Compare commits

..
Author SHA1 Message Date
Martin Angers b8bc6fd071 module-aware version 2018-09-03 16:56:58 -04:00
15 changed files with 63 additions and 707 deletions
-104
View File
@@ -1,104 +0,0 @@
image: fedora/latest
packages:
- tar
environment:
GOROOT: /tmp/go
GOPATH: /home/build
GOBIN: /home/build/bin
sources:
- https://github.com/PuerkitoBio/goquery
tasks:
- setup: |
mkdir bin
mkdir -p src/github.com/PuerkitoBio
mv goquery src/github.com/PuerkitoBio/
- go1_7: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.7.6.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_8: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.8.7.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_9: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.9.7.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_10: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.10.8.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_11: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.11.13.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_12: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.12.17.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_13: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.13.15.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_14: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.14.12.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_15: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.15.5.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
- go1_16: |
cd /tmp
rm -rf go
curl -Lo golang.tar.gz https://golang.org/dl/go1.16beta1.linux-amd64.tar.gz
tar xvf golang.tar.gz
cd /home/build/src/github.com/PuerkitoBio/goquery
/tmp/go/bin/go version
/tmp/go/bin/go get -t .
/tmp/go/bin/go test -v
-2
View File
@@ -1,2 +0,0 @@
github: [mna]
custom: ["https://www.buymeacoffee.com/mna"]
+7 -23
View File
@@ -1,31 +1,15 @@
arch:
- amd64
- ppc64le
language: go
go:
- 1.1
- 1.2.x
- 1.3.x
- 1.4.x
- 1.5.x
- 1.6.x
- 1.7.x
- 1.8.x
- 1.9.x
- 1.10.x
- 1.11.x
- 1.12.x
- 1.13.x
- 1.14.x
- 1.15.x
- "1.10.x"
- tip
jobs:
exclude:
- arch: ppc64le
go: 1.7.x
- arch: ppc64le
go: 1.8.x
- arch: ppc64le
go: 1.9.x
- arch: ppc64le
go: 1.10.x
- arch: ppc64le
go: 1.11.x
- arch: ppc64le
go: 1.12.x
+10 -22
View File
@@ -1,5 +1,5 @@
# goquery - a little like that j-thing, only in Go
[![builds.sr.ht status](https://builds.sr.ht/~mna/goquery/commits/fedora.yml.svg)](https://builds.sr.ht/~mna/goquery/commits/fedora.yml?) [![build status](https://secure.travis-ci.org/PuerkitoBio/goquery.svg?branch=master)](http://travis-ci.org/PuerkitoBio/goquery) [![Go Reference](https://pkg.go.dev/badge/github.com/PuerkitoBio/goquery.svg)](https://pkg.go.dev/github.com/PuerkitoBio/goquery) [![Sourcegraph Badge](https://sourcegraph.com/github.com/PuerkitoBio/goquery/-/badge.svg)](https://sourcegraph.com/github.com/PuerkitoBio/goquery?badge)
[![build status](https://secure.travis-ci.org/PuerkitoBio/goquery.svg?branch=master)](http://travis-ci.org/PuerkitoBio/goquery) [![GoDoc](https://godoc.org/github.com/PuerkitoBio/goquery?status.png)](http://godoc.org/github.com/PuerkitoBio/goquery) [![Sourcegraph Badge](https://sourcegraph.com/github.com/PuerkitoBio/goquery/-/badge.svg)](https://sourcegraph.com/github.com/PuerkitoBio/goquery?badge)
goquery brings a syntax and a set of features similar to [jQuery][] to the [Go language][go]. It is based on Go's [net/html package][html] and the CSS Selector library [cascadia][]. Since the net/html parser returns nodes, and not a full-featured DOM tree, jQuery's stateful manipulation functions (like height(), css(), detach()) have been left off.
@@ -37,10 +37,6 @@ Please note that because of the net/html dependency, goquery requires Go1.1+.
**Note that goquery's API is now stable, and will not break.**
* **2021-01-11 (v1.6.1)** : Fix panic when calling `{Prepend,Append,Set}Html` on a `Selection` that contains non-Element nodes.
