-
-
Save owulveryck/5f9a07762ce40e6f6d9028e76bd798e2 to your computer and use it in GitHub Desktop.
Support file for the rePocketable article
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"bytes" | |
"io" | |
"log" | |
"os" | |
"golang.org/x/net/html" | |
) | |
var sample = `<figure class="ja jb jc jd je jf cw cx paragraph-image"> <div role="button" tabindex="0" class="jg jh ji jj aj jk"> <div class="cw cx iz"> <div class="jq s ji jr"> <div class="js jt s"> <div class="jl jm t u v jn aj at jo jp"> <img alt="" class="t u v jn aj ju jv jw" src="https://miro.medium.com/max/60/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg?q=20" width="700" height="590" role="presentation" /> </div> <img alt="" class="jl jm t u v jn aj c" width="700" height="590" role="presentation" /><noscript><img alt="" class="t u v jn aj" src="https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg" width="700" height="590" srcSet="https://miro.medium.com/max/552/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 276w, https://miro.medium.com/max/1104/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 552w, https://miro.medium.com/max/1280/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 640w, https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 700w" sizes="700px" role="presentation" /></noscript> </div> </div> </div> </div> </figure>` | |
func Example() { | |
content := bytes.NewBufferString(sample) | |
n, err := html.Parse(content) | |
if err != nil { | |
log.Fatal(err) | |
} | |
err = preProcess(n) | |
if err != nil { | |
log.Fatal(err) | |
} | |
html.Render(os.Stdout, n) | |
// output: | |
// <html><head></head><body><figure class="ja jb jc jd je jf cw cx paragraph-image"> <div role="button" tabindex="0" class="jg jh ji jj aj jk"> <div class="cw cx iz"> <div class="jq s ji jr"> <div class="js jt s"> <div class="jl jm t u v jn aj at jo jp"> </div> <img alt="" class="t u v jn aj" src="https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg" width="700" height="590" srcset="https://miro.medium.com/max/552/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 276w, https://miro.medium.com/max/1104/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 552w, https://miro.medium.com/max/1280/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 640w, https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 700w" sizes="700px" role="presentation"/><noscript><img alt="" class="t u v jn aj" src="https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg" width="700" height="590" srcSet="https://miro.medium.com/max/552/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 276w, https://miro.medium.com/max/1104/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 552w, https://miro.medium.com/max/1280/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 640w, https://miro.medium.com/max/1400/1*RSH2vh_xgQtjB68Zb7oBaA.jpeg 700w" sizes="700px" role="presentation" /></noscript> </div> </div> </div> </div> </figure></body></html> | |
} | |
func preProcess(n *html.Node) error { | |
if n.Type == html.ElementNode && n.Data == "figure" { | |
f := &figure{ | |
images: make([]*html.Node, 0), | |
} | |
f.processFigure(n) | |
// Clear all other images (medium, towarddatascience, ...) | |
if len(f.images) > 1 { | |
for _, img := range f.images { | |
if img != f.validImage { | |
img.Parent.RemoveChild(img) | |
} | |
} | |
} | |
} | |
for c := n.FirstChild; c != nil; c = c.NextSibling { | |
err := preProcess(c) | |
if err != nil { | |
return err | |
} | |
} | |
return nil | |
} | |
type figure struct { | |
images []*html.Node | |
validImage *html.Node | |
} | |
func (f *figure) processFigure(n *html.Node) error { | |
if n.Type == html.ElementNode && n.Data == "img" { | |
f.images = append(f.images, n) | |
} | |
if n.Data == "noscript" { | |
if originalImg := n.PrevSibling; originalImg.Data == "img" { | |
// the img data is encoded as a string in the n.FirstChild.Data field | |
// Let's parse it as a node: | |
doc, err := html.Parse(bytes.NewBufferString(n.FirstChild.Data)) | |
if err != nil { | |
return err | |
} | |
img := getImgNode(doc) | |
if img != nil { | |
originalImg.Attr = img.Attr | |
} | |
f.validImage = originalImg | |
} | |
} | |
for c := n.FirstChild; c != nil; c = c.NextSibling { | |
err := f.processFigure(c) | |
if err != io.EOF { | |
return err | |
} | |
} | |
return io.EOF | |
} | |
func getImgNode(node *html.Node) *html.Node { | |
if node.Type == html.ElementNode && node.Data == "img" { | |
return node | |
} | |
for child := node.FirstChild; child != nil; child = child.NextSibling { | |
n := getImgNode(child) | |
if n != nil { | |
return n | |
} | |
} | |
return nil | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment