mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-02 05:38:12 +00:00
a237ebabba
* feat: adopt directory-based docs versioning with Edge channel Switch docs.crewai.com from navigation-only versioning (every version selector entry rendered the same docs/<lang>/* source files) to Mintlify's directory-based versioning so each version selector entry renders its own snapshot. Add an "Edge" channel under docs/edge/<lang>/* that always reflects main HEAD for unreleased work, eliminating pre-release leakage onto frozen release labels. External links to canonical /<lang>/* URLs are preserved via wildcard redirects that always land on the current default version. Layout: - docs/edge/<lang>/* rolling source (you edit here) - docs/edge/enterprise-api.*.yaml - docs/v<X.Y.Z>/<lang>/* frozen, immutable snapshots - docs/v<X.Y.Z>/enterprise-api.*.yaml - docs/images/ shared, append-only - docs/docs.json nav + redirects URLs follow the Mintlify-idiomatic shape: /edge/<lang>/<page> for Edge, /v<X.Y.Z>/<lang>/<page> for every frozen snapshot. The wildcard redirects /<lang>/:slug* -> /<default>/<lang>/:slug* keep stale links working, and every freeze rewrites them (plus all per-section/per-page redirects) so destinations always resolve to the current default without depending on a second redirect hop. Release flow integration (devtools release): - New module crewai_devtools.docs_versioning.freeze() materialises docs/v<X.Y.Z>/ from docs/edge/, rewrites openapi: refs inside the snapshot, inserts the version into every language block in docs.json, and refreshes all redirect destinations. - _update_docs_and_create_pr() in cli.py now calls that freeze during Phase 2 of devtools release. Edge changelogs are updated first (so the snapshot freeze picks them up), then the snapshot is staged alongside docs.json, branched as docs/freeze-v<X.Y.Z>, and the PR is titled [docs-freeze] docs: snapshot and changelog for v<X.Y.Z> — the title prefix the new CI guard reads. - The PR still gates tag, GitHub release, PyPI publish, and the enterprise release as before; no new PRs are added. - Pre-releases (1.X.YaN, 1.X.YbN, ...) skip the snapshot — they ride Edge — and the docs PR title omits the [docs-freeze] prefix. - docs_check (AI-generated docs scaffolding) writes to docs/edge/<lang>/* so newly-generated unreleased docs land in Edge and never accidentally touch a frozen snapshot. Migration scripts (one-shot): - scripts/docs/freeze_historical_versions.py reconstructs all 16 historical snapshots (v1.10.0 .. v1.14.7) from git tags via git archive | tar, rewriting openapi: MDX refs so each snapshot reads its own enterprise-api YAML rather than the live one. - scripts/docs/prefix_version_paths.py one-shot-migrates docs.json: rewrites every page path in 16 versioned blocks to point under docs/v<X.Y.Z>/, inserts a new Edge entry per language, tags v1.14.7 as Latest (default), prunes pages whose target file doesn't exist in the snapshot (e.g. docs/ar/ didn't exist before v1.12.0), and writes the wildcard + per-section redirects. - scripts/docs/freeze_current_edge.py is now a thin CLI wrapper around docs_versioning.freeze for manual one-off freezes (e.g. retroactively snapshotting a forgotten release). CI guards (.github/workflows/docs-snapshots.yml): - Frozen snapshots under docs/v[0-9]*/ are immutable; only PRs whose title contains [docs-freeze] (i.e. release-cut PRs generated by devtools release or the manual wrapper) may modify them. - Images under docs/images/ are append-only since snapshots share a single image directory. Deleting or renaming an image breaks every historical snapshot that still references it. Restored docs/images/crewai-otel-export.png from PR #3673; it was deleted in PR #4908 but v1.10.0 / v1.10.1 snapshots still reference it. Restoring instead of editing the snapshots preserves historical rendering fidelity and validates the new append-only rule retroactively. Tests: - lib/devtools/tests/test_docs_versioning.py covers the freeze: file copy, openapi rewrite, version insertion, default demotion, redirect upserts, per-section redirect rewriting, idempotency, and invalid inputs. Verified locally with mintlify broken-links: 0 broken links across the full site (Edge + 16 frozen versions, 4 locales). AGENTS.md (repo root) is the contributor guide for the new model; RELEASING.md is the release-cut runbook; README's Contribution section links to both. Co-authored-by: Cursor <cursoragent@cursor.com> * style: resolve linter issues --------- Co-authored-by: Cursor <cursoragent@cursor.com>
109 lines
5.2 KiB
Plaintext
109 lines
5.2 KiB
Plaintext
---
|
|
title: "Visão Geral"
|
|
description: "Extraia dados de websites e automatize interações com o navegador utilizando poderosas ferramentas de scraping"
|
|
icon: "face-smile"
|
|
mode: "wide"
|
|
---
|
|
|
|
Essas ferramentas permitem que seus agentes interajam com a web, extraiam dados de websites e automatizem tarefas baseadas em navegador. De raspagem simples a automação complexa de navegador, essas ferramentas cobrem todas as suas necessidades de interação com a web.
