[Go] goquery 教學

程式語言：Go
Package：goquery
官方文件
官方 GitHub

功能：jquery-like 分析 html
jQuery Selectors
必需自行處理成 UTF-8 編碼，才丟進 goquery 處理
  1. package main
  2.  
  3. import (
  4.     "bytes"
  5.     "fmt"
  6.     "io/ioutil"
  7.     "log"
  8.     "net/http"
  9.  
  10.     "github.com/PuerkitoBio/goquery"
  11.     "golang.org/x/text/encoding/traditionalchinese"
  12.     "golang.org/x/text/transform"
  13. )
  14.  
  15. func main() {
  16.     // Request the HTML page.
  17.     res, err := http.Get("https://www.google.com.tw/")
  18.     if err != nil {
  19.         log.Fatal(err)
  20.     }
  21.     defer res.Body.Close()
  22.  
  23.     if res.StatusCode != 200 {
  24.         log.Fatalf("status code error: %d %s", res.StatusCode, res.Status)
  25.     }
  26.  
  27.     b, err := ioutil.ReadAll(res.Body)
  28.     // goquery 限定需為 UTF-8
  29.     b, _ = DecodeBig5(b)
  30.     r := bytes.NewReader(b)
  31.     // Load the HTML document
  32.     dom, err := goquery.NewDocumentFromReader(r)
  33.     if err != nil {
  34.         log.Fatal(err)
  35.     }
  36.  
  37.     data := make(map[string]string)
  38.     // Find the link items
  39.     dom.Find("a").Each(func(i int, s *goquery.Selection) {
  40.         // For each item found, get the band and title
  41.         title := s.Text()
  42.         url, _ := s.Attr("href")
  43.         data[title] = url
  44.     })
  45.  
  46.     fmt.Printf("%+v", data)
  47. }
  48.  
  49. //convert BIG5 to UTF-8
  50. func DecodeBig5(s []byte) ([]byte, error) {
  51.     I := bytes.NewReader(s)
  52.     O := transform.NewReader(I, traditionalchinese.Big5.NewDecoder())
  53.     b, err := ioutil.ReadAll(O)
  54.     if err != nil {
  55.         return nil, err
  56.     }
  57.     return b, nil
  58. }
  59.  
  60. //convert UTF-8 to BIG5
  61. func EncodeBig5(s []byte) ([]byte, error) {
  62.     I := bytes.NewReader(s)
  63.     O := transform.NewReader(I, traditionalchinese.Big5.NewEncoder())
  64.     b, err := ioutil.ReadAll(O)
  65.     if err != nil {
  66.         return nil, err
  67.     }
  68.     return b, nil
  69. }
  1. package main
  2.  
  3. import (
  4.     "bufio"
  5.     "fmt"
  6.     "io"
  7.     "log"
  8.     "net/http"
  9.  
  10.     "github.com/PuerkitoBio/goquery"
  11.     "github.com/pkg/errors"
  12.     "golang.org/x/net/html/charset"
  13.     "golang.org/x/text/encoding"
  14.     "golang.org/x/text/transform"
  15. )
  16.  
  17. func main() {
  18.     // Request the HTML page.
  19.     resp, err := http.Get("http://www.zhenai.com/zhenghun")
  20.     if err != nil {
  21.         panic(err)
  22.     }
  23.     defer resp.Body.Close()
  24.  
  25.     if resp.StatusCode != 200 {
  26.         log.Fatalf("status code error: %d %s", resp.StatusCode, resp.Status)
  27.     }
  28.  
  29.     // 自動判斷編碼，轉為 UTF-8，需注意有時會判斷錯誤
  30.     e, _, _, _ := DetermineEncodingFromReader(resp.Body)
  31.     utf8Reader := transform.NewReader(resp.Body, e.NewDecoder())
  32.  
  33.     // Load the HTML document
  34.     dom, err := goquery.NewDocumentFromReader(utf8Reader)
  35.     if err != nil {
  36.         log.Fatal(err)
  37.     }
  38.  
  39.     data := make(map[string]string)
  40.     // Find the link items
  41.     dom.Find("a").Each(func(i int, s *goquery.Selection) {
  42.         // For each item found, get the band and title
  43.         title := s.Text()
  44.         url, _ := s.Attr("href")
  45.         data[title] = url
  46.     })
  47.  
  48.     fmt.Printf("%+v", data)
  49. }
  50.  
  51. // DetermineEncodingFromReader 偵測 reader 的編碼
  52. func DetermineEncodingFromReader(r io.Reader) (encoding.Encoding, string, bool, error) {
  53.     b, err := bufio.NewReader(r).Peek(1024)
  54.     if err != nil {
  55.         fmt.Printf("r: %s : %s", r, err)
  56.         err = errors.Wrap(err, "bufio.NewReader")
  57.         return nil, "", false, err
  58.     }
  59.  
  60.     e, name, certain := charset.DetermineEncoding(b, "")
  61.     return e, name, certain, nil
  62. }

