Skip to main content

scrape_plain_text_bedrock

""" 
Basic example of scraping pipeline using SmartScraper from text
"""
import os
import json
from dotenv import load_dotenv
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

load_dotenv()

# ************************************************
# Read the text file
# ************************************************

FILE_NAME = "inputs/plain_html_example.txt"
curr_dir = os.path.dirname(os.path.realpath(__file__))
file_path = os.path.join(curr_dir, FILE_NAME)

# It could be also a http request using the request model
with open(file_path, 'r', encoding="utf-8") as file:
text = file.read()

# ************************************************
# Define the configuration for the graph
# ************************************************

graph_config = {
"llm": {
"client": "client_name",
"model": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
"temperature": 0.0
}
}

# ************************************************
# Create the SmartScraperGraph instance and run it
# ************************************************

smart_scraper_graph = SmartScraperGraph(
prompt="List me all the projects with their description.",
source=text,
config=graph_config
)

result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))

# ************************************************
# Get graph execution info
# ************************************************

graph_exec_info = smart_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))