datei
 `Adlisting.txt` erstellt, in der sich die Inhalte der Anzeige wie
 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
 
 Das ist die Hauptseite meines kleinanzeigen.de Accounts:

README.md

@@ -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
 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
 
 This is the index of my kleinanzeigen.de Account:
@@ -195,6 +204,7 @@ Price: 99 € VB
 Id: 1919191919
 Category: Sachbücher
 Condition: Sehr Gut
+Type: Buch
 Created: 10.12.2023
 
 This is the description text.

ad.go

@@ -1,5 +1,5 @@
 /*
-Copyright © 2023-2024 Thomas von Dein
+Copyright © 2023-2025 Thomas von Dein
 
 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
@@ -18,6 +18,7 @@ along with this program. If not, see <http://www.gnu.org/licenses/>.
 package main
 
 import (
+	"bufio"
 	"log/slog"
 	"strings"
 	"time"
@@ -31,7 +32,12 @@ type Ad struct {
 	Title        string `goquery:"h1"`
 	Slug         string
 	ID           string
-	Condition    string `goquery:".addetailslist--detail--value,text"`
+	Details      string            `goquery:".addetailslist--detail,text"`
+	Attributes   map[string]string // processed afterwards
+	Condition    string            // post processed from details for backward compatibility
+	Type         string            // post processed from details for backward compatibility
+	Color        string            // post processed from details for backward compatibility
+	Material     string            // post processed from details for backward compatibility
 	Category     string
 	CategoryTree []string `goquery:".breadcrump-link,text"`
 	Price        string   `goquery:"h2#viewad-price"`
@@ -39,6 +45,9 @@ type Ad struct {
 	Text         string   `goquery:"p#viewad-description-text,html"`
 	Images       []string `goquery:".galleryimage-element img,[src]"`
 	Expire       string
+
+	// runtime computed
+	Year, Day, Month string
 }
 
 // Used by slog to pretty print an ad
@@ -50,7 +59,6 @@ func (ad *Ad) LogValue() slog.Value {
 		slog.Int("imagecount", len(ad.Images)),
 		slog.Int("bodysize", len(ad.Text)),
 		slog.String("categorytree", strings.Join(ad.CategoryTree, "+")),
-		slog.String("condition", ad.Condition),
 		slog.String("created", ad.Created),
 		slog.String("expire", ad.Expire),
 	)
@@ -80,3 +88,64 @@ func (ad *Ad) CalculateExpire() {
 		}
 	}
 }
+
+/*
+Decode attributes like color or condition. See
+https://github.com/TLINDEN/kleingebaeck/issues/117
+for more details. In short: the HTML delivered by
+kleinanzeigen.de has no css attribute for the keys
+so we cannot extract key=>value mappings of the
+ad details but have to parse them manually.
+
+The ad.Details member contains this after goq run:
+
+Art
+
+	Weitere Kinderzimmermöbel
+
+	Farbe
+	Holz
+
+	Zustand
+	In Ordnung
+
+We parse this into ad.Attributes and fill in some
+static members for backward compatibility reasons.
+*/
+func (ad *Ad) DecodeAttributes() {
+	rd := strings.NewReader(ad.Details)
+	scanner := bufio.NewScanner(rd)
+
+	isattr := true
+	attr := ""
+	attrmap := map[string]string{}
+
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+
+		if line == "" {
+			continue
+		}
+
+		if isattr {
+			attr = line
+		} else {
+			attrmap[attr] = line
+		}
+
+		isattr = !isattr
+	}
+
+	ad.Attributes = attrmap
+
+	switch {
+	case Exists(ad.Attributes, "Zustand"):
+		ad.Condition = ad.Attributes["Zustand"]
+	case Exists(ad.Attributes, "Farbe"):
+		ad.Color = ad.Attributes["Farbe"]
+	case Exists(ad.Attributes, "Art"):
+		ad.Type = ad.Attributes["Type"]
+	case Exists(ad.Attributes, "Material"):
+		ad.Material = ad.Attributes["Material"]
+	}
+}

config.go

@@ -1,5 +1,5 @@
 /*
-Copyright © 2023-2024 Thomas von Dein
+Copyright © 2023-2025 Thomas von Dein
 
 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
@@ -34,17 +34,25 @@ import (
 )
 
 const (
-	VERSION    string = "0.3.10"
+	VERSION    string = "0.3.18"
 	Baseuri    string = "https://www.kleinanzeigen.de"
 	Listuri    string = "/s-bestandsliste.html"
 	Defaultdir string = "."
 