讀取網頁

  1. package main
  2.  
  3. import (
  4.     "fmt"
  5.     "log"
  6.     "strings"
  7.  
  8.     "github.com/PuerkitoBio/goquery"
  9. )
  10.  
  11. func main() {
  12.     html := ""
  13.  
  14.     // Load the HTML document
  15.     dom, err := goquery.NewDocumentFromReader(strings.NewReader(html))
  16.     if err != nil {
  17.         log.Fatal(err)
  18.     }
  19.  
  20.     str, _ := dom.Html()
  21.  
  22.     fmt.Printf("%s", str)
  23. }

使用範例

html 如下
html := `
<html>
<head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
    <p class="story">Once upon a time there were three little sisters; and their names were
    <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
    <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
    <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
    and they lived at the bottom of a well.
</p>
<p class="story">...</p>`

// Load the HTML document
dom, err := goquery.NewDocumentFromReader(strings.NewReader(html))
if err != nil {
    log.Fatal(err)
}

var sel *goquery.Selection

訪問方法

幾乎等同 jQuery，可參考 [jQuery] 基本架構
可將 dom 視為 $，可理解到 goquery & jQuery 差異極小
  1. sel = dom.Find("a")
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  4. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  5. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  6.  
  7. sel = dom.Find("a.sister#link1")
  8. prettyPrint(sel.Nodes)
  9. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]

搜尋方法

  1. sel = dom.Find("p").Children()
  2. prettyPrint(sel.Nodes)
  3. // "b" []
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  5. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  6. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  7.  
  8. sel = dom.Find("p").ChildrenFiltered("#link1")
  9. prettyPrint(sel.Nodes)
  10. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  1. sel = dom.Find("p.title").Siblings()
  2. prettyPrint(sel.Nodes)
  3. // "p" [{ class story}]
  4. // "p" [{ class story}]
  5.  
  6. sel = dom.Find("a#link2").Siblings()
  7. prettyPrint(sel.Nodes)
  8. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  9. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  10.  
  11. sel = dom.Find("a#link2").SiblingsFiltered("#link1")
  12. prettyPrint(sel.Nodes)
  13. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  1. // 除 children 外，包含 text nodes
  2. sel = dom.Find("body").Contents()
  3. prettyPrint(sel.Nodes)
  4. // "\n    " []
  5. // "p" [{ class title}]
  6. // "\n        " []
  7. // "p" [{ class story}]
  8. // "\n    " []
  9. // "p" [{ class story}]
  1. // 含自己往上找，找到最接近的 parents
  2. sel = dom.Find("a").Closest("a")
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  5. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  6. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  7.  
  8. sel = dom.Find("a").Closest("p")
  9. prettyPrint(sel.Nodes)
  10. // "p" [{ class story}]
  1. // 找到其 parent，只往上查找一層，會自動移除重覆的
  2. sel = dom.Find("a").Parent()
  3. prettyPrint(sel.Nodes)
  4. // "p" [{ class story}]
  5.  
  6. sel = dom.Find("a").ParentFiltered("body")
  7. prettyPrint(sel.Nodes)
  8. // None
  1. // 找到其 parents，往上查找不停止，找出所有符合條件的，會自動移除重覆的
  2. sel = dom.Find("a").Parents()
  3. prettyPrint(sel.Nodes)
  4. // "p" [{ class story}]
  5. // "body" []
  6. // "html" []
  7.  
  8. sel = dom.Find("a").ParentsFiltered("body")
  9. prettyPrint(sel.Nodes)
  10. // "body" []
  1. // 選擇第一個
  2. sel = dom.Find("a").Eq(0)
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  1. // 可為 string 也可以是 function
  2. sel = dom.Find("p").Filter(".story")
  3. prettyPrint(sel.Nodes)
  4. // "p" [{ class story}]
  5. // "p" [{ class story}]
  6.  
  7. sel = dom.Find("p").FilterFunction(func(i int, s *goquery.Selection) bool { return s.Text() == "..." })
  8. prettyPrint(sel.Nodes)
  9. // "p" [{ class story}]
  1. sel = dom.Find("a").Not("#link1")
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  4. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  1. sel = dom.Find("a#link2").Next()
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  4.  
  5. sel = dom.Find("a#link2").NextFiltered("a")
  6. prettyPrint(sel.Nodes)
  7. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  1. sel = dom.Find("a#link2").Prev()
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  4.  
  5. sel = dom.Find("a#link2").PrevFiltered("a")
  6. prettyPrint(sel.Nodes)
  7. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  1. sel = dom.Find("a#link1").NextAll()
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  4. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  5.  
  6. sel = dom.Find("a#link1").NextAllFiltered("#link3")
  7. prettyPrint(sel.Nodes)
  8. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  1. sel = dom.Find("a#link3").PrevAll()
  2. prettyPrint(sel.Nodes)
  3. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  5.  
  6. sel = dom.Find("a#link3").PrevAllFiltered("#link1")
  7. prettyPrint(sel.Nodes)
  8. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  9.  
  1. // 回傳上一個 filter 結果
  2. sel = dom.Find("a").Parent().End() // 等同 sel = dom.Find("a")
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  5. // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  6. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]

