wehub-resource-sync
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
"""
|
|
Basic example of scraping pipeline using CSVScraperGraph from CSV documents
|
|
"""
|
|
|
|
import os
|
|
|
|
from scrapegraphai.graphs import CSVScraperGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
# ************************************************
|
|
# Read the CSV file
|
|
# ************************************************
|
|
|
|
FILE_NAME = "inputs/username.csv"
|
|
curr_dir = os.path.dirname(os.path.realpath(__file__))
|
|
file_path = os.path.join(curr_dir, FILE_NAME)
|
|
|
|
with open(file_path, "r") as file:
|
|
text = file.read()
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"model": "ollama/llama3",
|
|
"temperature": 0,
|
|
"format": "json", # Ollama needs the format to be specified explicitly
|
|
# "model_tokens": 2000, # set context length arbitrarily
|
|
"base_url": "http://localhost:11434",
|
|
},
|
|
"embeddings": {
|
|
"model": "ollama/nomic-embed-text",
|
|
"temperature": 0,
|
|
"base_url": "http://localhost:11434",
|
|
},
|
|
"verbose": True,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the CSVScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
csv_scraper_graph = CSVScraperGraph(
|
|
prompt="List me all the last names",
|
|
source=str(text), # Pass the content of the file, not the file object
|
|
config=graph_config,
|
|
)
|
|
|
|
result = csv_scraper_graph.run()
|
|
print(result)
|
|
|
|
# ************************************************
|
|
# Get graph execution info
|
|
# ************************************************
|
|
|
|
graph_exec_info = csv_scraper_graph.get_execution_info()
|
|
print(prettify_exec_info(graph_exec_info))
|