fix #74: warn if about to write to already visited ad, overwrite if -f

config.go

@@ -34,7 +34,7 @@ import (
 )
 
 const (
-	VERSION    string = "0.3.3"
+	VERSION    string = "0.3.4"
 	Baseuri    string = "https://www.kleinanzeigen.de"
 	Listuri    string = "/s-bestandsliste.html"
 	Defaultdir string = "."
@@ -65,6 +65,8 @@ const (
 	WIN string = "windows"
 )
 
+var DirsVisited map[string]int
+
 const Usage string = `This is kleingebaeck, the kleinanzeigen.de backup tool.
 
 Usage: kleingebaeck [-dvVhmoclu] [<ad-listing-url>,...]
@@ -77,7 +79,7 @@ Options:
 -l --limit   <num>      Limit the ads to download to <num>, default: load all.
 -c --config  <file>     Use config file <file> (default: ~/.kleingebaeck).
    --ignoreerrors       Ignore HTTP errors, may lead to incomplete ad backup.
--f --force              Download images even if they already exist.
+-f --force              Overwrite images and ads even if the already exist.
 -m --manual             Show manual.
 -h --help               Show usage.
 -V --version            Show program version.

go.mod

@@ -14,7 +14,7 @@ require (
 	github.com/lmittmann/tint v1.0.4
 	github.com/mattn/go-isatty v0.0.20
 	github.com/spf13/pflag v1.0.5
-	github.com/tlinden/yadu v0.1.1
+	github.com/tlinden/yadu v0.1.2
 	golang.org/x/sync v0.5.0
 )
 
@@ -33,7 +33,7 @@ require (
 	github.com/pelletier/go-toml v1.9.5 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	golang.org/x/net v0.0.0-20220722155237-a158d28d115b // indirect
-	golang.org/x/sys v0.14.0 // indirect
+	golang.org/x/sys v0.17.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 
 )

go.sum

@@ -66,6 +66,8 @@ github.com/tlinden/yadu v0.1.0 h1:qtCi1jxg392qVRLFyrJ2LYu6/PiKSp1LT02EX+mNLME=
 github.com/tlinden/yadu v0.1.0/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
 github.com/tlinden/yadu v0.1.1 h1:116oEUy9b4PcMF5wLL2dCFA/sn/praYutOnao07MROw=
 github.com/tlinden/yadu v0.1.1/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
+github.com/tlinden/yadu v0.1.2 h1:TYYVnUJwziRJ9YPbIbRf9ikmDw0Q8Ifixm+J/kBQFh8=
+github.com/tlinden/yadu v0.1.2/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 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=
@@ -81,6 +83,8 @@ golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.14.0 h1:Vz7Qs629MkJkGyHxUlRHizWJRG2j8fbQKjELVSNhy7Q=
 golang.org/x/sys v0.14.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.17.0 h1:25cE3gD+tdBA7lp7QfhuV+rJiE9YXTcS3VG1SqssI/Y=
+golang.org/x/sys v0.17.0/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 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

kleingebaeck.1

@@ -133,7 +133,7 @@
 .\" ========================================================================
 .\"
 .IX Title "KLEINGEBAECK 1"
-.TH KLEINGEBAECK 1 "2024-01-25" "1" "User Commands"
+.TH KLEINGEBAECK 1 "2024-02-10" "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
@@ -152,7 +152,7 @@ kleingebaeck \- kleinanzeigen.de backup tool
 \&    \-l \-\-limit   <num>      Limit the ads to download to <num>, default: load all.
 \&    \-c \-\-config  <file>     Use config file <file> (default: ~/.kleingebaeck).
 \&       \-\-ignoreerrors       Ignore HTTP errors, may lead to incomplete ad backup.
-\&    \-f \-\-force              Download images even if they already exist.
+\&    \-f \-\-force              Overwrite images and ads even if the already exist.
 \&    \-m \-\-manual             Show manual.
 \&    \-h \-\-help               Show usage.
 \&    \-V \-\-version            Show program version.

kleingebaeck.go

@@ -14,7 +14,7 @@ SYNOPSYS
         -l --limit   <num>      Limit the ads to download to <num>, default: load all.
         -c --config  <file>     Use config file <file> (default: ~/.kleingebaeck).
            --ignoreerrors       Ignore HTTP errors, may lead to incomplete ad backup.
-        -f --force              Download images even if they already exist.
+        -f --force              Overwrite images and ads even if the already exist.
         -m --manual             Show manual.
         -h --help               Show usage.
         -V --version            Show program version.

kleingebaeck.pod

@@ -13,7 +13,7 @@ kleingebaeck - kleinanzeigen.de backup tool
     -l --limit   <num>      Limit the ads to download to <num>, default: load all.
     -c --config  <file>     Use config file <file> (default: ~/.kleingebaeck).
        --ignoreerrors       Ignore HTTP errors, may lead to incomplete ad backup.
-    -f --force              Download images even if they already exist.
+    -f --force              Overwrite images and ads even if the already exist.
     -m --manual             Show manual.
     -h --help               Show usage.
     -V --version            Show program version.

main.go

@@ -123,6 +123,9 @@ func Main(output io.Writer) int {
 		return Die(err)
 	}
 
+	// setup ad dir registry, needed to check for duplicates
+	DirsVisited = make(map[string]int)
+
 	switch {
 	case len(conf.Adlinks) >= 1:
 		// directly backup ad listing[s]

scrape.go

@@ -126,6 +126,11 @@ func ScrapeAd(fetch *Fetcher, uri string) error {
 
 	advertisement.CalculateExpire()
 
+	proceed := CheckAdVisited(fetch.Config, advertisement.Slug)
+	if !proceed {
+		return nil
+	}
+
 	// write listing
 	addir, err := WriteAd(fetch.Config, advertisement)
 	if err != nil {

store.go

@@ -133,3 +133,24 @@ func fileExists(filename string) bool {
 
 	return !info.IsDir()
 }
+
+// check if  an addir has  already been  processed by current  run and
+// decide what to do
+func CheckAdVisited(conf *Config, adname string) bool {
+	if Exists(DirsVisited, adname) {
+		if conf.ForceDownload {
+			slog.Warn("an ad with the same name has already been downloaded, overwriting", "addir", adname)
+			return true
+		}
+
+		// don't overwrite
+		slog.Warn("an ad with the same name has already been downloaded, skipping (use -f to overwrite)", "addir", adname)
+		return false
+	}
+
+	// register
+	DirsVisited[adname] = 1
+
+	// overwrite
+	return true
+}

t/httproot/templates/render.sh

@@ -1,5 +1,7 @@
 #!/bin/sh -x
 base="../kleinanzeigen"
+
+rm -rf $base
 mkdir -p $base
 
 echo "Generating /s-bestandsliste.html"

util.go

@@ -74,3 +74,12 @@ func IsNoTty() bool {
 func GetThrottleTime() time.Duration {
 	return time.Duration(rand.Intn(MaxThrottle-MinThrottle+1)+MinThrottle) * time.Millisecond
 }
+
+// look if a key in a map exists, generic variant
+func Exists[K comparable, V any](m map[K]V, v K) bool {
+	if _, ok := m[v]; ok {
+		return true
+	}
+
+	return false
+}