llm-html
CMDOP Skill — install and use via CMDOP agent:
cmdop-skill install llm-html
LLM-optimized HTML cleaning: hydration extraction, token budgets, multiple output formats.
Install
pip install llm-html
Quick Start
from llm_html import HTMLCleaner, CleanerConfig, OutputFormat
# Basic cleaning
cleaner = HTMLCleaner()
result = cleaner.clean(html)
print(f"Reduction: {result.stats.reduction_percent}%")
# Hydration-first (extracts SSR data from Next.js, Nuxt, etc.)
if result.hydration_data:
data = result.hydration_data
else:
cleaned = result.html
Convenience Functions
from llm_html import clean, clean_to_json, clean_html, clean_for_llm
# Quick clean
result = clean(html)
# Get JSON if SSR data available, otherwise cleaned HTML
data = clean_to_json(html)
# Pipeline with full control
result = clean_html(html, max_tokens=5000)
result = clean_for_llm(html, output_format="markdown")
Output Formats
from llm_html import to_markdown, to_aom_yaml, to_xtree
md = to_markdown(html)
aom = to_aom_yaml(html)
xtree = to_xtree(html)
Downsampling
Token-budget targeting with D2Snap algorithm:
from llm_html import downsample_html, estimate_tokens
tokens = estimate_tokens(html)
if tokens > 10000:
html = downsample_html(html, target_tokens=8000)
Semantic Chunking
Split large pages into LLM-sized chunks:
from llm_html import SemanticChunker, ChunkConfig
config = ChunkConfig(max_tokens=8000, max_items=20)
chunker = SemanticChunker(config)
result = chunker.chunk(soup)
for chunk in result.chunks:
process(chunk.html)
Shadow DOM
Flatten Web Components for LLM visibility:
from llm_html import flatten_shadow_dom
flat = flatten_shadow_dom(html)
Helpers
from llm_html import html_to_text, extract_links, extract_images, json_to_toon
text = html_to_text(html)
links = extract_links(html, base_url="https://example.com")
images = extract_images(html)
toon = json_to_toon({"key": "value"})
License
MIT
Metadata
Release files for llm-html 0.1.14
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llm_html-0.1.14.tar.gz | 53.8 kB | Without provenance | Details for llm_html-0.1.14.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_html-0.1.14-py3-none-any.whl | Python 3 | none | any | Details for llm_html-0.1.14-py3-none-any.whl |
Total release size: 124.5 kB
Release files / llm_html-0.1.14.tar.gz
| Download URL | llm_html-0.1.14.tar.gz |
|---|---|
| Size | 53.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
50dce8f524b9b2d532c87cb09e664f5786d8d1981ae3069fa70279dc6930a79e
|
|
BLAKE2b-256 checksum How to use checksums |
275440733a4aa8dbd78d2429193570879e988969985da414bdb63251e4cede7a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.18
|
Release files / llm_html-0.1.14-py3-none-any.whl
| Download URL | llm_html-0.1.14-py3-none-any.whl |
|---|---|
| Size | 70.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d6c5ebddaa8fc5d224437cce89084179da1080cd9159faccea101028a4cd72ab
|
|
BLAKE2b-256 checksum How to use checksums |
da8de6183905dd70ab0b3d3e11a215be506754c3c959a3f80aa248d98bc19c9b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.18
|
Security for llm-html 0.1.14
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.