Attributes

  1. // 會以第一個 a 為主
  2. sel = dom.Find("a")
  3. fmt.Println(sel.Attr("id"))
  4. // link1 true
  5. fmt.Println(sel.AttrOr("noid", "nil"))
  6. // nil
  7.  
  8. sel = dom.Find("a")
  9. fmt.Println(sel.Attr("class"))
  10. // sister true
  11. fmt.Println(sel.AttrOr("noclass", "nil"))
  12. // nil
  1. // 只要任何 elements 有就是 True
  2. sel = dom.Find("p")
  3. fmt.Println(sel.HasClass("story"))
  4. // true
  1. // 回傳所有元件的 text
  2. sel = dom.Find("title")
  3. fmt.Println(sel.Text())
  4. // The Dormouse's story

Properties

  1. // 兩者意義一樣
  2. sel = dom.Find("a")
  3. fmt.Println(sel.Length())
  4. // 3
  5. fmt.Println(sel.Size())
  6. // 3

網頁內容

  1. sel = dom.Find("head")
  2. fmt.Println(sel.Html())
  3. //<title>The Dormouse&#39;s story</title> <nil>
  1. sel = dom.Find("head")
  2. fmt.Println(goquery.OuterHtml(sel))
  3. // <head><title>The Dormouse&#39;s story</title></head> <nil>

