API Веб-скрейпинг
Получайте общедоступные веб-страницы и документы в формате HTML, Markdown, текста для LLM или обычного текста: по одной странице, пакетами или обходом всего сайта. Используйте этот справочник, чтобы выбрать нужный эндпоинт и точно увидеть, что он возвращает.
Операции
POST /v1/scrape
POST
/v1/scrape
Кредиты: 1-20/item
Параметры тела запроса
| Параметр | Тип | обязателен |
|---|---|---|
| url | string | обязателен |
| mode |
string
Допустимые значения
standardresilientrenderedrendered_resilient
По умолчанию
standard
|
опционально |
| output |
string
Допустимые значения
htmltextmarkdownllm
По умолчанию
html
|
опционально |
| only_main_content |
boolean
По умолчанию
false
|
опционально |
| include_selectors | string[] | опционально |
| exclude_selectors | string[] | опционально |
| links |
boolean
По умолчанию
false
|
опционально |
| headers | object | опционально |
| cookies | object | опционально |
Поля ответа
| Поле | Тип |
|---|---|
data |
object |
data.url |
string |
data.final_url |
string |
data.status |
integer | null |
data.outcome |
string |
data.content_type |
string | null |
data.content |
string |
data.bytes |
integer |
data.truncated |
boolean |
data.redirect_count |
integer |
data.attempt_count |
integer |
data.duration_ms |
integer |
data.fetched_at |
string |
data.headers |
object |
data.rendered |
boolean |
data.links[] |
object[] |
data.links[] |
object |
data.links[].url |
string |
data.links[].text |
string |
data.document |
object |
data.document.kind |
string |
data.document.title |
string | null |
data.document.pages |
integer | null |
data.document.sheets[] |
string[] |
data.document.truncated |
boolean |
data.document.error |
string |
data.depth |
integer |
data.forwarded |
object |
data.forwarded.header_names[] |
string[] |
data.forwarded.cookie_names[] |
string[] |
data.forwarded.scope |
string |
billing |
object |
billing.credits_charged |
integer |
billing.credits_refunded |
integer |
billing.credits_per_item |
integer |
billing.credits_net |
integer |
billing.policy |
string |
Пример запроса
curl -X POST "https://domscan.net/v1/scrape" \
-H "Content-Type: application/json" \
-H "X-API-Key: $DOMSCAN_API_KEY" \
-d '{
"url": "https://example.com/",
"mode": "standard",
"output": "markdown"
}'const response = await fetch("https://domscan.net/v1/scrape", {
method: "POST",
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY, "Content-Type": "application/json" },
body: JSON.stringify({
"url": "https://example.com/",
"mode": "standard",
"output": "markdown"
}),
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.post(
"https://domscan.net/v1/scrape",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
json={
"url": "https://example.com/",
"mode": "standard",
"output": "markdown",
},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader(`{
"url": "https://example.com/",
"mode": "standard",
"output": "markdown"
}`)
req, err := http.NewRequest(http.MethodPost, "https://domscan.net/v1/scrape", body)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/scrape")
request = Net::HTTP::Post.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
request["Content-Type"] = "application/json"
request.body = JSON.generate({
"url" => "https://example.com/",
"mode" => "standard",
"output" => "markdown"
})
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"data": {
"url": "https://example.com",
"final_url": "https://example.com",
"status": 1,
"outcome": "success",
"content_type": "domain",
"content": "example",
"bytes": 1,
"truncated": false,
"redirect_count": 1,
"attempt_count": 1,
"duration_ms": 1,
"fetched_at": "2026-08-27T12:00:00Z",
"headers": {},
"rendered": false,
"links": [
{
"url": "https://example.com",
"text": "example"
}
],
"document": {
"kind": "pdf",
"title": "example",
"pages": 1,
"sheets": [
"example"
],
"truncated": false,
"error": "DOCUMENT_UNREADABLE"
},
"depth": 1,
"forwarded": {
"header_names": [
