RFC: optional actionable-snapshot ExtractionStrategy — elements + selectors + state, ~68% lighter than raw_markdown for action-selection
Les mainteneurs répondent en général sous 1 jour
Personne n'a encore pris cette issue.
Évaluation
- Difficulté
- 4/5
- Temps estimé
- 3-5 jours
- Accessibilité débutants
- 35/100
Piste de recherche
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.
Rédigé par le modèle d'indexation à partir du texte de l'issue.
Description
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.
- Langage dominant
- Python
- Étoiles
- 87.2k
- Forks
- 9.1k
- Merge moyen
- 1 j 6 h
- PR mergées (30 j)
- 25
Préparer son environnement
- Fournit un Dockerfile ou un fichier Docker Compose
- Propose un modèle de pull request
- Lire le guide de contribution
Par où commencer
- Lisez l'issue en entier, puis le guide de contribution du projet.
- Signalez en commentaire que vous la prenez — cela évite que deux personnes fassent le même travail.
- Forkez le dépôt et travaillez sur une branche.
- Ouvrez une pull request qui référence le numéro de l'issue.
Autres issues de unclecode/crawl4ai
-
BUG: UserAgentGenerator.generate ignores browser_type and returns a random browser stackPeut-être pris @HhH666-ux l’a pris aujourd’hui. Ouverte
Difficulté 2/5 1-3 heures Accessibilité débutants 85/100
Les mainteneurs répondent en général sous 1 jour
-
[Bug]: Hardened docker-compose (read_only) keeps full Chromium from starting: crashpad needs a writable ~/.configPeut-être pris Une pull request liée à cette issue est ouverte ou déjà fusionnée. Ouverte🐞 Bug 📌 Root caused
Difficulté 2/5 1-3 heures Accessibilité débutants 70/100
unclecode/crawl4ai#2494 · 1 commentaire ·
Les mainteneurs répondent en général sous 1 jour
-
[Feature]: Crawl4aiDockerClient has no public option for the API token the 0.9 server requiresOuverte⚙ Done ✨ Enhancement
Difficulté 2/5 1-3 heures Accessibilité débutants 77/100
Les mainteneurs répondent en général sous 1 jour
-
⚙ Done 🐞 Bug 📌 Root caused
Difficulté 2/5 1-3 heures Accessibilité débutants 72/100
Les mainteneurs répondent en général sous 1 jour
-
[Bug]: PDF images saved with save_images_locally=True come back with an empty src in result.mediaOuverte⚙ Done 🐞 Bug
Difficulté 2/5 1-3 heures Accessibilité débutants 78/100
unclecode/crawl4ai#2469 · 1 commentaire ·
Les mainteneurs répondent en général sous 1 jour
Toutes les issues de unclecode/crawl4ai
Issues similaires
-
Difficulté 2/5 1-3 heures Accessibilité débutants 76/100
Les mainteneurs répondent en général sous 1 jour
-
documentation
Difficulté 2/5 1-3 heures Accessibilité débutants 85/100
Les mainteneurs répondent en général sous 1 jour
-
Install the skills as a Claude Code pluginPeut-être pris @ruban-24 l’a pris aujourd’hui. Ouverte
Difficulté 2/5 1-3 heures Accessibilité débutants 76/100
Les mainteneurs répondent en général sous 6 jours
-
Make the usage of time-zone aware UTC timestamps the norm across the pynxtools NOMAD ecosystemOuverte
Difficulté 2/5 1-3 heures Accessibilité débutants 62/100
FAIRmat-NFDI/pynxtools#874 ·
-
Eval: PublicationOuvertedata
Difficulté 2/5 1-3 heures Accessibilité débutants 66/100