mirror of
https://codeberg.org/scip/kleingebaeck.git
synced 2025-12-17 20:41:01 +01:00
Compare commits
2 Commits
v0.3.11
...
fix/gocrit
| Author | SHA1 | Date | |
|---|---|---|---|
| 4602eccdf0 | |||
| 81de0d1a8f |
10
.github/dependabot.yml
vendored
10
.github/dependabot.yml
vendored
@@ -1,10 +0,0 @@
|
||||
version: 2
|
||||
updates:
|
||||
- package-ecosystem: "gomod"
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: "monthly"
|
||||
- package-ecosystem: "github-actions"
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: "monthly"
|
||||
10
.github/workflows/ci.yaml
vendored
10
.github/workflows/ci.yaml
vendored
@@ -10,13 +10,13 @@ jobs:
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- name: Set up Go
|
||||
uses: actions/setup-go@v5
|
||||
uses: actions/setup-go@v3
|
||||
with:
|
||||
go-version: ${{ matrix.version }}
|
||||
id: go
|
||||
|
||||
- name: checkout
|
||||
uses: actions/checkout@v4
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: build
|
||||
run: go build
|
||||
@@ -39,9 +39,9 @@ jobs:
|
||||
name: lint
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/setup-go@v5
|
||||
- uses: actions/setup-go@v3
|
||||
with:
|
||||
go-version: 1.21
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/checkout@v3
|
||||
- name: golangci-lint
|
||||
uses: golangci/golangci-lint-action@v6
|
||||
uses: golangci/golangci-lint-action@v3
|
||||
|
||||
6
.github/workflows/pushimage.yaml
vendored
6
.github/workflows/pushimage.yaml
vendored
@@ -15,20 +15,20 @@ jobs:
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: Log in to the Container registry
|
||||
uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567
|
||||
uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
|
||||
with:
|
||||
registry: https://ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@48aba3b46d1b1fec4febb7c5d0c644b249a11355
|
||||
uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
|
||||
with:
|
||||
push: true
|
||||
tags: ghcr.io/tlinden/kleingebaeck:${{ github.ref_name}}
|
||||
|
||||
- name: Build and push latest Docker image
|
||||
uses: docker/build-push-action@48aba3b46d1b1fec4febb7c5d0c644b249a11355
|
||||
uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
|
||||
with:
|
||||
push: true
|
||||
tags: ghcr.io/tlinden/kleingebaeck:latest
|
||||
|
||||
43
README-de.md
43
README-de.md
@@ -222,49 +222,6 @@ Sowie alle Bilder.
|
||||
Das Format kann man mit der Variable `template` in der Konfiguration
|
||||
ändern. Die `example.conf` enthält ein Beispiel für das Standard Template.
|
||||
|
||||
## Verhalten des Tools
|
||||
|
||||
Es gibt einige Dinge über das Verhalten von kleingebäck, über die Du
|
||||
Bescheid wissen solltest:
|
||||
|
||||
- alle HTML Seiten und Bilder werden immer heruntergeladen
|
||||
- es wird ein (konfigurierbarer) Useragent verwendet
|
||||
- HTTP Cookies werden beachtet
|
||||
- bei Fehlern wird dreimal mit unterschiedlichem Abstand erneut
|
||||
versucht
|
||||
- Bilder Downloads laufen parallelisiert mit leicht unterschiedlichen
|
||||
zeitlichen Abständen ab
|
||||
- Gleich aussehende Bilder werden nicht überschrieben
|
||||
|
||||
Der letzte Punkt muss genauer erläutert werden:
|
||||
|
||||
Wenn man bei Kleinanzeigen.de eine Anzeige einstellt und Bilder
|
||||
postet, werden diese dort in ihrer Grösse reduziert (durch Kompression
|
||||
und Verkleinerung der Bilder usw.). Diese reduzierten Bilder werden
|
||||
dann von kleingebäck heruntergeladen. Falls Du Deine original Bilder
|
||||
behalten hast, kannst Du diese danach in das Backupverzeichnis
|
||||
kopieren. Bei einem erneuten kleingebäck-Lauf werden diese Bilder dann
|
||||
nicht überschrieben.