"example"
],
"cookie_names": [
"example"
],
"scope": "requested_origin"
}
},
"billing": {
"credits_charged": 1,
"credits_refunded": 1,
"credits_per_item": 1,
"credits_net": 1,
"policy": "effort_based"
}
}
Коды состояния HTTP
200OK400Неверный запрос401Не авторизован402Требуется оплата403Доступ запрещен409HTTP 409422HTTP 422429Слишком много запросов503Сервис недоступен
POST /v1/scrape/jobs
POST
/v1/scrape/jobs
Кредиты: 1-20/item
Параметры тела запроса
| Параметр | Тип | обязателен |
|---|---|---|
| notify_webhook | unknown | опционально |
| mode |
string
Допустимые значения
standardresilientrenderedrendered_resilient
По умолчанию
standard
|
опционально |
| output |
string
Допустимые значения
htmltextmarkdownllm
По умолчанию
html
|
опционально |
| urls | unknown[] | обязателен |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.mode |
string |
job.output |
string |
job.total |
integer |
job.counts |
object |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.billing |
object |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_per_item |
integer |
job.billing.credits_net |
integer |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
idempotent_replay |
boolean |
Пример запроса
curl -X POST "https://domscan.net/v1/scrape/jobs" \
-H "Content-Type: application/json" \
-H "X-API-Key: $DOMSCAN_API_KEY" \
-d '{
"mode": "resilient",
"output": "text",
"urls": [
"https://example.com/",
{
"url": "https://example.org/",
"reference": "page-2"
}
]
}'const response = await fetch("https://domscan.net/v1/scrape/jobs", {
method: "POST",
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY, "Content-Type": "application/json" },
body: JSON.stringify({
"mode": "resilient",
"output": "text",
"urls": [
"https://example.com/",
{
"url": "https://example.org/",
"reference": "page-2"
}
]
}),
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.post(
"https://domscan.net/v1/scrape/jobs",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
json={
"mode": "resilient",
"output": "text",
"urls": [
"https://example.com/",
{
"url": "https://example.org/",
"reference": "page-2",
},
],
},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader(`{
"mode": "resilient",
"output": "text",
"urls": [
"https://example.com/",
{
"url": "https://example.org/",
"reference": "page-2"
}
]
}`)
req, err := http.NewRequest(http.MethodPost, "https://domscan.net/v1/scrape/jobs", body)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/scrape/jobs")
request = Net::HTTP::Post.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
request["Content-Type"] = "application/json"
request.body = JSON.generate({
"mode" => "resilient",
"output" => "text",
"urls" => [
"https://example.com/",
{
"url" => "https://example.org/",
"reference" => "page-2"
}
]
})
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"mode": "standard",
"output": "html",
"total": 1,
"counts": {
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1
},
"billing": {
"credits_charged": 1,
"credits_refunded": 1,
"credits_per_item": 1,
"credits_net": 1,
"policy": "effort_based"
},
"status_url": "https://example.com",
"results_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
},
"idempotent_replay": false
}
Коды состояния HTTP
202Принято400Неверный запрос401Не авторизован402Требуется оплата403Доступ запрещен409HTTP 409429Слишком много запросов503Сервис недоступен
GET /v1/scrape/jobs/:job_id
GET
/v1/scrape/jobs/:job_id
Кредиты: 0
Параметры запроса
| Параметр | Тип | обязателен |
|---|---|---|
| job_id | string | обязателен |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.mode |
string |
job.output |
string |
job.total |
integer |
job.counts |
object |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.billing |
object |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_per_item |
integer |
job.billing.credits_net |
integer |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
Пример запроса