更改方法

  1. // # 複製原本的內容並回傳，可用在不想被更改的元件上
  2. var domCopy *goquery.Selection
  3. domCopy = dom.Find(".title").Clone()
  1. // # 會將原本的 class 替換掉
  2. domCopy = dom.Clone()
  3. sel = domCopy.Find("a").SetAttr("class", "classA")
  4. prettyPrint(sel.Nodes)
  5. // "a" [{ href http://example.com/elsie} { class classA} { id link1}]
  6. // "a" [{ href http://example.com/lacie} { class classA} { id link2}]
  7. // "a" [{ href http://example.com/tillie} { class classA} { id link3}]
  8. domCopy = dom.Clone()
  9. sel = domCopy.Find("a#link2").SetAttr("id", "link4")
  10. prettyPrint(domCopy.Find("a").Nodes)
  11. // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  12. // "a" [{ href http://example.com/lacie} { class sister} { id link4}]
  13. // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  1. // # 保留原本的 class
  2. domCopy = dom.Clone()
  3. sel = domCopy.Find("a").AddClass("classB")
  4. prettyPrint(sel.Nodes)
  5. // "a" [{ href http://example.com/elsie} { class sister  classB} { id link1}]
  6. // "a" [{ href http://example.com/lacie} { class sister  classB} { id link2}]
  7. // "a" [{ href http://example.com/tillie} { class sister  classB} { id link3}]
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("p").RemoveClass("story")
  3. prettyPrint(sel.Nodes)
  4. // "p" [{ class title}]
  5. // "p" []
  6. // "p" []
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").ToggleClass("brother").ToggleClass("sister")
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { class brother} { id link1}]
  5. // "a" [{ href http://example.com/lacie} { class brother} { id link2}]
  6. // "a" [{ href http://example.com/tillie} { class brother} { id link3}]
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").SetAttr("val", "123")
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { class sister} { id link1} { val 123}]
  5. // "a" [{ href http://example.com/lacie} { class sister} { id link2} { val 123}]
  6. // "a" [{ href http://example.com/tillie} { class sister} { id link3} { val 123}]
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").RemoveAttr("class")
  3. prettyPrint(sel.Nodes)
  4. // "a" [{ href http://example.com/elsie} { id link1}]
  5. // "a" [{ href http://example.com/lacie} { id link2}]
  6. // "a" [{ href http://example.com/tillie} { id link3}]
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find(".title").SetText("123")
  3. fmt.Println(goquery.OuterHtml(sel))
  4. // # 原來的 <b> 被移除了
  5. // <p class="title">123</p> <nil>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find(".title").BeforeHtml("<div>before</div>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. // <div>before</div><p class="title"><b>The Dormouse&#39;s story</b></p>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find(".title").AfterHtml("<div>after</div>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. // <p class="title"><b>The Dormouse&#39;s story</b></p><div>after</div>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find(".title").PrependHtml("<div>prepend</div>")
  3. fmt.Println(goquery.OuterHtml(sel))
  4. // <p class="title"><div>prepend</div><b>The Dormouse&#39;s story</b></p>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find(".title").AppendHtml("<div>append</div>")
  3. fmt.Println(goquery.OuterHtml(sel))
  4. // <p class="title"><b>The Dormouse&#39;s story</b><div>append</div></p>
  1. // 將 prepend 元件放到 find 所有元件裡面的前面，原本的 prepend 元件仍存在
  2. domCopy = dom.Clone()
  3. sel = domCopy.Find("a").Prepend("title")
  4. fmt.Println(domCopy.Find("body").Html())
  5. fmt.Println("=============")
  6. // <p class="title"><b>The Dormouse&#39;s story</b></p>
  7. //     <p class="story">Once upon a time there were three little sisters; and their names were
  8. //     <a href="http://example.com/elsie" class="sister" id="link1"><title>The Dormouse&#39;s story</title>Elsie</a>,
  9. //     <a href="http://example.com/lacie" class="sister" id="link2"><title>The Dormouse&#39;s story</title>Lacie</a> and
  10. //     <a href="http://example.com/tillie" class="sister" id="link3"><title>The Dormouse&#39;s story</title>Tillie</a>;
  11. //     and they lived at the bottom of a well.
  12. // </p>
  1. //將 append 元件放到 find 所有元件裡面的後面，原本的 append 元件仍存在
  2. domCopy = dom.Clone()
  3. sel = domCopy.Find("a").Append("title")
  4. fmt.Println(domCopy.Find("body").Html())
  5. fmt.Println("=============")
  6. // <p class="title"><b>The Dormouse&#39;s story</b></p>
  7. //     <p class="story">Once upon a time there were three little sisters; and their names were
  8. //     <a href="http://example.com/elsie" class="sister" id="link1">Elsie<title>The Dormouse&#39;s story</title></a>,
  9. //     <a href="http://example.com/lacie" class="sister" id="link2">Lacie<title>The Dormouse&#39;s story</title></a> and
  10. //     <a href="http://example.com/tillie" class="sister" id="link3">Tillie<title>The Dormouse&#39;s story</title></a>;
  11. //     and they lived at the bottom of a well.
  12. // </p>
  1. // 清空內容
  2. domCopy = dom.Clone()
  3. sel = domCopy.Find("p").Empty()
  4. fmt.Println(domCopy.Find("body").Html())
  5. fmt.Println("=============")
  6. // <p class="title"></p>
  7. //     <p class="story"></p>
  8. // <p class="story"></p>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("p").Remove()
  3. fmt.Println(domCopy.Html())
  4. fmt.Println("=============")
  5. // <html><head><title>The Dormouse&#39;s story</title></head>
  6. // <body>
  7. //
  8. // </body></html>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("p").SetHtml("<b>test</b>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. fmt.Println("=============")
  5. // <p class="title"><b>test</b></p>
  6. //     <p class="story"><b>test</b></p>
  7. // <p class="story"><b>test</b></p>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").ReplaceWithHtml("<p></p>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. fmt.Println("=============")
  5. // <p class="title"><b>The Dormouse&#39;s story</b></p>
  6. //     <p class="story">Once upon a time there were three little sisters; and their names were
  7. //     <p></p>,
  8. //     <p></p> and
  9. //     <p></p>;
  10. //     and they lived at the bottom of a well.
  11. // </p>
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").WrapHtml("<div></div>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. fmt.Println("=============")
  5. // <div><a href="http://example.com/elsie" class="sister" id="link1">Elsie</a></div>,
  6. // <div><a href="http://example.com/lacie" class="sister" id="link2">Lacie</a></div> and
  7. // <div><a href="http://example.com/tillie" class="sister" id="link3">Tillie</a></div>;
  1. domCopy = dom.Clone()
  2. sel = domCopy.Find("a").WrapAllHtml("<div></div>")
  3. fmt.Println(domCopy.Find("body").Html())
  4. fmt.Println("=============")
  5. // <p class="title"><b>The Dormouse&#39;s story</b></p>
  6. //     <p class="story">Once upon a time there were three little sisters; and their names were
  7. //     <div><a href="http://example.com/elsie" class="sister" id="link1">Elsie</a><a href="http://example.com/lacie" class="sister" id="link2">Lacie</a><a href="http://example.com/tillie" class="sister" id="link3">Tillie</a></div>,
  8. //      and
  9. //     ;
  10. //     and they lived at the bottom of a well.
  11. // </p>

