Forcing Timeouts
WebScrapingAPI allows you to adjust the timeout value in order to obtain lazy loaded content.
When dealing with websites that require longer load time for the full DOM, WebScrapingAPI's default timeout value may result in returning only the portion of the DOM that was gathered until the timeout was triggered.
In that particular case, if you notice that the response from our API only includes fractions of the DOM, you may want to tweak the load time by passing the
timeout=$value
parameter.Your full GET request should then be sent to the following address:
https://api.webscrapingapi.com/v1?api_key=<YOUR_API_KEY>&url=<TARGETED_URL>&timeout=$value
cURL
NodeJS
Python
PHP
Golang
Java
.NET
Ruby
curl --request GET --url "https://api.webscrapingapi.com/v1?api_key=<YOUR_API_KEY>&url=https://httpbin.org/get&timeout=200"
const http = require("https");
const options = {
"method": "GET",
"hostname": "api.webscrapingapi.com",
"port": null,
"path": "/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200",
"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 requests
API_KEY = '<YOUR_API_KEY>'
SCRAPER_URL = 'https://api.webscrapingapi.com/v1'
TARGET_URL = 'https://httpbin.org/'
PARAMS = {
"api_key":API_KEY,
"url": TARGET_URL,
"timeout":200
}
response = requests.get(SCRAPER_URL, params=PARAMS)
print(response)
<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.webscrapingapi.com/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200",
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://api.webscrapingapi.com/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200"
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))
}
HttpResponse<String> response = Unirest.get("https://api.webscrapingapi.com/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200")
.asString();
var client = new RestClient("https://api.webscrapingapi.com/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);
require 'uri'
require 'net/http'
require 'openssl'
url = URI("https://api.webscrapingapi.com/v1?api_key=%7B%7Bapi_key%7D%7D&url=https%3A%2F%2Fhttpbin.org%2Fget&timeout=200")
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
Important! The
url
parameter has to be encoded. ( i.e. &url=https%3A%2F%2Fwww.webscrapingapi.com%2F ){
"status": "Failure",
"status_code": 422,
"created_at": "2022-04-26T11:57:23.242Z",
"processed_at": "2022-04-26T11:57:23.739Z",
"time_taken": {
"total": 0.701,
"scraping": 0.202,
"setup_worker": 0.403
},
"error": "The target page took more than 0.2 seconds to load, the website might be down. Retry the request or increase the value of 'timeout' parameter.",
"page_content": null
}
Last modified 7mo ago