Extract SPA Data

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://example.com/dashboard",
    "mode": "extract",
    "waitUntil": "domcontentloaded",
    "waitFor": { "selector": "h1", "timeoutMs": 15000 },
    "fields": {
      "title":    { "source": "dom", "selector": "h1",           "parse": "string" },
      "subtitle": { "source": "dom", "selector": "p.subtitle",   "parse": "string" },
      "count":    { "source": "dom", "selector": ".metric-value", "parse": "number" }
    },
    "countryCode": "GLOBAL",
    "userAgentMode": "random"
  }'

const response = await fetch("https://api.adscrawl.net/spa-extract", {
  method: "POST",
  headers: {
    "content-type": "application/json",
    "x-api-key": "YOUR_API_KEY",
  },
  body: JSON.stringify({
    url: "https://example.com/dashboard",
    mode: "extract",
    waitUntil: "domcontentloaded",
    waitFor: { selector: "h1", timeoutMs: 15000 },
    fields: {
      title:    { source: "dom", selector: "h1",            parse: "string" },
      subtitle: { source: "dom", selector: "p.subtitle",    parse: "string" },
      count:    { source: "dom", selector: ".metric-value", parse: "number" },
    },
    countryCode: "GLOBAL",
    userAgentMode: "random",
  }),
});

const result = await response.json();
console.log(result.data);

import httpx

response = httpx.post(
    "https://api.adscrawl.net/spa-extract",
    headers={
        "content-type": "application/json",
        "x-api-key": "YOUR_API_KEY",
    },
    json={
        "url": "https://example.com/dashboard",
        "mode": "extract",
        "waitUntil": "domcontentloaded",
        "waitFor": {"selector": "h1", "timeoutMs": 15000},
        "fields": {
            "title":    {"source": "dom", "selector": "h1",             "parse": "string"},
            "subtitle": {"source": "dom", "selector": "p.subtitle",     "parse": "string"},
            "count":    {"source": "dom", "selector": ".metric-value",  "parse": "number"},
        },
        "countryCode": "GLOBAL",
        "userAgentMode": "random",
    },
)

response.raise_for_status()
print(response.json()["data"])

{
  "mode": "extract",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "data": {
    "title": "Example Dashboard"
  },
  "missingFields": []
}

{
  "mode": "inspect",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "candidates": {
    "dom": { "metrics": [], "tables": [] },
    "network": []
  },
  "suggestedPlan": {
    "fields": {},
    "schema": {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
  }
}

{
  "mode": "extract",
  "page": {
    "url": "https://trends.google.com/trends/explore?q=adspower%2Cplaywright",
    "title": "Google Trends"
  },
  "data": {
    "averages": [
      { "query": "adspower",    "extractedValue": 42 },
      { "query": "playwright",  "extractedValue": 71 }
    ],
    "interestOverTime": []
  },
  "missingFields": [],
  "source": "sunbrowser",
  "cached": false,
  "stale": false,
  "collectedAt": "2026-08-03T02:04:05.123456789Z",
  "attempts": 2
}

{
  "code": "INSUFFICIENT_CREDITS"
}

{
  "code": "SPA_REQUIRED_FIELDS_MISSING"
}

POST

spa-extract

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://example.com/dashboard",
    "mode": "extract",
    "waitUntil": "domcontentloaded",
    "waitFor": { "selector": "h1", "timeoutMs": 15000 },
    "fields": {
      "title":    { "source": "dom", "selector": "h1",           "parse": "string" },
      "subtitle": { "source": "dom", "selector": "p.subtitle",   "parse": "string" },
      "count":    { "source": "dom", "selector": ".metric-value", "parse": "number" }
    },
    "countryCode": "GLOBAL",
    "userAgentMode": "random"
  }'

const response = await fetch("https://api.adscrawl.net/spa-extract", {
  method: "POST",
  headers: {
    "content-type": "application/json",
    "x-api-key": "YOUR_API_KEY",
  },
  body: JSON.stringify({
    url: "https://example.com/dashboard",
    mode: "extract",
    waitUntil: "domcontentloaded",
    waitFor: { selector: "h1", timeoutMs: 15000 },
    fields: {
      title:    { source: "dom", selector: "h1",            parse: "string" },
      subtitle: { source: "dom", selector: "p.subtitle",    parse: "string" },
      count:    { source: "dom", selector: ".metric-value", parse: "number" },
    },
    countryCode: "GLOBAL",
    userAgentMode: "random",
  }),
});

const result = await response.json();
console.log(result.data);

import httpx

response = httpx.post(
    "https://api.adscrawl.net/spa-extract",
    headers={
        "content-type": "application/json",
        "x-api-key": "YOUR_API_KEY",
    },
    json={
        "url": "https://example.com/dashboard",
        "mode": "extract",
        "waitUntil": "domcontentloaded",
        "waitFor": {"selector": "h1", "timeoutMs": 15000},
        "fields": {
            "title":    {"source": "dom", "selector": "h1",             "parse": "string"},
            "subtitle": {"source": "dom", "selector": "p.subtitle",     "parse": "string"},
            "count":    {"source": "dom", "selector": ".metric-value",  "parse": "number"},
        },
        "countryCode": "GLOBAL",
        "userAgentMode": "random",
    },
)

response.raise_for_status()
print(response.json()["data"])

