wehub-resource-sync
58 lines
1.5 KiB
Python
58 lines
1.5 KiB
Python
"""
|
|
Basic example of scraping pipeline using XMLScraperGraph from XML documents
|
|
"""
|
|
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
from scrapegraphai.graphs import XMLScraperGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Read the XML file
|
|
# ************************************************
|
|
|
|
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()
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
openai_key = os.getenv("OPENAI_API_KEY")
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": openai_key,
|
|
"model": "openai/gpt-4o",
|
|
},
|
|
"verbose": False,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the XMLScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
xml_scraper_graph = XMLScraperGraph(
|
|
prompt="List me all the authors, title and genres of the books",
|
|
source=text, # Pass the content of the file, not the file object
|
|
config=graph_config,
|
|
)
|
|
|
|
result = xml_scraper_graph.run()
|
|
print(result)
|
|
|
|
# ************************************************
|
|
# Get graph execution info
|
|
# ************************************************
|
|
|
|
graph_exec_info = xml_scraper_graph.get_execution_info()
|
|
print(prettify_exec_info(graph_exec_info))
|