Crawl erstellen

Starte einen neuen Crawl

curl --request POST \
  --url https://api.olostep.com/v1/crawls \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "start_url": "<string>",
  "max_pages": 123,
  "include_urls": [
    "<string>"
  ],
  "exclude_urls": [
    "<string>"
  ],
  "max_depth": 123,
  "include_external": true,
  "include_subdomain": true,
  "search_query": "<string>",
  "top_n": 123,
  "webhook": "<string>",
  "timeout": 123,
  "follow_robots_txt": true,
  "scrape_options": {
    "formats": [
      "markdown",
      "screenshot"
    ],
    "parser": "@olostep/extract-emails"
  }
}
'

import requests

url = "https://api.olostep.com/v1/crawls"

payload = {
    "start_url": "<string>",
    "max_pages": 123,
    "include_urls": ["<string>"],
    "exclude_urls": ["<string>"],
    "max_depth": 123,
    "include_external": True,
    "include_subdomain": True,
    "search_query": "<string>",
    "top_n": 123,
    "webhook": "<string>",
    "timeout": 123,
    "follow_robots_txt": True,
    "scrape_options": {
        "formats": ["markdown", "screenshot"],
        "parser": "@olostep/extract-emails"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    start_url: '<string>',
    max_pages: 123,
    include_urls: ['<string>'],
    exclude_urls: ['<string>'],
    max_depth: 123,
    include_external: true,
    include_subdomain: true,
    search_query: '<string>',
    top_n: 123,
    webhook: '<string>',
    timeout: 123,
    follow_robots_txt: true,
    scrape_options: {formats: ['markdown', 'screenshot'], parser: '@olostep/extract-emails'}
  })
};

fetch('https://api.olostep.com/v1/crawls', 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.olostep.com/v1/crawls",
  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([
    'start_url' => '<string>',
    'max_pages' => 123,
    'include_urls' => [
        '<string>'
    ],
    'exclude_urls' => [
        '<string>'
    ],
    'max_depth' => 123,
    'include_external' => true,
    'include_subdomain' => true,
    'search_query' => '<string>',
    'top_n' => 123,
    'webhook' => '<string>',
    'timeout' => 123,
    'follow_robots_txt' => true,
    'scrape_options' => [
        'formats' => [
                'markdown',
                'screenshot'
        ],
        'parser' => '@olostep/extract-emails'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.olostep.com/v1/crawls"

	payload := strings.NewReader("{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.olostep.com/v1/crawls")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.olostep.com/v1/crawls")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}"

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

{
  "id": "<string>",
  "object": "<string>",
  "status": "<string>",
  "created": 123,
  "start_date": "<string>",
  "start_url": "<string>",
  "max_pages": 123,
  "max_depth": 123,
  "exclude_urls": [
    "<string>"
  ],
  "include_urls": [
    "<string>"
  ],
  "include_external": true,
  "search_query": "<string>",
  "top_n": 123,
  "current_depth": 123,
  "pages_count": 123,
  "webhook": "<string>",
  "follow_robots_txt": true,
  "credits_consumed": 123,
  "cost_usd": 123
}

POST

crawls

Starte einen neuen Crawl

curl --request POST \
  --url https://api.olostep.com/v1/crawls \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "start_url": "<string>",
  "max_pages": 123,
  "include_urls": [
    "<string>"
  ],
  "exclude_urls": [
    "<string>"
  ],
  "max_depth": 123,
  "include_external": true,
  "include_subdomain": true,
  "search_query": "<string>",
  "top_n": 123,
  "webhook": "<string>",
  "timeout": 123,
  "follow_robots_txt": true,
  "scrape_options": {
    "formats": [
      "markdown",
      "screenshot"
    ],
    "parser": "@olostep/extract-emails"
  }
}
'

import requests

url = "https://api.olostep.com/v1/crawls"

payload = {
    "start_url": "<string>",
    "max_pages": 123,
    "include_urls": ["<string>"],
    "exclude_urls": ["<string>"],
    "max_depth": 123,
    "include_external": True,
    "include_subdomain": True,
    "search_query": "<string>",
    "top_n": 123,
    "webhook": "<string>",
    "timeout": 123,
    "follow_robots_txt": True,
    "scrape_options": {
        "formats": ["markdown", "screenshot"],
        "parser": "@olostep/extract-emails"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    start_url: '<string>',
    max_pages: 123,
    include_urls: ['<string>'],
    exclude_urls: ['<string>'],
    max_depth: 123,
    include_external: true,
    include_subdomain: true,
    search_query: '<string>',
    top_n: 123,
    webhook: '<string>',
    timeout: 123,
    follow_robots_txt: true,
    scrape_options: {formats: ['markdown', 'screenshot'], parser: '@olostep/extract-emails'}
  })
};

fetch('https://api.olostep.com/v1/crawls', 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.olostep.com/v1/crawls",
  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([
    'start_url' => '<string>',
    'max_pages' => 123,
    'include_urls' => [
        '<string>'
    ],
    'exclude_urls' => [
        '<string>'
    ],
    'max_depth' => 123,
    'include_external' => true,
    'include_subdomain' => true,
    'search_query' => '<string>',
    'top_n' => 123,
    'webhook' => '<string>',
    'timeout' => 123,
    'follow_robots_txt' => true,
    'scrape_options' => [
        'formats' => [
                'markdown',
                'screenshot'
        ],
        'parser' => '@olostep/extract-emails'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.olostep.com/v1/crawls"

	payload := strings.NewReader("{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.olostep.com/v1/crawls")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.olostep.com/v1/crawls")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"start_url\": \"<string>\",\n  \"max_pages\": 123,\n  \"include_urls\": [\n    \"<string>\"\n  ],\n  \"exclude_urls\": [\n    \"<string>\"\n  ],\n  \"max_depth\": 123,\n  \"include_external\": true,\n  \"include_subdomain\": true,\n  \"search_query\": \"<string>\",\n  \"top_n\": 123,\n  \"webhook\": \"<string>\",\n  \"timeout\": 123,\n  \"follow_robots_txt\": true,\n  \"scrape_options\": {\n    \"formats\": [\n      \"markdown\",\n      \"screenshot\"\n    ],\n    \"parser\": \"@olostep/extract-emails\"\n  }\n}"