{
  "mode": "extract",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "data": {
    "title": "Example Dashboard"
  },
  "missingFields": []
}

{
  "mode": "inspect",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "candidates": {
    "dom": { "metrics": [], "tables": [] },
    "network": []
  },
  "suggestedPlan": {
    "fields": {},
    "schema": {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
  }
}

{
  "mode": "extract",
  "page": {
    "url": "https://trends.google.com/trends/explore?q=adspower%2Cplaywright",
    "title": "Google Trends"
  },
  "data": {
    "averages": [
      { "query": "adspower",    "extractedValue": 42 },
      { "query": "playwright",  "extractedValue": 71 }
    ],
    "interestOverTime": []
  },
  "missingFields": [],
  "source": "sunbrowser",
  "cached": false,
  "stale": false,
  "collectedAt": "2026-08-03T02:04:05.123456789Z",
  "attempts": 2
}

{
  "code": "INSUFFICIENT_CREDITS"
}

{
  "code": "SPA_REQUIRED_FIELDS_MISSING"
}

Submit a page URL and extraction configuration to retrieve structured data from a JavaScript-rendered SPA. You can use custom field definitions, a built-in template, or inspect mode to discover what data is available on a page.

string

Full HTTP(S) URL for the target SPA using port 80 or 443. Required for most templates. For google-trends-explore, prefer the keyword field instead. SimilarWeb requires a full page URL, not a bare domain.

string

Recommended for google-trends-explore. Provide 1 to 5 unique, non-empty comma-separated keywords, each at most 100 Unicode characters (for example, "adspower,playwright"). The server builds the canonical Trends URL automatically. Explicit null, numeric, or empty-string values return INVALID_KEYWORD and never fall back to url.

string

Extraction mode. Defaults to "extract".

Value	Behaviour
`"extract"`	Runs field or template extraction and returns structured `data`.
`"inspect"`	Returns DOM and network candidates discovered on the page along with a `suggestedPlan` you can copy into a future extract request.

string

Built-in site template ID. When provided, fields are supplied by the template rather than your request. Available template IDs:

"similarweb-overview" — website traffic, engagement, and ranking metrics.
"google-trends-explore" — interest-over-time data and relative averages for up to 5 keywords.
"chrome-web-store-app-info" — extension metadata from the Chrome Web Store (with CRX manifest fallback).

object

Template-specific parameters declared by the selected template. Refer to the template’s input specification from GET /spa-extract/templates.

string

Navigation event to wait for before extraction. Custom extraction defaults to "domcontentloaded". Site templates use the request value first, then the template default, then "domcontentloaded".

Value	Behaviour
`"domcontentloaded"`	Waits for DOMContentLoaded — recommended for most SPAs.
`"load"`	Waits for `window.load` including images and stylesheets.
`"networkidle"`	Waits until no network connections for 500 ms. May timeout on long-polling sites.

object

Wait for a specific element or text to appear after SPA navigation and actions complete. selector and text may be combined.

Show waitFor fields

string

Wait for the first matching element to become visible.

string

Wait for the first element containing this text to become visible.

number

Timeout in milliseconds. Defaults to 15,000 and never exceeds the remaining task timeout.

array

Optional page interactions executed in array order before extraction. Each step is capped at 30 seconds.

Show action types

object

{ type: "wait", milliseconds: number } — Pause for 0 to 30,000 ms.

object

{ type: "waitForSelector", selector: string, timeoutMs?: number } — Wait for an element to become visible.

object

{ type: "click", selector: string } — Click the first matching element.

object

{ type: "fill", selector: string, value: string } — Clear and fill the first matching input.

object

{ type: "press", selector: string, key: string } — Press a key on the first matching element.

object

{ type: "scroll", selector?: string, x?: number, y?: number } — Scroll an element into view or scroll the page. y defaults to 800.

object

Record of named field definitions for extract mode. Each key becomes a property in the response data object. Use this when you are not using a template.