+	/*
+		   Also possible: loop through .Attributes:
+
+		DefaultTemplate string = "Title: {{.Title}}\nPrice: {{.Price}}\nId: {{.ID}}\n" +
+			"Category: {{.Category}}\n{{ range $key,$val := .Attributes }}{{ $key }}: {{ $val }}\n{{ end }}" +
+			"Created: {{.Created}}\nExpire: {{.Expire}}\n\n{{.Text}}\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"
 
 	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"
 
 	DefaultUserAgent string = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " +

example.conf

@@ -12,19 +12,36 @@ user = 00000000
 loglevel = "verbose"
 
 # directory where  to store downloaded  ads. kleingebaeck will  try to
-# create it. must be a quoted string.
+# create it. must be a quoted string. You can also include a couple of 
-outdir = "test"
+# template variables, e.g:
+# outdir = "test-{{.Year}}-{{.Month}}-{{.Day}}"
+outdir = "test" 
 
-# template for  stored adlistings.  To enable  it, remove  the comment
+# template for  stored adlistings.
-# chars up until the last #"""
+template="""
-#template="""
+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}}
 
-#{{.Text}}
+{{.Text}}
-# """
+"""
 
+# Ads may contain more attributes than just the Condition. To print
+# all attributes, loop over all of them:
+
+template="""
+Title: {{.Title}}
+Price: {{.Price}}
+Id: {{.Id}}
+Category: {{.Category}}
+{{ range $key,$val := .Attributes }}{{ $key }}: {{ $val }}
+{{ end }}
+Type: {{.Type}}
+Created: {{.Created}}
+
+{{.Text}}
+"""

go.mod

@@ -13,27 +13,29 @@ 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 v1.0.7
 	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
-	golang.org/x/sync v0.9.0
+	golang.org/x/image v0.23.0
+	golang.org/x/sync v0.10.0
 )
 
 require (
 	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/fatih/color v1.16.0 // indirect
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/go-viper/mapstructure/v2 v2.2.1 // 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/reflectwalk v1.0.2 // indirect
 	github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
 	github.com/pelletier/go-toml v1.9.5 // 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
 
 )

go.sum

@@ -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 v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE=
 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 v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
 github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
@@ -39,10 +41,12 @@ 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 v1.0.7 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/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 v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 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/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 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/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 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/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 v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
-golang.org/x/sync v0.9.0/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 v0.0.0-20220811171246-fbc7d0a398ab/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/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=
 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=

image.go

@@ -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
 			}
 
-			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)
 		}
 	}

kleingebaeck.1

@@ -133,7 +133,7 @@
 .\" ========================================================================
 .\"
 .IX Title "KLEINGEBAECK 1"
-.TH KLEINGEBAECK 1 "2024-02-10" "1" "User Commands"
+.TH KLEINGEBAECK 1 "2025-02-27" "1" "User Commands"
 .\" For nroff, turn off justification.  Always turn off hyphenation; it makes
 .\" way too many mistakes in technical documents.
 .if n .ad l
@@ -260,6 +260,29 @@ The ad directory name can be modified using the following ad values:
 .PP
 It can only be configured in the config file. By default only
 \&\f(CW\*(C`{{.Slug}}\*(C'\fR is being used, this is the title of the ad in url format.
+.SS "\s-1AD NAME TEMPLATE\s0"
+.IX Subsection "AD NAME TEMPLATE"
+The name of the directory per ad can be tuned as well:
+.ie n .IP """{{.Year}}""" 4
+.el .IP "\f(CW{{.Year}}\fR" 4
+.IX Item "{{.Year}}"
+.PD 0
+.ie n .IP """{{.Month}}""" 4
+.el .IP "\f(CW{{.Month}}\fR" 4
+.IX Item "{{.Month}}"
+.ie n .IP """{{.Day}}""" 4
+.el .IP "\f(CW{{.Day}}\fR" 4
+.IX Item "{{.Day}}"
+.ie n .IP """{{.Slug}}""" 4
+.el .IP "\f(CW{{.Slug}}\fR" 4
+.IX Item "{{.Slug}}"
+.ie n .IP """{{.Category}}""" 4
+.el .IP "\f(CW{{.Category}}\fR" 4
+.IX Item "{{.Category}}"
+.ie n .IP """{{.ID}}""" 4
+.el .IP "\f(CW{{.ID}}\fR" 4
+.IX Item "{{.ID}}"
+.PD
 .SS "\s-1AD TEMPLATE\s0"
 .IX Subsection "AD TEMPLATE"
 The ad listing itself can be modified as well, using the same
@@ -267,12 +290,13 @@ variables as the ad name template above.
 .PP
 This is the default template:
 .PP
-.Vb 7
+.Vb 8
 \&    Title: {{.Title}}
 \&    Price: {{.Price}}
 \&    Id: {{.ID}}
 \&    Category: {{.Category}}
 \&    Condition: {{.Condition}}
+\&    Type: {{.Type}}
 \&    Created: {{.Created}}
 \&    Expire: {{.Expire}}
 \&    
@@ -343,7 +367,7 @@ Also there's currently no parallelization implemented. This will
 change in the future.
 .SH "LICENSE"
 .IX Header "LICENSE"
-Copyright 2023\-2024 Thomas von Dein
+Copyright 2023\-2025 Thomas von Dein
 .PP
 This program is free software: you can redistribute it and/or modify
 it under the terms of the \s-1GNU\s0 General Public License as published by