* **2020-10-08 (v1.6.0)** : Parse html in context of the container node for all functions that deal with html strings (`AfterHtml`, `AppendHtml`, etc.). Thanks to [@thiemok][thiemok] and [@davidjwilkins][djw] for their work on this.
* **2020-02-04 (v1.5.1)** : Update module dependencies.
* **2018-11-15 (v1.5.0)** : Go module support (thanks @Zaba505).
* **2018-06-07 (v1.4.1)** : Add `NewDocumentFromReader` examples.
* **2018-03-24 (v1.4.0)** : Deprecate `NewDocument(url)` and `NewDocumentFromResponse(response)`.
* **2018-01-28 (v1.3.0)** : Add `ToEnd` constant to `Slice` until the end of the selection (thanks to @davidjwilkins for raising the issue).
@@ -123,11 +119,12 @@ func ExampleScrape() {
}
// Find the review items
doc.Find(".left-content article .post-title").Each(func(i int, s *goquery.Selection) {
// For each item found, get the title
title := s.Find("a").Text()
fmt.Printf("Review %d: %s\n", i, title)
})
doc.Find(".sidebar-reviews article .content-block").Each(func(i int, s *goquery.Selection) {
// For each item found, get the band and title
band := s.Find("a").Text()
title := s.Find("i").Text()
fmt.Printf("Review %d: %s - %s\n", i, band, title)
})
}
func main() {
@@ -140,14 +137,8 @@ func main() {
- [Goq][goq], an HTML deserialization and scraping library based on goquery and struct tags.
- [andybalholm/cascadia][cascadia], the CSS selector library used by goquery.
- [suntong/cascadia][cascadiacli], a command-line interface to the cascadia CSS selector library, useful to test selectors.
- [gocolly/colly](https://github.com/gocolly/colly), a lightning fast and elegant Scraping Framework
- [asciimoo/colly](https://github.com/asciimoo/colly), a lightning fast and elegant Scraping Framework
- [gnulnx/goperf](https://github.com/gnulnx/goperf), a website performance test tool that also fetches static assets.
- [MontFerret/ferret](https://github.com/MontFerret/ferret), declarative web scraping.
- [tacusci/berrycms](https://github.com/tacusci/berrycms), a modern simple to use CMS with easy to write plugins
- [Dataflow kit](https://github.com/slotix/dataflowkit), Web Scraping framework for Gophers.
- [Geziyor](https://github.com/geziyor/geziyor), a fast web crawling & scraping framework for Go. Supports JS rendering.
- [Pagser](https://github.com/foolin/pagser), a simple, easy, extensible, configurable HTML parser to struct based on goquery and struct tags.
- [stitcherd](https://github.com/vhodges/stitcherd), A server for doing server side includes using css selectors and DOM updates.
## Support
@@ -160,9 +151,8 @@ There are a number of ways you can support the project:
* Pull requests: please discuss new code in an issue first, unless the fix is really trivial.
- Make sure new code is tested.
- Be mindful of existing code - PRs that break existing code have a high probability of being declined, unless it fixes a serious issue.