curl -H "X-API-Key: $DOMSCAN_API_KEY" "https://domscan.net/v1/scrape/jobs/example"const response = await fetch("https://domscan.net/v1/scrape/jobs/example", {
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY },
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.get(
"https://domscan.net/v1/scrape/jobs/example",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
)
func main() {
req, err := http.NewRequest(http.MethodGet, "https://domscan.net/v1/scrape/jobs/example", nil)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/scrape/jobs/example")
request = Net::HTTP::Get.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"mode": "standard",
"output": "html",
"total": 1,
"counts": {
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1
},
"billing": {
"credits_charged": 1,
"credits_refunded": 1,
"credits_per_item": 1,
"credits_net": 1,
"policy": "effort_based"
},
"status_url": "https://example.com",
"results_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
}
}
Коды состояния HTTP
200OK401Не авторизован404Не найдено429Слишком много запросов
GET /v1/scrape/jobs/:job_id/results
GET
/v1/scrape/jobs/:job_id/results
Кредиты: 0
Параметры запроса
| Параметр | Тип | обязателен |
|---|---|---|
| job_id | string | обязателен |
| limit |
integer
По умолчанию
20
|
опционально |
| offset |
integer
По умолчанию
0
|
опционально |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.mode |
string |
job.output |
string |
job.total |
integer |
job.counts |
object |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.billing |
object |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_per_item |
integer |
job.billing.credits_net |
integer |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
results[] |
object[] |
results[] |
object |
results[].index |
integer |
results[].url |
string |
results[].reference |
string |
results[].status |
string |
results[].data |
object |
results[].data.url |
string |
results[].data.final_url |
string |
results[].data.status |
integer | null |
results[].data.outcome |
string |
results[].data.content_type |
string | null |
results[].data.content |
string |
results[].data.bytes |
integer |
results[].data.truncated |
boolean |
results[].data.redirect_count |
integer |
results[].data.attempt_count |
integer |
results[].data.duration_ms |
integer |
results[].data.fetched_at |
string |
results[].data.headers |
object |
results[].data.rendered |
boolean |
results[].data.links[] |
object[] |
results[].data.links[] |
object |
results[].data.links[].url |
string |
results[].data.links[].text |
string |
results[].data.document |
object |
results[].data.document.kind |
string |
results[].data.document.title |
string | null |
results[].data.document.pages |
integer | null |
results[].data.document.sheets[] |
string[] |
results[].data.document.truncated |
boolean |
results[].data.document.error |
string |
results[].data.depth |
integer |
results[].data.forwarded |
object |
results[].data.forwarded.header_names[] |
string[] |
results[].data.forwarded.cookie_names[] |
string[] |
results[].data.forwarded.scope |
string |
results[].billing |
object |
results[].billing.credits_charged |
integer |
results[].billing.credits_refunded |
integer |
results[].billing.credits_per_item |
integer |
results[].billing.credits_net |
integer |
results[].billing.policy |
string |
pagination |
object |
Пример запроса
curl -H "X-API-Key: $DOMSCAN_API_KEY" "https://domscan.net/v1/scrape/jobs/example/results?limit=25&offset=0"const response = await fetch("https://domscan.net/v1/scrape/jobs/example/results?limit=25&offset=0", {
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY },
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.get(
"https://domscan.net/v1/scrape/jobs/example/results?limit=25&offset=0",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
)
func main() {
req, err := http.NewRequest(http.MethodGet, "https://domscan.net/v1/scrape/jobs/example/results?limit=25&offset=0", nil)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/scrape/jobs/example/results?limit=25&offset=0")
