0% found this document useful (0 votes)
36 views34 pages

ScrapeGraphAI API Overview

ScrapeGraphAI provides an AI-powered web scraping API that allows users to extract specific information from webpages using natural language prompts. The API includes features like SmartScraper for content extraction, SearchScraper for web search requests, and Markdownify for converting webpages into Markdown format. Users can check the status of their requests and retrieve results through designated API endpoints.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
36 views34 pages

ScrapeGraphAI API Overview

ScrapeGraphAI provides an AI-powered web scraping API that allows users to extract specific information from webpages using natural language prompts. The API includes features like SmartScraper for content extraction, SearchScraper for web search requests, and Markdownify for converting webpages into Markdown format. Users can check the status of their requests and retrieve results through designated API endpoints.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
SmartScraper

Start SmartScraper
Extract content from a webpage using AI by providing a natural language prompt and a URL.
POST
/
v1
/
smartscraper
Try it
SmartScraper allows you to extract specific information from any webpage using AI. Simply

provide a URL and describe what information you want to extract in natural language.

Use Cases
Extract company information from websites
Gather product details from e-commerce pages
Collect contact information from business pages
Extract structured data from articles or blog posts

Example Response
Copy

{
"request_id": "<request-id>",
"status": "completed",
"website_url": "[Link]
"user_prompt": "Extract info about the company",
"result": {
"company_name": "ScrapeGraphAI",
"description": "ScrapeGraphAI is a powerful AI scraping API
designed for efficient web data extraction to power LLM applications
and AI agents...",
"features": [
"Effortless, cost-effective, and AI-powered data extraction",
"Handles proxy rotation and rate limits",
"Supports a wide variety of websites"
],
"contact_email": "contact@[Link]",
"social_links": {
"github": "[Link]
"linkedin": "[Link]
"twitter": "[Link]
},
"..."
},
"error": ""
}

Authorizations

SGAI-APIKEY

stringheaderrequired

Body
application/json

Either website_url or website_html must be provided

user_prompt

stringrequired

Example:
"Extract info about the company"

website_url

string

Example:
"[Link]

website_html

string

HTML content, maximum size 2MB


Example:
"<html><body><h1>Title</h1><p>Content</p></body></html>"
headers

object

Optional headers to send with the request, including cookies and user agent
Show child attributes
Example:
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36",
"Cookie": "cookie1=value1; cookie2=value2"
}

output_schema

object | null

Response
200
200422

application/json

Successful Response

request_id

stringrequired

status

enum<string>required

Available options: queued, processing, completed, failed

website_url

stringrequired

user_prompt

stringrequired
result

object | null

error

stringdefault:

Was this page helpful?


Yes
No
Error Handling
Get SmartScraper Status
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl -X POST '[Link] \
-H 'SGAI-APIKEY: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"user_prompt": "Extract info about the company",
"website_url": "[Link]
}'
200
422
Copy
{
"request_id": "<string>",
"status": "queued",
"website_url": "<string>",
"user_prompt": "<string>",
"result": {},
"error": ""
}
Start SmartScraper - ScrapeGraphAI

ScrapeGraphAI home page


Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
SmartScraper

Get SmartScraper Status


Check the status and retrieve results of a SmartScraper request.
GET
/
v1
/
smartscraper
/
{request_id}
Try it
This endpoint allows you to check the status of a SmartScraper request and retrieve its

results once completed.

Status Values
queued: Request is waiting to be processed
processing: Request is being processed
completed: Request has finished successfully
failed: Request failed to process

Authorizations

SGAI-APIKEY

stringheaderrequired

Path Parameters

request_id

stringrequired

Response
200
200422

application/json

Successful Response

request_id

stringrequired
status

enum<string>required

Available options: queued, processing, completed, failed

website_url

stringrequired

user_prompt

stringrequired

result

object | null

error

stringdefault:

Was this page helpful?


