Fix/timeformat (#122)

* Fix #121: confused day with month thanks to time.Format
* Add outdir template variable example

.github/workflows/release.yaml

@@ -1,8 +1,8 @@
-name: build-and-test
+name: build-release
 on:
   push:
     tags:
-      - "*"
+      - "v*.*.*"
 
 jobs:
   release:
@@ -10,10 +10,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Set up Go
-        uses: actions/setup-go@v1
+        uses: actions/setup-go@v5
         with:
           go-version: 1.22.11
 
@@ -30,3 +30,58 @@ jobs:
           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}}

README.md

@@ -204,6 +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

@@ -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"`
@@ -50,7 +56,6 @@ 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 +85,64 @@ 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 = "0.3.13"
+	VERSION    string = "0.3.17"
 	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}}\nCondition: {{.Condition}}\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}}\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 
+# 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

@@ -23,6 +23,7 @@ require (
 
 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

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=

kleingebaeck.1

@@ -133,7 +133,7 @@
 .\" ========================================================================
 .\"
 .IX Title "KLEINGEBAECK 1"
-.TH KLEINGEBAECK 1 "2024-02-10" "1" "User Commands"
+.TH KLEINGEBAECK 1 "2025-02-10" "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
@@ -267,12 +267,13 @@ 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}}
 \&    

kleingebaeck.go

@@ -111,6 +111,7 @@ TEMPLATES
         Id: {{.ID}}
         Category: {{.Category}}
         Condition: {{.Condition}}
+        Type: {{.Type}}
         Created: {{.Created}}
         Expire: {{.Expire}}
     

kleingebaeck.pod

@@ -131,6 +131,7 @@ This is the default template:
     Id: {{.ID}}
     Category: {{.Category}}
     Condition: {{.Condition}}
+    Type: {{.Type}}
     Created: {{.Created}}
     Expire: {{.Expire}}
     

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>
@@ -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"},
 	},
@@ -317,7 +334,9 @@ 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"},
 	},
@@ -328,7 +347,9 @@ var adsrc = []AdConfig{
 		Category:  "Klunker",
 		Text:      "Thing to sale",
 		Slug:      "seventh-ad",
-		Condition: "works",
+		Condition: "Sehr Gut",
+		Color:     "Gelpb",
+		Type:      "Schmuck",
 		Created:   "Yesterday",
 		Images:    []string{"t/1.png", "t/1.gif", "t/1.webp", "t/1.jpg"},
 	},

scrape.go

@@ -124,6 +124,7 @@ 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

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)