blob: e8090b08b6a209479a25518449800eea0dba63cf (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
package main
import (
"fmt"
"log"
"strings"
"github.com/PuerkitoBio/goquery"
"github.com/gocolly/colly"
)
func ScrapeWhic() {
c := colly.NewCollector(
colly.AllowedDomains("whic.de"),
)
c.OnHTML("li.item", func(e *colly.HTMLElement) {
whisky_name := e.ChildAttr("a", "title")
whisky_url := e.ChildAttr("a", "href")
log.Println(whisky_name)
log.Println(whisky_url)
e.ForEach(".price-box", func(i int, e *colly.HTMLElement) {
e.ForEach(".old-price", func(i int, e *colly.HTMLElement) {
log.Println(e.ChildText(".price"))
})
e.ForEach(".special-price", func(i int, e *colly.HTMLElement) {
log.Println(e.ChildText(".price"))
})
})
/*
* colly does not parse a <noscript>, thus we are reading the content and parse it as html.
*/
img_link_noisy := e.ChildText(".product-image")
doc, err := goquery.NewDocumentFromReader(strings.NewReader(img_link_noisy))
if err != nil {
log.Fatal(err)
}
log.Println(doc.Find("img").Attr("src"))
fmt.Println("")
})
c.Visit("https://whic.de/angebote")
}
func main() {
ScrapeWhic()
}
|
