Files
crawl4ai/docs/releases_review/v0.7.5_video_walkthrough.ipynb
Nasrin 7cac008c10 Release/v0.7.6 (#1556)
* fix(docker-api): migrate to modern datetime library API

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

* Fix examples in README.md

* feat(docker): add user-provided hooks support to Docker API

Implements comprehensive hooks functionality allowing users to provide custom Python
functions as strings that execute at specific points in the crawling pipeline.

Key Features:
- Support for all 8 crawl4ai hook points:
  • on_browser_created: Initialize browser settings
  • on_page_context_created: Configure page context
  • before_goto: Pre-navigation setup
  • after_goto: Post-navigation processing
  • on_user_agent_updated: User agent modification handling
  • on_execution_started: Crawl execution initialization
  • before_retrieve_html: Pre-extraction processing
  • before_return_html: Final HTML processing

Implementation Details:
- Created UserHookManager for validation, compilation, and safe execution
- Added IsolatedHookWrapper for error isolation and timeout protection
- AST-based validation ensures code structure correctness
- Sandboxed execution with restricted builtins for security
- Configurable timeout (1-120 seconds) prevents infinite loops
- Comprehensive error handling ensures hooks don't crash main process
- Execution tracking with detailed statistics and logging

API Changes:
- Added HookConfig schema with code and timeout fields
- Extended CrawlRequest with optional hooks parameter
- Added /hooks/info endpoint for hook discovery
- Updated /crawl and /crawl/stream endpoints to support hooks

Safety Features:
- Malformed hooks return clear validation errors
- Hook errors are isolated and reported without stopping crawl
- Execution statistics track success/failure/timeout rates
- All hook results are JSON-serializable

Testing:
- Comprehensive test suite covering all 8 hooks
- Error handling and timeout scenarios validated
- Authentication, performance, and content extraction examples
- 100% success rate in production testing

Documentation:
- Added extensive hooks section to docker-deployment.md
- Security warnings about user-provided code risks
- Real-world examples using httpbin.org, GitHub, BBC
- Best practices and troubleshooting guide

ref #1377

* fix(deep-crawl): BestFirst priority inversion; remove pre-scoring truncation. ref #1253

  Use negative scores in PQ to visit high-score URLs first and drop link cap prior to scoring; add test for ordering.

* docs: Update URL seeding examples to use proper async context managers
- Wrap all AsyncUrlSeeder usage with async context managers
- Update URL seeding adventure example to use "sitemap+cc" source, focus on course posts, and add stream=True parameter to fix runtime error

* fix(crawler): Removed the incorrect reference in browser_config variable #1310

* docs: update Docker instructions to use the latest release tag

* fix(docker): Fix LLM API key handling for multi-provider support

Previously, the system incorrectly used OPENAI_API_KEY for all LLM providers
due to a hardcoded api_key_env fallback in config.yml. This caused authentication
errors when using non-OpenAI providers like Gemini.

Changes:
- Remove api_key_env from config.yml to let litellm handle provider-specific env vars
- Simplify get_llm_api_key() to return None, allowing litellm to auto-detect keys
- Update validate_llm_provider() to trust litellm's built-in key detection
- Update documentation to reflect the new automatic key handling

The fix leverages litellm's existing capability to automatically find the correct
environment variable for each provider (OPENAI_API_KEY, GEMINI_API_TOKEN, etc.)
without manual configuration.

ref #1291

* docs: update adaptive crawler docs and cache defaults; remove deprecated examples (#1330)
- Replace BaseStrategy with CrawlStrategy in custom strategy examples (DomainSpecificStrategy, HybridStrategy)
- Remove “Custom Link Scoring” and “Caching Strategy” sections no longer aligned with current library
- Revise memory pruning example to use adaptive.get_relevant_content and index-based retention of top 500 docs
- Correct Quickstart note: default cache mode is CacheMode.BYPASS; instruct enabling with CacheMode.ENABLED

* fix(utils): Improve URL normalization by avoiding quote/unquote to preserve '+' signs. ref #1332

* feat: Add comprehensive website to API example with frontend

This commit adds a complete, web scraping API example that demonstrates how to get structured data from any website and use it like an API using the crawl4ai library with a minimalist frontend interface.

Core Functionality
- AI-powered web scraping with plain English queries
- Dual scraping approaches: Schema-based (faster) and LLM-based (flexible)
- Intelligent schema caching for improved performance
- Custom LLM model support with API key management
- Automatic duplicate request prevention

Modern Frontend Interface
- Minimalist black-and-white design inspired by modern web apps
- Responsive layout with smooth animations and transitions
- Three main pages: Scrape Data, Models Management, API Request History
- Real-time results display with JSON formatting
- Copy-to-clipboard functionality for extracted data
- Toast notifications for user feedback
- Auto-scroll to results when scraping starts

Model Management System
- Web-based model configuration interface
- Support for any LLM provider (OpenAI, Gemini, Anthropic, etc.)
- Simplified configuration requiring only provider and API token
- Add, list, and delete model configurations
- Secure storage of API keys in local JSON files

API Request History
- Automatic saving of all API requests and responses
- Display of request history with URL, query, and cURL commands
- Duplicate prevention (same URL + query combinations)
- Request deletion functionality
- Clean, simplified display focusing on essential information

Technical Implementation

Backend (FastAPI)
- RESTful API with comprehensive endpoints
- Pydantic models for request/response validation
- Async web scraping with crawl4ai library
- Error handling with detailed error messages
- File-based storage for models and request history

Frontend (Vanilla JS/CSS/HTML)
- No framework dependencies - pure HTML, CSS, JavaScript
- Modern CSS Grid and Flexbox layouts
- Custom dropdown styling with SVG arrows
- Responsive design for mobile and desktop
- Smooth scrolling and animations

Core Library Integration
- WebScraperAgent class for orchestration
- ModelConfig class for LLM configuration management
- Schema generation and caching system
- LLM extraction strategy support
- Browser configuration with headless mode

* fix(dependencies): add cssselect to project dependencies

Fixes bug reported in issue #1405
[Bug]: Excluded selector (excluded_selector) doesn't work

This commit reintroduces the cssselect library which was removed by PR (https://github.com/unclecode/crawl4ai/pull/1368) and merged via (437395e490).

Integration tested against 0.7.4 Docker container. Reintroducing cssselector package eliminated errors seen in logs and excluded_selector functionality was restored.

Refs: #1405

* fix(docker): resolve filter serialization and JSON encoding errors in deep crawl strategy (ref #1419)

  - Fix URLPatternFilter serialization by preventing private __slots__ from being serialized as constructor params
  - Add public attributes to URLPatternFilter to store original constructor parameters for proper serialization
  - Handle property descriptors in CrawlResult.model_dump() to prevent JSON serialization errors
  - Ensure filter chains work correctly with Docker client and REST API

  The issue occurred because:
  1. Private implementation details (_simple_suffixes, etc.) were being serialized and passed as constructor arguments during deserialization
  2. Property descriptors were being included in the serialized output, causing "Object of type property is not JSON serializable" errors

  Changes:
  - async_configs.py: Comment out __slots__ serialization logic (lines 100-109)
  - filters.py: Add patterns, use_glob, reverse to URLPatternFilter __slots__ and store as public attributes
  - models.py: Convert property descriptors to strings in model_dump() instead of including them directly

* fix(logger): ensure logger is a Logger instance in crawling strategies. ref #1437

* feat(docker): Add temperature and base_url parameters for LLM configuration. ref #1035

  Implement hierarchical configuration for LLM parameters with support for:
  - Temperature control (0.0-2.0) to adjust response creativity
  - Custom base_url for proxy servers and alternative endpoints
  - 4-tier priority: request params > provider env > global env > defaults

  Add helper functions in utils.py, update API schemas and handlers,
  support environment variables (LLM_TEMPERATURE, OPENAI_TEMPERATURE, etc.),
  and provide comprehensive documentation with examples.

* feat(docker): improve docker error handling
- Return comprehensive error messages along with status codes for api internal errors.
- Fix fit_html property serialization issue in both /crawl and /crawl/stream endpoints
- Add sanitization to ensure fit_html is always JSON-serializable (string or None)
- Add comprehensive error handling test suite.

* #1375 : refactor(proxy) Deprecate 'proxy' parameter in BrowserConfig and enhance proxy string parsing

- Updated ProxyConfig.from_string to support multiple proxy formats, including URLs with credentials.
- Deprecated the 'proxy' parameter in BrowserConfig, replacing it with 'proxy_config' for better flexibility.
- Added warnings for deprecated usage and clarified behavior when both parameters are provided.
- Updated documentation and tests to reflect changes in proxy configuration handling.

* Remove deprecated test for 'proxy' parameter in BrowserConfig and update .gitignore to include test_scripts directory.

* feat: add preserve_https_for_internal_links flag to maintain HTTPS during crawling. Ref #1410

Added a new `preserve_https_for_internal_links` configuration flag that preserves the original HTTPS scheme for same-domain links even when the server redirects to HTTP.

* feat: update documentation for preserve_https_for_internal_links. ref #1410

* fix: drop Python 3.9 support and require Python >=3.10.
The library no longer supports Python 3.9 and so it was important to drop all references to python 3.9.
Following changes have been made:
- pyproject.toml: set requires-python to ">=3.10"; remove 3.9 classifier
- setup.py: set python_requires to ">=3.10"; remove 3.9 classifier
- docs: update Python version mentions
  - deploy/docker/c4ai-doc-context.md: options -> 3.10, 3.11, 3.12, 3.13

* issue #1329 refactor(crawler): move unwanted properties to CrawlerRunConfig class

* fix(auth): fixed Docker JWT authentication. ref #1442

* remove: delete unused yoyo snapshot subproject

* fix: raise error on last attempt failure in perform_completion_with_backoff. ref #989

* Commit without API

* fix: update option labels in request builder for clarity

* fix: allow custom LLM providers for adaptive crawler embedding config. ref: #1291

  - Change embedding_llm_config from Dict to Union[LLMConfig, Dict] for type safety
  - Add backward-compatible conversion property _embedding_llm_config_dict
  - Replace all hardcoded OpenAI embedding configs with configurable options
  - Fix LLMConfig object attribute access in query expansion logic
  - Add comprehensive example demonstrating multiple provider configurations
  - Update documentation with both LLMConfig object and dictionary usage patterns

  Users can now specify any LLM provider for query expansion in embedding strategy:
  - New: embedding_llm_config=LLMConfig(provider='anthropic/claude-3', api_token='key')
  - Old: embedding_llm_config={'provider': 'openai/gpt-4', 'api_token': 'key'} (still works)

* refactor(BrowserConfig): change deprecation warning for 'proxy' parameter to UserWarning

* feat(StealthAdapter): fix stealth features for Playwright integration. ref #1481

* #1505 fix(api): update config handling to only set base config if not provided by user

* fix(docker-deployment): replace console.log with print for metadata extraction

* Release v0.7.5: The Update

- Updated version to 0.7.5
- Added comprehensive demo and release notes
- Updated documentation

* refactor(release): remove memory management section for cleaner documentation. ref #1443

* feat(docs): add brand book and page copy functionality

- Add comprehensive brand book with color system, typography, components
- Add page copy dropdown with markdown copy/view functionality
- Update mkdocs.yml with new assets and branding navigation
- Use terminal-style ASCII icons and condensed menu design

* Update gitignore add local scripts folder

* fix: remove this import as it causes python to treat "json" as a variable in the except block

* fix: always return a list, even if we catch an exception

* feat(marketplace): Add Crawl4AI marketplace with secure configuration

- Implement marketplace frontend and admin dashboard
- Add FastAPI backend with environment-based configuration
- Use .env file for secrets management
- Include data generation scripts
- Add proper CORS configuration
- Remove hardcoded password from admin login
- Update gitignore for security

* fix(marketplace): Update URLs to use /marketplace path and relative API endpoints

- Change API_BASE to relative '/api' for production
- Move marketplace to /marketplace instead of /marketplace/frontend
- Update MkDocs navigation
- Fix logo path in marketplace index

* fix(docs): hide copy menu on non-markdown pages

* feat(marketplace): add sponsor logo uploads

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* feat(docs): add chatgpt quick link to page actions

* fix(marketplace): align admin api with backend endpoints

* fix(marketplace): isolate api under marketplace prefix

* fix(marketplace): resolve app detail page routing and styling issues

- Fixed JavaScript errors from missing HTML elements (install-code, usage-code, integration-code)
- Added missing CSS classes for tabs, overview layout, sidebar, and integration content
- Fixed tab navigation to display horizontally in single line
- Added proper padding to tab content sections (removed from container, added to content)
- Fixed tab selector from .nav-tab to .tab-btn to match HTML structure
- Added sidebar styling with stats grid and metadata display
- Improved responsive design with mobile-friendly tab scrolling
- Fixed code block positioning for copy buttons
- Removed margin from first headings to prevent extra spacing
- Added null checks for DOM elements in JavaScript to prevent errors

These changes resolve the routing issue where clicking on apps caused page redirects,
and fix the broken layout where CSS was not properly applied to the app detail page.

* fix(marketplace): prevent hero image overflow and secondary card stretching

- Fixed hero image to 200px height with min/max constraints
- Added object-fit: cover to hero-image img elements
- Changed secondary-featured align-items from stretch to flex-start
- Fixed secondary-card height to 118px (no flex: 1 stretching)
- Updated responsive grid layouts for wider screens
- Added flex: 1 to hero-content for better content distribution

These changes ensure a rigid, predictable layout that prevents:
1. Large images from pushing text content down
2. Single secondary cards from stretching to fill entire height

* feat: Add hooks utility for function-based hooks with Docker client integration. ref #1377

   Add hooks_to_string() utility function that converts Python function objects
   to string representations for the Docker API, enabling developers to write hooks
   as regular Python functions instead of strings.

   Core Changes:
   - New hooks_to_string() utility in crawl4ai/utils.py using inspect.getsource()
   - Docker client now accepts both function objects and strings for hooks
   - Automatic detection and conversion in Crawl4aiDockerClient._prepare_request()
   - New hooks and hooks_timeout parameters in client.crawl() method

   Documentation:
   - Docker client examples with function-based hooks (docs/examples/docker_client_hooks_example.py)
   - Updated main Docker deployment guide with comprehensive hooks section
   - Added unit tests for hooks utility (tests/docker/test_hooks_utility.py)

* feat: Add hooks utility for function-based hooks with Docker client integration. ref #1377

   Add hooks_to_string() utility function that converts Python function objects
   to string representations for the Docker API, enabling developers to write hooks
   as regular Python functions instead of strings.

   Core Changes:
   - New hooks_to_string() utility in crawl4ai/utils.py using inspect.getsource()
   - Docker client now accepts both function objects and strings for hooks
   - Automatic detection and conversion in Crawl4aiDockerClient._prepare_request()
   - New hooks and hooks_timeout parameters in client.crawl() method

   Documentation:
   - Docker client examples with function-based hooks (docs/examples/docker_client_hooks_example.py)
   - Updated main Docker deployment guide with comprehensive hooks section
   - Added unit tests for hooks utility (tests/docker/test_hooks_utility.py)

* fix(docs): clarify Docker Hooks System with function-based API in README

* docs: Add demonstration files for v0.7.5 release, showcasing the new Docker Hooks System and all other features.

* docs: Update 0.7.5 video walkthrough

* docs: add complete SDK reference documentation

Add comprehensive single-page SDK reference combining:
- Installation & Setup
- Quick Start
- Core API (AsyncWebCrawler, arun, arun_many, CrawlResult)
- Configuration (BrowserConfig, CrawlerConfig, Parameters)
- Crawling Patterns
- Content Processing (Markdown, Fit Markdown, Selection, Interaction, Link & Media)
- Extraction Strategies (LLM and No-LLM)
- Advanced Features (Session Management, Hooks & Auth)

Generated using scripts/generate_sdk_docs.py in ultra-dense mode
optimized for AI assistant consumption.

Stats: 23K words, 185 code blocks, 220KB

* feat: add AI assistant skill package for Crawl4AI

- Create comprehensive skill package for AI coding assistants
- Include complete SDK reference (23K words, v0.7.4)
- Add three extraction scripts (basic, batch, pipeline)
- Implement version tracking in skill and scripts
- Add prominent download section on homepage
- Place skill in docs/assets for web distribution

The skill enables AI assistants like Claude, Cursor, and Windsurf
to effectively use Crawl4AI with optimized workflows for markdown
generation and data extraction.

