feat: proof of concept

This commit is contained in:
Felipe M 2022-01-02 23:11:00 +01:00
parent eca5e16955
commit fe33dd5360
Signed by: fmartingr
GPG Key ID: 716BC147715E716F
7 changed files with 250 additions and 0 deletions

50
cmd/server/main.go Normal file
View File

@ -0,0 +1,50 @@
package main
import (
"encoding/json"
"fmt"
"log"
"net/http"
"net/url"
"github.com/fmartingr/bazaar/pkg/manager"
"github.com/fmartingr/bazaar/pkg/shop/akira"
)
func main() {
m := manager.NewManager()
m.Register(akira.Domains, akira.NewAkiraShopFactory())
http.HandleFunc("/item", func(rw http.ResponseWriter, r *http.Request) {
if err := r.ParseForm(); err != nil {
fmt.Fprintf(rw, "ParseForm() err: %v", err)
return
}
itemUrl, err := url.Parse(r.PostForm.Get("url"))
if err != nil {
rw.WriteHeader(400)
return
}
shop := m.Get(itemUrl.Host)
if shop == nil {
rw.WriteHeader(400)
return
}
product, err := shop.Get(itemUrl.String())
if err != nil {
rw.WriteHeader(500)
return
}
payload, _ := json.Marshal(product)
rw.Header().Add("Content-Type", "application/json")
rw.Write(payload)
})
if err := http.ListenAndServe(":5001", http.DefaultServeMux); err != nil {
log.Printf("Error: %s", err)
}
}

16
go.mod Normal file
View File

@ -0,0 +1,16 @@
module github.com/fmartingr/bazaar
go 1.16
require (
github.com/PuerkitoBio/goquery v1.8.0 // indirect
github.com/antchfx/htmlquery v1.2.4 // indirect
github.com/antchfx/xmlquery v1.3.8 // indirect
github.com/gobwas/glob v0.2.3 // indirect
github.com/gocolly/colly v1.2.0
github.com/kennygrant/sanitize v1.2.4 // indirect
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
github.com/temoto/robotstxt v1.1.2 // indirect
golang.org/x/net v0.0.0-20211208012354-db4efeb81f4b // indirect
google.golang.org/appengine v1.6.7 // indirect
)

53
go.sum Normal file
View File

@ -0,0 +1,53 @@
github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0gta/U=
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/antchfx/htmlquery v1.2.4 h1:qLteofCMe/KGovBI6SQgmou2QNyedFUW+pE+BpeZ494=
github.com/antchfx/htmlquery v1.2.4/go.mod h1:2xO6iu3EVWs7R2JYqBbp8YzG50gj/ofqs5/0VZoDZLc=
github.com/antchfx/xmlquery v1.3.8 h1:dRnBQM3Vk5BVJFvFwsHOLAox+mEiNw5ZusaUNCrEdoU=
github.com/antchfx/xmlquery v1.3.8/go.mod h1:wojC/BxjEkjJt6dPiAqUzoXO5nIMWtxHS8PD8TmN4ks=
github.com/antchfx/xpath v1.2.0 h1:mbwv7co+x0RwgeGAOHdrKy89GvHaGvxxBtPK0uF9Zr8=
github.com/antchfx/xpath v1.2.0/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI=
github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e h1:1r7pUrabqp18hOBcwBwiTsbnFeTZHV9eER/QT5JVZxY=
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/protobuf v1.3.1 h1:YF8+flBXS5eO826T4nzqPrxfhQThhXl0YzfuUPu4SBg=
github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
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/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca h1:NugYot0LIVPxTvN8n+Kvkn6TrbMyxQiuvKdEwFdR9vI=
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0Q=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg=
github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
golang.org/x/net v0.0.0-20200421231249-e086a090c8fd/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
golang.org/x/net v0.0.0-20200813134508-3edf25e44fcc/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.0.0-20211208012354-db4efeb81f4b h1:MWaHNqZy3KTpuTMAGvv+Kw+ylsEpmyJZizz1dqxnu28=
golang.org/x/net v0.0.0-20211208012354-db4efeb81f4b/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
golang.org/x/text v0.3.6 h1:aRYxNxv6iGQlyVaZmk6ZgYEDa+Jg18DxebPSrd6bg1M=
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=
google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c=
google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=

