Skip to main content
The /api/extract endpoint converts page content into structured items.

​
A simple extraction

Key parameters:
  • url or urls (single URL or a list)
  • template (string or object)
The template can be a dictionary or a string:
  • Dictionary/object: output items follow the keys you provide.
  • String: FetchFox infers a schema from your prompt.
Example: 
curl -X POST "https://api.fetchfox.ai/api/extract" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $FETCHFOX_API_KEY" \
-d '{
   "urls": [
     "https://pokemondb.net/pokedex/bulbasaur",
     "https://pokemondb.net/pokedex/ivysaur",
     "https://pokemondb.net/pokedex/venusaur"
   ],
   "template": {
     "name": "Name of the pokemon",
     "number": "National pokedex number",
     "stats": "Base stats as a dictionary"
   }
}'
Response: 
{
  "jobId": "j8rcgsnxq3",
  "results": {
    "items": [
      {
        "name": "Bulbasaur",
        "number": "0001",
        "stats": {
          "HP": 45,
          "Attack": 49,
          "Defense": 49,
          "Sp. Atk": 65,
          "Sp. Def": 65,
          "Speed": 45,
          "Total": 318
        },
        "_url": "https://pokemondb.net/pokedex/bulbasaur",
        "_htmlUrl": "https://ffcloud.s3.amazonaws.com/visit/html/4h0o70v9fh.html"
      },
      "...more results..."
    ]
  },
  "metrics": { "...cost and usage metrics..." }
}

​
Extracting multiple items per URL

By default, FetchFox extracts one item per URL. To extract multiple items from each page, set perPage to many. Example: 
curl -X POST "https://api.fetchfox.ai/api/extract" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $FETCHFOX_API_KEY" \
-d '{
   "urls": [
     "https://pokemondb.net/pokedex/bulbasaur",
     "https://pokemondb.net/pokedex/ivysaur",
     "https://pokemondb.net/pokedex/venusaur"
   ],
   "template": {
     "moveName": "Name of the pokemon move",
     "moveType": "Name of the move type",
     "movePower": "The power of the move"
   },
   "perPage": "many"
}'
Response: 
{
  "jobId": "fjszygdh38",
  "results": {
    "items": [
      {
        "moveName": "Growl",
        "moveType": "Normal",
        "movePower": "100",
        "_url": "https://pokemondb.net/pokedex/ivysaur",
        "_htmlUrl": "https://ffcloud.s3.amazonaws.com/visit/html/xz6rjf8h2v.html"
      },
      {
        "moveName": "Growth",
        "moveType": "Normal",
        "movePower": "—",
        "_url": "https://pokemondb.net/pokedex/ivysaur",
        "_htmlUrl": "https://ffcloud.s3.amazonaws.com/visit/html/xz6rjf8h2v.html"
      },
      "...more items..."
    ]
  },
  "metrics": { "...cost and usage metrics..." }
}
When perPage: "many" is used, the response includes a divide artifact showing the selector used to split the page into repeated item blocks.

​
Boosted extractions

The first few extractions for a given page pattern and template are usually done by sending page HTML to an AI model. After FetchFox has a few successful examples, the backend asks a more advanced model to write extraction code for that pattern and template. Later extractions can then run that generated code directly. That means repeated extractions usually get faster over time, and boosted runs typically have no AI cost for the extraction step.