|
||||
|
||||
Wir verwenden dafür einen Algorythmus namens [distance
|
||||
hashing](https://github.com/corona10/goimagehash). Dieser Algorithmus
|
||||
prüft die Ähnlichkeit von Bildern. Diese können in ihrer Auflösung,
|
||||
Kompression, Farbtiefe und vielem mehr manipuliert worden sein und
|
||||
trotzdem als das "gleiche Bild" erkannt werden (wohlgemerkt nicht "das
|
||||
selbe": die Dateien sind durchaus unterschiedlich!). Bis zu einer
|
||||
Distance von 5 überschreiben wir keine Bilder, weil wir dann davon
|
||||
ausgehen, dass das lokal Vorhandene das Original ist.
|
||||
|
||||
Bitte beachte aber, dass dies KEIN Cachingmechanismus ist: die Bilder
|
||||
werden trotzdem immer alle heruntergeladen. Das muss so sein, da wir
|
||||
uns nicht die Dateinamen anschauen können, da kleinanzeigen.de diese
|
||||
nämlich zu Zahlen umbenennt. Und die Dateinamen können sich auch
|
||||
ändern, wenn der User in der Anzeige die Bilder umarrangiert hat.
|
||||
|
||||
Du kannst dieses Verhalten mit der Option **--force** ausschalten. Du
|
||||
kannst ausserdem mit der Option **--ignoreerrors** auch alle Fehler
|
||||
ignorieren, die beim Bilderdownload auftreten könnten.
|
||||
|
||||
## Documentation
|
||||
|
||||
Die Dokumentation kann man
|
||||
|
||||
42
README.md
42
README.md
@@ -207,48 +207,6 @@ variable. The supplied sample config contains the default template.
|
||||
|
||||
All images will be stored in the same directory.
|
||||
|
||||
## Tool Behavior
|
||||
|
||||
There are a bunch of things you might want to know about the behavior
|
||||
of the kleingebäck tool:
|
||||
|
||||
- all HTML pages and IMAGEs are always being downloaded
|
||||
- we use a (customizable) user agent
|
||||
- we respect HTTP cookies
|
||||
- in the case of an error, the tool does 3 retries, the time it waits
|
||||
between tries is longer for each retry
|
||||
- image download is parallized using small time differences to look
|
||||
more natural
|
||||
- same images are not being overwritten on subsequent download
|
||||
|
||||
|
||||
The latter needs to be elaborated a bit more:
|
||||
|
||||
If you publish an ad on kleinanzeigen.de and post images, those images
|
||||
will be reduced in size by the site (by compressing and down sizing
|
||||
them). This reduced images will be downloaded by kleingebäck. However,
|
||||
you may still own the original images and may want to put them into
|
||||
that backup directory so that you have all things for one ad together.
|
||||
|
||||
You can easily do that, because kleingebäck won't overwrite those
|
||||
original images. It uses something called a distance hash using
|
||||
[goimagehash](https://github.com/corona10/goimagehash). This
|
||||
algorithmus checks the similarity of images. If an image has been
|
||||
resized it is still very similar to the original one. We accept a
|
||||
maximum of a distance of 5, everything above leads to overwrite.
|
||||
|
||||
This works with resizes, cropped and otherwise manipulated images as
|
||||
long as the image still shows the original contents good enough.
|
||||
|
||||
Also note, that this is NOT a caching mechanism: the images will be
|
||||
downloaded anyway during each run. We also can't look at the file
|
||||
names because kleinanzeigen.de renames all images to numbers. And
|
||||
those might even change if the user re-arranges the images.