request = Net::HTTP::Get.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"mode": "standard",
"output": "html",
"total": 1,
"counts": {
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1
},
"billing": {
"credits_charged": 1,
"credits_refunded": 1,
"credits_per_item": 1,
"credits_net": 1,
"policy": "effort_based"
},
"status_url": "https://example.com",
"results_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
},
"results": [
{
"index": 1,
"url": "https://example.com",
"reference": "example",
"status": "pending",
"data": {
"url": "https://example.com",
"final_url": "https://example.com",
"status": 1,
"outcome": "success",
"content_type": "domain",
"content": "example",
"bytes": 1,
"truncated": false,
"redirect_count": 1,
"attempt_count": 1,
"duration_ms": 1,
"fetched_at": "2026-08-27T12:00:00Z",
"headers": {},
"rendered": false,
"links": [
{
"url": "https://example.com",
"text": "example"
}
],
"document": {
"kind": "pdf",
"title": "example",
"pages": 1,
"sheets": [
"example"
],
"truncated": false,
"error": "DOCUMENT_UNREADABLE"
},
"depth": 1,
"forwarded": {
"header_names": [
"example"
],
"cookie_names": [
"example"
],
"scope": "requested_origin"
}
},
"billing": {
"credits_charged": 1,
"credits_refunded": 1,
"credits_per_item": 1,
"credits_net": 1,
"policy": "effort_based"
}
}
],
"pagination": {}
}
Коды состояния HTTP
200OK400Неверный запрос401Не авторизован404Не найдено410HTTP 410429Слишком много запросов
POST /v1/crawl/jobs
POST
/v1/crawl/jobs
Кредиты: 1-20/item
Параметры тела запроса
| Параметр | Тип | обязателен |
|---|---|---|
| url | string | обязателен |
| max_pages |
integer
По умолчанию
25
|
опционально |
| max_depth |
integer
По умолчанию
3
|
опционально |
| include_paths | string[] | опционально |
| exclude_paths | string[] | опционально |
| allow_subdomains |
boolean
По умолчанию
false
|
опционально |
| ignore_query_parameters |
boolean
По умолчанию
false
|
опционально |
| use_sitemap |
boolean
По умолчанию
true
|
опционально |
| mode |
string
Допустимые значения
standardresilientrenderedrendered_resilient
По умолчанию
standard
|
опционально |
| output |
string
Допустимые значения
htmltextmarkdownllm
По умолчанию
markdown
|
опционально |
| only_main_content |
boolean
По умолчанию
false
|
опционально |
| include_selectors | string[] | опционально |
| exclude_selectors | string[] | опционально |
| links |
boolean
По умолчанию
false
|
опционально |
| notify_webhook | unknown | опционально |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.url |
string |
job.mode |
string |
job.output |
string |
job.options |
object |
job.options.max_pages |
integer |
job.options.max_depth |
integer |
job.options.include_paths[] |
string[] |
job.options.exclude_paths[] |
string[] |
job.options.allow_subdomains |
boolean |
job.options.ignore_query_parameters |
boolean |
job.options.use_sitemap |
boolean |
job.options.only_main_content |
boolean |
job.options.include_selectors[] |
string[] |
job.options.exclude_selectors[] |
string[] |
job.options.links |
boolean |
job.counts |
object |
job.counts.queued |
integer |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.counts.cancelled |
integer |
job.robots_txt |
string | null |
job.stop_reason |
string | null |
job.billing |
object |
job.billing.credits_per_page |
integer |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_net |
integer |
job.billing.credits_due |
integer |
job.billing.settled |
boolean |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.cancel_url |
string | null |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
idempotent_replay |
boolean |
Пример запроса
curl -X POST "https://domscan.net/v1/crawl/jobs" \
-H "Content-Type: application/json" \
-H "X-API-Key: $DOMSCAN_API_KEY" \
-d '{
"url": "https://example.com/docs/",
"max_pages": 50,
"max_depth": 3,
"include_paths": [