kleingebaeck.go

@@ -100,6 +100,16 @@ TEMPLATES
     It can only be configured in the config file. By default only
     "{{.Slug}}" is being used, this is the title of the ad in url format.
 
+  AD NAME TEMPLATE
+    The name of the directory per ad can be tuned as well:
+
+    "{{.Year}}"
+    "{{.Month}}"
+    "{{.Day}}"
+    "{{.Slug}}"
+    "{{.Category}}"
+    "{{.ID}}"
+
   AD TEMPLATE
     The ad listing itself can be modified as well, using the same variables
     as the ad name template above.
@@ -111,6 +121,7 @@ TEMPLATES
         Id: {{.ID}}
         Category: {{.Category}}
         Condition: {{.Condition}}
+        Type: {{.Type}}
         Created: {{.Created}}
         Expire: {{.Expire}}
     
@@ -173,7 +184,7 @@ LIMITATIONS
     in the future.
 
 LICENSE
-    Copyright 2023-2024 Thomas von Dein
+    Copyright 2023-2025 Thomas von Dein
 
     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

kleingebaeck.pod

@@ -119,6 +119,27 @@ The ad directory name can be modified using the following ad values:
 It can only be configured in the config file. By default only
 C<{{.Slug}}> is being used, this is the title of the ad in url format.
 
+=head2 AD NAME TEMPLATE
+
+The name of the directory per ad can be tuned as well:
+
+=over
+
+=item C<{{.Year}}>
+
+=item C<{{.Month}}>
+
+=item C<{{.Day}}>
+
+=item C<{{.Slug}}>
+
+=item C<{{.Category}}>
+
+=item C<{{.ID}}>
+
+
+=back
+
 =head2 AD TEMPLATE
 
 The ad listing itself can be modified as well, using the same
@@ -131,6 +152,7 @@ This is the default template:
     Id: {{.ID}}
     Category: {{.Category}}
     Condition: {{.Condition}}
+    Type: {{.Type}}
     Created: {{.Created}}
     Expire: {{.Expire}}
     
@@ -201,7 +223,7 @@ change in the future.
 
 =head1 LICENSE
 
-Copyright 2023-2024 Thomas von Dein
+Copyright 2023-2025 Thomas von Dein
 
 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

main_test.go

@@ -93,6 +93,10 @@ const ADTPL string = `DOCTYPE html>
         <li class="addetailslist--detail">
           Zustand<span class="addetailslist--detail--value" >
           {{ .Condition }}</span>
+          Farbe<span class="addetailslist--detail--value" >
+          {{ .Color }}</span>
+          Art<span class="addetailslist--detail--value" >
+          {{ .Type }}</span>
         </li>
       </ul>
     </div>
@@ -182,13 +186,13 @@ 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,
 	},
 }
@@ -251,11 +255,14 @@ type AdConfig struct {
 	Price     string
 	Category  string
 	Condition string
+	Type      string
+	Color     string
 	Created   string
 	Text      string
 	Images    []string // files in ./t/
 }
 