Show field definition

string

required

"dom" to read from the page HTML, or "network" to read from intercepted JSON responses.

string

CSS selector for a DOM field.

string

DOM read mode: "text" (default), "html", or "attribute".

string

Attribute name, used when value is "attribute".

string

Substring to match against a response URL for a network field.

string

JSON path within the matched network response, for example $.data.metrics[0].value.

boolean

Whether a DOM field should return all matching elements as an array.

string

Coerce the value to "string", "number", "integer", "boolean", or "json".

string

Optional regular expression. When a capture group is present, group 1 is used.

boolean

Missing required fields return 422 SPA_REQUIRED_FIELDS_MISSING.

object

Legacy alias for fields, used only when fields is absent. String values are treated as DOM CSS selectors. Does not validate the response JSON and does not return schemaValid or schemaErrors fields. Prefer fields for all new integrations.

number

Maximum time to wait for the task to complete, in milliseconds. Must be a positive integer no greater than 3,600,000.

object

Viewport dimensions used when rendering the page.

Show viewport fields

number

Viewport width in pixels.

number

Viewport height in pixels.

string

Browser locale, for example "en-US". May follow trusted proxy metadata when omitted.

string

IANA timezone identifier, for example "Asia/Shanghai". May follow trusted proxy metadata when omitted.

object

Geolocation coordinates exposed to the page via the Geolocation API.

Show geolocation fields

number

Latitude in decimal degrees.

number

Longitude in decimal degrees.

object

Custom proxy configuration. Cannot be combined with countryCode.

Show proxy fields

string

Full proxy URL such as http://host:port or socks5://host:port. Cannot be combined with host.

string

"http" or "socks5". Used in the split form.

string

Proxy host. Used in the split form.

number | string

Port from 1 to 65535.

string

Proxy username. Must be supplied together with password.

string

Proxy password. Must be supplied together with username.

string

Managed residential proxy region. Cannot be combined with proxy.

"GLOBAL" — dynamic exit from 15 popular regions.
Two-letter country code — prefers a trusted proxy with dynamic fallback.
Omitted — a random trusted proxy is selected automatically.

string

"random" lets the server pick a User-Agent from its library. Requests without an explicit userAgent default to "random".

string

Operating system used when userAgentMode is "random". Accepted values: "windows" (default) or "macos".

string

Explicit User-Agent string. Overrides the random selection.

object

Browser fingerprint settings. When omitted, every signal defaults to random while keeping OS, GPU, CPU, memory, fonts, and device signals coherent.

Show fingerprint fields

string

"forward", "real", or "disabled".

string

"random" or "real". Controls WebGL vendor and renderer metadata.

string

"random", "real", or "disabled".

string

"random" or "real". Controls WebGL image noise.

string

"random" or "real". Controls canvas noise.

string

"random" or "real". Controls audio fingerprint noise.

string

"random" or "real". Controls layout measurement noise.

string

"random" or "real". Returns an OS-matched speech voice list.

string

"random" or "real". Returns an OS-matched font list.

string

"random" or "real". Generates a coherent CPU thread count and memory pair.

string

"random", "enabled", or "disabled".

array

Cookie list injected into the browser context before navigation.

google-trends-explore ignores omitted, null, or empty-array values. Any non-empty or malformed cookies on a Trends request return 400 INVALID_TRENDS_COOKIES.

Show cookie fields

string

required

Cookie name.

string

required

Cookie value.

string

required

Target domain such as .example.com.

string

Cookie path. Defaults to /.

boolean

Whether the cookie is sent only over HTTPS.

boolean

Whether the cookie is inaccessible to client-side JavaScript.

string

SameSite attribute.

boolean

Set true for a session cookie.

number

Unix expiry timestamp in seconds. Also accepted as expires or expiry.

Response

string

"extract" or "inspect", mirroring the request mode.

object

Page metadata.

Show page fields

string

Final page URL.

string

Page title.

object

Extracted structured data. Keys match your fields definition or the template’s output fields.

array

List of field keys that were not found.

string

"sunbrowser" — result came from a live browser collection. "cache" — result was served from the server cache. Present on Trends responses.

boolean

Whether this response was served from cache.

boolean

Whether the cached result is stale.

string

RFC3339Nano timestamp of when the result was actually collected.

number

Collection attempt count. Cache HIT responses use 0; stale responses use the attempt count at the time the Worker reported them.

object

Present in inspect mode. DOM and network extraction candidates discovered on the page.

object

Present in inspect mode. A plan with fields and schema you can copy into a future extract request.

Code	Meaning
200	Inspection results or extracted structured data.
400	Invalid URL, keyword, proxy, region, User-Agent, or Trends cookies.
401	Missing or invalid `x-api-key`.
402	Insufficient balance (`INSUFFICIENT_CREDITS`).
404	Chrome Web Store listing unavailable and CRX fallback could not recover it.
422	Required fields missing, invalid template or field config, or Worker rejected the task.
429	Task rate limited, or Google Trends upstream 429.
502	Proxy or target failure, invalid Trends data, or all candidate identities exhausted.
503	Queue, Worker, or managed resources unavailable; or Trends identity plan expired.
504	Task, navigation, or proxy timeout; or Trends response not observed.
500	Unclassified task execution failure.