|
||||
|
||||
You can override this behavior using the **--force** option. Another
|
||||
option, **--ignoreerrors**, can be used to ignore all kinds of image
|
||||
errors.
|
||||
|
||||
## Documentation
|
||||
|
||||
You can read the documentation [online](https://github.com/TLINDEN/kleingebaeck/blob/main/kleingebaeck.pod) or locally once you have installed kleingebaeck with: `kleingebaeck --manual`.
|
||||
|
||||
23
config.go
23
config.go
@@ -34,7 +34,7 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
VERSION string = "0.3.11"
|
||||
VERSION string = "0.3.5"
|
||||
Baseuri string = "https://www.kleinanzeigen.de"
|
||||
Listuri string = "/s-bestandsliste.html"
|
||||
Defaultdir string = "."
|
||||
@@ -183,22 +183,13 @@ func InitConfig(output io.Writer) (*Config, error) {
|
||||
|
||||
// Load the config file[s]
|
||||
for _, cfgfile := range configfiles {
|
||||
path, err := os.Stat(cfgfile)
|
||||
|
||||
if err != nil {
|
||||
// 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)
|
||||
if path, err := os.Stat(cfgfile); !os.IsNotExist(err) {
|
||||
if !path.IsDir() {
|
||||
if err := kloader.Load(file.Provider(cfgfile), toml.Parser()); err != nil {
|
||||
return nil, fmt.Errorf("error loading config file: %w", err)
|
||||
}
|
||||
}
|
||||
|
||||
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)
|
||||
}
|
||||
}
|
||||
} // else: we ignore the file if it doesn't exists
|
||||
}
|
||||
|
||||
// env overrides config file
|
||||
|
||||
25
go.mod
25
go.mod
@@ -4,37 +4,36 @@ go 1.21
|
||||
|
||||
require (
|
||||
astuart.co/goq v1.0.0
|
||||
github.com/corona10/goimagehash v1.1.0
|
||||
github.com/inconshreveable/mousetrap v1.1.0
|
||||
github.com/jarcoal/httpmock v1.3.1
|
||||
github.com/knadh/koanf/parsers/toml 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/file v1.1.2
|
||||
github.com/knadh/koanf/providers/env v0.1.0
|
||||
github.com/knadh/koanf/providers/file v0.1.0
|
||||
github.com/knadh/koanf/providers/posflag v0.1.0
|
||||
github.com/knadh/koanf/v2 v2.1.2
|
||||
github.com/lmittmann/tint v1.0.6
|
||||
github.com/knadh/koanf/v2 v2.0.1
|
||||
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 v0.1.3
|
||||
golang.org/x/image v0.23.0
|
||||
golang.org/x/sync v0.10.0
|
||||
github.com/tlinden/yadu v0.1.2
|
||||
golang.org/x/sync v0.5.0
|
||||
)
|
||||
|
||||
require (
|
||||
github.com/PuerkitoBio/goquery v1.5.1 // indirect
|
||||
github.com/andybalholm/cascadia v1.1.0 // indirect
|
||||
github.com/corona10/goimagehash 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/fsnotify/fsnotify v1.6.0 // indirect
|
||||
github.com/knadh/koanf/maps v0.1.1 // indirect
|
||||
github.com/mattn/go-colorable v0.1.13 // indirect
|
||||
github.com/mitchellh/copystructure v1.2.0 // indirect
|
||||
github.com/mitchellh/mapstructure v1.5.0 // 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
|
||||
github.com/pkg/errors v0.9.1 // indirect
|
||||
golang.org/x/net v0.0.0-20220722155237-a158d28d115b // indirect
