mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-15 21:00:30 +08:00
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
"""
|
|
Basic example of scraping pipeline using CSVScraperGraph from CSV documents
|
|
"""
|
|
import os
|
|
from dotenv import load_dotenv
|
|
import pandas as pd
|
|
from scrapegraphai.graphs import CSVScraperGraph
|
|
from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# 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)
|
|
|
|
text = pd.read_csv(file_path)
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": "***************************",
|
|
"model": "oneapi/qwen-turbo",
|
|
"base_url": "http://127.0.0.1:3000/v1", # 设置 OneAPI URL
|
|
}
|
|
}
|
|
|
|
# ************************************************
|
|
# 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))
|
|
|
|
# Save to json or csv
|
|
convert_to_csv(result, "result")
|
|
convert_to_json(result, "result")
|