"/docs/**"
],
"output": "llm",
"only_main_content": true
}'const response = await fetch("https://domscan.net/v1/crawl/jobs", {
method: "POST",
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY, "Content-Type": "application/json" },
body: JSON.stringify({
"url": "https://example.com/docs/",
"max_pages": 50,
"max_depth": 3,
"include_paths": [
"/docs/**"
],
"output": "llm",
"only_main_content": true
}),
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.post(
"https://domscan.net/v1/crawl/jobs",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
json={
"url": "https://example.com/docs/",
"max_pages": 50,
"max_depth": 3,
"include_paths": [
"/docs/**",
],
"output": "llm",
"only_main_content": True,
},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader(`{
"url": "https://example.com/docs/",
"max_pages": 50,
"max_depth": 3,
"include_paths": [
"/docs/**"
],
"output": "llm",
"only_main_content": true
}`)
req, err := http.NewRequest(http.MethodPost, "https://domscan.net/v1/crawl/jobs", body)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/crawl/jobs")
request = Net::HTTP::Post.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
request["Content-Type"] = "application/json"
request.body = JSON.generate({
"url" => "https://example.com/docs/",
"max_pages" => 50,
"max_depth" => 3,
"include_paths" => [
"/docs/**"
],
"output" => "llm",
"only_main_content" => true
})
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"url": "https://example.com",
"mode": "standard",
"output": "html",
"options": {
"max_pages": 1,
"max_depth": 1,
"include_paths": [
"example"
],
"exclude_paths": [
"example"
],
"allow_subdomains": false,
"ignore_query_parameters": false,
"use_sitemap": false,
"only_main_content": false,
"include_selectors": [
"example"
],
"exclude_selectors": [
"example"
],
"links": false
},
"counts": {
"queued": 1,
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1,
"cancelled": 1
},
"billing": {
"credits_per_page": 1,
"credits_charged": 1,
"credits_refunded": 1,
"credits_net": 1,
"credits_due": 1,
"settled": false,
"policy": "effort_based"
},
"robots_txt": "rules",
"stop_reason": "exhausted",
"status_url": "https://example.com",
"results_url": "https://example.com",
"cancel_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
},
"idempotent_replay": false
}
Коды состояния HTTP
202Принято400Неверный запрос401Не авторизован402Требуется оплата403Доступ запрещен409HTTP 409429Слишком много запросов503Сервис недоступен
GET /v1/crawl/jobs/:job_id
GET
/v1/crawl/jobs/:job_id
Кредиты: 0
Параметры запроса
| Параметр | Тип | обязателен |
|---|---|---|
| job_id | string | обязателен |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.url |
string |
job.mode |
string |
job.output |
string |
job.options |
object |
job.options.max_pages |
integer |
job.options.max_depth |
integer |
job.options.include_paths[] |
string[] |
job.options.exclude_paths[] |
string[] |
job.options.allow_subdomains |
boolean |
job.options.ignore_query_parameters |
boolean |
job.options.use_sitemap |
boolean |
job.options.only_main_content |
boolean |
job.options.include_selectors[] |
string[] |
job.options.exclude_selectors[] |
string[] |
job.options.links |
boolean |
job.counts |
object |
job.counts.queued |
integer |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.counts.cancelled |
integer |
job.robots_txt |
string | null |
job.stop_reason |
string | null |
job.billing |
object |
job.billing.credits_per_page |
integer |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_net |
integer |
job.billing.credits_due |
integer |
job.billing.settled |
boolean |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.cancel_url |
string | null |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
Пример запроса
curl -H "X-API-Key: $DOMSCAN_API_KEY" "https://domscan.net/v1/crawl/jobs/example"const response = await fetch("https://domscan.net/v1/crawl/jobs/example", {