* Sponsor the developer
- See the Github Sponsor button at the top of the repo on github
- or via BuyMeACoffee.com, below
If you desperately want to send money my way, I have a BuyMeACoffee.com page:
<a href="https://www.buymeacoffee.com/mna" target="_blank"><img src="https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png" alt="Buy Me A Coffee" style="height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;" ></a>
@@ -185,5 +175,3 @@ The [BSD 3-Clause license][bsd], the same as the [Go language][golic]. Cascadia'
[thatguystone]: https://github.com/thatguystone
[piotr]: https://github.com/piotrkowalczuk
[goq]: https://github.com/andrewstuart/goq
[thiemok]: https://github.com/thiemok
[djw]: https://github.com/davidjwilkins
+1 -2
View File
@@ -1,7 +1,6 @@
package goquery
import (
"strconv"
"testing"
)
@@ -32,7 +31,7 @@ func BenchmarkMap(b *testing.B) {
sel := DocW().Find("td")
f := func(i int, s *Selection) string {
tmp++
return strconv.Itoa(tmp)
return string(tmp)
}
b.StartTimer()
for i := 0; i < b.N; i++ {
-20
View File
@@ -2,8 +2,6 @@ package goquery
import (
"testing"
"github.com/andybalholm/cascadia"
)
func BenchmarkFind(b *testing.B) {
@@ -802,21 +800,3 @@ func BenchmarkClosestNodes(b *testing.B) {
b.Fatalf("want 2, got %d", n)
}
}
func BenchmarkSingleMatcher(b *testing.B) {
doc := Doc()
multi := cascadia.MustCompile(`div`)
single := SingleMatcher(multi)
b.ResetTimer()
b.Run("multi", func(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = doc.FindMatcher(multi)
}
})
b.Run("single", func(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = doc.FindMatcher(single)
}
})
}
+3 -3
View File
@@ -4,13 +4,13 @@
The `go.net/html` package used by `goquery` requires that the html document is UTF-8 encoded. When you know the encoding of the html page is not UTF-8, you can use the `iconv` package to convert it to UTF-8 (there are various implementation of the `iconv` API, see [godoc.org][iconv] for other options):
```bash
```
$ go get -u github.com/djimenez/iconv-go
```
and then:
```golang
```
// Load the URL
res, err := http.Get(url)
if err != nil {
@@ -51,7 +51,7 @@ You can find a code example using `otto` [in this gist][exotto]. Thanks to githu
If all you need is a normal `for` loop over all nodes in the current selection, where `Map/Each`-style iteration is not necessary, you can use the following:
```golang
```
sel := Doc().Find(".selector")
for i := range sel.Nodes {
single := sel.Eq(i)
-28
View File
@@ -80,31 +80,3 @@ func ExampleNewDocumentFromReader_string() {
// Output: Header
}
func ExampleSingle() {
html := `
<html>
<body>
<div>1</div>
<div>2</div>
<div>3</div>
</body>
</html>
`
doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
if err != nil {
log.Fatal(err)
}
// By default, the selector string selects all matching nodes
multiSel := doc.Find("div")
fmt.Println(multiSel.Text())
// Using goquery.Single, only the first match is selected
singleSel := doc.FindMatcher(goquery.Single("div"))
fmt.Println(singleSel.Text())
// Output:
// 123
// 1
}
+2 -4
View File
@@ -1,8 +1,6 @@
module github.com/PuerkitoBio/goquery
require (
github.com/andybalholm/cascadia v1.1.0
golang.org/x/net v0.0.0-20200202094626-16171245cfb2
github.com/andybalholm/cascadia v1.0.0
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d
)
go 1.13
+4 -7
View File
@@ -1,8 +1,5 @@
github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20200202094626-16171245cfb2 h1:CCH4IOTTfewWjGOlSp+zGcjutRKlBEZQ6wTn8ozI/nI=
golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d h1:g9qWBGx4puODJTMVyoPrpoxPFgVGd+z1DZwjfRu4d0I=
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+31 -136
View File
@@ -39,15 +39,8 @@ func (s *Selection) AfterSelection(sel *Selection) *Selection {
// AfterHtml parses the html and inserts it after the set of matched elements.
//
// This follows the same rules as Selection.Append.
func (s *Selection) AfterHtml(htmlStr string) *Selection {
return s.eachNodeHtml(htmlStr, true, func(node *html.Node, nodes []*html.Node) {
nextSibling := node.NextSibling
for _, n := range nodes {
if node.Parent != nil {
node.Parent.InsertBefore(n, nextSibling)
}
}
})
func (s *Selection) AfterHtml(html string) *Selection {
return s.AfterNodes(parseHtml(html)...)
}
// AfterNodes inserts the nodes after each element in the set of matched elements.
@@ -92,12 +85,8 @@ func (s *Selection) AppendSelection(sel *Selection) *Selection {
}
// AppendHtml parses the html and appends it to the set of matched elements.
func (s *Selection) AppendHtml(htmlStr string) *Selection {
return s.eachNodeHtml(htmlStr, false, func(node *html.Node, nodes []*html.Node) {
for _, n := range nodes {
node.AppendChild(n)
}
})
func (s *Selection) AppendHtml(html string) *Selection {
return s.AppendNodes(parseHtml(html)...)