* fix: remove non-existent wiki link and clarify skill usage instructions

* fix: update Crawl4AI skill with corrected parameters and examples

- Fixed CrawlerConfig → CrawlerRunConfig throughout
- Fixed parameter names (timeout → page_timeout, store_html removed)
- Fixed schema format (selector → baseSelector)
- Corrected proxy configuration (in BrowserConfig, not CrawlerRunConfig)
- Fixed fit_markdown usage with content filters
- Added comprehensive references to docs/examples/ directory
- Created safe packaging script to avoid root directory pollution
- All scripts tested and verified working

* fix: thoroughly verify and fix all Crawl4AI skill examples

- Cross-checked every section against actual docs
- Fixed BM25ContentFilter parameters (user_query, bm25_threshold)
- Removed incorrect wait_for selector from basic example
- Added comprehensive test suite (4 test files)
- All examples now tested and verified working
- Tests validate: basic crawling, markdown generation, data extraction, advanced patterns
- Package size: 76.6 KB (includes tests for future validation)

* feat(ci): split release pipeline and add Docker caching

- Split release.yml into PyPI/GitHub release and Docker workflows
- Add GitHub Actions cache for Docker builds (10-15x faster rebuilds)
- Implement dual-trigger for docker-release.yml (auto + manual)
- Add comprehensive workflow documentation in .github/workflows/docs/
- Backup original workflow as release.yml.backup

* feat: add webhook notifications for crawl job completion

Implements webhook support for the crawl job API to eliminate polling requirements.

Changes:
- Added WebhookConfig and WebhookPayload schemas to schemas.py
- Created webhook.py with WebhookDeliveryService class
- Integrated webhook notifications in api.py handle_crawl_job
- Updated job.py CrawlJobPayload to accept webhook_config
- Added webhook configuration section to config.yml
- Included comprehensive usage examples in WEBHOOK_EXAMPLES.md

Features:
- Webhook notifications on job completion (success/failure)
- Configurable data inclusion in webhook payload
- Custom webhook headers support
- Global default webhook URL configuration
- Exponential backoff retry logic (5 attempts: 1s, 2s, 4s, 8s, 16s)
- 30-second timeout per webhook call

Usage:
POST /crawl/job with optional webhook_config:
- webhook_url: URL to receive notifications
- webhook_data_in_payload: include full results (default: false)
- webhook_headers: custom headers for authentication

Generated with Claude Code https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

* docs: add webhook documentation to Docker README

Added comprehensive webhook section to README.md including:
- Overview of asynchronous job queue with webhooks
- Benefits and use cases
- Quick start examples
- Webhook authentication
- Global webhook configuration
- Job status polling alternative

Updated table of contents and summary to include webhook feature.
Maintains consistent tone and style with rest of README.

Generated with Claude Code https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

* docs: add webhook example for Docker deployment

Added docker_webhook_example.py demonstrating:
- Submitting crawl jobs with webhook configuration
- Flask-based webhook receiver implementation
- Three usage patterns:
  1. Webhook notification only (fetch data separately)
  2. Webhook with full data in payload
  3. Traditional polling approach for comparison

Includes comprehensive comments explaining:
- Webhook payload structure
- Authentication headers setup
- Error handling
- Production deployment tips

Example is fully functional and ready to run with Flask installed.

Generated with Claude Code https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

* test: add webhook implementation validation tests

Added comprehensive test suite to validate webhook implementation:
- Module import verification
- WebhookDeliveryService initialization
- Pydantic model validation (WebhookConfig)
- Payload construction logic
- Exponential backoff calculation
- API integration checks

All tests pass (6/6), confirming implementation is correct.

Generated with Claude Code https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

* test: add comprehensive webhook feature test script

Added end-to-end test script that automates webhook feature testing:

Script Features (test_webhook_feature.sh):
- Automatic branch switching and dependency installation
- Redis and server startup/shutdown management
- Webhook receiver implementation
- Integration test for webhook notifications
- Comprehensive cleanup and error handling
- Returns to original branch after completion

Test Flow:
1. Fetch and checkout webhook feature branch
2. Activate venv and install dependencies
3. Start Redis and Crawl4AI server
4. Submit crawl job with webhook config
5. Verify webhook delivery and payload
6. Clean up all processes and return to original branch

Documentation:
- WEBHOOK_TEST_README.md with usage instructions
- Troubleshooting guide
- Exit codes and safety features

Usage: ./tests/test_webhook_feature.sh

Generated with Claude Code https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: properly serialize Pydantic HttpUrl in webhook config

Use model_dump(mode='json') instead of deprecated dict() method to ensure
Pydantic special types (HttpUrl, UUID, etc.) are properly serialized to
JSON-compatible native Python types.

This fixes webhook delivery failures caused by HttpUrl objects remaining
as Pydantic types in the webhook_config dict, which caused JSON
serialization errors and httpx request failures.

Also update mcp requirement to >=1.18.0 for compatibility.

* feat: add webhook support for /llm/job endpoint

Add comprehensive webhook notification support for the /llm/job endpoint,
following the same pattern as the existing /crawl/job implementation.

Changes:
- Add webhook_config field to LlmJobPayload model (job.py)
- Implement webhook notifications in process_llm_extraction() with 4
  notification points: success, provider validation failure, extraction
  failure, and general exceptions (api.py)
- Store webhook_config in Redis task data for job tracking
- Initialize WebhookDeliveryService with exponential backoff retry logic
Documentation:
- Add Example 6 to WEBHOOK_EXAMPLES.md showing LLM extraction with webhooks
- Update Flask webhook handler to support both crawl and llm_extraction tasks
- Add TypeScript client examples for LLM jobs
- Add comprehensive examples to docker_webhook_example.py with schema support
- Clarify data structure differences between webhook and API responses

Testing:
- Add test_llm_webhook_feature.py with 7 validation tests (all passing)
- Verify pattern consistency with /crawl/job implementation
- Add implementation guide (WEBHOOK_LLM_JOB_IMPLEMENTATION.md)

* fix: remove duplicate comma in webhook_config parameter

* fix: update Crawl4AI Docker container port from 11234 to 11235

* Release v0.7.6: The 0.7.6 Update

- Updated version to 0.7.6
- Added comprehensive demo and release notes
- Updated all documentation
- Update the veriosn in Dockerfile to 0.7.6

---------

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Nezar Ali <abu5sohaib@gmail.com>
Co-authored-by: Soham Kukreti <kukretisoham@gmail.com>
Co-authored-by: James T. Wood <jamesthomaswood@gmail.com>
Co-authored-by: AHMET YILMAZ <tawfik@kidocode.com>
Co-authored-by: nafeqq-1306 <nafiquee@yahoo.com>
Co-authored-by: unclecode <unclecode@kidocode.com>
Co-authored-by: Martin Sjöborg <martin.sjoborg@quartr.se>
Co-authored-by: Martin Sjöborg <martin@sjoborg.org>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2025-10-22 20:41:06 +08:00

1517 lines
88 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 🚀 Crawl4AI v0.7.5 - Complete Feature Walkthrough\n",
"\n",
"Welcome to Crawl4AI v0.7.5! This notebook demonstrates all the new features introduced in this release.\n",
"\n",
"## 📋 What's New in v0.7.5\n",
"\n",
"1. **🔧 Docker Hooks System** - NEW! Complete pipeline customization with user-provided Python functions\n",
"2. **🤖 Enhanced LLM Integration** - Custom providers with temperature control\n",
"3. **🔒 HTTPS Preservation** - Secure internal link handling\n",
"4. **🛠️ Multiple Bug Fixes** - Community-reported issues resolved\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 📦 Setup and Installation\n",
"\n",
"First, let's make sure we have the latest version installed:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Crawl4AI v0.7.5 ready!\n"
]
}
],
"source": [
"# # Install or upgrade to v0.7.5\n",
"# !pip install -U crawl4ai==0.7.5 --quiet\n",
"\n",
"# Import required modules\n",
"import asyncio\n",
"import nest_asyncio\n",
"nest_asyncio.apply() # For Jupyter compatibility\n",
"\n",
"from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode\n",
"from crawl4ai import FilterChain, URLPatternFilter, BFSDeepCrawlStrategy\n",
"from crawl4ai import hooks_to_string\n",
"\n",
"print(\"✅ Crawl4AI v0.7.5 ready!\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🔧 Feature 1: Docker Hooks System (NEW! 🆕)\n",
"\n",
"### What is it?\n",
"v0.7.5 introduces a **completely new Docker Hooks System** that lets you inject custom Python functions at 8 key points in the crawling pipeline. This gives you full control over:\n",
"- Authentication setup\n",
"- Performance optimization\n",
"- Content processing\n",
"- Custom behavior at each stage\n",
"\n",
"### Three Ways to Use Docker Hooks\n",
"\n",
"The Docker Hooks System offers three approaches, all part of this new feature:\n",
"\n",
"1. **String-based hooks** - Write hooks as strings for REST API\n",
"2. **Using `hooks_to_string()` utility** - Convert Python functions to strings\n",
"3. **Docker Client auto-conversion** - Pass functions directly (most convenient)\n",
"\n",
"All three approaches are NEW in v0.7.5!"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🔒 Feature 2: HTTPS Preservation for Internal Links\n",
"\n",
"### Problem\n",
"When crawling HTTPS sites, internal links sometimes get downgraded to HTTP, breaking authentication and causing security warnings.\n",
"\n",
"### Solution \n",
"The new `preserve_https_for_internal_links=True` parameter maintains HTTPS protocol for all internal links."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🔒 Testing HTTPS Preservation\n",
"\n",
"============================================================\n"
]
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">[</span><span style=\"color: #008080; text-decoration-color: #008080\">INIT</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">]</span><span style=\"color: #008080; text-decoration-color: #008080\">.... → Crawl4AI </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7</span><span style=\"color: #008080; text-decoration-color: #008080\">.</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span><span style=\"color: #008080; text-decoration-color: #008080\"> </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;36m[\u001b[0m\u001b[36mINIT\u001b[0m\u001b[1;36m]\u001b[0m\u001b[36m...\u001b[0m\u001b[36m. → Crawl4AI \u001b[0m\u001b[1;36m0.7\u001b[0m\u001b[36m.\u001b[0m\u001b[1;36m5\u001b[0m\u001b[36m \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">98s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m98s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">01s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m01s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">2.</span><span style=\"color: #008000; text-decoration-color: #008000\">00s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m2.\u001b[0m\u001b[32m00s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">72s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m72s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">01s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m01s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">73s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m73s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/login</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">83s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/login\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m83s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/login</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">00s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/login\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m00s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/login</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">83s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/login\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m83s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/tag/change/page/1</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">11s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/tag/change/page/1\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m11s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/tag/change/page/1</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">00s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/tag/change/page/1\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m00s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/tag/change/page/1</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">12s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/tag/change/page/1\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m12s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/author/Albert-Einstein</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">32s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/author/Albert-Einstein\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m32s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/author/Albert-Einstein</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">00s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/author/Albert-Einstein\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m00s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://quotes.toscrape.com/author/Albert-Einstein</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">33s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://quotes.toscrape.com/author/Albert-Einstein\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m33s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"📊 Results:\n",
" Pages crawled: 5\n",
" Total internal links (from first page): 47\n",
" HTTPS links: 47 ✅\n",
" HTTP links: 0 \n",
" HTTPS preservation rate: 100.0%\n",
"\n",
"🔗 Sample HTTPS-preserved links:\n",
" → https://quotes.toscrape.com/\n",
" → https://quotes.toscrape.com/login\n",
" → https://quotes.toscrape.com/author/Albert-Einstein\n",
" → https://quotes.toscrape.com/tag/change/page/1\n",
" → https://quotes.toscrape.com/tag/deep-thoughts/page/1\n",
"\n",
"============================================================\n",
"✅ HTTPS Preservation Demo Complete!\n",
"\n"
]
}
],
"source": [
"async def demo_https_preservation():\n",
" \"\"\"\n",
" Demonstrate HTTPS preservation with deep crawling\n",
" \"\"\"\n",
" print(\"🔒 Testing HTTPS Preservation\\n\")\n",
" print(\"=\" * 60)\n",
" \n",
" # Setup URL filter for quotes.toscrape.com\n",
" url_filter = URLPatternFilter(\n",
" patterns=[r\"^(https:\\/\\/)?quotes\\.toscrape\\.com(\\/.*)?$\"]\n",
" )\n",
" \n",
" # Configure crawler with HTTPS preservation\n",
" config = CrawlerRunConfig(\n",
" exclude_external_links=True,\n",
" preserve_https_for_internal_links=True, # 🆕 NEW in v0.7.5\n",
" cache_mode=CacheMode.BYPASS,\n",
" deep_crawl_strategy=BFSDeepCrawlStrategy(\n",
" max_depth=2,\n",
" max_pages=5,\n",
" filter_chain=FilterChain([url_filter])\n",
" )\n",
" )\n",
" \n",
" async with AsyncWebCrawler() as crawler:\n",
" # With deep_crawl_strategy, arun() returns a list of CrawlResult objects\n",
" results = await crawler.arun(\n",
" url=\"https://quotes.toscrape.com\",\n",
" config=config\n",
" )\n",
" \n",
" # Analyze the first result\n",
" if results and len(results) > 0:\n",
" first_result = results[0]\n",
" internal_links = [link['href'] for link in first_result.links['internal']]\n",
" \n",
" # Check HTTPS preservation\n",
" https_links = [link for link in internal_links if link.startswith('https://')]\n",
" http_links = [link for link in internal_links if link.startswith('http://') and not link.startswith('https://')]\n",
" \n",
" print(f\"\\n📊 Results:\")\n",
" print(f\" Pages crawled: {len(results)}\")\n",
" print(f\" Total internal links (from first page): {len(internal_links)}\")\n",
" print(f\" HTTPS links: {len(https_links)} ✅\")\n",
" print(f\" HTTP links: {len(http_links)} {'⚠️' if http_links else ''}\")\n",
" if internal_links:\n",
" print(f\" HTTPS preservation rate: {len(https_links)/len(internal_links)*100:.1f}%\")\n",
" \n",
" print(f\"\\n🔗 Sample HTTPS-preserved links:\")\n",
" for link in https_links[:5]:\n",
" print(f\" → {link}\")\n",
" else:\n",
" print(f\"\\n⚠ No results returned\")\n",
" \n",
" print(\"\\n\" + \"=\" * 60)\n",
" print(\"✅ HTTPS Preservation Demo Complete!\\n\")\n",
"\n",
"# Run the demo\n",