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY },
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.get(
"https://domscan.net/v1/crawl/jobs/example",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
)
func main() {
req, err := http.NewRequest(http.MethodGet, "https://domscan.net/v1/crawl/jobs/example", nil)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/crawl/jobs/example")
request = Net::HTTP::Get.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"url": "https://example.com",
"mode": "standard",
"output": "html",
"options": {
"max_pages": 1,
"max_depth": 1,
"include_paths": [
"example"
],
"exclude_paths": [
"example"
],
"allow_subdomains": false,
"ignore_query_parameters": false,
"use_sitemap": false,
"only_main_content": false,
"include_selectors": [
"example"
],
"exclude_selectors": [
"example"
],
"links": false
},
"counts": {
"queued": 1,
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1,
"cancelled": 1
},
"billing": {
"credits_per_page": 1,
"credits_charged": 1,
"credits_refunded": 1,
"credits_net": 1,
"credits_due": 1,
"settled": false,
"policy": "effort_based"
},
"robots_txt": "rules",
"stop_reason": "exhausted",
"status_url": "https://example.com",
"results_url": "https://example.com",
"cancel_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
}
}
Коды состояния HTTP
200OK401Не авторизован404Не найдено429Слишком много запросов
GET /v1/crawl/jobs/:job_id/results
GET
/v1/crawl/jobs/:job_id/results
Кредиты: 0
Параметры запроса
| Параметр | Тип | обязателен |
|---|---|---|
| job_id | string | обязателен |
| limit |
integer
По умолчанию
20
|
опционально |
| offset |
integer
По умолчанию
0
|
опционально |
Поля ответа
| Поле | Тип |
|---|---|
job |
object |
job.id |
string |
job.status |
string |
job.url |
string |
job.mode |
string |
job.output |
string |
job.options |
object |
job.options.max_pages |
integer |
job.options.max_depth |
integer |
job.options.include_paths[] |
string[] |
job.options.exclude_paths[] |
string[] |
job.options.allow_subdomains |
boolean |
job.options.ignore_query_parameters |
boolean |
job.options.use_sitemap |
boolean |
job.options.only_main_content |
boolean |
job.options.include_selectors[] |
string[] |
job.options.exclude_selectors[] |
string[] |
job.options.links |
boolean |
job.counts |
object |
job.counts.queued |
integer |
job.counts.pending |
integer |
job.counts.processing |
integer |
job.counts.succeeded |
integer |
job.counts.failed |
integer |
job.counts.cancelled |
integer |
job.robots_txt |
string | null |
job.stop_reason |
string | null |
job.billing |
object |
job.billing.credits_per_page |
integer |
job.billing.credits_charged |
integer |
job.billing.credits_refunded |
integer |
job.billing.credits_net |
integer |
job.billing.credits_due |
integer |
job.billing.settled |
boolean |
job.billing.policy |
string |
job.status_url |
string |
job.results_url |
string |
job.cancel_url |
string | null |
job.poll_after_ms |
integer | null |
job.created_at |
string |
job.started_at |
string | null |
job.completed_at |
string | null |
job.updated_at |
string |
job.processing_deadline_at |
string |
job.results_expires_at |
string |
results[] |
object[] |
results[] |
object |
results[].index |
integer |
results[].url |
string |
results[].depth |
integer |
results[].status |
string |
results[].data |
object |
results[].data.url |
string |
results[].data.final_url |
string |
results[].data.status |
integer | null |
results[].data.outcome |
string |
results[].data.content_type |
string | null |
results[].data.content |
string |
results[].data.bytes |
integer |
results[].data.truncated |
boolean |
results[].data.redirect_count |
integer |
results[].data.attempt_count |
integer |
results[].data.duration_ms |
integer |
results[].data.fetched_at |
string |
results[].data.headers |
object |
results[].data.rendered |
boolean |
results[].data.links[] |
object[] |
results[].data.links[] |
object |