特殊方法

  1. domCopy = dom.Clone()
  2. strList := domCopy.Find("a").Map(func(i int, s *goquery.Selection) string {
  3.  str := s.AttrOr("href", "None")
  4.  return str
  5. })
  6. fmt.Println(strList)
  7. // [http://example.com/elsie http://example.com/lacie http://example.com/tillie]
  1. // 以當前元件做判斷
  2. sel = domCopy.Find("p")
  3. fmt.Println(sel.Is("b"))
  4. // false
  1. // for loop
  2. sel := dom.Find(".selector")
  3. for i := range sel.Nodes {
  4.     single := sel.Eq(i)
  5.     // use `single` as a selection of 1 node
  6. }

完整原始碼

  1. package main
  2.  
  3. import (
  4.     "fmt"
  5.     "log"
  6.     "strings"
  7.  
  8.     "github.com/PuerkitoBio/goquery"
  9.     "golang.org/x/net/html"
  10. )
  11.  
  12. func main() {
  13.     html := `
  14. <html>
  15. <head><title>The Dormouse's story</title></head>
  16. <body>
  17. <p class="title"><b>The Dormouse's story</b></p>
  18.     <p class="story">Once upon a time there were three little sisters; and their names were
  19.     <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
  20.     <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
  21.     <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
  22.     and they lived at the bottom of a well.
  23. </p>
  24. <p class="story">...</p>`
  25.  
  26.     // Load the HTML document
  27.     dom, err := goquery.NewDocumentFromReader(strings.NewReader(html))
  28.     if err != nil {
  29.         log.Fatal(err)
  30.     }
  31.  
  32.     var sel *goquery.Selection
  33.  
  34.     sel = dom.Find("a")
  35.     prettyPrint(sel.Nodes)
  36.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  37.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  38.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  39.  
  40.     sel = dom.Find("a.sister#link1")
  41.     prettyPrint(sel.Nodes)
  42.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  43.  
  44.     sel = dom.Find("p").Children()
  45.     prettyPrint(sel.Nodes)
  46.     // "b" []
  47.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  48.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  49.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  50.  
  51.     sel = dom.Find("p").ChildrenFiltered("#link1")
  52.     prettyPrint(sel.Nodes)
  53.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  54.  
  55.     sel = dom.Find("p.title").Siblings()
  56.     prettyPrint(sel.Nodes)
  57.     // "p" [{ class story}]
  58.     // "p" [{ class story}]
  59.  
  60.     sel = dom.Find("a#link2").Siblings()
  61.     prettyPrint(sel.Nodes)
  62.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  63.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  64.  
  65.     sel = dom.Find("a#link2").SiblingsFiltered("#link1")
  66.     prettyPrint(sel.Nodes)
  67.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  68.  
  69.     // 除 children 外，包含 text nodes
  70.     sel = dom.Find("body").Contents()
  71.     prettyPrint(sel.Nodes)
  72.     // "\n    " []
  73.     // "p" [{ class title}]
  74.     // "\n        " []
  75.     // "p" [{ class story}]
  76.     // "\n    " []
  77.     // "p" [{ class story}]
  78.  
  79.     // 含自己往上找，找到最接近的 parents
  80.     sel = dom.Find("a").Closest("a")
  81.     prettyPrint(sel.Nodes)
  82.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  83.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  84.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  85.  
  86.     sel = dom.Find("a").Closest("p")
  87.     prettyPrint(sel.Nodes)
  88.     // "p" [{ class story}]
  89.  
  90.     // 找到其 parent，只往上查找一層，會自動移除重覆的
  91.     sel = dom.Find("a").Parent()
  92.     prettyPrint(sel.Nodes)
  93.     // "p" [{ class story}]
  94.  
  95.     sel = dom.Find("a").ParentFiltered("body")
  96.     prettyPrint(sel.Nodes)
  97.     // None
  98.  
  99.     // 找到其 parents，往上查找不停止，找出所有符合條件的，會自動移除重覆的
  100.     sel = dom.Find("a").Parents()
  101.     prettyPrint(sel.Nodes)
  102.     // "p" [{ class story}]
  103.     // "body" []
  104.     // "html" []
  105.  
  106.     sel = dom.Find("a").ParentsFiltered("body")
  107.     prettyPrint(sel.Nodes)
  108.     // "body" []
  109.  
  110.     // 選擇第一個