"await demo_https_preservation()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🤖 Feature 3: Enhanced LLM Integration\n",
"\n",
"### What's New\n",
"- Custom `temperature` parameter for creativity control\n",
"- `base_url` for custom API endpoints\n",
"- Better multi-provider support\n",
"\n",
"### Example with Custom Temperature"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🤖 Testing Enhanced LLM Integration\n",
"\n",
"============================================================\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/var/folders/k0/7502j87n0_q4f9g82c0w8ks80000gn/T/ipykernel_15029/173393508.py:47: PydanticDeprecatedSince20: The `schema` method is deprecated; use `model_json_schema` instead. Deprecated in Pydantic V2.0 to be removed in V3.0. See Pydantic V2 Migration Guide at https://errors.pydantic.dev/2.12/migration/\n",
" schema=Article.schema(),\n"
]
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">[</span><span style=\"color: #008080; text-decoration-color: #008080\">INIT</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">]</span><span style=\"color: #008080; text-decoration-color: #008080\">.... → Crawl4AI </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7</span><span style=\"color: #008080; text-decoration-color: #008080\">.</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span><span style=\"color: #008080; text-decoration-color: #008080\"> </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;36m[\u001b[0m\u001b[36mINIT\u001b[0m\u001b[1;36m]\u001b[0m\u001b[36m...\u001b[0m\u001b[36m. → Crawl4AI \u001b[0m\u001b[1;36m0.7\u001b[0m\u001b[36m.\u001b[0m\u001b[1;36m5\u001b[0m\u001b[36m \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://en.wikipedia.org/wiki/Artificial_intelligence</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">3.</span><span style=\"color: #008000; text-decoration-color: #008000\">05s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://en.wikipedia.org/wiki/Artificial_intelligence\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m3.\u001b[0m\u001b[32m05s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://en.wikipedia.org/wiki/Artificial_intelligence</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">63s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://en.wikipedia.org/wiki/Artificial_intelligence\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m63s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">EXTRACT</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">. ■ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://en.wikipedia.org/wiki/Artificial_intelligence</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">20.</span><span style=\"color: #008000; text-decoration-color: #008000\">74s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mEXTRACT\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m. ■ \u001b[0m\u001b[4;32mhttps://en.wikipedia.org/wiki/Artificial_intelligence\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m20.\u001b[0m\u001b[32m74s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://en.wikipedia.org/wiki/Artificial_intelligence</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">24.</span><span style=\"color: #008000; text-decoration-color: #008000\">42s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://en.wikipedia.org/wiki/Artificial_intelligence\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m24.\u001b[0m\u001b[32m42s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"✅ LLM Extraction Successful!\n",
"\n",
"📄 Extracted Content:\n",
"[\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. AI can be applied in various fields and has numerous applications, including health, finance, and military.\",\n",
" \"main_topics\": [\n",
" \"Goals\",\n",
" \"Techniques\",\n",
" \"Applications\",\n",
" \"Ethics\",\n",
" \"History\",\n",
" \"Philosophy\",\n",
" \"Future\",\n",
" \"In fiction\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"The article discusses artificial intelligence (AI), its various techniques, applications, and advancements, particularly focusing on machine learning, deep learning, and neural networks. It highlights the evolution of AI technologies, including generative pre-trained transformers (GPT), and their impact on fields such as healthcare, gaming, and mathematics.\",\n",
" \"main_topics\": [\n",
" \"Classifiers and pattern matching\",\n",
" \"Artificial neural networks\",\n",
" \"Deep learning\",\n",
" \"Generative pre-trained transformers (GPT)\",\n",
" \"Hardware and software for AI\",\n",
" \"Applications of AI\",\n",
" \"AI in healthcare\",\n",
" \"AI in games\",\n",
" \"AI in mathematics\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is the capability of computational systems to perform tasks typically associated with human intelligence, such as learning, reasoning, problem-solving, perception, and decision-making. It is a field of research in computer science that develops methods and software enabling machines to perceive their environment and take actions to achieve defined goals. AI has seen significant advancements and applications in various domains, including web search engines, recommendation systems, virtual assistants, and autonomous vehicles, among others.\",\n",
" \"main_topics\": [\n",
" \"Goals\",\n",
" \"Reasoning and problem-solving\",\n",
" \"Knowledge representation\",\n",
" \"Planning and decision-making\",\n",
" \"Learning\",\n",
" \"Applications\",\n",
" \"Philosophy\",\n",
" \"History\",\n",
" \"Controversies\",\n",
" \"Ethics\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"The article discusses artificial intelligence (AI), its various techniques, and applications. It covers the foundational concepts of AI, including machine learning, natural language processing, perception, social intelligence, and general intelligence. The article also highlights the methods used in AI research, such as search and optimization, logic, probabilistic methods, and classifiers.\",\n",
" \"main_topics\": [\n",
" \"Markov decision processes\",\n",
" \"Machine learning\",\n",
" \"Supervised learning\",\n",
" \"Unsupervised learning\",\n",
" \"Reinforcement learning\",\n",
" \"Transfer learning\",\n",
" \"Deep learning\",\n",
" \"Natural language processing\",\n",
" \"Machine perception\",\n",
" \"Social intelligence\",\n",
" \"Artificial general intelligence\",\n",
" \"Search and optimization\",\n",
" \"Logic\",\n",
" \"Probabilistic methods\",\n",
" \"Classifiers and statistical learning methods\",\n",
" \"Artificial neural networks\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the complexities and challenges associated with artificial intelligence (AI), particularly focusing on issues of bias, fairness, transparency, and the potential risks posed by AI technologies. It highlights the ethical implications of AI systems, the lack of diversity among AI developers, and the existential risks associated with advanced AI.\",\n",
" \"main_topics\": [\n",
" \"Bias and fairness in AI\",\n",
" \"Lack of transparency in AI systems\",\n",
" \"Weaponization of AI\",\n",
" \"Technological unemployment due to AI\",\n",
" \"Existential risk from AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"The article discusses the advancements and applications of artificial intelligence (AI) across various fields, including mathematics, finance, military, generative AI, and more. It highlights the capabilities of AI models, their limitations, and the ethical considerations surrounding their use.\",\n",
" \"main_topics\": [\n",
" \"Mathematics\",\n",
" \"Finance\",\n",
" \"Military applications\",\n",
" \"Generative AI\",\n",
" \"AI agents\",\n",
" \"Web search\",\n",
" \"Sexuality\",\n",
" \"Industry-specific tasks\",\n",
" \"Ethics\",\n",
" \"Privacy and copyright\",\n",
" \"Dominance by tech giants\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses various aspects of artificial intelligence (AI), including its impact on privacy, copyright issues, environmental concerns, misinformation, and algorithmic bias. It highlights the dominance of big tech companies in the AI landscape and the increasing power demands of AI technologies.\",\n",
" \"main_topics\": [\n",
" \"Privacy and Fairness\",\n",
" \"Generative AI and Copyright\",\n",
" \"Dominance by Tech Giants\",\n",
" \"Power Needs and Environmental Impacts\",\n",
" \"Misinformation\",\n",
" \"Algorithmic Bias and Fairness\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"The article discusses the mixed opinions among experts regarding the risks associated with artificial intelligence (AI), particularly concerning superintelligent AI. It highlights concerns from notable figures in the field about existential risks, the importance of establishing safety guidelines, and the ongoing debate between pessimistic and optimistic views on AI's future impact. The article also covers ethical considerations, open-source developments, regulatory efforts, and the historical context of AI research.\",\n",
" \"main_topics\": [\n",
" \"Expert opinions on AI risks\",\n",
" \"Existential risk from superintelligent AI\",\n",
" \"Ethical machines and alignment\",\n",
" \"Open-source AI\",\n",
" \"Regulation of artificial intelligence\",\n",
" \"History of artificial intelligence\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the history, development, and various approaches to artificial intelligence (AI), highlighting key milestones, challenges, and philosophical debates surrounding the field. It covers the evolution from early optimism and funding cuts to the resurgence of interest through expert systems and deep learning, as well as the implications of AI advancements on society.\",\n",
