"""
Basic example of scraping pipeline using SmartScraper using Azure OpenAI Key
"""
import os
from dotenv import load_dotenv
from langchain_openai import AzureChatOpenAI
from langchain_openai import AzureOpenAIEmbeddings
from scrapegraphai.graphs import XMLScraperGraph
from scrapegraphai.utils import prettify_exec_info
load_dotenv()
FILE_NAME = "inputs/books.xml"
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()
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}
}
smart_scraper_graph = XMLScraperGraph(
prompt="List me all the authors, title and genres of the books",
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))