test: added basic testing to casadellibro

* added composition for shops, which now require a ShopOptions with a client
* added a mock client that returns data from a file in order to test
  the scrapper
* updated all shops
This commit is contained in:
Felipe Martin Garcia 2022-08-06 10:12:45 +02:00
parent 9ac3f2ff2d
commit d55c36c0e2
Signed by: fmartingr
GPG Key ID: 716BC147715E716F
16 changed files with 395 additions and 21 deletions

4
go.mod
View File

@ -5,9 +5,13 @@ go 1.18
require (
github.com/PuerkitoBio/goquery v1.8.0
github.com/goodsign/monday v1.0.0
github.com/stretchr/testify v1.8.0
)
require (
github.com/andybalholm/cascadia v1.3.1 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
golang.org/x/net v0.0.0-20220805013720-a33c5aa5df48 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
)

15
go.sum
View File

@ -2,8 +2,18 @@ github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0g
github.com/PuerkitoBio/goquery v1.8.0/go.mod h1:ypIiRMtY7COPGk+I/YbZLbxsxn9g5ejnI2HSMtkjZvI=
github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
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/goodsign/monday v1.0.0 h1:Yyk/s/WgudMbAJN6UWSU5xAs8jtNewfqtVblAlw0yoc=
github.com/goodsign/monday v1.0.0/go.mod h1:r4T4breXpoFwspQNM+u2sLxJb2zyTaxVGqUfTBjWOu8=
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/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0 h1:pSgiaMZlXftHpm5L7V1+rVB+AZJydKsMxsQBIJw4PKk=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.0.0-20220805013720-a33c5aa5df48 h1:N9Vc/rorQUDes6B9CNdIxAn5jODGj2wzfrei2x4wNj4=
golang.org/x/net v0.0.0-20220805013720-a33c5aa5df48/go.mod h1:YDH+HFinaLZZlnHAfSS6ZXJJ9M9t4Dl22yv3iI2vPwk=
@ -12,3 +22,8 @@ golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7w
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
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/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

7
pkg/clients/clients.go Normal file
View File

@ -0,0 +1,7 @@
package clients
import "io"
type Client interface {
Get(url string) (io.Reader, error)
}

30
pkg/clients/http.go Normal file
View File

@ -0,0 +1,30 @@
package clients
import (
"fmt"
"io"
"net/http"
)
type HttpClient struct {
http http.Client
}
func (c HttpClient) Get(url string) (io.Reader, error) {
res, err := c.http.Get(url)
if err != nil {
return nil, fmt.Errorf("error retrieving url: %s", err)
}
if res.StatusCode != 200 {
return nil, fmt.Errorf("error retrieving url: %d %s", res.StatusCode, res.Status)
}
return res.Body, nil
}
func NewBasicHttpClient() HttpClient {
return HttpClient{
http: http.Client{},
}
}

29
pkg/clients/mock.go Normal file
View File

@ -0,0 +1,29 @@
package clients
import (
"fmt"
"io"
"net/url"
"github.com/fmartingr/bazaar/pkg/clients/mockdata"
)
type MockClient struct{}
func (c MockClient) Get(urlString string) (io.Reader, error) {
parsedUrl, err := url.Parse(urlString)
if err != nil {
return nil, fmt.Errorf("error parsing url: %s", urlString)
}
f, err := mockdata.Data.Open(parsedUrl.Host + ".html")
if err != nil {
return nil, fmt.Errorf("can't open mock data for %s", parsedUrl.Host)
}
return f, nil
}
func NewMockClient() MockClient {
return MockClient{}
}

View File

@ -0,0 +1,6 @@
package mockdata
import "embed"
//go:embed *.html
var Data embed.FS

File diff suppressed because one or more lines are too long

View File

@ -4,6 +4,7 @@ import (
"fmt"
"net/url"
"github.com/fmartingr/bazaar/pkg/clients"
"github.com/fmartingr/bazaar/pkg/models"
)
@ -14,7 +15,8 @@ type Manager struct {
}
func (m *Manager) Register(domains []string, shopFactory models.ShopFactory) error {
shop := shopFactory()
baseShop := models.NewShopOptions(clients.NewBasicHttpClient())
shop := shopFactory(baseShop)
for _, domain := range domains {
if _, exists := m.domains[domain]; exists {

View File

@ -1,7 +1,19 @@
package models
type ShopFactory func() Shop
import "github.com/fmartingr/bazaar/pkg/clients"
type ShopFactory func(baseShop ShopOptions) Shop
type Shop interface {
Get(url string) (*Product, error)
}
type ShopOptions struct {
Client clients.Client
}
func NewShopOptions(client clients.Client) ShopOptions {
return ShopOptions{
Client: client,
}
}