Yes
No
Start SmartScraper
Start SearchScraper
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl '[Link]
\
-H 'SGAI-APIKEY: YOUR_API_KEY'
200
422
Copy
{
"request_id": "<string>",
"status": "queued",
"website_url": "<string>",
"user_prompt": "<string>",
"result": {},
"error": ""
}
Get SmartScraper Status - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
SmartScraper
Get SmartScraper Status
Check the status and retrieve results of a SmartScraper request.
GET
/
v1
/
smartscraper
/
{request_id}
Try it
This endpoint allows you to check the status of a SmartScraper request and retrieve its

results once completed.

Status Values
queued: Request is waiting to be processed
processing: Request is being processed
completed: Request has finished successfully
failed: Request failed to process

Authorizations

SGAI-APIKEY

stringheaderrequired

Path Parameters

request_id

stringrequired

Response
200
200422

application/json

Successful Response

request_id

stringrequired

status

enum<string>required

Available options: queued, processing, completed, failed

website_url

stringrequired

user_prompt

stringrequired

result

object | null

error

stringdefault:

Was this page helpful?


Yes
No
Start SmartScraper
Start SearchScraper
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl '[Link]
\
-H 'SGAI-APIKEY: YOUR_API_KEY'
200
422
Copy
{
"request_id": "<string>",
"status": "queued",
"website_url": "<string>",
"user_prompt": "<string>",
"result": {},
"error": ""
}
Get SmartScraper Status - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
SearchScraper

Start SearchScraper
Start a new AI-powered web search request
POST
/
v1
/
searchscraper
Try it

Request Body

user_prompt

stringrequired

The search query or question you want to ask. This should be a clear and specific prompt
that will guide the AI in finding and extracting relevant information.

Example: “What is the latest version of Python and what are its main features?”

headers

object

Optional headers to customize the search behavior. This can include user agent, cookies, or
other HTTP headers.

Example:

Copy
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36",
"Cookie": "cookie1=value1; cookie2=value2"
}

output_schema

object

Optional schema to structure the output. If provided, the AI will attempt to format the results
according to this schema.

Example:

Copy
{
"properties": {
"version": {"type": "string"},
"release_date": {"type": "string"},
"major_features": {"type": "array", "items": {"type": "string"}}
},
"required": ["version", "release_date", "major_features"]
}

Response

request_id

string

Unique identifier for the search request. Use this ID to check the status and retrieve results.

status

string

Status of the request. One of: “queued”, “processing”, “completed”, “failed”


user_prompt

string

The original search query that was submitted.

result

object

The search results. If an output_schema was provided, this will be structured according to
that schema.

reference_urls

array

List of URLs that were used as references for the answer.

error

string

Error message if the request failed. Empty string if successful.

Example Request
Copy

curl -X POST '[Link] \


-H 'SGAI-APIKEY: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"user_prompt": "What is the latest version of Python and what are
its main features?",
"output_schema": {
"properties": {
"version": {"type": "string"},
"release_date": {"type": "string"},
"major_features": {"type": "array", "items": {"type":
"string"}}
},
"required": ["version", "release_date", "major_features"]
}
}'

Example Response
Copy

{
"request_id": "123e4567-e89b-12d3-a456-426614174000",
"status": "completed",
"user_prompt": "What is the latest version of Python and what are
its main features?",
"result": {
"version": "3.12",
"release_date": "October 2, 2023",
"major_features": [
"Improved error messages",
"Per-interpreter GIL",
"Support for the Linux perf profiler",
"Faster startup time"
]
},
"reference_urls": [
"[Link]
"[Link]
],
"error": ""
}

Was this page helpful?


Yes
No
Get SmartScraper Status
Get SearchScraper Status
x
github
linkedin
Powered by Mintlify
200
Copy
{
"request_id": "<string>",
"status": "<string>",
"user_prompt": "<string>",
"result": {},
"reference_urls": [
{}
],
"error": "<string>"
}
Start SearchScraper - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
SearchScraper

Get SearchScraper Status


Get the status and results of a previous search request
GET
/
v1
/
searchscraper
/
{request_id}
Try it

Path Parameters

request_id

stringrequired

The unique identifier of the search request to retrieve.

