HTML

gllm-docproc | Tutorial: HTML Flat Parser | Use Case: Advanced DPO Pipeline | API Reference

HTML Flat Parser is responsible for parsing elements loaded from web content. It assigns a structure to each loaded element based on the HTML tags present in its metadata, mapping them into structures such as heading, paragraph, image, video, audio, table, header, footer, and title.

This page provides guide to use HTML Flat Parser in Document Processing Orchestrator (DPO).

Prerequisites

This example specifically requires completion of all setup steps listed on the Prerequisites page.

Installation

Linux, macOS, or Windows WSL

# you can use a Conda environment
pip install --extra-index-url https://oauth2accesstoken:$(gcloud auth print-access-token)@glsdk.gdplabs.id/gen-ai-internal/simple/ "gllm-docproc[html]"

Windows Powershell

Windows Command Prompt

You can use the following as a sample file: loaded_elements.json.

1

Create a script called main.py:

import json
from gllm_docproc.parser.html import HTMLFlatParser

# read JSON file with content and element_metadata
file_path = "./data/source/loaded_elements.json"
with open(file_path, "r", encoding="utf-8") as f:
    loaded_elements = json.load(f)

# initialize the HTML Flat Parser
parser = HTMLFlatParser()

# parse loaded elements
parsed_elements = parser.parse(loaded_elements)

2

Run the script:

python main.py

3

The loader & parser will generate the following: output JSON.