OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Parsera

Parsera is a Python library that uses large language models to extract specified information from websites and return it as structured records. Its documentation also describes an open web application for scraping a few pages and an API for more scalable scraping.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Parsera — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Parsera when you need to turn webpage content into records shaped around fields you specify, and can configure the documented model credentials and runtime prerequisites.

Who it is for

  • Developers building Python workflows that collect defined fields from webpages.
  • Teams evaluating a web application or API route for webpage extraction.

Documented uses

  • Describe the fields to collect from a URL and retrieve them as JSON records.
  • Request typed values, such as strings, integers or booleans, in structured extraction.
  • Run a documented extraction asynchronously or from the command line.
Before you choose

Requirements & limits

The documentation describes an open web application, local library use and an API. The documented local setup uses API credentials; the command-line instructions specify an OpenAI API key.

  • Choose among the web application, local library and API according to the documented scale distinction: a few pages, smaller-scale experiments, or a more scalable solution.
  • The Python setup requires installing both Parsera and Playwright.
  • Typed extraction supports several basic and compound data types and is documented as using the Structured Extractor.
  • Further documentation covers custom models, proxies, custom Playwright settings, extractors, cookies and Docker.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Extract webpage fields with the Python library

Run the documented basic workflow to collect specified fields from a webpage as JSON records.

Before you start

  • Python environment
  • Parsera installed with pip install parsera
  • Playwright installed with playwright install
  • A Parsera API key set as PARSERA_API_KEY

Steps

  1. Install Parsera and Playwright.

  2. Set PARSERA_API_KEY in the environment.

  3. Import Parsera, provide a URL and an elements mapping that names and describes the fields to extract.

  4. Create a Parsera instance and call run(url=url, elements=elements).

Expected outcome

A JSON list of records containing the requested fields.

Guide limitations

  • The documented API-key setup applies to the basic example; the documentation says custom LLMs use a separate configuration path.
  • The guide does not establish that extraction will work on every website.
Documentation 1 ↗
Source-based practical guide

Run Parsera from the command line

Use the documented CLI to parse a URL with a JSON schema or a schema file.

Before you start

  • Parsera installed in the Python environment
  • An OpenAI API key set in environment variables or a .env file
  • A URL and either a JSON schema or a schema filename

Steps

  1. Set OPENAI_API_KEY in an environment variable or .env file.

  2. Provide the URL and a JSON schema or filename using the documented CLI usage.

  3. Optionally provide an output filename.

Expected outcome

The CLI runs Parsera on the supplied URL and can write output to a specified file.

Guide limitations

  • The documentation gives the command form but does not specify the output-file format.
Documentation 1 ↗
Evidence and transparency

Sources & review

docs.parsera.org ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
3 November 2026
How we review sourcesSuggest a correction