View File

@ -14,6 +14,7 @@ import (
var Domains = []string{"www.akiracomics.com", "akiracomics.com"}
type AkiraShop struct {
models.ShopOptions
domains []string
}
@ -63,9 +64,10 @@ func (s *AkiraShop) Get(url string) (*models.Product, error) {
}
func NewAkiraShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
shop := AkiraShop{
domains: Domains,
ShopOptions: shopOptions,
domains: Domains,
}
return &shop
}

View File

@ -17,6 +17,7 @@ import (
var Domains = []string{"www.amazon.es", "www.amazon.com"}
type AmazonShop struct {
models.ShopOptions
domains []string
}
@ -97,9 +98,10 @@ func (s *AmazonShop) Get(url string) (*models.Product, error) {
}
func NewAmazonShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
shop := AmazonShop{
domains: Domains,
ShopOptions: shopOptions,
domains: Domains,
}
return &shop
}

View File

@ -3,7 +3,6 @@ package casadellibro
import (
"fmt"
"log"
"net/http"
"regexp"
"strconv"
"strings"
@ -21,21 +20,19 @@ const (
var Domains = []string{"www.casadellibro.com"}
type CasaDelLibroShop struct {
models.ShopOptions
domains []string
priceRegexp *regexp.Regexp
}
func (s *CasaDelLibroShop) Get(url string) (*models.Product, error) {
res, err := http.Get(url)
body, err := s.ShopOptions.Client.Get(url)
if err != nil {
return nil, fmt.Errorf("error retrieving url: %s", err)
return nil, fmt.Errorf("error during request: %s", err)
}
if res.StatusCode != 200 {
return nil, fmt.Errorf("error retrieving url: %d %s", res.StatusCode, res.Status)
}
doc, err := goquery.NewDocumentFromReader(res.Body)
doc, err := goquery.NewDocumentFromReader(body)
if err != nil {
return nil, fmt.Errorf("error parsing body: %s", err)
}
@ -88,13 +85,14 @@ func (s *CasaDelLibroShop) Get(url string) (*models.Product, error) {
}
func NewCasaDelLibroShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
r, err := regexp.Compile(`Price\"\:\"([\d+\.]+)`)
if err != nil {
log.Println(err)
}
shop := CasaDelLibroShop{
ShopOptions: shopOptions,
domains: Domains,
priceRegexp: r,
}

View File

@ -0,0 +1,31 @@
package casadellibro_test
import (
"testing"
"time"
"github.com/fmartingr/bazaar/pkg/clients"
"github.com/fmartingr/bazaar/pkg/models"
"github.com/fmartingr/bazaar/pkg/shop/casadellibro"
"github.com/stretchr/testify/assert"
)
func TestCasaDelLibro_Ok(t *testing.T) {
shop := casadellibro.NewCasaDelLibroShopFactory()(models.NewShopOptions(clients.NewMockClient()))
testUrl := "https://www.casadellibro.com/test/"
product, err := shop.Get(testUrl)
if err != nil {
t.Error(err)
return
}
assert.Greater(t, len(product.Description), 100)
assert.Equal(t, product.Name, "LA DEPENDIENTA")
assert.Equal(t, product.ImageURL, "https://imagessl0.casadellibro.com/a/l/t5/20/9788416634620.jpg")
assert.Equal(t, product.Price, 15.96)
assert.Equal(t, product.PriceText, "15.96")
assert.Equal(t, product.ReleaseDate.Format(time.RFC3339), "2019-01-01T00:00:00Z")
assert.Equal(t, product.URL, testUrl)
}

View File

@ -15,6 +15,7 @@ import (
var Domains = []string{"www.gtm-store.com"}
type GTMStoreShop struct {
models.ShopOptions
domains []string
}
@ -62,9 +63,10 @@ func (s *GTMStoreShop) Get(url string) (*models.Product, error) {
}
func NewGTMStoreShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
shop := GTMStoreShop{
domains: Domains,
ShopOptions: shopOptions,
domains: Domains,
}
return &shop
}

View File

@ -13,6 +13,7 @@ import (
var Domains = []string{"www.heroesdepapel.es"}
type HeroesDePapelShop struct {
models.ShopOptions
domains []string
}
@ -60,9 +61,10 @@ func (s *HeroesDePapelShop) Get(url string) (*models.Product, error) {
}
func NewHeroesDePapelShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
shop := HeroesDePapelShop{
domains: Domains,
ShopOptions: shopOptions,
domains: Domains,
}
return &shop
}

View File

@ -14,6 +14,7 @@ import (
var Domains = []string{"store.steampowered.com"}
type SteamShop struct {
models.ShopOptions
domains []string
}
@ -60,9 +61,10 @@ func (s *SteamShop) Get(url string) (*models.Product, error) {
}
func NewSteamShopFactory() models.ShopFactory {
return func() models.Shop {
return func(shopOptions models.ShopOptions) models.Shop {
shop := SteamShop{
domains: Domains,
ShopOptions: shopOptions,
domains: Domains,
}
return &shop
}