47
pkg/manager/main.go Normal file
View File

@ -0,0 +1,47 @@
package manager
import (
"fmt"
"github.com/fmartingr/bazaar/pkg/models"
"github.com/gocolly/colly"
)
type Manager struct {
domains map[string]models.Shop
collectorOptions []func(*colly.Collector)
}
func (m *Manager) Register(domains []string, shopFactory models.ShopFactory) error {
options := m.collectorOptions
options = append(options, colly.AllowedDomains(domains...))
shop := shopFactory(options)
for _, domain := range domains {
if _, exists := m.domains[domain]; exists {
return fmt.Errorf("domain %s is already registered", domain)
} else {
m.domains[domain] = shop
}
}
return nil
}
func (m *Manager) Get(host string) models.Shop {
shop, exists := m.domains[host]
if !exists {
return nil
}
return shop
}
func NewManager() Manager {
return Manager{
collectorOptions: []func(*colly.Collector){
colly.UserAgent("bazaar/0.0.1"),
},
domains: make(map[string]models.Shop),
}
}

9
pkg/models/product.go Normal file
View File

@ -0,0 +1,9 @@
package models
type Product struct {
Name string `json:"name"`
URL string `json:"url"`
InStock bool `json:"in_stock"`
PriceText string `json:"price_text"`
Price float64 `json:"price"`
}

9
pkg/models/shop.go Normal file
View File

@ -0,0 +1,9 @@
package models
import "github.com/gocolly/colly"
type ShopFactory func(collectorOptions []func(*colly.Collector)) Shop
type Shop interface {
Get(url string) (*Product, error)
}

66
pkg/shop/akira/akira.go Normal file
View File

@ -0,0 +1,66 @@
package akira
import (
"fmt"
"strconv"
"strings"
"sync"
"github.com/fmartingr/bazaar/pkg/models"
"github.com/gocolly/colly"
)
var Domains = []string{"www.akiracomics.com", "akiracomics.com"}
type AkiraShop struct {
collector *colly.Collector
domains []string
items map[string]*models.Product
itemsMu sync.RWMutex
}
func (s *AkiraShop) init() {
s.collector.OnRequest(func(r *colly.Request) {
fmt.Println("Visiting", r.URL.String())
})
s.collector.OnHTML(`div.panel-ficha-producto div.panel-grupo`, func(h *colly.HTMLElement) {
priceText := h.ChildText(`[itemprop="price"]`)
priceNum, err := strconv.ParseFloat(strings.ReplaceAll(strings.Split(priceText, " ")[0], ",", "."), 64)
if err != nil {
fmt.Println(err)
}
s.itemsMu.Lock()
s.items[h.Request.URL.String()] = &models.Product{
Name: h.ChildText("h1.titulo"),
InStock: h.ChildText("span.disponibilidad") == "Disponible",
URL: h.Request.URL.String(),
PriceText: priceText,
Price: priceNum,
}
s.itemsMu.Unlock()
})
}
func (s *AkiraShop) Get(url string) (*models.Product, error) {
if err := s.collector.Visit(url); err != nil {
return nil, fmt.Errorf("error getting product information: %s", err)
}
s.itemsMu.RLock()
defer s.itemsMu.RUnlock()
return s.items[url], nil
}
func NewAkiraShopFactory() models.ShopFactory {
return func(collectorOptions []func(*colly.Collector)) models.Shop {
shop := AkiraShop{
collector: colly.NewCollector(collectorOptions...),
domains: Domains,
items: make(map[string]*models.Product),
itemsMu: sync.RWMutex{},
}
shop.init()
return &shop
}
}