" \"main_topics\": [\n",
" \"History of AI\",\n",
" \"AI winter\",\n",
" \"Expert systems\",\n",
" \"Deep learning\",\n",
" \"Artificial general intelligence (AGI)\",\n",
" \"Philosophy of AI\",\n",
" \"Defining artificial intelligence\",\n",
" \"Evaluating approaches to AI\",\n",
" \"Symbolic AI vs. sub-symbolic AI\",\n",
" \"Narrow AI vs. general AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. It encompasses various subfields including machine learning, natural language processing, and robotics, and aims to create systems that can perform tasks that typically require human intelligence.\",\n",
" \"main_topics\": [\n",
" \"Organoid intelligence\",\n",
" \"Robotic process automation\",\n",
" \"Wetware computer\",\n",
" \"DARWIN EU\",\n",
" \"Artificial intelligence in Wikimedia projects\",\n",
" \"AI-generated content on Wikipedia\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"The article discusses the field of artificial intelligence (AI), exploring its various branches, methodologies, and philosophical implications. It highlights the ongoing debates within the AI community regarding the pursuit of general versus narrow AI, the nature of consciousness in machines, and the ethical considerations surrounding AI rights and welfare.\",\n",
" \"main_topics\": [\n",
" \"Soft vs. hard computing\",\n",
" \"Narrow vs. general AI\",\n",
" \"Philosophy of artificial intelligence\",\n",
" \"Consciousness\",\n",
" \"Computationalism and functionalism\",\n",
" \"AI welfare and rights\",\n",
" \"Superintelligence and the singularity\",\n",
" \"Transhumanism\",\n",
" \"Artificial intelligence in fiction\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the field of artificial intelligence (AI), covering its definitions, history, methodologies, and applications. It explores various aspects of AI, including machine learning, natural language processing, and robotics, as well as the challenges and ethical considerations associated with AI technologies.\",\n",
" \"main_topics\": [\n",
" \"Definitions of AI\",\n",
" \"History of AI\",\n",
" \"Machine Learning\",\n",
" \"Natural Language Processing\",\n",
" \"Robotics\",\n",
" \"Ethical Considerations\",\n",
" \"Applications of AI\",\n",
" \"AI Methodologies\",\n",
" \"Challenges in AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the advancements and implications of artificial intelligence (AI), particularly focusing on generative AI and its impact across various sectors including healthcare, finance, entertainment, and environmental concerns.\",\n",
" \"main_topics\": [\n",
" \"Generative AI in software development\",\n",
" \"AI in healthcare\",\n",
" \"AI in financial services\",\n",
" \"Impact of AI on Hollywood and entertainment\",\n",
" \"AI and environmental issues\",\n",
" \"AI's role in creativity\",\n",
" \"AI in search technologies\",\n",
" \"AI's energy consumption\",\n",
" \"AI and societal implications\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the concept of artificial intelligence (AI), its development, applications, and the ethical implications surrounding its use. It highlights the advancements in AI technology, including synthetic media and computational capitalism, and addresses concerns regarding misinformation and media manipulation through AI tools.\",\n",
" \"main_topics\": [\n",
" \"Definition of Artificial Intelligence\",\n",
" \"Advancements in AI technology\",\n",
" \"Synthetic media and computational capitalism\",\n",
" \"Ethical implications of AI\",\n",
" \"Misinformation and media manipulation\",\n",
" \"AI in surveillance and security\",\n",
" \"AI's impact on employment\",\n",
" \"Global regulatory frameworks for AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the concept of artificial intelligence (AI), its applications, advancements, and implications across various fields, including healthcare, programming, and national security. It highlights the evolution of AI technologies, notable achievements, and the ongoing debates surrounding ethical considerations and the future of AI.\",\n",
" \"main_topics\": [\n",
" \"Definition of Artificial Intelligence\",\n",
" \"Applications in Healthcare\",\n",
" \"AI Programming Languages\",\n",
" \"Ethical Considerations\",\n",
" \"AI in National Security\",\n",
" \"Generative AI\",\n",
" \"Recent Advancements in AI Technologies\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the field of artificial intelligence (AI), its development, applications, and the ethical considerations surrounding its use. It highlights the advancements in AI technologies, the impact on various sectors, and the ongoing debates regarding the implications of AI on society.\",\n",
" \"main_topics\": [\n",
" \"Definition of Artificial Intelligence\",\n",
" \"History and Development of AI\",\n",
" \"Applications of AI\",\n",
" \"Ethical Considerations in AI\",\n",
" \"Impact of AI on Employment\",\n",
" \"Governance and Regulation of AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article provides an overview of artificial intelligence (AI), its history, development, and various applications. It discusses the evolution of AI from its inception to its current state, highlighting key milestones and influential figures in the field. The article also addresses the philosophical implications of AI, its impact on society, and the ongoing debates surrounding its future.\",\n",
" \"main_topics\": [\n",
" \"History of AI\",\n",
" \"Key figures in AI development\",\n",
" \"Philosophical implications of AI\",\n",
" \"Applications of AI\",\n",
" \"Current trends in AI\",\n",
" \"Ethical considerations in AI\",\n",
" \"Future of AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses various aspects of artificial intelligence (AI), including its implications, challenges, and the need for regulatory frameworks to ensure ethical use. It highlights the perspectives of experts on the responsibilities of tech companies and governments in managing AI technologies.\",\n",
" \"main_topics\": [\n",
" \"Ethical implications of AI\",\n",
" \"Regulatory frameworks for AI\",\n",
" \"Transparency in AI systems\",\n",
" \"Compensation for data usage\",\n",
" \"Professional licensing for AI engineers\",\n",
" \"Limitations of natural language processing\",\n",
" \"AI in media and misinformation\",\n",
" \"AI technologies and their reliability\",\n",
" \"Generative AI and its understanding\",\n",
" \"AI applications in various fields\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the field of artificial intelligence (AI), its history, development, and various applications. It highlights the concerns and ethical considerations surrounding AI, as well as the potential impact on society and the economy.\",\n",
" \"main_topics\": [\n",
" \"History of AI\",\n",
" \"Applications of AI\",\n",
" \"Ethical considerations\",\n",
" \"Impact on society\",\n",
" \"Machine learning\",\n",
" \"Regulation of AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"The article discusses the field of artificial intelligence (AI), covering its history, development, and various applications. It highlights the advancements in AI technologies, the ethical implications, and the ongoing debates surrounding AI's impact on society.\",\n",
" \"main_topics\": [\n",
" \"History of AI\",\n",
" \"Development of AI technologies\",\n",
" \"Applications of AI\",\n",
" \"Ethical implications of AI\",\n",
" \"Debates on AI's societal impact\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning, reasoning, and self-correction. AI applications include expert systems, natural language processing, speech recognition, and machine vision.\",\n",
" \"main_topics\": [\n",
" \"Neural networks\",\n",
" \"Deep learning\",\n",
" \"Language models\",\n",
" \"Artificial general intelligence (AGI)\",\n",
" \"Computer vision\",\n",
" \"Speech recognition\",\n",
" \"Natural language processing\",\n",
" \"Robotics\",\n",
" \"Philosophy of artificial intelligence\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning, reasoning, and self-correction.\",\n",
" \"main_topics\": [\n",
" \"Definition of AI\",\n",
" \"Processes involved in AI\",\n",
" \"Applications of AI\",\n",
" \"Types of AI\",\n",
" \"Ethical considerations in AI\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial Intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning, reasoning, and self-correction. AI applications include expert systems, natural language processing, speech recognition, and machine vision.\",\n",
" \"main_topics\": [\n",
" \"Natural language processing\",\n",
" \"Knowledge representation and reasoning\",\n",
" \"Computer vision\",\n",
" \"Automated planning and scheduling\",\n",
" \"Search methodology\",\n",
" \"Control method\",\n",
" \"Philosophy of artificial intelligence\",\n",
" \"Distributed artificial intelligence\",\n",
" \"Machine learning\"\n",
" ],\n",
" \"error\": false\n",
" },\n",
" {\n",
" \"title\": \"Artificial intelligence\",\n",
" \"summary\": \"Artificial intelligence (AI) is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Leading AI textbooks define the field as the study of \\\"intelligent agents\\\": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term \\\"artificial intelligence\\\" is often used to describe machines (or computers) that mimic \\\"cognitive\\\" functions that humans associate with the human mind, such as \\\"learning\\\" and \\\"problem-solving\\\".\",\n",