+// used to generate ad listings returned by httpmock using templates
 var adsrc = []AdConfig{
 	{
 		Title: "First Ad",
@@ -263,7 +270,9 @@ var adsrc = []AdConfig{
 		Category:  "Klimbim",
 		Text:      "Thing to sale",
 		Slug:      "first-ad",
-		Condition: "works",
+		Condition: "Sehr Gut",
+		Color:     "Grün",
+		Type:      "Ball",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.jpg", "t/2.jpg"},
 	},
@@ -273,7 +282,9 @@ var adsrc = []AdConfig{
 		Category:  "Kram",
 		Text:      "Thing to sale",
 		Slug:      "second-ad",
-		Condition: "works",
+		Condition: "Gut",
+		Color:     "Lila",
+		Type:      "Schoki",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.jpg", "t/2.jpg"},
 	},
@@ -284,7 +295,9 @@ var adsrc = []AdConfig{
 		Category:  "Kuddelmuddel",
 		Text:      "Thing to sale",
 		Slug:      "third-ad",
-		Condition: "works",
+		Condition: "In Ordnung",
+		Color:     "Blau",
+		Type:      "Auto",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.jpg", "t/2.jpg"},
 	},
@@ -295,7 +308,9 @@ var adsrc = []AdConfig{
 		Category:  "Krempel",
 		Text:      "Thing to sale",
 		Slug:      "fourth-ad",
-		Condition: "works",
+		Condition: "Neu",
+		Color:     "Rot",
+		Type:      "Spielzeut",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.jpg", "t/2.jpg"},
 	},
@@ -306,7 +321,9 @@ var adsrc = []AdConfig{
 		Category:  "Kladderadatsch",
 		Text:      "Thing to sale",
 		Slug:      "fifth-ad",
-		Condition: "works",
+		Condition: "Sehr Gut",
+		Color:     "Braun",
+		Type:      "Parteibuch",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.jpg", "t/2.jpg"},
 	},
@@ -317,10 +334,25 @@ var adsrc = []AdConfig{
 		Category:  "Klunker",
 		Text:      "Thing to sale",
 		Slug:      "sixth-ad",
-		Condition: "works",
+		Condition: "Sehr Gut",
+		Color:     "Silber",
+		Type:      "Ring",
 		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: "Sehr Gut",
+		Color:     "Gelpb",
+		Type:      "Schmuck",
+		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 +395,7 @@ 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 +491,7 @@ 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))
 	}

mkrel.sh

@@ -45,15 +45,21 @@ for D in $DIST; do
     os=${D/\/*/}
     arch=${D/*\//}
     binfile="releases/${tool}-${os}-${arch}-${version}"
+    pie=""
 
     if test "$os" = "windows"; then
         binfile="${binfile}.exe"
     fi
+
+    if test "$D" = "linux/amd64"; then
+        pie="-buildmode=pie"
+    fi
     
     tardir="${tool}-${os}-${arch}-${version}"
     tarfile="releases/${tool}-${os}-${arch}-${version}.tar.gz"
     set -x
-    GOOS=${os} GOARCH=${arch} go build -tags osusergo,netgo -ldflags "-extldflags=-static" -o ${binfile}
+    GOOS=${os} GOARCH=${arch} go build -tags osusergo,netgo -ldflags "-extldflags=-static -w" --trimpath $pie -o ${binfile}
+    strip --strip-all ${binfile}
     mkdir -p ${tardir}
     cp ${binfile} README.md LICENSE ${tardir}/
     echo 'tool = kleingebaeck

scrape.go

@@ -1,5 +1,5 @@
 /*
-Copyright © 2023-2024 Thomas von Dein
+Copyright © 2023-2025 Thomas von Dein
 
 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
@@ -88,7 +88,13 @@ func ScrapeUser(fetch *Fetcher) error {
 
 // scrape an ad. uri is the full uri of the ad, dir is the basedir
 func ScrapeAd(fetch *Fetcher, uri string) error {
-	advertisement := &Ad{}
+	now := time.Now()
+
+	advertisement := &Ad{
+		Year:  now.Format("2006"),
+		Month: now.Format("01"),
+		Day:   now.Format("02"),
+	}
 
 	// extract slug and id from uri
 	uriparts := strings.Split(uri, "/")
@@ -124,6 +130,7 @@ func ScrapeAd(fetch *Fetcher, uri string) error {
 		return fmt.Errorf("could not extract ad data from page, got empty struct")
 	}
 
+	advertisement.DecodeAttributes()
 	advertisement.CalculateExpire()
 
 	// prepare ad dir name
@@ -170,7 +177,9 @@ 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 +201,11 @@ 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 +224,7 @@ 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
 			}

store.go

@@ -1,5 +1,5 @@
 /*
-Copyright © 2023-2024 Thomas von Dein
+Copyright © 2023-2025 Thomas von Dein
 
 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
@@ -44,8 +44,8 @@ func OutDirName(conf *Config) (string, error) {
 	now := time.Now()
 	data := OutdirData{
 		Year:  now.Format("2006"),
-		Month: now.Format("02"),
+		Month: now.Format("01"),
-		Day:   now.Format("01"),
+		Day:   now.Format("02"),
 	}
 
 	err = tmpl.Execute(&buf, data)