}
// AppendNodes appends the specified nodes to each node in the set of matched elements.
@@ -134,14 +123,8 @@ func (s *Selection) BeforeSelection(sel *Selection) *Selection {
// BeforeHtml parses the html and inserts it before the set of matched elements.
//
// This follows the same rules as Selection.Append.
func (s *Selection) BeforeHtml(htmlStr string) *Selection {
return s.eachNodeHtml(htmlStr, true, func(node *html.Node, nodes []*html.Node) {
for _, n := range nodes {
if node.Parent != nil {
node.Parent.InsertBefore(n, node)
}
}
})
func (s *Selection) BeforeHtml(html string) *Selection {
return s.BeforeNodes(parseHtml(html)...)
}
// BeforeNodes inserts the nodes before each element in the set of matched elements.
@@ -201,13 +184,8 @@ func (s *Selection) PrependSelection(sel *Selection) *Selection {
}
// PrependHtml parses the html and prepends it to the set of matched elements.
func (s *Selection) PrependHtml(htmlStr string) *Selection {
return s.eachNodeHtml(htmlStr, false, func(node *html.Node, nodes []*html.Node) {
firstChild := node.FirstChild
for _, n := range nodes {
node.InsertBefore(n, firstChild)
}
})
func (s *Selection) PrependHtml(html string) *Selection {
return s.PrependNodes(parseHtml(html)...)
}
// PrependNodes prepends the specified nodes to each node in the set of
@@ -234,19 +212,14 @@ func (s *Selection) Remove() *Selection {
return s
}
// RemoveFiltered removes from the current set of matched elements those that
// match the selector filter. It returns the Selection of removed nodes.
//
// For example if the selection s contains "<h1>", "<h2>" and "<h3>"
// and s.RemoveFiltered("h2") is called, only the "<h2>" node is removed
// (and returned), while "<h1>" and "<h3>" are kept in the document.
// RemoveFiltered removes the set of matched elements by selector.
// It returns the Selection of removed nodes.
func (s *Selection) RemoveFiltered(selector string) *Selection {
return s.RemoveMatcher(compileMatcher(selector))
}
// RemoveMatcher removes from the current set of matched elements those that
// match the Matcher filter. It returns the Selection of removed nodes.
// See RemoveFiltered for additional information.
// RemoveMatcher removes the set of matched elements.
// It returns the Selection of removed nodes.
func (s *Selection) RemoveMatcher(m Matcher) *Selection {
return s.FilterMatcher(m).Remove()
}
@@ -283,16 +256,8 @@ func (s *Selection) ReplaceWithSelection(sel *Selection) *Selection {
// It returns the removed elements.
//
// This follows the same rules as Selection.Append.
func (s *Selection) ReplaceWithHtml(htmlStr string) *Selection {
s.eachNodeHtml(htmlStr, true, func(node *html.Node, nodes []*html.Node) {
nextSibling := node.NextSibling
for _, n := range nodes {
if node.Parent != nil {
node.Parent.InsertBefore(n, nextSibling)
}
}
})
return s.Remove()
func (s *Selection) ReplaceWithHtml(html string) *Selection {
return s.ReplaceWithNodes(parseHtml(html)...)
}
// ReplaceWithNodes replaces each element in the set of matched elements with
@@ -307,17 +272,8 @@ func (s *Selection) ReplaceWithNodes(ns ...*html.Node) *Selection {
// SetHtml sets the html content of each element in the selection to
// specified html string.
func (s *Selection) SetHtml(htmlStr string) *Selection {
for _, context := range s.Nodes {
for c := context.FirstChild; c != nil; c = context.FirstChild {
context.RemoveChild(c)
}
}
return s.eachNodeHtml(htmlStr, false, func(node *html.Node, nodes []*html.Node) {
for _, n := range nodes {
node.AppendChild(n)
}
})
func (s *Selection) SetHtml(html string) *Selection {
return setHtmlNodes(s, parseHtml(html)...)
}
// SetText sets the content of each element in the selection to specified content.
@@ -373,23 +329,8 @@ func (s *Selection) WrapSelection(sel *Selection) *Selection {
// most child of the given HTML.
//
// It returns the original set of elements.
func (s *Selection) WrapHtml(htmlStr string) *Selection {
nodesMap := make(map[string][]*html.Node)
for _, context := range s.Nodes {
var parent *html.Node
if context.Parent != nil {
parent = context.Parent
} else {
parent = &html.Node{Type: html.ElementNode}
}
nodes, found := nodesMap[nodeName(parent)]
if !found {
nodes = parseHtmlWithContext(htmlStr, parent)
nodesMap[nodeName(parent)] = nodes
}
newSingleSelection(context, s.document).wrapAllNodes(cloneNodes(nodes)...)
}
return s
func (s *Selection) WrapHtml(html string) *Selection {
return s.wrapNodes(parseHtml(html)...)
}
// WrapNode wraps each element in the set of matched elements inside the inner-
@@ -441,18 +382,8 @@ func (s *Selection) WrapAllSelection(sel *Selection) *Selection {
// document.
//
// It returns the original set of elements.
func (s *Selection) WrapAllHtml(htmlStr string) *Selection {
var context *html.Node
var nodes []*html.Node
if len(s.Nodes) > 0 {
context = s.Nodes[0]
if context.Parent != nil {
nodes = parseHtmlWithContext(htmlStr, context)
} else {
nodes = parseHtml(htmlStr)
}
}
return s.wrapAllNodes(nodes...)
func (s *Selection) WrapAllHtml(html string) *Selection {
return s.wrapAllNodes(parseHtml(html)...)
}
func (s *Selection) wrapAllNodes(ns ...*html.Node) *Selection {
@@ -521,17 +452,8 @@ func (s *Selection) WrapInnerSelection(sel *Selection) *Selection {
// cloned before being inserted into the document.
//
// It returns the original set of elements.
func (s *Selection) WrapInnerHtml(htmlStr string) *Selection {
nodesMap := make(map[string][]*html.Node)
for _, context := range s.Nodes {
nodes, found := nodesMap[nodeName(context)]
if !found {
nodes = parseHtmlWithContext(htmlStr, context)
nodesMap[nodeName(context)] = nodes
}
newSingleSelection(context, s.document).wrapInnerNodes(cloneNodes(nodes)...)
}
return s
func (s *Selection) WrapInnerHtml(html string) *Selection {
return s.wrapInnerNodes(parseHtml(html)...)
}
// WrapInnerNode wraps an HTML structure, matched by the given selector, around
@@ -571,14 +493,16 @@ func parseHtml(h string) []*html.Node {
return nodes
}
func parseHtmlWithContext(h string, context *html.Node) []*html.Node {
// Errors are only returned when the io.Reader returns any error besides
// EOF, but strings.Reader never will
nodes, err := html.ParseFragment(strings.NewReader(h), context)
if err != nil {
panic("goquery: failed to parse HTML: " + err.Error())
func setHtmlNodes(s *Selection, ns ...*html.Node) *Selection {
for _, n := range s.Nodes {
for c := n.FirstChild; c != nil; c = n.FirstChild {
n.RemoveChild(c)
}
for _, c := range ns {
n.AppendChild(cloneNode(c))
}
}
return nodes
return s
}
// Get the first child that is an ElementNode
@@ -648,32 +572,3 @@ func (s *Selection) manipulateNodes(ns []*html.Node, reverse bool,
return s
}
// eachNodeHtml parses the given html string and inserts the resulting nodes in the dom with the mergeFn.
// The parsed nodes are inserted for each element of the selection.
// isParent can be used to indicate that the elements of the selection should be treated as the parent for the parsed html.
