mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-06 21:11:37 +08:00
63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
"""
|
|
Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
|
|
"""
|
|
|
|
import os
|
|
from dotenv import load_dotenv
|
|
import pandas as pd
|
|
from scrapegraphai.graphs import CSVScraperMultiGraph
|
|
from langchain_openai import AzureChatOpenAI
|
|
from langchain_openai import AzureOpenAIEmbeddings
|
|
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
|
|
# ************************************************
|
|
llm_model_instance = AzureChatOpenAI(
|
|
openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
|
|
azure_deployment=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
|
|
)
|
|
|
|
embedder_model_instance = AzureOpenAIEmbeddings(
|
|
azure_deployment=os.environ["AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME"],
|
|
openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
|
|
)
|
|
graph_config = {
|
|
"llm": {"model_instance": llm_model_instance},
|
|
"embeddings": {"model_instance": embedder_model_instance}
|
|
}
|
|
# ************************************************
|
|
# Create the CSVScraperMultiGraph instance and run it
|
|
# ************************************************
|
|
|
|
csv_scraper_graph = CSVScraperMultiGraph(
|
|
prompt="List me all the last names",
|
|
source=[str(text), str(text)],
|
|
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")
|