Skip to main content

scrape_plain_text_ollama

""" 
Basic example of scraping pipeline using SmartScraper from text
"""

import os
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

# ************************************************
# 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": {
"model": "ollama/mistral",
"temperature": 0,
"format": "json", # Ollama needs the format to be specified explicitly
# "model_tokens": 2000, # set context length arbitrarily
"base_url": "http://localhost:11434",
},
"verbose": True,
}

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

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

result = smart_scraper_graph.run()
print(result)

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

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