// A cache is used to avoid parsing the html multiple times should the elements of the selection result in the same context.
func (s *Selection) eachNodeHtml(htmlStr string, isParent bool, mergeFn func(n *html.Node, nodes []*html.Node)) *Selection {
// cache to avoid parsing the html for the same context multiple times
nodeCache := make(map[string][]*html.Node)
var context *html.Node
for _, n := range s.Nodes {
if isParent {
context = n.Parent
} else {
if n.Type != html.ElementNode {
continue
}
context = n
}
if context != nil {
nodes, found := nodeCache[nodeName(context)]
if !found {
nodes = parseHtmlWithContext(htmlStr, context)
nodeCache[nodeName(context)] = nodes
}
mergeFn(n, cloneNodes(nodes))
}
}
return s
}
-226
View File
@@ -1,7 +1,6 @@
package goquery
import (
"log"
"testing"
)
@@ -57,26 +56,6 @@ func TestAfterHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestAfterHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<td>Before1</td>
</tr>
<tr>
<td>Before2</td>
</tr>
</table>
</body>
</html>`)
doc.Find("table tr td").AfterHtml("<td class='c1'>Test</td><td class='c2'>Again</td>")
assertLength(t, doc.Find("table tr td").Nodes, 6)
assertClass(t, doc.Find("table tr td").Last(), "c2")
printSel(t, doc.Selection)
}
func TestAppend(t *testing.T) {
doc := Doc2Clone()
doc.Find("#main").Append("#nf6")
@@ -134,27 +113,6 @@ func TestAppendHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestAppendHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<td>Before1</td>
</tr>
<tr>
<td>Before2</td>
</tr>
</table>
</body>
</html>`)
doc.Find("table tr").AppendHtml("<td class='c1'>new1</td><td class='c2'>new2</td>")
assertLength(t, doc.Find("table td").Nodes, 6)
assertClass(t, doc.Find("table td").Last(), "c2")
printSel(t, doc.Selection)
}
func TestBefore(t *testing.T) {
doc := Doc2Clone()
doc.Find("#main").Before("#nf6")
@@ -193,27 +151,6 @@ func TestBeforeHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestBeforeHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<td>Before1</td>
</tr>
<tr>
<td>Before2</td>
</tr>
</table>
</body>
</html>`)
doc.Find("table tr td:first-child").BeforeHtml("<td class='c1'>new1</td><td class='c2'>new2</td>")
assertLength(t, doc.Find("table td").Nodes, 6)
assertClass(t, doc.Find("table td").First(), "c1")
printSel(t, doc.Selection)
}
func TestEmpty(t *testing.T) {
doc := Doc2Clone()
s := doc.Find("#main").Empty()
@@ -281,27 +218,6 @@ func TestPrependHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestPrependHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<td>Before1</td>
</tr>
<tr>
<td>Before2</td>
</tr>
</table>
</body>
</html>`)
doc.Find("table tr").PrependHtml("<td class='c1'>new node</td><td class='c2'>other new node</td>")
assertLength(t, doc.Find("table td").Nodes, 6)
assertClass(t, doc.Find("table tr td").First(), "c1")
printSel(t, doc.Selection)
}
func TestRemove(t *testing.T) {
doc := Doc2Clone()
doc.Find("#nf1").Remove()
@@ -362,28 +278,6 @@ func TestReplaceWithHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestReplaceWithHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<th>Before1</th>
</tr>
<tr>
<th>Before2</th>
</tr>
</table>
</body>
</html>`)
doc.Find("table th").ReplaceWithHtml("<td class='c1'>Test</td><td class='c2'>Replace</td>")
assertLength(t, doc.Find("table th").Nodes, 0)
assertLength(t, doc.Find("table tr td").Nodes, 4)
assertClass(t, doc.Find("table tr td").First(), "c1")
printSel(t, doc.Selection)
}
func TestSetHtml(t *testing.T) {
doc := Doc2Clone()
q := doc.Find("#main, #foot")
@@ -419,28 +313,6 @@ func TestSetHtmlEmpty(t *testing.T) {
printSel(t, doc.Selection)
}
func TestSetHtmlContext(t *testing.T) {
doc := loadString(t, `
<html>
<body>
<table>
<tr>
<th>Before1</th>
</tr>
<tr>
<th>Before2</th>
