JSON Auto Parser

Using the auto_parser parameter, you can get the scraped site in JSON format.

Auto Parser can be applied with both JavaScript rendering enabled or disabled.

JSON Auto Parser examples

GET https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1

⇡ Input

curl --request GET --url "https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1"

const http = require("https");

const options = {
  "method": "GET",
  "hostname": "scrape.shifter.io",
  "port": null,
  "path": "/v1?api_key=api_key&url=https://example.com&auto_parser=1",
  "headers": {}
};

const req = http.request(options, function (res) {
  const chunks = [];

  res.on("data", function (chunk) {
    chunks.push(chunk);
  });

  res.on("end", function () {
    const body = Buffer.concat(chunks);
    console.log(body.toString());
  });
});

req.end();

import http.client

conn = http.client.HTTPSConnection("scrape.shifter.io")

conn.request("GET", "/v1?api_key=api_key&url=https://example.com&auto_parser=1")

res = conn.getresponse()
data = res.read()

print(data.decode("utf-8"))

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io/ioutil"
)

func main() {

	url := "https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := ioutil.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}

var client = new RestClient("https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);

require 'uri'
require 'net/http'
require 'openssl'

url = URI("https://scrape.shifter.io/v1?api_key=api_key&url=https://example.com&auto_parser=1")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
http.verify_mode = OpenSSL::SSL::VERIFY_NONE

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

⇣ Output

{"0":{"tagName":"div","children":{"0":{"tagName":"h1","text":"Example Domain"},"1":{"tagName":"p","text":"This domain is for use in illustrative examples in documents. You may use this\n    domain in literature without prior coordination or asking for permission."},"2":{"tagName":"p","text":"More information...","children":{"0":{"tagName":"a","attributes":{"href":"https://www.iana.org/domains/example"},"text":"More information..."}}}}}}

PreviousExtraction Rules NextJavascript Instructions

Last updated 2 years ago

Was this helpful?