Compare commits

...
10 Commits
5 changed files with 81 additions and 2 deletions
+1
View File
@@ -11,5 +11,6 @@ go:
- 1.8.x
- 1.9.x
- "1.10.x"
- 1.11.x
- tip
+16 -1
View File
@@ -37,6 +37,8 @@ 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.**
* **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).
* **2018-01-11 (v1.2.0)** : Add `AddBack*` and deprecate `AndSelf` (thanks to @davidjwilkins).
@@ -95,12 +97,24 @@ package main
import (
"fmt"
"log"
"net/http"
"github.com/PuerkitoBio/goquery"
)
func ExampleScrape() {
doc, err := goquery.NewDocument("http://metalsucks.net")
// Request the HTML page.
res, err := http.Get("http://metalsucks.net")
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
if res.StatusCode != 200 {
log.Fatalf("status code error: %d %s", res.StatusCode, res.Status)
}
// Load the HTML document
doc, err := goquery.NewDocumentFromReader(res.Body)
if err != nil {
log.Fatal(err)
}
@@ -126,6 +140,7 @@ func main() {
- [suntong/cascadia][cascadiacli], a command-line interface to the cascadia CSS selector library, useful to test selectors.
- [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.
## Support
+53 -1
View File
@@ -3,14 +3,27 @@ package goquery_test
import (
"fmt"
"log"
"net/http"
"os"
"strings"
"github.com/PuerkitoBio/goquery"
)
// This example scrapes the reviews shown on the home page of metalsucks.net.
func Example() {
// Request the HTML page.
res, err := http.Get("http://metalsucks.net")
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
if res.StatusCode != 200 {
log.Fatalf("status code error: %d %s", res.StatusCode, res.Status)
}
// Load the HTML document
doc, err := goquery.NewDocument("http://metalsucks.net")
doc, err := goquery.NewDocumentFromReader(res.Body)
if err != nil {
log.Fatal(err)
}
@@ -28,3 +41,42 @@ func Example() {
// xOutput: voluntarily fail the Example output.
}
// This example shows how to use NewDocumentFromReader from a file.
func ExampleNewDocumentFromReader_file() {
// create from a file
f, err := os.Open("some/file.html")
if err != nil {
log.Fatal(err)
}
defer f.Close()
doc, err := goquery.NewDocumentFromReader(f)
if err != nil {
log.Fatal(err)
}
// use the goquery document...
_ = doc.Find("h1")
}
// This example shows how to use NewDocumentFromReader from a string.
func ExampleNewDocumentFromReader_string() {
// create from a string
data := `
<html>
<head>
<title>My document</title>
</head>
<body>
<h1>Header</h1>
</body>
</html>`
doc, err := goquery.NewDocumentFromReader(strings.NewReader(data))
if err != nil {
log.Fatal(err)
}
header := doc.Find("h1").Text()
fmt.Println(header)
// Output: Header
}
+6
View File
@@ -0,0 +1,6 @@
module github.com/PuerkitoBio/goquery
require (
github.com/andybalholm/cascadia v1.0.0
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a
)
+5
View File
@@ -0,0 +1,5 @@
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 v0.0.0-20181114220301-adae6a3d119a h1:gOpx8G595UYyvj8UK4+OFyY4rx037g3fmfhe5SasG3U=
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=