|
||||
golang.org/x/sys v0.17.0 // indirect
|
||||
gopkg.in/yaml.v3 v3.0.1 // indirect
|
||||
|
||||
)
|
||||
|
||||
66
go.sum
66
go.sum
@@ -13,12 +13,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
|
||||
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
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/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
|
||||
github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
|
||||
github.com/go-viper/mapstructure/v2 v2.2.1 h1:ZAaOCxANMuZx5RCeg0mBdEZk7DZasvvZIxtHqx8aGss=
|
||||
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/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
|
||||
github.com/fsnotify/fsnotify v1.6.0 h1:n+5WquG0fcWoWp6xPWfHdbskMCQaFnG6PfBrh1Ky4HY=
|
||||
github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=
|
||||
github.com/jarcoal/httpmock v1.3.1 h1:iUx3whfZWVf3jT01hQTO/Eo5sAYtB2/rqaUuOtpInww=
|
||||
github.com/jarcoal/httpmock v1.3.1/go.mod h1:3yb8rc4BI7TCBhFY8ng0gjuLKJNquuDNiPaZjnENuYg=
|
||||
github.com/knadh/koanf/maps v0.1.1 h1:G5TjmUh2D7G2YWf5SQQqSiHRJEjaicvU0KpypqB3NIs=
|
||||
@@ -27,20 +23,16 @@ github.com/knadh/koanf/parsers/toml v0.1.0 h1:S2hLqS4TgWZYj4/7mI5m1CQQcWurxUz6OD
|
||||
github.com/knadh/koanf/parsers/toml v0.1.0/go.mod h1:yUprhq6eo3GbyVXFFMdbfZSo928ksS+uo0FFqNMnO18=
|
||||
github.com/knadh/koanf/providers/confmap v0.1.0 h1:gOkxhHkemwG4LezxxN8DMOFopOPghxRVp7JbIvdvqzU=
|
||||
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/go.mod h1:mzFyRZueYhb37oPmC1HAv/oGEEuyvJDA98r3XAa8Gak=
|
||||
github.com/knadh/koanf/providers/file v1.1.2 h1:aCC36YGOgV5lTtAFz2qkgtWdeQsgfxUkxDOe+2nQY3w=
|
||||
github.com/knadh/koanf/providers/file v1.1.2/go.mod h1:/faSBcv2mxPVjFrXck95qeoyoZ5myJ6uxN8OOVNJJCI=
|
||||
github.com/knadh/koanf/providers/env v0.1.0 h1:LqKteXqfOWyx5Ab9VfGHmjY9BvRXi+clwyZozgVRiKg=
|
||||
github.com/knadh/koanf/providers/env v0.1.0/go.mod h1:RE8K9GbACJkeEnkl8L/Qcj8p4ZyPXZIQ191HJi44ZaQ=
|
||||
github.com/knadh/koanf/providers/file v0.1.0 h1:fs6U7nrV58d3CFAFh8VTde8TM262ObYf3ODrc//Lp+c=
|
||||
github.com/knadh/koanf/providers/file v0.1.0/go.mod h1:rjJ/nHQl64iYCtAW2QQnF0eSmDEX/YZ/eNFj5yR6BvA=
|
||||
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/v2 v2.1.2 h1:I2rtLRqXRy1p01m/utEtpZSSA6dcJbgGVuE27kW2PzQ=
|
||||
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/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 v1.0.6 h1:vkkuDAZXc0EFGNzYjWcV0h7eEX+uujH48f/ifSkJWgc=
|
||||
github.com/lmittmann/tint v1.0.6/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE=
|
||||
github.com/knadh/koanf/v2 v2.0.1 h1:1dYGITt1I23x8cfx8ZnldtezdyaZtfAuRtIFOiRzK7g=
|
||||
github.com/knadh/koanf/v2 v2.0.1/go.mod h1:ZeiIlIDXTE7w1lMT6UVcNiRAS2/rCeLn/GdLNvY1Dus=
|
||||
github.com/lmittmann/tint v1.0.4 h1:LeYihpJ9hyGvE0w+K2okPTGUdVLfng1+nDNVR4vWISc=
|
||||
github.com/lmittmann/tint v1.0.4/go.mod h1:HIS3gSy7qNwGCj+5oRjAutErFBl4BzdQP6cJZ0NfMwE=
|
||||
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
