go - go-colly:如何在c.OnResponse中获取HTML标题，以便填充结构？

Question

如何在c.OnResponse中获取HTML.title-还是有更好的替代方法用url / title / content填充Struct

最后，我需要填充以下结构并将其发布到elasticsearch。

type WebPage struct {
    Url     string `json:"url"`
    Title   string `json:"title"`
    Content string `json:"content"`
}

    // Print the response
    c.OnResponse(func(r *colly.Response) {
        pageCount++
        log.Println(r.Headers)


        webpage := WebPage{
            Url:     r.Ctx.Get("url"), //- can be put in ctx c.OnRequest, and r.Ctx.Get("url")
            Title:   "my title", //string(r.title), // Where to get this?
            Content: string(r.Body),  //string(r.Body) - can be done in c.OnResponse
        }

        enc := json.NewEncoder(os.Stdout)
        enc.SetIndent("", "  ")
        enc.Encode(webpage) // SEND it to elasticsearch 

        log.Println(fmt.Sprintf("%d  DONE Visiting : %s", pageCount, urlVisited))

    })

我可以通过以下方法获取标题，但是Ctx不可用，因此无法将“title”值放在Ctx中。还有其他选择吗？

    c.OnHTML("title", func(e *colly.HTMLElement) {
        fmt.Println(e.Text)
        e.Ctx.Put("title", e.Text) // NOT ACCESSIBLE!
    })

日志

2020/05/07 17:42:37 7  DONE Visiting : https://www.coursera.org/learn/build-portfolio-website-html-css
{
  "url": "https://www.coursera.org/learn/build-portfolio-website-html-css",
  "title": "my page title",
  "content": "page html body bla "
}
2020/05/07 17:42:37 8  DONE Visiting : https://www.coursera.org/learn/build-portfolio-website-html-css
{
  "url": "https://www.coursera.org/browse/social-sciences",
  "title": "my page title",
  "content": "page html body bla "
}

Answer 1

我创建了该结构的全局变量，并用不同的方法填充它
不知道这是否是最好的方法。

fun  main(){
....

    webpage := WebPage{} //Is this a right way to declare a mutable struct?

    c.OnRequest(func(r *colly.Request) { // url
        webpage.Url = r.URL.String() // Is this the right way to mutate?

    })

    c.OnResponse(func(r *colly.Response) { //get body
        pageCount++
        log.Println(fmt.Sprintf("%d  DONE Visiting : %s", pageCount, webpage.Url))

    })

    c.OnHTML("head title", func(e *colly.HTMLElement) { // Title
        webpage.Title = e.Text
    })
    c.OnHTML("html body", func(e *colly.HTMLElement) { // Body / content
        webpage.Content = e.Text  // Can url title body be misrepresented in multithread scenario?
    })

    c.OnHTML("a[href]", func(e *colly.HTMLElement) { // href , callback
        link := e.Attr("href")
        e.Request.Visit(link)
    })

    c.OnError(func(r *colly.Response, err error) { // Set error handler
        log.Println("Request URL:", r.Request.URL, "failed with response:", r, "\nError:", err)
    })

    c.OnScraped(func(r *colly.Response) { // DONE
        enc := json.NewEncoder(os.Stdout)
        enc.SetIndent("", "  ")
        enc.Encode(webpage)
    })