func (sn *SksNode) Fetch() error {
sn.Normalize()
req, err := http.NewRequest("GET", sn.uri, nil)
if err != nil {
return err
}
req.Header.Set("User-Agent", "sks_peers/0.2 (SKS mesh spidering)")
resp, err := HttpDoWithTimeout(http.DefaultClient, req, *flHttpFetchTimeout)
if err != nil {
return err
}
defer resp.Body.Close()
sn.Status = resp.Status
Log.Printf("[%s] Response status: %s", sn.Hostname, sn.Status)
sn.ServerHeader = resp.Header.Get("Server")
sn.ViaHeader = resp.Header.Get("Via")
//doc, err := ehtml.Parse(resp.Body)
buf, err := ioutil.ReadAll(resp.Body)
if err != nil {
return err
}
doc, err := htmlp.Parse(buf, htmlp.DefaultEncodingBytes, nil, htmlp.DefaultParseOption, htmlp.DefaultEncodingBytes)
if err != nil {
return err
}
sn.pageContent = doc
return nil
}
func fetchCardNames(names *[]string) {
res, err := http.Get(ravURL)
if err != nil {
fmt.Println(err)
}
response, err := ioutil.ReadAll(res.Body)
if err != nil {
fmt.Println(err)
}
res.Body.Close()
doc, err := html.Parse(response, html.DefaultEncodingBytes, nil, html.DefaultParseOption, html.DefaultEncodingBytes)
if err != nil {
fmt.Println(err)
}
html := doc.Root().FirstChild()
defer doc.Free()
results, err := html.Search("//tr[@class='cardItem']")
for _, row := range results {
name, err := row.Search("./td[@class='name']")
if err != nil {
fmt.Println(err)
continue
}
stringName := name[0].Content()
*names = append(*names, stringName)
}
if err != nil {
fmt.Println(err)
}
return
}
/*
ParseHtml parses an UTF-8 encoded byte array and returns an html.HtmlDocument. It uses parsing default options that ignore
errors or warnings, making it suitable for the poorly-formed 'tag soup' often found on the web.
If the content is not UTF-8 encoded or you want to customize the parsing options, you should call html.Parse directly.
*/
func ParseHtml(content []byte) (doc *html.HtmlDocument, err error) {
return html.Parse(content, html.DefaultEncodingBytes, nil, html.DefaultParseOption, html.DefaultEncodingBytes)
}
func TiendaInglesa(url string) (data ProductData, err error) {
// Find productId
urlObj, err := net_url.Parse(url)
if err != nil {
err = &ScrapeError{INVALID_PRODUCT_URL, "Invalid url. Could not parse."}
return
}
productIdList, present := urlObj.Query()["idarticulo"]
if !present || len(productIdList) != 1 {
err = &ScrapeError{INVALID_PRODUCT_URL, "Invalid url. Could not find idarticulo param."}
return
}
productId, err := strconv.Atoi(productIdList[0])
if err != nil {
err = &ScrapeError{INVALID_PRODUCT_URL, "Invalid url. idarticulo param is not integer."}
return
}
imgChan := make(chan string, 1)
go getImage(productId, imgChan)
resp, err := http.Get(url)
if err != nil {
log.Printf("Error getting site. ", err)
return
}
if finalUrl := resp.Request.URL.String(); strings.Contains(finalUrl, "articulo_no_habilitado") {
err = &ScrapeError{INVALID_PRODUCT_URL, "Product not found"}
return
}
if resp.StatusCode != http.StatusOK {
errorCode := int(resp.StatusCode/100) * 100
err = &ScrapeError{errorCode, "Request error. Invalid StatusCode"}
return
}
body, _ := ioutil.ReadAll(resp.Body)
doc, err := html.Parse(body, []byte("iso-8859-1"), nil, html.DefaultParseOption, html.DefaultEncodingBytes)
defer doc.Free()
if err != nil {
err = &ScrapeError{PARSING_ERROR, "Parsing error."}
return
}
// Find Title
results, err := doc.Search("//h1[@class='titulo_producto_top']")
if err != nil {
err = &ScrapeError{PARSING_ERROR, "Parsing error. No H1."}
return
}
if len(results) == 0 {
err = &ScrapeError{PARSING_ERROR, "Parsing error. No product title."}
return
}
name := strings.TrimSpace(results[0].Content())
// Find Price
results, err = doc.Search("//div[@class='contendor_precio']//td[@class='precio']")
if len(results) == 0 {
err = &ScrapeError{PARSING_ERROR, "Parsing error. No Price"}
return
}
priceStr := results[0].Content()
priceSplitList := strings.Fields(priceStr)
price, err := strconv.ParseFloat(priceSplitList[len(priceSplitList)-1], 64)
if err != nil {
log.Printf("Error parsing price")
return
}
// Find description
results, err = doc.Search("//div[@class='contenido_descripcion']")
var description string
if err == nil && len(results) > 0 {
description = strings.TrimSpace(results[0].Content())
}
// Find categories
results, err = doc.Search("//div[@class='navegacion']/a")
var categories []string
if err == nil && len(results) > 1 {
// Remove "Home" category.
results = results[1:]
categories = make([]string, len(results))
for i := range results {
categories[i] = strings.TrimSpace(results[i].Content())
}
}
//Image Url
imageUrl := <-imgChan
data = ProductData{
Name: name,
Url: url,
Price: price,
Description: description,
Categories: categories,
Fetched: time.Now().UTC().Format("2006-01-02T15:04Z"),
ImageUrl: imageUrl,
}
return
}
