我正在try 使用colly让特定的表循环其内容,但是表没有被识别,这是我到目前为止所得到的.
package main
import (
"fmt"
"github.com/gocolly/colly"
)
func main() {
c := colly.NewCollector(
colly.AllowedDomains("wikipedia.org", "en.wikipedia.org"),
)
links := make([]string, 0)
c.OnHTML("div.mw-parser-output", func(e *colly.HTMLElement) {
e.ForEach("table.wikitable.sortable.jquery-tablesorter > tbody > tr", func(_ int, elem *colly.HTMLElement) {
fmt.Println(elem.ChildAttr("a[href]", "href"))
links = append(links, elem.ChildAttr("a[href]", "href"))
})
})
c.OnRequest(func(r *colly.Request) {
fmt.Println("Visiting", r.URL.String())
})
c.Visit("https://en.wikipedia.org/wiki/List_of_countries_and_dependencies_by_population")
fmt.Println("Found urls for", len(links), "countries.")
}
我需要循环考虑表中的所有tr元素.