"""
Basic example of scraping pipeline using SmartScraper from text
"""
import os
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info
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)
with open(file_path, 'r', encoding="utf-8") as file:
text = file.read()
graph_config = {
"llm": {
"model": "ollama/mistral",
"temperature": 0,
"format": "json",
"base_url": "http://localhost:11434",
},
"embeddings": {
"model": "ollama/nomic-embed-text",
"temperature": 0,
"base_url": "http://localhost:11434",
},
"verbose": True,
}
smart_scraper_graph = SmartScraperGraph(
prompt="List me all the projects",
source=text,
config=graph_config
)
result = smart_scraper_graph.run()
print(result)
graph_exec_info = smart_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))