Example: “123e4567-e89b-12d3-a456-426614174000”

Response

request_id

string

The unique identifier of the search request.


status

string

Status of the request. One of: “queued”, “processing”, “completed”, “failed”

user_prompt

string

The original search query that was submitted.

result

object

The search results. If an output_schema was provided in the original request, this will be
structured according to that schema.

reference_urls

array

List of URLs that were used as references for the answer.

error

string

Error message if the request failed. Empty string if successful.

Example Request
Copy

curl '[Link]
12d3-a456-426614174000' \
-H 'SGAI-APIKEY: YOUR_API_KEY'
Example Response
Copy

{
"request_id": "123e4567-e89b-12d3-a456-426614174000",
"status": "completed",
"user_prompt": "What is the latest version of Python and what are
its main features?",
"result": {
"version": "3.12",
"release_date": "October 2, 2023",
"major_features": [
"Improved error messages",
"Per-interpreter GIL",
"Support for the Linux perf profiler",
"Faster startup time"
]
},
"reference_urls": [
"[Link]
"[Link]
],
"error": ""
}

Error Responses

400

object

Returned when the request_id is not a valid UUID.

Copy
{
"error": "request_id must be a valid UUID"
}

404

object

Returned when the request_id is not found.

Copy
{
"error": "Request not found"
}

Was this page helpful?


Yes
No
Start SearchScraper
Start Markdownify
x
github
linkedin
Powered by Mintlify
200
Copy
{
"400": {},
"404": {},
"request_id": "<string>",
"status": "<string>",
"user_prompt": "<string>",
"result": {},
"reference_urls": [
{}
],
"error": "<string>"
}
Get SearchScraper Status - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
Markdownify

Start Markdownify
Convert any webpage into clean, readable Markdown format.
POST
/
v1
/
markdownify
Try it
Markdownify converts webpage content into clean, well-formatted Markdown. This is useful

for content migration, documentation creation, or making web content more readable and

portable.
Features
Preserves content structure
Handles complex layouts
Maintains headings hierarchy
Converts tables
Preserves links and images
Cleans up unnecessary formatting

Example Response
Copy

{
"request_id": "65401e0d-8cd6-4d6a-88f6-e21255d1c06a",
"status": "completed",
"website_url": "[Link]
"result": "## Transform Websites into\nStructured Data\n\n### Just
One Prompt Away\n\nTransform any website into clean, organized data
for AI agents and Data Analytics.\nEnhance your apps with our AI-
powered API.\n\n### Save time\n\nNo more writing complex code or
dealing with manual extraction.\n\n### Save money\n\nWhy hire
expensive developers or pay for costly scraping services? Our API
gives you high-quality data extraction at a fraction of the cost.\n\
n### AI powered\n\nWe employ state-of-the-art AI technologies to
streamline the data extraction process...",
"error": ""
}

The response includes the complete webpage content converted to Markdown format. The

example above shows a truncated version of the response.

Authorizations
SGAI-APIKEY

stringheaderrequired

Body
application/json

website_url

stringrequired

Example:
"[Link]

headers

object

Optional headers to send with the request, including cookies and user agent
Show child attributes
Example:
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36",
"Cookie": "cookie1=value1; cookie2=value2"
}

Response
200
200422

application/json

Successful Response

request_id

stringrequired

status
enum<string>required

Available options: queued, processing, completed, failed

website_url

stringrequired

result

string | null

error

stringdefault:

Was this page helpful?


