mirror of
https://github.com/MervinPraison/PraisonAI.git
synced 2026-11-11 03:31:27 -10:00
47 lines
1.8 KiB
YAML
47 lines
1.8 KiB
YAML
framework: praisonai
|
|
topic: crawl and extract all data from each url from this page https://news.ycombinator.com/
|
|
agents: # Canonical: use 'agents' instead of 'roles'
|
|
web_scraper:
|
|
instructions: # Canonical An expert in data extraction from websites, adept at navigating and
|
|
retrieving detailed information.
|
|
goal: Extract URLs from the source page
|
|
role: Web Scraper
|
|
output_file: urls.txt
|
|
tasks:
|
|
url_extraction:
|
|
description: Use the code_interpret run python code to extract all URLs from the page located
|
|
at https://news.ycombinator.com/.
|
|
expected_output: A list of URLs extracted from the source page.
|
|
tools:
|
|
- 'code_interpret'
|
|
url_data_extractor:
|
|
instructions: # Canonical Specializes in crawling websites to gather comprehensive data, ensuring
|
|
nothing is missed from each link.
|
|
goal: Crawl each URL for data extraction
|
|
role: URL Data Extractor
|
|
context:
|
|
- web_scraper
|
|
tasks:
|
|
data_extraction:
|
|
description: Crawl each URL provided by the Web Scraper and extract all pertinent
|
|
data using the code_interpret to run python code.
|
|
expected_output: Raw data collected from each crawled URL.
|
|
tools:
|
|
- 'code_interpret'
|
|
data_organizer:
|
|
instructions: # Canonical Known for keen attention to detail, capable of structuring vast amounts
|
|
of information into usable formats efficiently.
|
|
goal: Organize extracted data into a structured format
|
|
role: Data Organizer
|
|
context:
|
|
- url_data_extractor
|
|
tasks:
|
|
data_structuring:
|
|
description: Organize the raw data received from the URL Data Extractor into
|
|
a structured JSON format.
|
|
expected_output: A JSON file containing structured data from all extracted
|
|
URLs.
|
|
tools:
|
|
- 'code_interpret'
|
|
dependencies: []
|