  111.     sel = dom.Find("a").Eq(0)
  112.     prettyPrint(sel.Nodes)
  113.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  114.  
  115.     // 可為 string 也可以是 function
  116.     sel = dom.Find("p").Filter(".story")
  117.     prettyPrint(sel.Nodes)
  118.     // "p" [{ class story}]
  119.     // "p" [{ class story}]
  120.  
  121.     sel = dom.Find("p").FilterFunction(func(i int, s *goquery.Selection) bool { return s.Text() == "..." })
  122.     prettyPrint(sel.Nodes)
  123.     // "p" [{ class story}]
  124.  
  125.     sel = dom.Find("a").Not("#link1")
  126.     prettyPrint(sel.Nodes)
  127.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  128.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  129.  
  130.     sel = dom.Find("a#link2").Next()
  131.     prettyPrint(sel.Nodes)
  132.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  133.  
  134.     sel = dom.Find("a#link2").NextFiltered("a")
  135.     prettyPrint(sel.Nodes)
  136.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  137.  
  138.     sel = dom.Find("a#link2").Prev()
  139.     prettyPrint(sel.Nodes)
  140.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  141.  
  142.     sel = dom.Find("a#link2").PrevFiltered("a")
  143.     prettyPrint(sel.Nodes)
  144.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  145.  
  146.     sel = dom.Find("a#link1").NextAll()
  147.     prettyPrint(sel.Nodes)
  148.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  149.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  150.  
  151.     sel = dom.Find("a#link1").NextAllFiltered("#link3")
  152.     prettyPrint(sel.Nodes)
  153.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  154.  
  155.     sel = dom.Find("a#link3").PrevAll()
  156.     prettyPrint(sel.Nodes)
  157.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  158.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  159.  
  160.     sel = dom.Find("a#link3").PrevAllFiltered("#link1")
  161.     prettyPrint(sel.Nodes)
  162.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  163.  
  164.     // 回傳上一個 filter 結果
  165.     sel = dom.Find("a").Parent().End() // 等同 sel = dom.Find("a")
  166.     prettyPrint(sel.Nodes)
  167.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  168.     // "a" [{ href http://example.com/lacie} { class sister} { id link2}]
  169.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  170.  
  171.     // 會以第一個 <a> 為主
  172.     sel = dom.Find("a")
  173.     fmt.Println(sel.Attr("id"))
  174.     // link1 true
  175.     fmt.Println(sel.AttrOr("noid", "nil"))
  176.     // nil
  177.  
  178.     sel = dom.Find("a")
  179.     fmt.Println(sel.Attr("class"))
  180.     // sister true
  181.     fmt.Println(sel.AttrOr("noclass", "nil"))
  182.     // nil
  183.  
  184.     // 只要任何 elements 有就是 True
  185.     sel = dom.Find("p")
  186.     fmt.Println(sel.HasClass("story"))
  187.     // true
  188.  
  189.     // 回傳所有元件的 text
  190.     sel = dom.Find("title")
  191.     fmt.Println(sel.Text())
  192.     // The Dormouse's story
  193.  
  194.     // 兩者意義一樣
  195.     sel = dom.Find("a")
  196.     fmt.Println(sel.Length())
  197.     // 3
  198.     fmt.Println(sel.Size())
  199.     // 3
  200.  
  201.     sel = dom.Find("head")
  202.     fmt.Println(sel.Html())
  203.     //<title>The Dormouse&#39;s story</title> <nil>
  204.  
  205.     sel = dom.Find("head")
  206.     fmt.Println(goquery.OuterHtml(sel))
  207.     // <head><title>The Dormouse&#39;s story</title></head> <nil>
  208.  
  209.     // # 複製原本的內容並回傳，可用在不想被更改的元件上
  210.     var domCopy *goquery.Selection
  211.     domCopy = dom.Find(".title").Clone()
  212.  
  213.     // # 會將原本的 class 替換掉
  214.     domCopy = dom.Clone()
  215.     sel = domCopy.Find("a").SetAttr("class", "classA")
  216.     prettyPrint(sel.Nodes)
  217.     // "a" [{ href http://example.com/elsie} { class classA} { id link1}]
  218.     // "a" [{ href http://example.com/lacie} { class classA} { id link2}]
  219.     // "a" [{ href http://example.com/tillie} { class classA} { id link3}]
  220.     domCopy = dom.Clone()
  221.     sel = domCopy.Find("a#link2").SetAttr("id", "link4")
  222.     prettyPrint(domCopy.Find("a").Nodes)