|
|
|
|
## **Ferramentas Disponíveis**
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Ferramenta de Scrape de Website" icon="globe" href="/pt-BR/tools/web-scraping/scrapewebsitetool">
|
|
Ferramenta de raspagem de uso geral para extrair conteúdo de qualquer site.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta de Scrape de Elemento" icon="crosshairs" href="/pt-BR/tools/web-scraping/scrapeelementfromwebsitetool">
|
|
Extraia elementos específicos de páginas web com capacidades de raspagem precisa.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Firecrawl Crawl" icon="spider" href="/pt-BR/tools/web-scraping/firecrawlcrawlwebsitetool">
|
|
Rastreie sites inteiros de forma sistemática com o poderoso mecanismo do Firecrawl.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Firecrawl Scrape" icon="fire" href="/pt-BR/tools/web-scraping/firecrawlscrapewebsitetool">
|
|
Raspagem web de alta performance com as capacidades avançadas do Firecrawl.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Firecrawl Search" icon="magnifying-glass" href="/pt-BR/tools/web-scraping/firecrawlsearchtool">
|
|
Pesquise e extraia conteúdos específicos utilizando os recursos de busca do Firecrawl.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Selenium Scraping" icon="robot" href="/pt-BR/tools/web-scraping/seleniumscrapingtool">
|
|
Automação de navegador e scraping com as capacidades do Selenium WebDriver.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta ScrapFly" icon="plane" href="/pt-BR/tools/web-scraping/scrapflyscrapetool">
|
|
Raspagem profissional de web com o serviço premium do ScrapFly.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta ScrapGraph" icon="network-wired" href="/pt-BR/tools/web-scraping/scrapegraphscrapetool">
|
|
Raspagem baseada em grafos para relacionamentos de dados complexos.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Spider" icon="spider" href="/pt-BR/tools/web-scraping/spidertool">
|
|
Rastreio abrangente de sites e capacidades de extração de dados.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta BrowserBase" icon="browser" href="/pt-BR/tools/web-scraping/browserbaseloadtool">
|
|
Automação de navegador baseada em nuvem com a infraestrutura do BrowserBase.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta HyperBrowser" icon="window-maximize" href="/pt-BR/tools/web-scraping/hyperbrowserloadtool">
|
|
Interações rápidas com o navegador através do engine otimizado do HyperBrowser.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Stagehand" icon="hand" href="/pt-BR/tools/web-scraping/stagehandtool">
|
|
Automação inteligente de navegador com comandos em linguagem natural.
|
|
</Card>
|
|
|
|
<Card title="Ferramenta Oxylabs Scraper" icon="globe" href="/pt-BR/tools/web-scraping/oxylabsscraperstool">
|
|
Acesse dados web em escala com o Oxylabs.
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
## **Casos de Uso Comuns**
|
|
|
|
- **Extração de Dados**: Raspagem de informações de produtos, preços e avaliações
|
|
- **Monitoramento de Conteúdo**: Acompanhe mudanças em sites e fontes de notícias
|
|
- **Geração de Leads**: Extraia informações de contato e dados de empresas
|
|
- **Pesquisa de Mercado**: Coleta de inteligência competitiva e dados de mercado
|
|
- **Testes & QA**: Automatize fluxos de teste e validação em navegadores
|
|
- **Mídias Sociais**: Extraia posts, comentários e análises de redes sociais
|
|
|
|
## **Exemplo de Início Rápido**
|
|
|
|
```python
|
|
from crewai_tools import ScrapeWebsiteTool, FirecrawlScrapeWebsiteTool, SeleniumScrapingTool
|
|
|
|
# Create scraping tools
|
|
simple_scraper = ScrapeWebsiteTool()
|
|
advanced_scraper = FirecrawlScrapeWebsiteTool()
|
|
browser_automation = SeleniumScrapingTool()
|
|
|
|
# Add to your agent
|
|
agent = Agent(
|
|
role="Web Research Specialist",
|
|
tools=[simple_scraper, advanced_scraper, browser_automation],
|
|
goal="Extract and analyze web data efficiently"
|
|
)
|
|
```
|
|
|
|
## **Boas Práticas de Scraping**
|
|
|
|
- **Respeite o robots.txt**: Sempre verifique e siga as políticas de scraping do website
|
|
- **Controle de Taxa (Rate Limiting)**: Implemente atrasos entre as requisições para evitar sobrecarregar servidores
|
|
- **User Agents**: Use strings de user agent apropriadas para identificar o seu bot
|
|
- **Conformidade Legal**: Certifique-se de que suas atividades de scraping estejam em conformidade com os termos de serviço
|
|
- **Tratamento de Erros**: Implemente um tratamento de erros robusto para problemas de rede e requisições bloqueadas
|
|
- **Qualidade dos Dados**: Valide e limpe os dados extraídos antes de processar
|
|
|
|
## **Guia de Seleção de Ferramentas**
|
|
|
|
- **Tarefas Simples**: Use `ScrapeWebsiteTool` para extração básica de conteúdo
|
|
- **Sites Dinâmicos com JavaScript**: Use `SeleniumScrapingTool` para conteúdo dinâmico
|
|
- **Escala & Performance**: Use `FirecrawlScrapeWebsiteTool` para scraping em grande volume
|
|
- **Infraestrutura em Nuvem**: Use `BrowserBaseLoadTool` para automação de navegador escalável
|
|
- **Fluxos Complexos**: Use `StagehandTool` para interações inteligentes com o navegador
|