|
||||
github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
|
||||
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
|
||||
@@ -50,41 +42,51 @@ github.com/maxatome/go-testdeep v1.12.0 h1:Ql7Go8Tg0C1D/uMMX59LAoYK7LffeJQ6X2T04
|
||||
github.com/maxatome/go-testdeep v1.12.0/go.mod h1:lPZc/HAcJMP92l7yI6TRz1aZN5URwUBUAfUNvrclaNM=
|
||||
github.com/mitchellh/copystructure v1.2.0 h1:vpKXTN4ewci03Vljg/q9QvCGUDttBOGBIa15WveJJGw=
|
||||
github.com/mitchellh/copystructure v1.2.0/go.mod h1:qLl+cE2AmVv+CoeAwDPye/v+N2HKCj9FbZEVFJRxO9s=
|
||||
github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
|
||||
github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
|
||||
github.com/mitchellh/reflectwalk v1.0.2 h1:G2LzWKi524PWgd3mLHV8Y5k7s6XUvT0Gef6zxSIeXaQ=
|
||||
github.com/mitchellh/reflectwalk v1.0.2/go.mod h1:mSTlrgnPZtwu0c4WaC2kGObEpuNDbx0jmZXqmk4esnw=
|
||||
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=
|
||||
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=
|
||||
github.com/pelletier/go-toml v1.9.5 h1:4yBQzkHv+7BHq2PQUZF3Mx0IYxG7LsP222s7Agd3ve8=
|
||||
github.com/pelletier/go-toml v1.9.5/go.mod h1:u1nR/EPcESfeI/szUZKdtJ0xRNbUoANCkoOuaOx1Y+c=
|
||||
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
|
||||
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
|
||||
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 v1.0.5/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=
|
||||
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
|
||||
github.com/tlinden/yadu v0.1.3 h1:5cRCUmj+l5yvlM2irtpFBIJwVV2DPEgYSaWvF19FtcY=
|
||||
github.com/tlinden/yadu v0.1.3/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
|
||||
github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
|
||||
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
|
||||
github.com/tlinden/yadu v0.0.0-20240118202225-ec3f0b7fc355 h1:EmgK+IGUz2m42bFKteLY5SYJLn/CyBrz6nkgS22K8Bk=
|
||||
github.com/tlinden/yadu v0.0.0-20240118202225-ec3f0b7fc355/go.mod h1:l3bRmHKL9zGAR6pnBHY2HRPxBecf7L74BoBgOOpTcUA=
|
||||
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/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 v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
|
||||
golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
|
||||
golang.org/x/net v0.0.0-20220722155237-a158d28d115b h1:PxfKdU9lEEDYjdIzOtC4qFWgkU2rGHdKlKowJSMN9h0=
|
||||
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
|
||||
golang.org/x/sync v0.5.0 h1:60k92dhOjHxJkrqnwsfl8KuaHbn/5dl0lUPUklKo3qE=
|
||||
golang.org/x/sync v0.5.0/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 v0.0.0-20220908164124-27713097b956/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 v0.14.0 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=
|
||||
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
|
||||
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
|
||||
58
image.go
58
image.go
@@ -20,16 +20,11 @@ package main
