UncleCode b5c2732f88 Add BBC Sp0ort Research Assistant pipeline example ...

- Implemented a comprehensive research pipeline using URLSeeder.
- Steps include user query input, optional LLM enhancement, URL discovery and ranking, content crawling, and synthesis generation.
- Introduced caching mechanism for enhanced query results and crawled content.
- Configurable settings for testing and production modes.
- Output results in JSON and Markdown formats with detailed research insights and citations.

2025-06-04 23:23:21 +08:00

..

assets

- User agent

2024-06-08 17:59:42 +08:00

cli

feat(cli): add command line interface with comprehensive features

2025-02-10 16:58:52 +08:00

docker

feat(docker-api): add job-based polling endpoints for crawl and LLM tasks

2025-05-01 21:24:52 +08:00

markdown

feat(markdown): add content source selection for markdown generation

2025-04-17 20:13:53 +08:00

url_seeder

Add BBC Sp0ort Research Assistant pipeline example

2025-06-04 23:23:21 +08:00

amazon_product_extraction_direct_url.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

amazon_product_extraction_using_hooks.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

amazon_product_extraction_using_use_javascript.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

arun_vs_arun_many.py

feat(crawler): optimize single URL handling and add performance comparison

2025-03-13 22:15:15 +08:00

async_webcrawler_multiple_urls_example.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

browser_optimization_example.py

Release prep (#749)

2025-02-28 19:53:35 +08:00

builtin_browser_example.py

feat(browser): add builtin browser management system

2025-03-20 12:13:59 +08:00

chainlit.md

Add research assistant example using Chainlit

2024-06-04 22:43:09 +08:00

crawlai_vs_firecrawl.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

crawler_monitor_example.py

feat(monitor): add real-time crawler monitoring system with memory management

2025-03-12 19:05:24 +08:00

crypto_analysis_example.py

feat(models): add dedicated tables field to CrawlResult

2025-04-24 18:36:25 +08:00

deepcrawl_example.py

fix(docs): correct section numbering in deepcrawl_example.py tutorial

2025-03-04 20:57:33 +08:00

dispatcher_example.py

feat(content): add target_elements parameter for selective content extraction

2025-03-10 18:54:51 +08:00

docker_config_obj.py

refactor(config): enhance serialization and config handling

2025-02-19 17:23:25 +08:00

docker_example.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

docker_python_rest_api.py

feat(crawler): optimize single URL handling and add performance comparison

2025-03-13 22:15:15 +08:00

docker_python_sdk.py

refactor(config): enhance serialization and config handling

2025-02-19 17:23:25 +08:00

extraction_strategies_examples.py

feat(browser): add standalone CDP browser launch and lxml extraction strategy

2025-03-07 20:55:56 +08:00

full_page_screenshot_and_pdf_export.md

docs + fix: Update example for full page screenshot & PDF export. Fix the bug Error: crawl4ai.async_webcrawler.AsyncWebCrawler.aprocess_html() got multiple values for keyword argument - for screenshot param. https://github.com/unclecode/crawl4ai/issues/822#issuecomment-2732602118

2025-03-18 17:20:24 +05:30

hello_world.py

feat(crawler): add session management and view-source support

2025-05-08 17:13:35 +08:00

hooks_example.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

identity_based_browsing.py

feat(profiles): add CLI command for crawling with browser profiles

2025-03-02 21:33:33 +08:00

language_support_example.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

llm_extraction_openai_pricing.py

feat(browser): add standalone CDP browser launch and lxml extraction strategy

2025-03-07 20:55:56 +08:00

llm_markdown_generator.py

feat(browser): add standalone CDP browser launch and lxml extraction strategy

2025-03-07 20:55:56 +08:00

network_console_capture_example.py

Fixed capturing console messages for case the url is the local file. Update docker configuration (work in progress)

2025-04-10 23:22:38 +08:00

proxy_rotation_demo.py

feat(proxy): add proxy rotation strategy

2025-02-09 18:49:10 +08:00

quickstart_examples_set_1.py

refactor(proxy): move ProxyConfig to async_configs and improve LLM token handling

2025-04-15 22:27:18 +08:00

quickstart_examples_set_2.py

refactor(docs): update import statement in quickstart.py for improved clarity

2025-04-05 23:12:06 +08:00

quickstart.ipynb

Release prep (#749)

2025-02-28 19:53:35 +08:00

quickstart.py

refactor(docs): update import statement in quickstart.py for improved clarity

2025-04-05 23:12:06 +08:00

README_BUILTIN_BROWSER.md

feat(browser): add builtin browser management system

2025-03-20 12:13:59 +08:00

regex_extraction_quickstart.py

feat(extraction): add RegexExtractionStrategy for pattern-based extraction

2025-05-02 21:15:24 +08:00

research_assistant.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

rest_call.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

sample_ecommerce.html

Push async version last changes for merge to main branch

2024-09-24 20:52:08 +08:00

scraping_strategies_performance.py

docs(examples): update demo scripts and fix output formats

2025-01-22 20:40:03 +08:00

serp_api_project_11_feb.py

Release prep (#749)

2025-02-28 19:53:35 +08:00

session_id_example.py

feat(crawler): add session management and view-source support

2025-05-08 17:13:35 +08:00

ssl_example.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

storage_state_tutorial.md

Implement new async crawler features and stability updates

2024-12-10 17:55:29 +08:00

summarize_page.py

Apply Ruff Corrections

2025-01-13 19:19:58 +08:00

tutorial_dynamic_clicks.md

Add PDF & screenshot functionality, new tutorial

2024-12-10 20:10:39 +08:00

tutorial_v0.5.py

refactor(proxy): move ProxyConfig to async_configs and improve LLM token handling

2025-04-15 22:27:18 +08:00

use_geo_location.py

feat(browser): add geolocation, locale and timezone support

2025-04-21 23:20:59 +08:00