</tr>
</table>
</body>
</html>`)
doc.Find("table tr").SetHtml("<td class='c1'>Test</td><td class='c2'>Again</td>")
assertLength(t, doc.Find("table th").Nodes, 0)
assertLength(t, doc.Find("table td").Nodes, 4)
assertLength(t, doc.Find("table tr").Nodes, 2)
printSel(t, doc.Selection)
}
func TestSetText(t *testing.T) {
doc := Doc2Clone()
q := doc.Find("#main, #foot")
@@ -639,101 +511,3 @@ func TestWrapInnerHtml(t *testing.T) {
printSel(t, doc.Selection)
}
func TestParsingRespectsVaryingContext(t *testing.T) {
docA := loadString(t, `
<html>
<body>
<a class="x"></a>
</body>
</html>`)
docTable := loadString(t, `
<html>
<body>
<table class="x"></table>
</body>
</html>`)
docBoth := loadString(t, `
<html>
<body>
<table class="x"></table>
<a class="x"></a>
</body>
</html>`)
sA := docA.Find(".x").AppendHtml("<tr><td>Hello</td></tr>")
sTable := docTable.Find(".x").AppendHtml("<tr><td>Hello</td></tr>")
sBoth := docBoth.Find(".x").AppendHtml("<tr><td>Hello</td></tr>")
printSel(t, docA.Selection)
printSel(t, docTable.Selection)
printSel(t, docBoth.Selection)
oA, _ := sA.Html()
oTable, _ := sTable.Html()
if oA == oTable {
t.Errorf("Expected inner html of <a> and <table> to not be equal, but got %s and %s", oA, oTable)
}
oBothTable, _ := sBoth.First().Html()
if oBothTable != oTable {
t.Errorf("Expected inner html of <table> and <table> in doc containing both tags to be equal, but got %s and %s",
oTable,
oBothTable)
}
oBothA, _ := sBoth.Last().Html()
if oBothA != oA {
t.Errorf("Expected inner html of <a> and <a> in doc containing both tags to be equal, but got %s and %s",
oA,
oBothA)
}
}
func TestHtmlWithNonElementNode(t *testing.T) {
const data = `
<html>
<head>
</head>
<body>
<p>
This is <span>some</span><b>text</b>.
</p>
</body>
</html>
`
cases := map[string]func(*Selection, string) *Selection{
"AfterHtml": (*Selection).AfterHtml,
"AppendHtml": (*Selection).AppendHtml,
"BeforeHtml": (*Selection).BeforeHtml,
"PrependHtml": (*Selection).PrependHtml,
"ReplaceWithHtml": (*Selection).ReplaceWithHtml,
"SetHtml": (*Selection).SetHtml,
}
for nm, fn := range cases {
// this test is only to make sure that the HTML parsing/manipulation
// methods do not raise panics when executed over Selections that contain
// non-Element nodes.
t.Run(nm, func(t *testing.T) {
doc := loadString(t, data)
sel := doc.Find("p").Contents()
func() {
defer func() {
if err := recover(); err != nil {
t.Fatal(err)
}
}()
fn(sel, "<div></div>")
}()
// print the resulting document in verbose mode
h, err := OuterHtml(doc.Selection)
if err != nil {
log.Fatal(err)
}
t.Log(h)
})
}
}
+1 -63
View File
@@ -7,6 +7,7 @@ import (
"net/url"
"github.com/andybalholm/cascadia"
"golang.org/x/net/html"
)
@@ -121,45 +122,6 @@ type Matcher interface {
Filter([]*html.Node) []*html.Node
}
// Single compiles a selector string to a Matcher that stops after the first
// match is found.
//
// By default, Selection.Find and other functions that accept a selector string
// to select nodes will use all matches corresponding to that selector. By
// using the Matcher returned by Single, at most the first match will be
// selected.
//
// For example, those two statements are semantically equivalent:
//
// sel1 := doc.Find("a").First()
// sel2 := doc.FindMatcher(goquery.Single("a"))
//
// The one using Single is optimized to be potentially much faster on large
// documents.
//
// Only the behaviour of the MatchAll method of the Matcher interface is
// altered compared to standard Matchers. This means that the single-selection
// property of the Matcher only applies for Selection methods where the Matcher
// is used to select nodes, not to filter or check if a node matches the
// Matcher - in those cases, the behaviour of the Matcher is unchanged (e.g.