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"image"
|
||||
_ "image/gif"
|
||||
_ "image/jpeg"
|
||||
_ "image/png"
|
||||
"image/jpeg"
|
||||
"log/slog"
|
||||
"os"
|
||||
"path/filepath"
|
||||
|
||||
_ "golang.org/x/image/webp"
|
||||
|
||||
"github.com/corona10/goimagehash"
|
||||
)
|
||||
|
||||
@@ -40,7 +35,6 @@ type Image struct {
|
||||
Hash *goimagehash.ImageHash
|
||||
Data *bytes.Reader
|
||||
URI string
|
||||
Mime string
|
||||
}
|
||||
|
||||
// used for logging to avoid printing Data
|
||||
@@ -55,52 +49,21 @@ func (img *Image) LogValue() slog.Value {
|
||||
// holds all images of an ad
|
||||
type Cache []*goimagehash.ImageHash
|
||||
|
||||
// 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
|
||||
|
||||
func NewImage(buf *bytes.Reader, filename, uri string) *Image {
|
||||
img := &Image{
|
||||
Filename: filename,
|
||||
URI: uri,
|
||||
Data: buf,
|
||||
Mime: imgconfig,
|
||||
}
|
||||
|
||||
slog.Debug("image MIME", "mime", img.Mime)
|
||||
|
||||
return img, nil
|
||||
return img
|
||||
}
|
||||
|
||||
// Calculate diff hash of the image
|
||||
func (img *Image) CalcHash() error {
|
||||
jpgdata, format, err := image.Decode(img.Data)
|
||||
jpgdata, err := jpeg.Decode(img.Data)
|
||||
if err != nil {
|
||||
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)")
|
||||
return fmt.Errorf("failed to decode JPEG image: %w", err)
|
||||
}
|
||||
|
||||
hash1, err := goimagehash.DifferenceHash(jpgdata)
|
||||
@@ -170,19 +133,12 @@ func ReadImages(addir string, dont bool) (Cache, error) {
|
||||
|
||||
reader := bytes.NewReader(data.Bytes())
|
||||
|
||||
img, err := NewImage(reader, filename, "")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
img := NewImage(reader, filename, "")
|
||||
if err := img.CalcHash(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if img.Hash != nil {
|
||||
slog.Debug("Caching image from file system", "image", img, "hash", img.Hash.ToString())
|
||||
}
|
||||
|
||||
slog.Debug("Caching image from file system", "image", img, "hash", img.Hash.ToString())
|
||||
cache = append(cache, img.Hash)
|
||||
}
|
||||
}
|
||||
|
||||
22
main.go
22
main.go
@@ -18,16 +18,13 @@ along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"os"
|
||||
"runtime"
|
||||
"runtime/debug"
|
||||
|
||||
"github.com/inconshreveable/mousetrap"
|
||||
"github.com/lmittmann/tint"
|
||||
"github.com/tlinden/yadu"
|
||||
)
|
||||
@@ -38,25 +35,6 @@ func main() {
|
||||
os.Exit(Main(os.Stdout))
|
||||
}
|
||||
|
||||
func init() {
|
||||
// if we're running on Windows AND if the user double clicked the
|
||||
// exe file from explorer, we tell them and then wait until any
|
||||
// key has been hit, which will make the cmd window disappear and
|
||||
// thus give the user time to read it.
|
||||
if runtime.GOOS == "windows" {
|
||||
if mousetrap.StartedByExplorer() {
|
||||
fmt.Println("Do no double click kleingebaeck.exe!")
|
||||
fmt.Println("Please open a command shell and run it from there.")