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

{
  "id": "<string>",
  "object": "<string>",
  "status": "<string>",
  "created": 123,
  "start_date": "<string>",
  "start_url": "<string>",
  "max_pages": 123,
  "max_depth": 123,
  "exclude_urls": [
    "<string>"
  ],
  "include_urls": [
    "<string>"
  ],
  "include_external": true,
  "search_query": "<string>",
  "top_n": 123,
  "current_depth": 123,
  "pages_count": 123,
  "webhook": "<string>",
  "follow_robots_txt": true,
  "credits_consumed": 123,
  "cost_usd": 123
}

Benachrichtigung bei Abschluss: Übergebe den webhook-Parameter mit deiner Endpoint-URL, um einen HTTP POST zu erhalten, wenn der Crawl abgeschlossen ist. Siehe Webhooks für Details.

Autorisierungen

Authorization

string

header

erforderlich

Bearer-Authentifizierungsheader in der Form Bearer , wobei dein Authentifizierungstoken ist.

Body

application/json

start_url

string

erforderlich

Der Startpunkt des Crawls.

max_pages

number

erforderlich

Maximale Anzahl von Seiten, die gecrawlt werden sollen. Empfohlen für die meisten Anwendungsfälle wie das Crawlen einer gesamten Website.

include_urls

string[]

URL-Pfadmuster, die im Crawl mit Glob-Syntax eingeschlossen werden sollen. Standardmäßig /**, was alle URLs einschließt. Verwende Muster wie /blog/**, um spezifische Abschnitte zu crawlen (z.B. nur Blog-Seiten), /products/*.html für Produktseiten oder mehrere Muster für verschiedene Abschnitte. Unterstützt Standard-Glob-Funktionen wie * (beliebige Zeichen) und ** (rekursives Matching).

exclude_urls

string[]

URL-Pfadnamen im Glob-Muster, die ausgeschlossen werden sollen. Zum Beispiel: /careers/**. Ausgeschlossene URLs haben Vorrang vor eingeschlossenen URLs.

max_depth

number

Maximale Tiefe des Crawls. Nützlich, um nur bis zu n-Grad von Links zu extrahieren.

include_external

boolean

Crawl von externen Links ersten Grades.

include_subdomain

boolean

Einbeziehen von Subdomains der Website. Standardmäßig false.

search_query

string

Eine optionale Suchanfrage, um spezifische Links zu finden und die Ergebnisse nach Relevanz zu sortieren.

top_n

number

Eine optionale Zahl, um nur die Top N relevantesten Links auf jeder Seite gemäß der Suchanfrage zu crawlen.

webhook

string<uri>

HTTPS-URL, um eine POST-Anfrage zu erhalten, wenn der Crawl abgeschlossen ist. Muss eine öffentlich zugängliche URL mit dem Protokoll http:// oder https:// sein. Kann nicht auf localhost oder private IP-Adressen verweisen. Siehe Webhooks für das Payload-Format und das Wiederholungsverhalten.

timeout

number

Beende den Crawl nach n Sekunden mit den bis dahin abgeschlossenen Seiten. Kann ~10s extra von der angegebenen Timeout-Zeit in Anspruch nehmen.

follow_robots_txt

boolean

Standard:true

Ob die Regeln von robots.txt beachtet werden sollen. Wenn auf false gesetzt, wird der Crawler die Website unabhängig von den Disallow-Direktiven in robots.txt scrapen. Standardmäßig true.

scrape_options

object

Steuert, was jede einzelne Seitenabfrage von der Olostep-API anfordert. Alle Felder sind optional.

Show child attributes

Antwort

Crawl erfolgreich gestartet.

string

Crawl-ID

object

string

Die Art des Objekts. "crawl" für diesen Endpunkt.

status

string

in_progress oder completed

created

number

Erstellungszeit im Epoch-Format

start_date

string

Erstellungszeit im Datumsformat

start_url

string

max_pages

number

max_depth

number

exclude_urls

string[]

include_urls

string[]

include_external

boolean

search_query

string

top_n

number

current_depth

number

Die aktuelle Tiefe des Crawl-Prozesses.

pages_count

number

Anzahl der gecrawlten Seiten

webhook

string

follow_robots_txt

boolean

credits_consumed

integer | null

Anzahl der durch diese Anfrage verbrauchten Credits. Wird nach Abschluss der Ausführung ausgefüllt. Credits sind die Grundlage für die Abrechnung.

cost_usd

number | null

Geschätzte Kosten in USD für diese Anfrage. Wird nach Abschluss der Ausführung ausgefüllt. Berechnet aus den verbrauchten Credits und deinem Tarif — 99% genau, aber credits_consumed ist der maßgebliche Wert.

Batch-Elemente Crawl-Informationen

Allgemein

Abschürfungen

Chargen

Durchläufe

Karten

Antworten

Suche

Monitore

Dateien

Zeitpläne

Abrufen

Kontostand & Abrechnung

Autorisierungen

Body

Antwort