RFC: optional actionable-snapshot ExtractionStrategy — elements + selectors + state, ~68% lighter than raw_markdown for action-selection
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Idoneità per principianti
- 35/100
Direzione di ricerca
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.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
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.
- Lingua principale
- Python
- Stelle
- 87.2k
- Fork
- 9.1k
- Merge medio
- 1g 6h
- PR unite (30g)
- 25
Preparare l'ambiente
- Include un Dockerfile o un file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di unclecode/crawl4ai
-
BUG: UserAgentGenerator.generate ignores browser_type and returns a random browser stackForse già presa @HhH666-ux l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 85/100
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: Hardened docker-compose (read_only) keeps full Chromium from starting: crashpad needs a writable ~/.configForse già presa Una pull request collegata a questa issue è aperta o già unita. Aperta🐞 Bug 📌 Root caused
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
unclecode/crawl4ai#2494 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
[Feature]: Crawl4aiDockerClient has no public option for the API token the 0.9 server requiresAperta⚙ Done ✨ Enhancement
Difficoltà 2/5 1-3 ore Idoneità per principianti 77/100
I maintainer di solito rispondono entro 1 giorno
-
⚙ Done 🐞 Bug 📌 Root caused
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: PDF images saved with save_images_locally=True come back with an empty src in result.mediaAperta⚙ Done 🐞 Bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
unclecode/crawl4ai#2469 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di unclecode/crawl4ai
Issue simili
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
I maintainer di solito rispondono entro 1 giorno
-
documentation
Difficoltà 2/5 1-3 ore Idoneità per principianti 85/100
I maintainer di solito rispondono entro 1 giorno
-
Install the skills as a Claude Code pluginForse già presa @ruban-24 l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
I maintainer di solito rispondono entro 6 giorni
-
Make the usage of time-zone aware UTC timestamps the norm across the pynxtools NOMAD ecosystemAperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 62/100
FAIRmat-NFDI/pynxtools#874 ·
-
Eval: PublicationApertadata
Difficoltà 2/5 1-3 ore Idoneità per principianti 66/100