ScientryBackend / fetch_data.py
raannakasturi's picture
Refactor summarization and email sending logic; improve error handling and environment variable checks
f50b29d
raw
history blame
3.2 kB
from gradio_client import Client
import json
from concurrent.futures import ThreadPoolExecutor, as_completed
def fetch_category_ids(api_key):
if not api_key:
raise ValueError("API access key not found. Please check your environment variables.")
cat_ids_api_client = Client("raannakasturi/ReXploreIDFetchingAPI")
try:
result = cat_ids_api_client.predict(
user_access_key=api_key,
api_name="/fetch_paper_ids"
)
cat_ids = json.loads(result)
if cat_ids.get('status') == 'success':
return cat_ids.get('data')
else:
print(f"Failed to fetch category IDs: {cat_ids.get('message', 'No message provided')}")
return None
except Exception as e:
print(f"Exception while fetching category IDs: {e}")
return None
def fetch_single_paper_data(paper_id):
paper_data_api_client = Client("raannakasturi/ReXplorePaperDataFetcher")
try:
result = paper_data_api_client.predict(
id=paper_id,
api_name="/fetch_paper_data"
)
paper_data = json.loads(result)
if paper_data.get('status') == 'success':
return paper_id, paper_data.get('data')
else:
print(f"Failed to fetch data for paper ID {paper_id}: {paper_data.get('message', 'Unknown error')}")
return paper_id, None
except Exception as e:
print(f"Exception while fetching data for paper ID {paper_id}: {e}")
return paper_id, None
def fetch_paper_data_concurrently(paper_ids, max_threads=12):
paper_id_data = {}
with ThreadPoolExecutor(max_workers=max_threads) as executor:
future_to_paper = {executor.submit(fetch_single_paper_data, pid): pid for pid in paper_ids}
for future in as_completed(future_to_paper):
paper_id = future_to_paper[future]
try:
pid, data = future.result()
if data:
paper_id_data[pid] = data
except Exception as e:
print(f"Error fetching data for paper ID {paper_id}: {e}")
return paper_id_data
def fetch_paper_data_with_category(api_key):
all_data = {}
try:
cat_ids = fetch_category_ids(api_key)
if cat_ids:
for category, info in cat_ids.items():
print(f"Fetching data for category: {category}")
try:
paper_ids = info.get('ids', [])
if paper_ids:
paper_data = fetch_paper_data_concurrently(paper_ids)
if paper_data:
all_data[category] = paper_data
else:
print(f"No paper IDs found for category: {category}")
except Exception as e:
print(f"Error fetching data for category {category}: {e}")
continue
return json.dumps(all_data, indent=4, ensure_ascii=False)
except Exception as e:
print(f"Exception while fetching paper data by category: {e}")
return None