Web web Parse API

Turn a PDF, Word, Excel, PowerPoint or HTML file into markdown

curl --request POST \
  --url https://api.stophy.dev/v1/web/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file": "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=",
  "filename": "tides.html"
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    file: 'PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=',
    filename: 'tides.html'
  })
};

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

import requests

url = "https://api.stophy.dev/v1/web/parse"

payload = {
    "file": "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=",
    "filename": "tides.html"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "success": true,
  "data": {
    "isTruncated": true,
    "markdown": "<string>",
    "metadata": {
      "title": "<string>",
      "contentType": "<string>",
      "numPages": 0
    }
  },
  "creditsUsed": 123,
  "requestId": "<string>"
}

{
  "success": false,
  "error": {
    "code": "cliSessionCompleted",
    "message": "<string>",
    "retryable": true,
    "requestId": "<string>",
    "retryAfterSeconds": 123,
    "requiredCredits": 123,
    "availableCredits": 123,
    "billingUrl": "https://stophy.dev/billing"
  }
}

{
  "success": false,
  "error": {
    "code": "cliSessionCompleted",
    "message": "<string>",
    "retryable": true,
    "requestId": "<string>",
    "retryAfterSeconds": 123,
    "requiredCredits": 123,
    "availableCredits": 123,
    "billingUrl": "https://stophy.dev/billing"
  }
}

POST

web

parse

Turn a PDF, Word, Excel, PowerPoint or HTML file into markdown

curl --request POST \
  --url https://api.stophy.dev/v1/web/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file": "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=",
  "filename": "tides.html"
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    file: 'PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=',
    filename: 'tides.html'
  })
};

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

import requests

url = "https://api.stophy.dev/v1/web/parse"

payload = {
    "file": "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=",
    "filename": "tides.html"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "success": true,
  "data": {
    "isTruncated": true,
    "markdown": "<string>",
    "metadata": {
      "title": "<string>",
      "contentType": "<string>",
      "numPages": 0
    }
  },
  "creditsUsed": 123,
  "requestId": "<string>"
}

{
  "success": false,
  "error": {
    "code": "cliSessionCompleted",
    "message": "<string>",
    "retryable": true,
    "requestId": "<string>",
    "retryAfterSeconds": 123,
    "requiredCredits": 123,
    "availableCredits": 123,
    "billingUrl": "https://stophy.dev/billing"
  }
}

{
  "success": false,
  "error": {
    "code": "cliSessionCompleted",
    "message": "<string>",
    "retryable": true,
    "requestId": "<string>",
    "retryAfterSeconds": 123,
    "requiredCredits": 123,
    "availableCredits": 123,
    "billingUrl": "https://stophy.dev/billing"
  }
}

Turn a PDF, Word, Excel, PowerPoint or HTML file into markdown.

Request

file is required.

This endpoint can be called without an API key, subject to per-address limits. Pagination requires a key.

import { Stophy } from "stophy";

const stophy = new Stophy({ apiKey: process.env.STOPHY_API_KEY });
const result = await stophy.web.parse({ file: "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=", filename: "tides.html" });
console.log(result.data);

from stophy import Stophy

stophy = Stophy()  # reads STOPHY_API_KEY
result = stophy.web.parse(file="PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=", filename="tides.html")
print(result["data"])

curl -X POST https://api.stophy.dev/v1/web/parse \
  -H "Authorization: Bearer $STOPHY_API_KEY" \
  -H "content-type: application/json" \
  -d '{"file":"PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=","filename":"tides.html"}'

stophy web parse "PGh0bWw+PGhlYWQ+PHRpdGxlPkhvdyB0aWRlcyB3b3JrPC90aXRsZT48L2hlYWQ+PGJvZHk+PG1haW4+PGgxPkhvdyB0aWRlcyB3b3JrPC9oMT48cD5UaGUgTW9vbiBwdWxscyBvbiB0aGUgb2NlYW5zIGFuZCBtYWtlcyB0d28gYnVsZ2VzIG9mIHdhdGVyIHRoYXQgbW92ZSBhcm91bmQgdGhlIEVhcnRoIGFzIGl0IHR1cm5zLCBzbyBtb3N0IGNvYXN0cyBzZWUgdHdvIGhpZ2ggdGlkZXMgYW5kIHR3byBsb3cgdGlkZXMgZXZlcnkgZGF5LjwvcD48L21haW4+PC9ib2R5PjwvaHRtbD4=" --filename tides.html

Response

If successful, the response body contains the standard envelope. data contains markdown, isTruncated and metadata. The following example is a real response, truncated: each list shows one item and long strings are cut.

{
  "success": true,
  "data": {
    "markdown": "# How tides work\n\nThe Moon pulls on the oceans and makes two bulges of water that move around the Earth as it turns,…",
    "isTruncated": false,
    "metadata": {
      "title": "How tides work",
      "contentType": "text/html"
    }
  },
  "creditsUsed": 1,
  "requestId": "2fe9dbad-fc48-4890-9751-0b24b596035b"
}

To read a page or a PDF by its address, use Web web Scrape.

Optional parameters

Parameter	Type	Description
`filename`	string	The file’s name, such as report.docx. The type is read from the file itself.
`maxPages`	integer	Read at most this many PDF pages, sheets or slides; `isTruncated` says when the file had more. Must be between 1 and 100. If unset, defaults to `100`.

Billing

Each successful request consumes 1 credit, regardless of the number of items returned. Requests that fail, or that return no items, are not billed.

Pagination

This method is not paginated. A single request returns the complete result.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

maxTextLength

integer

Cut every text value in the response to this many characters. A value that was cut ends with …, and a page whose text was cut has isTruncated set to true. A screenshot is never cut. Leave it out to get the full text.

Required range: x >= 1

Body

application/json

file

string

required

The file's bytes as base64, up to 10 MB: a PDF, a Word .docx, an Excel .xlsx, a PowerPoint .pptx or an HTML file.

Minimum string length: 1

filename

string

The file's name, such as report.docx. The type is read from the file itself.

Required string length: 1 - 255

maxPages

integer

default:100

Read at most this many PDF pages, sheets or slides; isTruncated says when the file had more.

Required range: 1 <= x <= 100

Response

The data, and the credits this call used.

success

any

required

data

object

required

Show child attributes

creditsUsed

integer

required

requestId

string

required

Using the API

Catalog

Account

Search and AI answers

Video

Social

Places and travel

Jobs

Shopping

Apps

Real estate

Ads

Web web Parse API

Request

Response

Optional parameters

Billing

Authorizations

Query Parameters

Body

Response

​Request

​Response

​Optional parameters

​Billing

​Pagination

Authorizations

Query Parameters

Body

Response

Request

Response

Optional parameters

Billing

Pagination