|
||||
fmt.Println()
|
||||
fmt.Print("Press any key to quit: ")
|
||||
_, err := bufio.NewReader(os.Stdin).ReadString('\n')
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func Main(output io.Writer) int {
|
||||
logLevel := &slog.LevelVar{}
|
||||
opts := &tint.Options{
|
||||
|
||||
21
main_test.go
21
main_test.go
@@ -182,13 +182,13 @@ var tests = []Tests{
|
||||
{
|
||||
name: "download-all-ads",
|
||||
args: base + " -o t/out -u 1",
|
||||
expect: "Successfully downloaded 7 ads with 16 images to t/out",
|
||||
expect: "Successfully downloaded 6 ads with 12 images to t/out",
|
||||
exitcode: 0,
|
||||
},
|
||||
{
|
||||
name: "download-all-ads-using-config",
|
||||
args: "kleingebaeck -c t/fullconfig.conf",
|
||||
expect: "Successfully downloaded 7 ads with 16 images to t/out",
|
||||
expect: "Successfully downloaded 6 ads with 12 images to t/out",
|
||||
exitcode: 0,
|
||||
},
|
||||
}
|
||||
@@ -321,17 +321,6 @@ var adsrc = []AdConfig{
|
||||
Created: "Yesterday",
|
||||
Images: []string{"t/1.jpg", "t/2.jpg"},
|
||||
},
|
||||
{
|
||||
Title: "Ad with multiple img formats",
|
||||
ID: "7",
|
||||
Price: "5€",
|
||||
Category: "Klunker",
|
||||
Text: "Thing to sale",
|
||||
Slug: "seventh-ad",
|
||||
Condition: "works",
|
||||
Created: "Yesterday",
|
||||
Images: []string{"t/1.png", "t/1.gif", "t/1.webp", "t/1.jpg"},
|
||||
},
|
||||
}
|
||||
|
||||
// An Adsource is used to construct a httpmock responder for a
|
||||
@@ -374,7 +363,7 @@ func InitValidSources() []Adsource {
|
||||
|
||||
// valid ad listing page 2
|
||||
list2 := []AdConfig{
|
||||
adsrc[3], adsrc[4], adsrc[5], adsrc[6],
|
||||
adsrc[3], adsrc[4], adsrc[5],
|
||||
}
|
||||
|
||||
// valid ad listing page 3, which is empty
|
||||
@@ -470,7 +459,7 @@ func SetIntercept(ads []Adsource) {
|
||||
}
|
||||
|
||||
// we just use 2 images, put this here
|
||||
for _, image := range []string{"t/1.jpg", "t/2.jpg", "t/1.png", "t/1.gif", "t/1.webp"} {
|
||||
for _, image := range []string{"t/1.jpg", "t/2.jpg"} {
|
||||
httpmock.RegisterResponder("GET", image,
|
||||
httpmock.NewBytesResponder(200, GetImage(image)).HeaderAdd(headers))
|
||||
}
|
||||
@@ -537,7 +526,7 @@ func TestMain(t *testing.T) {
|
||||
// verify if downloaded ads match
|
||||
for _, ad := range adsrc {
|
||||
if err := VerifyAd(&ad); err != nil {
|
||||
t.Error(err.Error())
|
||||
t.Errorf(err.Error())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
12
scrape.go
12
scrape.go
@@ -170,9 +170,7 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
|
||||
|
||||
for _, imguri := range advertisement.Images {
|
||||
imguri := imguri
|
||||
|
||||
// we append the suffix later in NewImage() based on image format
|
||||
basefilename := filepath.Join(adpath, fmt.Sprintf("%d", img))
|
||||
file := filepath.Join(adpath, fmt.Sprintf("%d.jpg", img))
|
||||
|
||||
egroup.Go(func() error {
|
||||
// wait a little
|
||||
@@ -194,11 +192,7 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
|
||||
|
||||
reader := bytes.NewReader(buf.Bytes())
|
||||
|
||||
image, err := NewImage(reader, basefilename, imguri)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
image := NewImage(reader, file, imguri)
|
||||
err = image.CalcHash()
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -217,7 +211,7 @@ func ScrapeImages(fetch *Fetcher, advertisement *Ad, addir string) error {
|
||||
return fmt.Errorf("failed to seek(0) on image reader: %w", err)
|
||||
}
|
||||
|
||||
err = WriteImage(image.Filename, reader)
|
||||
err = WriteImage(file, reader)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
4
store.go
4
store.go
@@ -149,9 +149,7 @@ func ReadImage(filename string) (*bytes.Buffer, error) {
|
||||
|
||||
func fileExists(filename string) bool {
|
||||
info, err := os.Stat(filename)
|
||||
|
||||
if err != nil {
|
||||
// return false on any error
|
||||
if os.IsNotExist(err) {
|
||||
return false
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user