Last active
April 20, 2018 03:13
-
-
Save adrianmoses/7655322 to your computer and use it in GitHub Desktop.
goquery example
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 | |
/* | |
* Script that scrapes google front page | |
* Usage: ./google [<query>] | |
* e.g. ./google hacker news | |
*/ | |
import ( | |
"fmt" | |
"net/http" | |
"net/url" | |
"io" | |
"os" | |
"strings" | |
"github.com/PuerkitoBio/goquery" | |
) | |
func checkError(err error){ | |
if err != nil { | |
panic(err) | |
os.Exit(1) | |
} | |
} | |
func main() { | |
query := strings.Join(os.Args[1:], "+") | |
response, err := http.Get("http://google.com/search?q=" + query) | |
checkError(err) | |
defer response.Body.Close() | |
doc, err := goquery.NewDocumentFromReader(io.Reader(response.Body)) | |
checkError(err) | |
doc.Find("h3.r a").Each(func(i int, s *goquery.Selection) { | |
str, exists := s.Attr("href") | |
if exists { | |
u, err := url.Parse(str) | |
checkError(err) | |
m, _ := url.ParseQuery(u.RawQuery) | |
fmt.Println("\033[1;35m"+s.Text()+"\033[0m", m["q"][0]) | |
} else { | |
fmt.Println(s.Text()) | |
} | |
}) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment