Skip to main content

scrape_xml_gemini

"""
Basic example of scraping pipeline using SmartScraper from XML documents
"""

import os
from dotenv import load_dotenv
from scrapegraphai.graphs import SmartScraperGraph
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
# ************************************************

gemini_key = os.getenv("GOOGLE_APIKEY")

graph_config = {
"llm": {
"api_key": gemini_key,
"model": "google_vertexai/gemini-1.5-pro",
"temperature": 0,
"streaming": True
},
}

# ************************************************
# Create the SmartScraperGraph instance and run it
# ************************************************

smart_scraper_graph = SmartScraperGraph(
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 = smart_scraper_graph.run()
print(result)


# ************************************************
# Get graph execution info
# ************************************************

graph_exec_info = smart_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))