results[].data.links[].url |
string |
results[].data.links[].text |
string |
results[].data.document |
object |
results[].data.document.kind |
string |
results[].data.document.title |
string | null |
results[].data.document.pages |
integer | null |
results[].data.document.sheets[] |
string[] |
results[].data.document.truncated |
boolean |
results[].data.document.error |
string |
results[].data.depth |
integer |
results[].data.forwarded |
object |
results[].data.forwarded.header_names[] |
string[] |
results[].data.forwarded.cookie_names[] |
string[] |
results[].data.forwarded.scope |
string |
pagination |
object |
Пример запроса
curl -H "X-API-Key: $DOMSCAN_API_KEY" "https://domscan.net/v1/crawl/jobs/example/results?limit=25&offset=0"const response = await fetch("https://domscan.net/v1/crawl/jobs/example/results?limit=25&offset=0", {
headers: { "X-API-Key": process.env.DOMSCAN_API_KEY },
});
const data = await response.json();
console.log(data);import os
import requests
response = requests.get(
"https://domscan.net/v1/crawl/jobs/example/results?limit=25&offset=0",
headers={"X-API-Key": os.environ["DOMSCAN_API_KEY"]},
)
print(response.json())package main
import (
"fmt"
"io"
"net/http"
"os"
)
func main() {
req, err := http.NewRequest(http.MethodGet, "https://domscan.net/v1/crawl/jobs/example/results?limit=25&offset=0", nil)
if err != nil {
panic(err)
}
req.Header.Set("X-API-Key", os.Getenv("DOMSCAN_API_KEY"))
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
data, err := io.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(resp.Status, string(data))
}require "json"
require "net/http"
uri = URI("https://domscan.net/v1/crawl/jobs/example/results?limit=25&offset=0")
request = Net::HTTP::Get.new(uri)
request["X-API-Key"] = ENV.fetch("DOMSCAN_API_KEY")
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
http.request(request)
end
puts JSON.pretty_generate(JSON.parse(response.body))Пример ответа
{
"job": {
"id": "example-id",
"status": "queued",
"url": "https://example.com",
"mode": "standard",
"output": "html",
"options": {
"max_pages": 1,
"max_depth": 1,
"include_paths": [
"example"
],
"exclude_paths": [
"example"
],
"allow_subdomains": false,
"ignore_query_parameters": false,
"use_sitemap": false,
"only_main_content": false,
"include_selectors": [
"example"
],
"exclude_selectors": [
"example"
],
"links": false
},
"counts": {
"queued": 1,
"pending": 1,
"processing": 1,
"succeeded": 1,
"failed": 1,
"cancelled": 1
},
"billing": {
"credits_per_page": 1,
"credits_charged": 1,
"credits_refunded": 1,
"credits_net": 1,
"credits_due": 1,
"settled": false,
"policy": "effort_based"
},
"robots_txt": "rules",
"stop_reason": "exhausted",
"status_url": "https://example.com",
"results_url": "https://example.com",
"cancel_url": "https://example.com",
"poll_after_ms": 1,
"created_at": "2026-08-27T12:00:00Z",
"started_at": "2026-08-27T12:00:00Z",
"completed_at": "2026-08-27T12:00:00Z",
"updated_at": "2026-08-27T12:00:00Z",
"processing_deadline_at": "2026-08-27T12:00:00Z",
"results_expires_at": "2026-08-27T12:00:00Z"
},
"results": [
{
"index": 1,
"url": "https://example.com",
"depth": 1,
"status": "pending",
"data": {
"url": "https://example.com",
"final_url": "https://example.com",
"status": 1,
"outcome": "success",
"content_type": "domain",
"content": "example",
"bytes": 1,
"truncated": false,
"redirect_count": 1,
"attempt_count": 1,
"duration_ms": 1,
"fetched_at": "2026-08-27T12:00:00Z",
"headers": {},
"rendered": false,
"links": [
{
"url": "https://example.com",
"text": "example"
}
],
"document": {
"kind": "pdf",
"title": "example",
"pages": 1,
"sheets": [
"example"
],
"truncated": false,
"error": "DOCUMENT_UNREADABLE"
},
"depth": 1,
"forwarded": {
"header_names": [
"example"
],
"cookie_names": [
"example"
],
"scope": "requested_origin"
}
}
}
],
"pagination": {}
}
Коды состояния HTTP
200OK400Неверный запрос401Не авторизован404Не найдено410HTTP 410429Слишком много запросов