Start a crawl

curl --request POST \
  --url https://api.hydrafetch.com/v1/web/crawl \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "url": "https://example.com",
  "limit": 100,
  "maxDepth": 2,
  "includePaths": [
    "^/blog/.*"
  ],
  "excludePaths": [
    "^/tag/.*"
  ],
  "allowSubdomains": false,
  "allowExternalLinks": false,
  "ignoreQueryParameters": false,
  "sitemap": "include",
  "scrapeOptions": {
    "formats": [
      "markdown"
    ],
    "onlyMainContent": true,
    "includeTags": [
      "<string>"
    ],
    "excludeTags": [
      "<string>"
    ],
    "removeBase64Images": true,
    "blockAds": true,
    "includeLinks": true,
    "renderJs": true,
    "waitFor": 15000,
    "timeout": 60500,
    "location": {
      "country": "us",
      "languages": [
        "en-US",
        "en"
      ]
    },
    "headers": {},
    "preferStructure": true,
    "maxAge": 302400000
  }
}
'

import requests

url = "https://api.hydrafetch.com/v1/web/crawl"

payload = {
    "url": "https://example.com",
    "limit": 100,
    "maxDepth": 2,
    "includePaths": ["^/blog/.*"],
    "excludePaths": ["^/tag/.*"],
    "allowSubdomains": False,
    "allowExternalLinks": False,
    "ignoreQueryParameters": False,
    "sitemap": "include",
    "scrapeOptions": {
        "formats": ["markdown"],
        "onlyMainContent": True,
        "includeTags": ["<string>"],
        "excludeTags": ["<string>"],
        "removeBase64Images": True,
        "blockAds": True,
        "includeLinks": True,
        "renderJs": True,
        "waitFor": 15000,
        "timeout": 60500,
        "location": {
            "country": "us",
            "languages": ["en-US", "en"]
        },
        "headers": {},
        "preferStructure": True,
        "maxAge": 302400000
    }
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: 'https://example.com',
    limit: 100,
    maxDepth: 2,
    includePaths: ['^/blog/.*'],
    excludePaths: ['^/tag/.*'],
    allowSubdomains: false,
    allowExternalLinks: false,
    ignoreQueryParameters: false,
    sitemap: 'include',
    scrapeOptions: {
      formats: ['markdown'],
      onlyMainContent: true,
      includeTags: ['<string>'],
      excludeTags: ['<string>'],
      removeBase64Images: true,
      blockAds: true,
      includeLinks: true,
      renderJs: true,
      waitFor: 15000,
      timeout: 60500,
      location: {country: 'us', languages: ['en-US', 'en']},
      headers: {},
      preferStructure: true,
      maxAge: 302400000
    }
  })
};

fetch('https://api.hydrafetch.com/v1/web/crawl', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hydrafetch.com/v1/web/crawl",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'url' => 'https://example.com',
    'limit' => 100,
    'maxDepth' => 2,
    'includePaths' => [
        '^/blog/.*'
    ],
    'excludePaths' => [
        '^/tag/.*'
    ],
    'allowSubdomains' => false,
    'allowExternalLinks' => false,
    'ignoreQueryParameters' => false,
    'sitemap' => 'include',
    'scrapeOptions' => [
        'formats' => [
                'markdown'
        ],
        'onlyMainContent' => true,
        'includeTags' => [
                '<string>'
        ],
        'excludeTags' => [
                '<string>'
        ],
        'removeBase64Images' => true,
        'blockAds' => true,
        'includeLinks' => true,
        'renderJs' => true,
        'waitFor' => 15000,
        'timeout' => 60500,
        'location' => [
                'country' => 'us',
                'languages' => [
                                'en-US',
                                'en'
                ]
        ],
        'headers' => [
                
        ],
        'preferStructure' => true,
        'maxAge' => 302400000
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.hydrafetch.com/v1/web/crawl"

	payload := strings.NewReader("{\n  \"url\": \"https://example.com\",\n  \"limit\": 100,\n  \"maxDepth\": 2,\n  \"includePaths\": [\n    \"^/blog/.*\"\n  ],\n  \"excludePaths\": [\n    \"^/tag/.*\"\n  ],\n  \"allowSubdomains\": false,\n  \"allowExternalLinks\": false,\n  \"ignoreQueryParameters\": false,\n  \"sitemap\": \"include\",\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"includeLinks\": true,\n    \"renderJs\": true,\n    \"waitFor\": 15000,\n    \"timeout\": 60500,\n    \"location\": {\n      \"country\": \"us\",\n      \"languages\": [\n        \"en-US\",\n        \"en\"\n      ]\n    },\n    \"headers\": {},\n    \"preferStructure\": true,\n    \"maxAge\": 302400000\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.hydrafetch.com/v1/web/crawl")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://example.com\",\n  \"limit\": 100,\n  \"maxDepth\": 2,\n  \"includePaths\": [\n    \"^/blog/.*\"\n  ],\n  \"excludePaths\": [\n    \"^/tag/.*\"\n  ],\n  \"allowSubdomains\": false,\n  \"allowExternalLinks\": false,\n  \"ignoreQueryParameters\": false,\n  \"sitemap\": \"include\",\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"includeLinks\": true,\n    \"renderJs\": true,\n    \"waitFor\": 15000,\n    \"timeout\": 60500,\n    \"location\": {\n      \"country\": \"us\",\n      \"languages\": [\n        \"en-US\",\n        \"en\"\n      ]\n    },\n    \"headers\": {},\n    \"preferStructure\": true,\n    \"maxAge\": 302400000\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.hydrafetch.com/v1/web/crawl")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"https://example.com\",\n  \"limit\": 100,\n  \"maxDepth\": 2,\n  \"includePaths\": [\n    \"^/blog/.*\"\n  ],\n  \"excludePaths\": [\n    \"^/tag/.*\"\n  ],\n  \"allowSubdomains\": false,\n  \"allowExternalLinks\": false,\n  \"ignoreQueryParameters\": false,\n  \"sitemap\": \"include\",\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"includeLinks\": true,\n    \"renderJs\": true,\n    \"waitFor\": 15000,\n    \"timeout\": 60500,\n    \"location\": {\n      \"country\": \"us\",\n      \"languages\": [\n        \"en-US\",\n        \"en\"\n      ]\n    },\n    \"headers\": {},\n    \"preferStructure\": true,\n    \"maxAge\": 302400000\n  }\n}"

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

{
  "crawlId": "019f3c09-6fae-740f-9257-10c2b6af7f43",
  "status": "queued"
}