RFC: optional actionable-snapshot ExtractionStrategy — elements + selectors + state, ~68% lighter than raw_markdown for action-selection
Los mantenedores suelen responder en 1 día
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 35/100
Línea de trabajo
Read Crawl4AI's ExtractionStrategy implementation and the existing optional LLM strategies to understand how strategies are integrated and dependencies handled. The proposed adapter uses ZeroDOM's parse_html, to_compact_text, and ref_map APIs; the issue says it has been verified against zerodom 0.1.4. If maintainers invite a PR, add the strategy module, a test, and a short docs example; done means it runs through CrawlerRunConfig with HTML input and stays opt-in.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Problem
Agents built on top of Crawl4AI that need to act on a page (click/fill) mostly need
one thing from a crawl: the actionable elements and a way to target each. Today the
lightest thing available is cleaned content / markdown — great for reading and
extraction, but it carries the page's prose and doesn't hand back stable selectors to act
with. There's no actionable, selector-backed representation to reach for.
Proposed solution
An opt-in ExtractionStrategy (ZeroDOMExtractionStrategy) that returns a flat,
uniquely-addressable actionable snapshot as extracted_content:
[01] Log in
[02] input Password filled
[03] button Sign in
with the CSS selectors kept out of the model context in a ref_map
({"01": "body > a", ...}) so a downstream agent can act on what it read. State markers
are inline (x checked, empty, filled, active tab…), and sensitive values are
redacted (a filled password/card/CVV/SSN shows as filled, never the value).
It's thin glue over ZeroDOM (zerodom>=0.1.4
on PyPI), already verified to conform and run through Crawl4AI's own run() path with
input_format="html":
from crawl4ai.extraction_strategy import ExtractionStrategy
class ZeroDOMExtractionStrategy(ExtractionStrategy):
def __init__(self, viewport_only=False, with_selectors=True, **kwargs):
kwargs["input_format"] = "html"
super().__init__(**kwargs)
self.viewport_only = viewport_only; self.with_selectors = with_selectors
import zerodom # optional dep; imported only when this strategy is used
def extract(self, url, html, *q, **kwargs):
from zerodom import parse_html
g = parse_html(html or "", url=url, viewport_only=self.viewport_only)
b = {"index": 0, "tags": ["zerodom.snapshot"], "content": g.to_compact_text(terse=True)}
if self.with_selectors: b["ref_map"] = g.ref_map()
return [b]
CrawlerRunConfig(extraction_strategy=ZeroDOMExtractionStrategy())
Fully opt-in: no change to markdown/scraping/other extraction, and no new hard
dependency — zerodom is imported only if you instantiate the strategy (same pattern
as the LLM strategies' optional deps).
Measured — against Crawl4AI's own raw_markdown
Same pages, run through Crawl4AI via raw:// (its real pipeline), tokens via tiktoken
cl100k_base. Snapshot vs the page's own raw_markdown:
| page | raw_markdown | snapshot | fewer |
|---|---|---|---|
| en.wikipedia.org (Web scraping) | 16,717 | 5,178 | 69% |
| docs.python.org/3 | 13,654 | 1,016 | 93% |
| flask.palletsprojects.com | 16,289 | 2,462 | 85% |
| developer.mozilla.org | 3,977 | 1,649 | 59% |
| go.dev | 3,975 | 1,440 | 64% |
| news.ycombinator.com | 4,304 | 2,652 | 38% |
| www.python.org | 4,125 | 1,300 | 68% |
| gov.uk | 2,506 | 693 | 72% |
| www.rust-lang.org | 1,314 | 262 | 80% |
| httpbin.org/forms/post | 51 | 103 | −102% |
Median ~68% fewer tokens across 15 pages. Honest edges: on a trivial form-only page
(httpbin.org/forms/post) the snapshot is larger — there's almost no prose to drop and
the element list has its own floor. And this is deliberately not like-for-like:
markdown is prose for reading/extraction; this is actionable elements for acting. It's
leaner because it drops prose — but it's also the only representation here that carries
selectors + element state, which markdown doesn't. So the win is "a purpose-built, lighter
action representation Crawl4AI doesn't have today," not "a better markdown."
For reference vs other tools (not Crawl4AI): ~1/5 the tokens of Stagehand's
observe() a11y tree and ~49% leaner than agent-browser snapshot -i at matching
coverage — methodology/raw runs in the ZeroDOM repo (benchmarks/). Parse is
deterministic, no LLM, network-free.
Honest scope / caveats
- For the single-shot action-perception use case — not a markdown or data-extraction
replacement (it drops prose by design). - Crawl4AI hands the strategy already-rendered HTML, so state comes from the static
DOM that HTML exposes (aria/native attributes, serialized values). Live-only DOM
properties set purely in JS after render aren't visible to an HTML-only parse.
Alternatives considered
- Trimming markdown/content in place — smaller win, and it couples the action and
extraction paths that want different things. - Keeping it fully external — works today, but a first-class opt-in strategy is where
it actually saves users tokens on the action path without plumbing.
Are you open to an invited PR?
The adapter is written and verified to conform to ExtractionStrategy and run through
Crawl4AI's pipeline against the published zerodom 0.1.4. Happy to open a PR with the
strategy module + a test + a short docs example on your word — wanted to check interest
and get a pointer to where you'd like it to live first.
- Lenguaje dominante
- Python
- Estrellas
- 87.2k
- Forks
- 9.1k
- Merge medio
- 1 d 6 h
- PR fusionados (30 d)
- 25
Preparar el entorno
- Incluye un Dockerfile o un archivo de Docker Compose
- Tiene una plantilla de pull request
- Leer la guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de unclecode/crawl4ai
-
BUG: UserAgentGenerator.generate ignores browser_type and returns a random browser stackPosiblemente ocupada @HhH666-ux la tomó hoy. Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 85/100
Los mantenedores suelen responder en 1 día
-
[Bug]: Hardened docker-compose (read_only) keeps full Chromium from starting: crashpad needs a writable ~/.configPosiblemente ocupada Un pull request vinculado a esta issue está abierto o ya se fusionó. Abierto🐞 Bug 📌 Root caused
Dificultad 2/5 1-3 horas Aptitud para principiantes 70/100
unclecode/crawl4ai#2494 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
[Feature]: Crawl4aiDockerClient has no public option for the API token the 0.9 server requiresAbierto⚙ Done ✨ Enhancement
Dificultad 2/5 1-3 horas Aptitud para principiantes 77/100
Los mantenedores suelen responder en 1 día
-
⚙ Done 🐞 Bug 📌 Root caused
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
Los mantenedores suelen responder en 1 día
-
[Bug]: PDF images saved with save_images_locally=True come back with an empty src in result.mediaAbierto⚙ Done 🐞 Bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
unclecode/crawl4ai#2469 · 1 comentario ·
Los mantenedores suelen responder en 1 día
Todos los issues de unclecode/crawl4ai
Issues similares
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 1 día
-
documentation
Dificultad 2/5 1-3 horas Aptitud para principiantes 85/100
Los mantenedores suelen responder en 1 día
-
Install the skills as a Claude Code pluginPosiblemente ocupada @ruban-24 la tomó hoy. Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 6 días
-
Make the usage of time-zone aware UTC timestamps the norm across the pynxtools NOMAD ecosystemAbierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 62/100
FAIRmat-NFDI/pynxtools#874 ·
-
Eval: PublicationAbiertodata
Dificultad 2/5 1-3 horas Aptitud para principiantes 66/100