API features

Readable HTML and clean text

Receive the article body as cleaned HTML and paragraph-preserving plain text for different downstream needs.

Complete article metadata

Capture the final URL, title, description, author, publication time, and source in one request.

Primary image and image candidates

Use the main image plus ordered, deduplicated image records with alt text and available dimensions.

LLM and RAG-ready output

Feed normalized article text into retrieval, summarization, classification, and knowledge workflows.

Multilingual webpage support

Extract readable content from common international encodings, including English and Chinese pages.

Search and monitoring workflows

Standardize public articles for indexing, competitive research, archives, and scheduled content analysis.

API Document

HTTP Protocol:HTTPS

HTTP Method:POST

HTTP Endpoint:https://api.gugudata.io/v1/websitetools/fetchcontent

Response Type:application/json; charset=utf-8

DEMO Endpoint:https://api.gugudata.io/v1/websitetools/fetchcontent/demo

Live Demo:Try Interactive Demo

Postman Collection:Run in Postman

API Request Parameters

Name	Type	Is Required	Default Value	Remark
appkey	string	true	YOUR_APPKEY	API key used to authenticate the request.
url	string	true	https://gugudata.github.io/gugudata-io/guides/article-content-extraction-api-seo-guide/	Complete public HTTP or HTTPS article URL.

API Response Parameters

Name	Type	Remark
url	string	Final article URL after redirects.
title	string	Extracted article title or an empty string.
description	string	Article summary or an empty string.
content	string	Clean readable article HTML.
contentText	string	Plain article text with paragraph boundaries.
image	string	Primary article image URL or an empty string.
images	array<object>	Stable image list with src, absoluteUrl, alt, width, and height.
author	string	Article author or an empty string.
published	string	Publication time or an empty string.
source	string	Source publisher or host.

API Response Status Codes

Status Code	Explanation of Status Code	Remarks
200	Request processed successfully.	Some endpoints expose a separate application-level status field in the response body, such as `dataStatus.statusCode`.
400	Invalid request parameters or request format.	Check required fields, data types, and request body format.
401	Missing or unknown application key.	Provide a valid `appkey` with the request.
403	The application key is recognized but access is not allowed.	The key may be expired, inactive, or not permitted for the requested API.
422	The target response cannot be extracted as an article.	Use an HTML article page with readable body content and a valid redirect chain.
429	Request rate or trial usage limit exceeded.	Reduce request frequency and retry with backoff. If a trial allowance is exhausted, check Trial Keys for remaining requests and subscribe to continue.
502	The target website could not be reached successfully.	Retry later or verify that the target website is available.
503	The extraction service is temporarily unavailable.	Retry later or contact support if the error persists.

Remote MCP

AI client access

Use this API through GuGuData Remote MCP

Connect your AI client once, authorize in the browser, and the client can use the GuGuData API tools available to your account. You do not need to paste an appkey into the MCP client.

Endpoint https://mcp.gugudata.io/mcp

Open MCP Guide

Generic MCP configuration

{
  "mcpServers": {
    "gugudata": {
      "url": "https://mcp.gugudata.io/mcp",
      "transportType": "streamable-http"
    }
  }
}

Code Snippets

Run in Postman Open LLM Page

Webpage Content Extraction

Extract article text and metadata from a public webpage for search or content processing.

Input and coverage: Use a public HTTP(S) article URL. Page access restrictions and source structure can affect extraction; metadata may be absent.

Example request

Replace YOUR_APPKEY with your own API key. This request uses the normal API endpoint.

curl --fail-with-body 'https://api.gugudata.io/v1/websitetools/fetchcontent?appkey=YOUR_APPKEY' \
  --request POST \
  --header 'Content-Type: application/json' \
  --data '{"url": "https://gugudata.github.io/gugudata-io/guides/article-content-extraction-api-seo-guide/"}'

View sample Demo response

This is a fixed Demo sample, shortened for readability. It is not the response to your example request. Your results depend on the input and dataset. File URLs are temporary and have been removed.

{
  "dataStatus": {
    "statusCode": 200,
    "status": "SUCCESS",
    "statusDescription": "successfully",
    "dataTotalCount": 1
  },
  "data": {
    "url": "https://gugudata.github.io/gugudata-io/guides/article-content-extraction-api-seo-guide/",
    "title": "Article Content Extraction API Integration Guide | GuGuData.io Guides",
    "description": "Extract LLM-ready article text, readable HTML, metadata, images, author, publication time, and source for RAG, search, monitoring, and analysis.",
    "content": "<div><div><h1>Article Content Extraction API Integration Guide</h1>\n<p>Search teams, content platforms, and data products often start with the same messy input: a public article URL. The page may include navigation, cookie banners, related posts, comments, scripts, and layout HTML. What you usually need for an SEO workflow is much smaller and much more structured: the article title, description, readable body, plain text, main image, image candidates, author, published time, and source domain.</p>\n<p>The <a href=\"https://gugudata.io/details/fetchcontent\">GuGuData Article Content Extraction API</a> is designed for that exact job. It extracts clean article content from a public webpage URL and returns a normalized JSON response that can be stored, indexed, summarized, compared, or passed int…",
    "contentText": "Article Content Extraction API Integration Guide\nSearch teams, content platforms, and data products often start with the same messy input: a public article URL. The page may include navigation, cookie banners, related posts, comments, scripts, and layout HTML. What you usually need for an SEO workflow is much smaller and much more structured: the article title, description, readable body, plain text, main image, image candidates, author, published time, and source domain.\nThe GuGuData Article Content Extraction API is designed for that exact job. It extracts clean article content from a public webpage URL and returns a normalized JSON response that can be stored, indexed, summarized, compared, or passed into downstream SEO automation.\nThis guide explains where the API fits in an SEO stack,…",
    "image": "",
    "images": [],
    "author": "",
    "published": "2026-07-08 00:00",
    "source": "gugudata.github.io"
  }
}

API documentation Try Demo

Frequently asked questions

Common questions about request limits, trials, renewal, and cancellation.

What does the 5 requests per second limit mean?

It is a request-rate limit, not a concurrency allowance. Keep your request rate at or below 5 per second. If the service returns a rate-limit response, reduce the frequency and retry with backoff.

Is total paid usage limited?

There is no total request cap during an active paid subscription and no usage-based overage charge.

How does the free trial work?

Each account can receive a limited trial key. Requests are shared across APIs in the same category. Check Trial Keys for the exact allowance and remaining requests.

How do renewal and cancellation work?

The plan renews annually until canceled. Manage or cancel the renewal from Dashboard → Orders & Billing. Access continues through the paid period after cancellation. See the Terms of Service for the current refund policy. If the billing portal is unavailable, contact support.

Technical support

Need help choosing an API or getting started?

[email protected]

Service terms

Read our service terms and privacy policy before subscribing.