// FilterMatcher(Single("div")) will still result in a Selection with multiple
// "div"s if there were many "div"s in the Selection to begin with).
func Single(selector string) Matcher {
return singleMatcher{compileMatcher(selector)}
}
// SingleMatcher returns a Matcher matches the same nodes as m, but that stops
// after the first match is found.
//
// See the documentation of function Single for more details.
func SingleMatcher(m Matcher) Matcher {
if _, ok := m.(singleMatcher); ok {
// m is already a singleMatcher
return m
}
return singleMatcher{m}
}
// compileMatcher compiles the selector string s and returns
// the corresponding Matcher. If s is an invalid selector string,
// it returns a Matcher that fails all matches.
@@ -171,30 +133,6 @@ func compileMatcher(s string) Matcher {
return cs
}
type singleMatcher struct {
Matcher
}
func (m singleMatcher) MatchAll(n *html.Node) []*html.Node {
// Optimized version - stops finding at the first match (cascadia-compiled
// matchers all use this code path).
if mm, ok := m.Matcher.(interface{ MatchFirst(*html.Node) *html.Node }); ok {
node := mm.MatchFirst(n)
if node == nil {
return nil
}
return []*html.Node{node}
}
// Fallback version, for e.g. test mocks that don't provide the MatchFirst
// method.
nodes := m.Matcher.MatchAll(n)
if len(nodes) > 0 {
return nodes[:1:1]
}
return nil
}
// invalidMatcher is a Matcher that always fails to match.
type invalidMatcher struct{}
-53
View File
@@ -7,7 +7,6 @@ import (
"strings"
"testing"
"github.com/andybalholm/cascadia"
"golang.org/x/net/html"
)
@@ -122,14 +121,6 @@ func loadDoc(page string) *Document {
return NewDocumentFromNode(node)
}
func loadString(t *testing.T, doc string) *Document {
d, err := NewDocumentFromReader(strings.NewReader(doc))
if err != nil {
t.Error("Failed to parse test document")
}
return d
}
func TestNewDocument(t *testing.T) {
if f, e := os.Open("./testdata/page.html"); e != nil {
t.Error(e.Error())
@@ -209,47 +200,3 @@ func TestIssue103(t *testing.T) {
}
t.Log(text)
}
func TestSingle(t *testing.T) {
data := `
<html>
<body>
<div class="b">1</div>
<div class="a">2</div>
<div class="a">3</div>
<p class="b">4</p>
</body>
</html>
`
doc, err := NewDocumentFromReader(strings.NewReader(data))
if err != nil {
t.Fatal(err)
}
text := doc.FindMatcher(Single("div")).Text()
if text != "1" {
t.Fatalf("want %q, got %q", "1", text)
}
// Verify semantic equivalence
sel1 := doc.Find("div").First()
sel2 := doc.FindMatcher(Single("div"))
if sel1.Text() != sel2.Text() {
t.Fatalf("want sel1 to equal sel2")
}
// Here, the Single has no effect as the selector is used to filter
// from the existing selection, not to find nodes in the document.
divs := doc.Find("div")
text = divs.FilterMatcher(Single(".a")).Text()
if text != "23" {
t.Fatalf("want %q, got %q", "23", text)
}
classA := cascadia.MustCompile(".a")
classB := cascadia.MustCompile(".b")
text = doc.FindMatcher(classB).AddMatcher(SingleMatcher(classA)).Text()
if text != "142" {
t.Fatalf("want %q, got %q", "142", text)
}
}
+4 -14
View File
@@ -36,22 +36,12 @@ func NodeName(s *Selection) string {
if s.Length() == 0 {
return ""
}
return nodeName(s.Get(0))
}
// nodeName returns the node name of the given html node.
// See NodeName for additional details on behaviour.
func nodeName(node *html.Node) string {
if node == nil {
return ""
}
switch node.Type {
switch n := s.Get(0); n.Type {
case html.ElementNode, html.DoctypeNode:
return node.Data
return n.Data
default:
if node.Type >= 0 && int(node.Type) < len(nodeNames) {
return nodeNames[node.Type]
if n.Type >= 0 && int(n.Type) < len(nodeNames) {
return nodeNames[n.Type]
}
return ""
}