One credit is consumed after request validation but before the task is enqueued. Request bodies are limited to 1 MiB.

More examples

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://example.com/dashboard",
    "mode": "extract",
    "waitUntil": "domcontentloaded",
    "waitFor": { "selector": "h1", "timeoutMs": 15000 },
    "fields": {
      "title":    { "source": "dom", "selector": "h1",           "parse": "string" },
      "subtitle": { "source": "dom", "selector": "p.subtitle",   "parse": "string" },
      "count":    { "source": "dom", "selector": ".metric-value", "parse": "number" }
    },
    "countryCode": "GLOBAL",
    "userAgentMode": "random"
  }'

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "template": "similarweb-overview",
    "url": "https://www.similarweb.com/website/dolphin-anty.com/#overview",
    "countryCode": "GLOBAL"
  }'

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "template": "google-trends-explore",
    "keyword": "adspower,playwright"
  }'

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://example.com/dashboard",
    "mode": "inspect"
  }'

curl -sS -X POST "https://api.adscrawl.net/spa-extract" \
  -H "content-type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://example.com/dashboard",
    "mode": "extract",
    "waitUntil": "domcontentloaded",
    "waitFor": { "selector": "h1", "timeoutMs": 15000 },
    "fields": {
      "title":    { "source": "dom", "selector": "h1",           "parse": "string" },
      "subtitle": { "source": "dom", "selector": "p.subtitle",   "parse": "string" },
      "count":    { "source": "dom", "selector": ".metric-value", "parse": "number" }
    },
    "countryCode": "GLOBAL",
    "userAgentMode": "random"
  }'

const response = await fetch("https://api.adscrawl.net/spa-extract", {
  method: "POST",
  headers: {
    "content-type": "application/json",
    "x-api-key": "YOUR_API_KEY",
  },
  body: JSON.stringify({
    url: "https://example.com/dashboard",
    mode: "extract",
    waitUntil: "domcontentloaded",
    waitFor: { selector: "h1", timeoutMs: 15000 },
    fields: {
      title:    { source: "dom", selector: "h1",            parse: "string" },
      subtitle: { source: "dom", selector: "p.subtitle",    parse: "string" },
      count:    { source: "dom", selector: ".metric-value", parse: "number" },
    },
    countryCode: "GLOBAL",
    userAgentMode: "random",
  }),
});

const result = await response.json();
console.log(result.data);

import httpx

response = httpx.post(
    "https://api.adscrawl.net/spa-extract",
    headers={
        "content-type": "application/json",
        "x-api-key": "YOUR_API_KEY",
    },
    json={
        "url": "https://example.com/dashboard",
        "mode": "extract",
        "waitUntil": "domcontentloaded",
        "waitFor": {"selector": "h1", "timeoutMs": 15000},
        "fields": {
            "title":    {"source": "dom", "selector": "h1",             "parse": "string"},
            "subtitle": {"source": "dom", "selector": "p.subtitle",     "parse": "string"},
            "count":    {"source": "dom", "selector": ".metric-value",  "parse": "number"},
        },
        "countryCode": "GLOBAL",
        "userAgentMode": "random",
    },
)

response.raise_for_status()
print(response.json()["data"])

{
  "mode": "extract",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "data": {
    "title": "Example Dashboard"
  },
  "missingFields": []
}

{
  "mode": "inspect",
  "page": {
    "url": "https://example.com/dashboard",
    "title": "Example Dashboard"
  },
  "candidates": {
    "dom": { "metrics": [], "tables": [] },
    "network": []
  },
  "suggestedPlan": {
    "fields": {},
    "schema": {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
  }
}

{
  "mode": "extract",
  "page": {
    "url": "https://trends.google.com/trends/explore?q=adspower%2Cplaywright",
    "title": "Google Trends"
  },
  "data": {
    "averages": [
      { "query": "adspower",    "extractedValue": 42 },
      { "query": "playwright",  "extractedValue": 71 }
    ],
    "interestOverTime": []
  },
  "missingFields": [],
  "source": "sunbrowser",
  "cached": false,
  "stale": false,
  "collectedAt": "2026-08-03T02:04:05.123456789Z",
  "attempts": 2
}

{
  "code": "INSUFFICIENT_CREDITS"
}

{
  "code": "SPA_REQUIRED_FIELDS_MISSING"
}

Overview

Browser Tasks

Remote CDP

Cloud Browsers

Response

More examples

​Response

​More examples

Response

More examples