" \"main_topics\": [\n",
" \"Automation\",\n",
" \"Ethics of technology\",\n",
" \"AI alignment\",\n",
" \"AI safety\",\n",
" \"Technological singularity\",\n",
" \"Machine ethics\",\n",
" \"Existential risk from artificial intelligence\",\n",
" \"Artificial general intelligence\",\n",
" \"AI takeover\",\n",
" \"AI capability control\"\n",
" ],\n",
" \"error\": false\n",
" }\n",
"]\n",
"\n",
"============================================================\n",
"✅ Enhanced LLM Demo Complete!\n",
"\n"
]
}
],
"source": [
"from crawl4ai import LLMExtractionStrategy, LLMConfig\n",
"from pydantic import BaseModel, Field\n",
"import os\n",
"\n",
"# Define extraction schema\n",
"class Article(BaseModel):\n",
" title: str = Field(description=\"Article title\")\n",
" summary: str = Field(description=\"Brief summary of the article\")\n",
" main_topics: list[str] = Field(description=\"List of main topics covered\")\n",
"\n",
"async def demo_enhanced_llm():\n",
" \"\"\"\n",
" Demonstrate enhanced LLM integration with custom temperature\n",
" \"\"\"\n",
" print(\"🤖 Testing Enhanced LLM Integration\\n\")\n",
" print(\"=\" * 60)\n",
" \n",
" # Check for API key\n",
" api_key = os.getenv('OPENAI_API_KEY')\n",
" if not api_key:\n",
" print(\"⚠️ Note: Set OPENAI_API_KEY environment variable to test LLM extraction\")\n",
" print(\"For this demo, we'll show the configuration only.\\n\")\n",
" \n",
" print(\"📝 Example LLM Configuration with new v0.7.5 features:\")\n",
" print(\"\"\"\n",
"llm_strategy = LLMExtractionStrategy(\n",
" llm_config=LLMConfig(\n",
" provider=\"openai/gpt-4o-mini\",\n",
" api_token=\"your-api-key\",\n",
" temperature=0.7, # 🆕 NEW: Control creativity (0.0-2.0)\n",
" base_url=\"custom-endpoint\" # 🆕 NEW: Custom API endpoint\n",
" ),\n",
" schema=Article.schema(),\n",
" extraction_type=\"schema\",\n",
" instruction=\"Extract article information\"\n",
")\n",
" \"\"\")\n",
" return\n",
" \n",
" # Create LLM extraction strategy with custom temperature\n",
" llm_strategy = LLMExtractionStrategy(\n",
" llm_config=LLMConfig(\n",
" provider=\"openai/gpt-4o-mini\",\n",
" api_token=api_key,\n",
" temperature=0.3, # 🆕 Lower temperature for more focused extraction\n",
" ),\n",
" schema=Article.schema(),\n",
" extraction_type=\"schema\",\n",
" instruction=\"Extract the article title, a brief summary, and main topics discussed.\"\n",
" )\n",
" \n",
" config = CrawlerRunConfig(\n",
" extraction_strategy=llm_strategy,\n",
" cache_mode=CacheMode.BYPASS\n",
" )\n",
" \n",
" async with AsyncWebCrawler() as crawler:\n",
" result = await crawler.arun(\n",
" url=\"https://en.wikipedia.org/wiki/Artificial_intelligence\",\n",
" config=config\n",
" )\n",
" \n",
" if result.success:\n",
" print(\"\\n✅ LLM Extraction Successful!\")\n",
" print(f\"\\n📄 Extracted Content:\")\n",
" print(result.extracted_content)\n",
" else:\n",
" print(f\"\\n❌ Extraction failed: {result.error_message}\")\n",
" \n",
" print(\"\\n\" + \"=\" * 60)\n",
" print(\"✅ Enhanced LLM Demo Complete!\\n\")\n",
"\n",
"# Run the demo\n",
"await demo_enhanced_llm()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Creating Reusable Hook Functions\n",
"\n",
"First, let's create some hook functions that we can reuse:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Reusable hook library created!\n",
"\n",
"📚 Available hooks:\n",
" • block_images_hook - Speed optimization\n",
" • set_viewport_hook - Consistent rendering\n",
" • add_custom_headers_hook - Custom headers\n",
" • scroll_page_hook - Lazy content loading\n",
" • log_page_metrics_hook - Page analytics\n"
]
}
],
"source": [
"# Define reusable hooks as Python functions\n",
"\n",
"async def block_images_hook(page, context, **kwargs):\n",
" \"\"\"\n",
" Performance optimization: Block images to speed up crawling\n",
" \"\"\"\n",
" print(\"[Hook] Blocking images for faster loading...\")\n",
" await context.route(\n",
" \"**/*.{png,jpg,jpeg,gif,webp,svg,ico}\",\n",
" lambda route: route.abort()\n",
" )\n",
" return page\n",
"\n",
"async def set_viewport_hook(page, context, **kwargs):\n",
" \"\"\"\n",
" Set consistent viewport size for rendering\n",
" \"\"\"\n",
" print(\"[Hook] Setting viewport to 1920x1080...\")\n",
" await page.set_viewport_size({\"width\": 1920, \"height\": 1080})\n",
" return page\n",
"\n",
"async def add_custom_headers_hook(page, context, url, **kwargs):\n",
" \"\"\"\n",
" Add custom headers before navigation\n",
" \"\"\"\n",
" print(f\"[Hook] Adding custom headers for {url}...\")\n",
" await page.set_extra_http_headers({\n",
" 'X-Crawl4AI-Version': '0.7.5',\n",
" 'X-Custom-Header': 'docker-hooks-demo',\n",
" 'Accept-Language': 'en-US,en;q=0.9'\n",
" })\n",
" return page\n",
"\n",
"async def scroll_page_hook(page, context, **kwargs):\n",
" \"\"\"\n",
" Scroll page to load lazy-loaded content\n",
" \"\"\"\n",
" print(\"[Hook] Scrolling page to load lazy content...\")\n",
" await page.evaluate(\"window.scrollTo(0, document.body.scrollHeight)\")\n",
" await page.wait_for_timeout(1000)\n",
" await page.evaluate(\"window.scrollTo(0, 0)\")\n",
" await page.wait_for_timeout(500)\n",
" return page\n",
"\n",
"async def log_page_metrics_hook(page, context, **kwargs):\n",
" \"\"\"\n",
" Log page metrics before extracting HTML\n",
" \"\"\"\n",
" metrics = await page.evaluate('''\n",
" () => ({\n",
" images: document.images.length,\n",
" links: document.links.length,\n",
" scripts: document.scripts.length,\n",
" title: document.title\n",
" })\n",
" ''')\n",
" print(f\"[Hook] Page Metrics - Title: {metrics['title']}\")\n",
" print(f\" Images: {metrics['images']}, Links: {metrics['links']}, Scripts: {metrics['scripts']}\")\n",
" return page\n",
"\n",
"print(\"✅ Reusable hook library created!\")\n",
"print(\"\\n📚 Available hooks:\")\n",
"print(\" • block_images_hook - Speed optimization\")\n",
"print(\" • set_viewport_hook - Consistent rendering\")\n",
"print(\" • add_custom_headers_hook - Custom headers\")\n",
"print(\" • scroll_page_hook - Lazy content loading\")\n",
"print(\" • log_page_metrics_hook - Page analytics\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Using hooks_to_string() Utility\n",
"\n",
"The new `hooks_to_string()` utility converts Python function objects to strings that can be sent to the Docker API:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Converted 3 hook functions to string format\n",
"\n",
"📝 Example of converted hook (first 200 chars):\n",
"async def block_images_hook(page, context, **kwargs):\n",
" \"\"\"\n",
" Performance optimization: Block images to speed up crawling\n",
" \"\"\"\n",
" print(\"[Hook] Blocking images for faster loading...\")\n",
" awai...\n",
"\n",
"💡 Benefits of hooks_to_string():\n",
" ✓ Write hooks as Python functions (IDE support, type checking)\n",
" ✓ Automatically converts to string format for Docker API\n",
" ✓ Reusable across projects\n",
" ✓ Easy to test and debug\n"
]
}
],
"source": [
"# Convert functions to strings using the NEW utility\n",
"hooks_as_strings = hooks_to_string({\n",
" \"on_page_context_created\": block_images_hook,\n",
" \"before_goto\": add_custom_headers_hook,\n",
" \"before_retrieve_html\": scroll_page_hook,\n",
"})\n",
"\n",
"print(\"✅ Converted 3 hook functions to string format\")\n",
"print(\"\\n📝 Example of converted hook (first 200 chars):\")\n",
"print(hooks_as_strings[\"on_page_context_created\"][:200] + \"...\")\n",
"\n",
"print(\"\\n💡 Benefits of hooks_to_string():\")\n",
"print(\" ✓ Write hooks as Python functions (IDE support, type checking)\")\n",
"print(\" ✓ Automatically converts to string format for Docker API\")\n",
"print(\" ✓ Reusable across projects\")\n",
"print(\" ✓ Easy to test and debug\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 8 Available Hook Points\n",
"\n",
"The Docker Hooks System provides 8 strategic points where you can inject custom behavior:\n",
"\n",
"1. **on_browser_created** - Browser initialization\n",
"2. **on_page_context_created** - Page context setup\n",
"3. **on_user_agent_updated** - User agent configuration\n",
"4. **before_goto** - Pre-navigation setup\n",
"5. **after_goto** - Post-navigation processing\n",
"6. **on_execution_started** - JavaScript execution start\n",
"7. **before_retrieve_html** - Pre-extraction processing\n",
"8. **before_return_html** - Final HTML processing"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Complete Docker Hooks Demo\n",
"\n",
"**Note**: For a complete demonstration of all Docker Hooks approaches including:\n",
"- String-based hooks with REST API\n",
"- hooks_to_string() utility usage\n",
"- Docker Client with automatic conversion\n",
"- Complete pipeline with all 8 hook points\n",
"\n",
"See the separate file: **`v0.7.5_docker_hooks_demo.py`**\n",
"\n",
"This standalone Python script provides comprehensive, runnable examples of the entire Docker Hooks System."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🛠️ Feature 4: Bug Fixes Summary\n",
"\n",
"### Major Fixes in v0.7.5\n",
"\n",
"1. **URL Processing** - Fixed '+' sign preservation in query parameters\n",
"2. **Proxy Configuration** - Enhanced proxy string parsing (old parameter deprecated)\n",
"3. **Docker Error Handling** - Better error messages with status codes\n",
"4. **Memory Management** - Fixed leaks in long-running sessions\n",