Yes
No
Get SearchScraper Status
Get Markdownify Status
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl -X POST '[Link] \
-H 'SGAI-APIKEY: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"website_url": "[Link]
}'
200
422
Copy
{
"request_id": "<string>",
"status": "queued",
"website_url": "<string>",
"result": "<string>",
"error": ""
}
Start Markdownify - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
Markdownify

Get Markdownify Status


Check the status and retrieve results of a Markdownify request.
GET
/
v1
/
markdownify
/
{request_id}
Try it
This endpoint allows you to check the status of a Markdownify request and retrieve its

results once completed.

Status Values
queued: Request is waiting to be processed
processing: Request is being processed
completed: Request has finished successfully
failed: Request failed to process

Authorizations

SGAI-APIKEY

stringheaderrequired

Path Parameters

request_id

stringrequired

Response
200
200422

application/json

Successful Response
request_id

stringrequired

status

enum<string>required

Available options: queued, processing, completed, failed

website_url

stringrequired

result

string | null

error

stringdefault:

Was this page helpful?


Yes
No
Start Markdownify
Get Credits
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl '[Link]
\
-H 'SGAI-APIKEY: YOUR_API_KEY'
200
422
Copy
{
"request_id": "<string>",
"status": "queued",
"website_url": "<string>",
"result": "<string>",
"error": ""
}
Get Markdownify Status - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
User
Get Credits
Get the remaining credits and total credits used for your account.
GET
/
v1
/
credits
Try it
This endpoint allows you to check your account’s credit balance and usage. Each API

request consumes a different number of credits:

Markdownify: 2 credits per request


SmartScraper: 10 credits per request
SearchScraper: 30 credits per request

The response shows:

remaining_credits: Number of credits available for use


total_credits_used: Total number of credits consumed so far

Authorizations

SGAI-APIKEY

stringheaderrequired

Response
200 - application/json

Successful Response

remaining_credits

integerrequired

total_credits_used

integerrequired

Was this page helpful?


Yes
No
Get Markdownify Status
Submit Feedback
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl '[Link] \
-H 'SGAI-APIKEY: YOUR_API_KEY'
200
Copy
{
"remaining_credits": 123,
"total_credits_used": 123
}
Get Credits - ScrapeGraphAI

ScrapeGraphAI home page

Search...
⌘K
Status
Support
Dashboard

Home
Cookbook
API Reference
Official Website
Community
Blog
API Documentation
Introduction
Error Handling
SmartScraper
POST
Start SmartScraper
GET
Get SmartScraper Status
SearchScraper
POST
Start SearchScraper
GET
Get SearchScraper Status
Markdownify
POST
Start Markdownify
GET
Get Markdownify Status
User
GET
Get Credits
POST
Submit Feedback
User

Submit Feedback
Submit feedback for a specific request with rating and optional comments.
POST
/
v1
/
feedback
Try it
This endpoint allows you to submit feedback for any request you’ve made using our services

(SmartScraper, SearchScraper, or Markdownify). Your feedback helps us improve our

services.

Rating System
Rating scale: 0-5 stars
Optional feedback text for additional comments
Each feedback is linked to a specific request ID

Authorizations

SGAI-APIKEY
stringheaderrequired

Body
application/json

request_id

stringrequired

ID of the request/session this feedback is for

rating

integerrequired

Required range: 0 <= x <= 5

feedback_text

string | null

Response
200
200422

application/json

Successful Response

feedback_id

stringrequired

request_id

stringrequired

feedback_timestamp

stringrequired
message

stringdefault:Feedback submitted successfully

Was this page helpful?


Yes
No
Get Credits
x
github
linkedin
Powered by Mintlify
cURL
Python
JavaScript
PHP
Go
Java
Copy
curl -X POST '[Link] \
-H 'SGAI-APIKEY: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"request_id": "123e4567-e89b-12d3-a456-426614174000",
"rating": 5,
"feedback_text": "Great service!"
}'
200
422
Copy
{
"feedback_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"message": "Feedback submitted successfully",
"feedback_timestamp": "2023-11-07T05:31:56Z"
}
Submit Feedback - ScrapeGraphAI

You might also like