mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-09 21:19:20 +08:00
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
"""
|
|
Basic example of scraping pipeline using JSONScraperGraph from JSON documents
|
|
"""
|
|
import os
|
|
from dotenv import load_dotenv
|
|
from scrapegraphai.graphs import JSONScraperGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Read the JSON file
|
|
# ************************************************
|
|
deepseek_key = os.getenv("DEEPSEEK_APIKEY")
|
|
|
|
FILE_NAME = "inputs/example.json"
|
|
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
|
|
# ************************************************
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"model": "deepseek/deepseek-chat",
|
|
"api_key": deepseek_key,
|
|
},
|
|
"verbose": True,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the JSONScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
json_scraper_graph = JSONScraperGraph(
|
|
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 = json_scraper_graph.run()
|
|
print(result)
|