"5. **JWT Authentication** - Fixed Docker JWT validation\n",
"6. **Playwright Stealth** - Fixed stealth features\n",
"7. **API Configuration** - Fixed config handling\n",
"8. **Deep Crawl Strategy** - Resolved JSON encoding errors\n",
"9. **LLM Provider Support** - Fixed custom provider integration\n",
"10. **Performance** - Resolved backoff strategy failures\n",
"\n",
"### New Proxy Configuration Example"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ New proxy configuration format demonstrated\n",
"\n",
"📝 Benefits:\n",
" • More explicit and clear\n",
" • Better authentication support\n",
" • Consistent with industry standards\n"
]
}
],
"source": [
"# OLD WAY (Deprecated)\n",
"# browser_config = BrowserConfig(proxy=\"http://proxy:8080\")\n",
"\n",
"# NEW WAY (v0.7.5)\n",
"browser_config_with_proxy = BrowserConfig(\n",
" proxy_config={\n",
" \"server\": \"http://proxy.example.com:8080\",\n",
" \"username\": \"optional-username\", # Optional\n",
" \"password\": \"optional-password\" # Optional\n",
" }\n",
")\n",
"\n",
"print(\"✅ New proxy configuration format demonstrated\")\n",
"print(\"\\n📝 Benefits:\")\n",
"print(\" • More explicit and clear\")\n",
"print(\" • Better authentication support\")\n",
"print(\" • Consistent with industry standards\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🎯 Complete Example: Combining Multiple Features\n",
"\n",
"Let's create a real-world example that uses multiple v0.7.5 features together:"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🎯 Complete v0.7.5 Feature Demo\n",
"\n",
"============================================================\n",
"\n",
"1⃣ Using Docker Hooks System (NEW!)\n",
" ✓ Converted 3 hooks to string format\n",
" ✓ Ready to send to Docker API\n",
"\n",
"2⃣ Enabling HTTPS Preservation\n",
" ✓ HTTPS preservation enabled\n",
"\n",
"3⃣ Using New Proxy Configuration Format\n",
" ✓ New proxy config format ready\n",
"\n",
"4⃣ Executing Crawl with All Features\n"
]
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">[</span><span style=\"color: #008080; text-decoration-color: #008080\">INIT</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">]</span><span style=\"color: #008080; text-decoration-color: #008080\">.... → Crawl4AI </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7</span><span style=\"color: #008080; text-decoration-color: #008080\">.</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span><span style=\"color: #008080; text-decoration-color: #008080\"> </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;36m[\u001b[0m\u001b[36mINIT\u001b[0m\u001b[1;36m]\u001b[0m\u001b[36m...\u001b[0m\u001b[36m. → Crawl4AI \u001b[0m\u001b[1;36m0.7\u001b[0m\u001b[36m.\u001b[0m\u001b[1;36m5\u001b[0m\u001b[36m \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">FETCH</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">... ↓ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://example.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">29s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mFETCH\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m...\u001b[0m\u001b[32m ↓ \u001b[0m\u001b[4;32mhttps://example.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m29s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">SCRAPE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\">.. ◆ </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://example.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">0.</span><span style=\"color: #008000; text-decoration-color: #008000\">00s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mSCRAPE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m.. ◆ \u001b[0m\u001b[4;32mhttps://example.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m0.\u001b[0m\u001b[32m00s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[</span><span style=\"color: #008000; text-decoration-color: #008000\">COMPLETE</span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">]</span><span style=\"color: #008000; text-decoration-color: #008000\"> ● </span><span style=\"color: #008000; text-decoration-color: #008000; text-decoration: underline\">https://example.com</span><span style=\"color: #008000; text-decoration-color: #008000\"> |</span>\n",
"<span style=\"color: #008000; text-decoration-color: #008000\">✓ | ⏱: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">1.</span><span style=\"color: #008000; text-decoration-color: #008000\">29s </span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32m[\u001b[0m\u001b[32mCOMPLETE\u001b[0m\u001b[1;32m]\u001b[0m\u001b[32m ● \u001b[0m\u001b[4;32mhttps://example.com\u001b[0m\u001b[32m |\u001b[0m\n",
"\u001b[32m✓\u001b[0m\u001b[32m | ⏱: \u001b[0m\u001b[1;32m1.\u001b[0m\u001b[32m29s \u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" ✓ Crawl successful!\n",
"\n",
"📊 Results:\n",
" • Pages crawled: 1\n",
" • Title: Example Domain\n",
" • Content length: 119 characters\n",
" • Links found: 0\n",
"\n",
"============================================================\n",
"✅ Complete Feature Demo Finished!\n",
"\n"
]
}
],
"source": [
"async def complete_demo():\n",
" \"\"\"\n",
" Comprehensive demo combining multiple v0.7.5 features\n",
" \"\"\"\n",
" print(\"🎯 Complete v0.7.5 Feature Demo\\n\")\n",
" print(\"=\" * 60)\n",
" \n",
" # Use function-based hooks (NEW Docker Hooks System)\n",
" print(\"\\n1⃣ Using Docker Hooks System (NEW!)\")\n",
" hooks = {\n",
" \"on_page_context_created\": set_viewport_hook,\n",
" \"before_goto\": add_custom_headers_hook,\n",
" \"before_retrieve_html\": log_page_metrics_hook\n",
" }\n",
" \n",
" # Convert to strings using the NEW utility\n",
" hooks_strings = hooks_to_string(hooks)\n",
" print(f\" ✓ Converted {len(hooks_strings)} hooks to string format\")\n",
" print(\" ✓ Ready to send to Docker API\")\n",
" \n",
" # Use HTTPS preservation\n",
" print(\"\\n2⃣ Enabling HTTPS Preservation\")\n",
" url_filter = URLPatternFilter(\n",
" patterns=[r\"^(https:\\/\\/)?example\\.com(\\/.*)?$\"]\n",
" )\n",
" \n",
" config = CrawlerRunConfig(\n",
" exclude_external_links=True,\n",
" preserve_https_for_internal_links=True, # v0.7.5 feature\n",
" cache_mode=CacheMode.BYPASS,\n",
" deep_crawl_strategy=BFSDeepCrawlStrategy(\n",
" max_depth=1,\n",
" max_pages=3,\n",
" filter_chain=FilterChain([url_filter])\n",
" )\n",
" )\n",
" print(\" ✓ HTTPS preservation enabled\")\n",
" \n",
" # Use new proxy config format\n",
" print(\"\\n3⃣ Using New Proxy Configuration Format\")\n",
" browser_config = BrowserConfig(\n",
" headless=True,\n",
" # proxy_config={ # Uncomment if you have a proxy\n",
" # \"server\": \"http://proxy:8080\"\n",
" # }\n",
" )\n",
" print(\" ✓ New proxy config format ready\")\n",
" \n",
" # Run the crawl\n",
" print(\"\\n4⃣ Executing Crawl with All Features\")\n",
" async with AsyncWebCrawler(config=browser_config) as crawler:\n",
" # With deep_crawl_strategy, returns a list\n",
" results = await crawler.arun(\n",
" url=\"https://example.com\",\n",
" config=config\n",
" )\n",
" \n",
" if results and len(results) > 0:\n",
" result = results[0] # Get first result\n",
" print(\" ✓ Crawl successful!\")\n",
" print(f\"\\n📊 Results:\")\n",
" print(f\" • Pages crawled: {len(results)}\")\n",
" print(f\" • Title: {result.metadata.get('title', 'N/A')}\")\n",
" print(f\" • Content length: {len(result.markdown.raw_markdown)} characters\")\n",
" print(f\" • Links found: {len(result.links['internal']) + len(result.links['external'])}\")\n",
" else:\n",
" print(f\" ⚠️ No results returned\")\n",
" \n",
" print(\"\\n\" + \"=\" * 60)\n",
" print(\"✅ Complete Feature Demo Finished!\\n\")\n",
"\n",
"# Run complete demo\n",
"await complete_demo()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"\n",
"## 🎓 Summary\n",
"\n",
"### What We Covered\n",
"\n",
"✅ **HTTPS Preservation** - Maintain secure protocols throughout crawling \n",
"✅ **Enhanced LLM Integration** - Custom temperature and provider configuration \n",
"✅ **Docker Hooks System (NEW!)** - Complete pipeline customization with 3 approaches \n",
"✅ **hooks_to_string() Utility (NEW!)** - Convert functions for Docker API \n",
"✅ **Bug Fixes** - New proxy config and multiple improvements \n",
"\n",
"### Key Highlight: Docker Hooks System 🌟\n",
"\n",
"The **Docker Hooks System** is completely NEW in v0.7.5. It offers:\n",
"- 8 strategic hook points in the pipeline\n",
"- 3 ways to use hooks (strings, utility, auto-conversion)\n",
"- Full control over crawling behavior\n",
"- Support for authentication, optimization, and custom processing\n",
"\n",
"### Next Steps\n",
"\n",
"1. **Docker Hooks Demo** - See `v0.7.5_docker_hooks_demo.py` for complete Docker Hooks examples\n",
"2. **Documentation** - Visit [docs.crawl4ai.com](https://docs.crawl4ai.com) for full reference\n",
"3. **Examples** - Check [GitHub examples](https://github.com/unclecode/crawl4ai/tree/main/docs/examples)\n",
"4. **Community** - Join [Discord](https://discord.gg/jP8KfhDhyN) for support\n",
"\n",
"---\n",
"\n",
"## 📚 Resources\n",
"\n",
"- 📖 [Full Documentation](https://docs.crawl4ai.com)\n",
"- 🐙 [GitHub Repository](https://github.com/unclecode/crawl4ai)\n",
"- 📝 [Release Notes](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.5.md)\n",
"- 💬 [Discord Community](https://discord.gg/jP8KfhDhyN)\n",
"- 🐦 [Twitter](https://x.com/unclecode)\n",
"\n",
"---\n",
"\n",
"**Happy Crawling with v0.7.5! 🚀**"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}