  223.     // "a" [{ href http://example.com/elsie} { class sister} { id link1}]
  224.     // "a" [{ href http://example.com/lacie} { class sister} { id link4}]
  225.     // "a" [{ href http://example.com/tillie} { class sister} { id link3}]
  226.  
  227.     // # 保留原本的 class
  228.     domCopy = dom.Clone()
  229.     sel = domCopy.Find("a").AddClass("classB")
  230.     prettyPrint(sel.Nodes)
  231.     // "a" [{ href http://example.com/elsie} { class sister  classB} { id link1}]
  232.     // "a" [{ href http://example.com/lacie} { class sister  classB} { id link2}]
  233.     // "a" [{ href http://example.com/tillie} { class sister  classB} { id link3}]
  234.  
  235.     domCopy = dom.Clone()
  236.     sel = domCopy.Find("p").RemoveClass("story")
  237.     prettyPrint(sel.Nodes)
  238.     // "p" [{ class title}]
  239.     // "p" []
  240.     // "p" []
  241.  
  242.     domCopy = dom.Clone()
  243.     sel = domCopy.Find("a").ToggleClass("brother").ToggleClass("sister")
  244.     prettyPrint(sel.Nodes)
  245.     // "a" [{ href http://example.com/elsie} { class brother} { id link1}]
  246.     // "a" [{ href http://example.com/lacie} { class brother} { id link2}]
  247.     // "a" [{ href http://example.com/tillie} { class brother} { id link3}]
  248.  
  249.     domCopy = dom.Clone()
  250.     sel = domCopy.Find("a").SetAttr("val", "123")
  251.     prettyPrint(sel.Nodes)
  252.     // "a" [{ href http://example.com/elsie} { class sister} { id link1} { val 123}]
  253.     // "a" [{ href http://example.com/lacie} { class sister} { id link2} { val 123}]
  254.     // "a" [{ href http://example.com/tillie} { class sister} { id link3} { val 123}]
  255.  
  256.     domCopy = dom.Clone()
  257.     sel = domCopy.Find("a").RemoveAttr("class")
  258.     prettyPrint(sel.Nodes)
  259.     // "a" [{ href http://example.com/elsie} { id link1}]
  260.     // "a" [{ href http://example.com/lacie} { id link2}]
  261.     // "a" [{ href http://example.com/tillie} { id link3}]
  262.  
  263.     domCopy = dom.Clone()
  264.     sel = domCopy.Find(".title").SetText("123")
  265.     fmt.Println(goquery.OuterHtml(sel))
  266.     // # 原來的 <b> 被移除了
  267.     // <p class="title">123</p> <nil>
  268.  
  269.     domCopy = dom.Clone()
  270.     sel = domCopy.Find(".title").BeforeHtml("<div>before</div>")
  271.     fmt.Println(domCopy.Find("body").Html())
  272.     // <div>before</div><p class="title"><b>The Dormouse&#39;s story</b></p>
  273.  
  274.     domCopy = dom.Clone()
  275.     sel = domCopy.Find(".title").AfterHtml("<div>after</div>")
  276.     fmt.Println(domCopy.Find("body").Html())
  277.     // <p class="title"><b>The Dormouse&#39;s story</b></p><div>after</div>
  278.  
  279.     domCopy = dom.Clone()
  280.     sel = domCopy.Find(".title").PrependHtml("<div>prepend</div>")
  281.     fmt.Println(goquery.OuterHtml(sel))
  282.     // <p class="title"><div>prepend</div><b>The Dormouse&#39;s story</b></p>
  283.  
  284.     domCopy = dom.Clone()
  285.     sel = domCopy.Find(".title").AppendHtml("<div>append</div>")
  286.     fmt.Println(goquery.OuterHtml(sel))
  287.     // <p class="title"><b>The Dormouse&#39;s story</b><div>append</div></p>
  288.  
  289.     // 將 prepend 元件放到 find 所有元件裡面的前面，原本的 prepend 元件仍存在
  290.     domCopy = dom.Clone()
  291.     sel = domCopy.Find("a").Prepend("title")
  292.     fmt.Println(domCopy.Find("body").Html())
  293.     fmt.Println("=============")
  294.     // <p class="title"><b>The Dormouse&#39;s story</b></p>
  295.     //     <p class="story">Once upon a time there were three little sisters; and their names were
  296.     //     <a href="http://example.com/elsie" class="sister" id="link1"><title>The Dormouse&#39;s story</title>Elsie</a>,
  297.     //     <a href="http://example.com/lacie" class="sister" id="link2"><title>The Dormouse&#39;s story</title>Lacie</a> and
  298.     //     <a href="http://example.com/tillie" class="sister" id="link3"><title>The Dormouse&#39;s story</title>Tillie</a>;
  299.     //     and they lived at the bottom of a well.
  300.     // </p>
  301.  
  302.     //將 append 元件放到 find 所有元件裡面的後面，原本的 append 元件仍存在
  303.     domCopy = dom.Clone()
