commit 579886d6a47eaf0f86715be0c37ef89f69a7282e Author: Nicolas MASSE Date: Fri Mar 11 05:25:18 2022 +0100 initial commit diff --git a/cli/main.go b/cli/main.go new file mode 100644 index 0000000..0c3d011 --- /dev/null +++ b/cli/main.go @@ -0,0 +1,20 @@ +package main + +import ( + "fmt" + + "github.com/nmasse-itix/evdb/ficheauto" +) + +func main() { + scrapper := ficheauto.NewScrapper("https://www.fiches-auto.fr") + cars := scrapper.Scrape() + for _, car := range cars { + fmt.Println(car) + } + // scrapper := ademe.NewScrapper("https://carlabelling.ademe.fr") + // cars := scrapper.Scrape() + // for _, car := range cars { + // fmt.Println(car) + // } +} diff --git a/ficheauto/ficheauto.go b/ficheauto/ficheauto.go new file mode 100644 index 0000000..ce476c7 --- /dev/null +++ b/ficheauto/ficheauto.go @@ -0,0 +1,174 @@ +package ficheauto + +import ( + "fmt" + "regexp" + "strconv" + "strings" + + "github.com/gocolly/colly" +) + +type Car struct { + Brand string // Brand name + Model string // Model + Variant + Weight int // Weight (kg) + Layout string // Motor on front, rear wheels or both + Power int // Power (ch) + Acceleration float32 // From 0 to 100km/h (s) + MaxSpeed int // Max speed (km/h) + TrunkSpace int // Available space in the trunk (dm3) + BatteryCapacity float32 // Battery capacity (kWh) + MaxChargingPower int // Maximum charging power (kW) + RetailPrice int // Retail price (k€) +} + +func (car Car) String() string { + return fmt.Sprintf("%s %s (%d ch, %.1f kWh)", car.Brand, car.Model, car.Power, car.BatteryCapacity) +} + +type Scrapper struct { + url string + c *colly.Collector +} + +func NewScrapper(baseUrl string) *Scrapper { + scrapper := Scrapper{ + url: fmt.Sprintf("%s/articles-auto/electrique/s-852-comparatif-des-voitures-electriques.php", baseUrl), + c: colly.NewCollector(), + } + return &scrapper +} + +func (s *Scrapper) Scrape() []Car { + var cars []Car + + s.c.OnHTML("table", func(table *colly.HTMLElement) { + if table.Attr("bordercolor") != "#C0C0C0" { + return + } + table.ForEach("tbody", func(_ int, tbody *colly.HTMLElement) { + var cols []string = []string{} + tbody.ForEach("tr", func(i int, tr *colly.HTMLElement) { + var vals []string = []string{} + tr.ForEach("td", func(j int, td *colly.HTMLElement) { + val := strings.TrimSpace(td.Text) + //fmt.Println(val) + if i == 0 { + cols = append(cols, val) + } else { + vals = append(vals, val) + } + }) + if i > 0 { + data, err := slice2map(cols, vals) + if err != nil { + fmt.Println(err) + return + } + car, err := map2car(data) + if err != nil { + fmt.Println(err) + return + } + cars = append(cars, car) + } + }) + }) + }) + + s.c.Visit(s.url) + + return cars +} + +var nameRegexp, miscRegexp *regexp.Regexp + +func init() { + nameRegexp = regexp.MustCompile(`^([A-Za-z0-9]+) +(.*) +\(([0-9]+) ?kg\)`) + miscRegexp = regexp.MustCompile(`^([.0-9]+)`) +} + +func getInt(s string) (int, error) { + matches := miscRegexp.FindStringSubmatch(s) + if len(matches) != 2 { + return 0, fmt.Errorf("wrong number of matches: '%s'", s) + } + i, err := strconv.ParseInt(matches[1], 10, 32) + if err != nil { + return 0, err + } + return int(i), nil +} + +func getFloat(s string) (float32, error) { + matches := miscRegexp.FindStringSubmatch(s) + if len(matches) != 2 { + return 0, fmt.Errorf("wrong number of matches: '%s'", s) + } + f, err := strconv.ParseFloat(matches[1], 32) + if err != nil { + return 0, err + } + return float32(f), nil +} + +func map2car(data map[string]string) (Car, error) { + var car Car + matches := nameRegexp.FindStringSubmatch(data["Modèles"]) + if len(matches) != 4 { + return Car{}, fmt.Errorf("wrong number of matches: '%s'", data["Modèles"]) + } + car.Brand = strings.TrimSpace(matches[1]) + car.Model = strings.TrimSpace(matches[2]) + w, err := strconv.ParseInt(matches[3], 10, 32) + if err != nil { + return Car{}, err + } + car.Weight = int(w) + car.Layout = data["Motr."] + car.Acceleration, err = getFloat(data["0/100sec."]) + if err != nil { + fmt.Println(err) + } + car.BatteryCapacity, err = getFloat(data["Bat.kWh"]) + if err != nil { + fmt.Println(err) + } + car.MaxChargingPower, err = getInt(data["Puiss.ChargeMAX"]) + if err != nil { + fmt.Println(err) + } + car.MaxSpeed, err = getInt(data["Vmaxkm/h"]) + if err != nil { + fmt.Println(err) + } + car.Power, err = getInt(data["Puiss.ch"]) + if err != nil { + fmt.Println(err) + } + car.RetailPrice, err = getInt(data["Prix"]) + if err != nil { + fmt.Println(err) + } + car.TrunkSpace, err = getInt(data["CoffreLitres"]) + if err != nil { + fmt.Println(err) + } + //fmt.Println(data) + + return car, nil +} + +func slice2map(cols, vals []string) (map[string]string, error) { + if len(cols) != len(vals) { + return nil, fmt.Errorf("length mismatch") + } + + var ret map[string]string = make(map[string]string, len(cols)) + for i := range cols { + ret[cols[i]] = vals[i] + } + + return ret, nil +} diff --git a/go.mod b/go.mod new file mode 100644 index 0000000..8d2a03c --- /dev/null +++ b/go.mod @@ -0,0 +1,16 @@ +module github.com/nmasse-itix/evdb + +go 1.16 + +require ( + github.com/PuerkitoBio/goquery v1.8.0 // indirect + github.com/antchfx/htmlquery v1.2.4 // indirect + github.com/antchfx/xmlquery v1.3.9 // 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 v0.0.0-20220225172249-27dd8689420f // indirect + google.golang.org/appengine v1.6.7 // indirect +) diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..430a0e5 --- /dev/null +++ b/go.sum @@ -0,0 +1,57 @@ +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 v1.3.9 h1:Y+zyMdiUZ4fasTQTkDb3DflOXP7+obcYEh80SISBmnQ= +github.com/antchfx/xmlquery v1.3.9/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 v0.0.0-20220225172249-27dd8689420f h1:oA4XRj0qtSt8Yo1Zms0CUlsT3KG69V2UGQWPBxujDmc= +golang.org/x/net v0.0.0-20220225172249-27dd8689420f/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk= +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/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +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/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +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=