  304.     sel = domCopy.Find("a").Append("title")
  305.     fmt.Println(domCopy.Find("body").Html())
  306.     fmt.Println("=============")
  307.     // <p class="title"><b>The Dormouse&#39;s story</b></p>
  308.     //     <p class="story">Once upon a time there were three little sisters; and their names were
  309.     //     <a href="http://example.com/elsie" class="sister" id="link1">Elsie<title>The Dormouse&#39;s story</title></a>,
  310.     //     <a href="http://example.com/lacie" class="sister" id="link2">Lacie<title>The Dormouse&#39;s story</title></a> and
  311.     //     <a href="http://example.com/tillie" class="sister" id="link3">Tillie<title>The Dormouse&#39;s story</title></a>;
  312.     //     and they lived at the bottom of a well.
  313.     // </p>
  314.  
  315.     // 清空內容
  316.     domCopy = dom.Clone()
  317.     sel = domCopy.Find("p").Empty()
  318.     fmt.Println(domCopy.Find("body").Html())
  319.     fmt.Println("=============")
  320.     // <p class="title"></p>
  321.     //     <p class="story"></p>
  322.     // <p class="story"></p>
  323.  
  324.     domCopy = dom.Clone()
  325.     sel = domCopy.Find("p").Remove()
  326.     fmt.Println(domCopy.Html())
  327.     fmt.Println("=============")
  328.     // <html><head><title>The Dormouse&#39;s story</title></head>
  329.     // <body>
  330.     //
  331.     // </body></html>
  332.  
  333.     domCopy = dom.Clone()
  334.     sel = domCopy.Find("p").SetHtml("<b>test</b>")
  335.     fmt.Println(domCopy.Find("body").Html())
  336.     fmt.Println("=============")
  337.     // <p class="title"><b>test</b></p>
  338.     //     <p class="story"><b>test</b></p>
  339.     // <p class="story"><b>test</b></p>
  340.  
  341.     domCopy = dom.Clone()
  342.     sel = domCopy.Find("a").ReplaceWithHtml("<p></p>")
  343.     fmt.Println(domCopy.Find("body").Html())
  344.     fmt.Println("=============")
  345.     // <p class="title"><b>The Dormouse&#39;s story</b></p>
  346.     //     <p class="story">Once upon a time there were three little sisters; and their names were
  347.     //     <p></p>,
  348.     //     <p></p> and
  349.     //     <p></p>;
  350.     //     and they lived at the bottom of a well.
  351.     // </p>
  352.  
  353.     domCopy = dom.Clone()
  354.     sel = domCopy.Find("a").WrapHtml("<div></div>")
  355.     fmt.Println(domCopy.Find("body").Html())
  356.     fmt.Println("=============")
  357.     // <div><a href="http://example.com/elsie" class="sister" id="link1">Elsie</a></div>,
  358.     // <div><a href="http://example.com/lacie" class="sister" id="link2">Lacie</a></div> and
  359.     // <div><a href="http://example.com/tillie" class="sister" id="link3">Tillie</a></div>;
  360.  
  361.     domCopy = dom.Clone()
  362.     sel = domCopy.Find("a").WrapAllHtml("<div></div>")
  363.     fmt.Println(domCopy.Find("body").Html())
  364.     fmt.Println("=============")
  365.     // <p class="title"><b>The Dormouse&#39;s story</b></p>
  366.     //     <p class="story">Once upon a time there were three little sisters; and their names were
  367.     //     <div><a href="http://example.com/elsie" class="sister" id="link1">Elsie</a><a href="http://example.com/lacie" class="sister" id="link2">Lacie</a><a href="http://example.com/tillie" class="sister" id="link3">Tillie</a></div>,
  368.     //      and
  369.     //     ;
  370.     //     and they lived at the bottom of a well.
  371.     // </p>
  372.  
  373.     domCopy = dom.Clone()
  374.     strList := domCopy.Find("a").Map(func(i int, s *goquery.Selection) string {
  375.         str := s.AttrOr("href", "None")
  376.         return str
  377.     })
  378.     fmt.Println(strList)
  379.     // [http://example.com/elsie http://example.com/lacie http://example.com/tillie]
  380.  
  381.     // 以當前元件做判斷
  382.     sel = domCopy.Find("p")
  383.     fmt.Println(sel.Is("b"))
  384.     // false
  385.  
  386. }
  387.  
  388. func prettyPrint(nodes []*html.Node) {
  389.     for _, n := range nodes {
  390.         fmt.Printf("%#v %v\n", n.Data, n.Attr)
  391.     }
  392.     fmt.Println()
  393.     fmt.Println("============")
  394. }

參考

golang goquery selector(选择器) 示例大全

留言

張貼留言