Spaces:
Sleeping
Sleeping
refresh
Browse files
main.py
CHANGED
|
@@ -445,7 +445,9 @@ def upload_to_hf(abstract_df, contents_df, processed_arxiv_ids):
|
|
| 445 |
|
| 446 |
|
| 447 |
def main():
|
| 448 |
-
items = get_zotero_items(debug=True)
|
|
|
|
|
|
|
| 449 |
print(f"# of items fetched from zotero: {len(items)}")
|
| 450 |
arxiv_items = get_arxiv_items(items)
|
| 451 |
print(f"# of arxiv papers: {len(arxiv_items)}")
|
|
@@ -531,7 +533,7 @@ def main():
|
|
| 531 |
contents_df = contents_df.drop_duplicates(subset=["arxiv_id"], keep="last").reset_index(drop=True)
|
| 532 |
|
| 533 |
# upload to hf
|
| 534 |
-
processed_arxiv_ids = list(set(processed_arxiv_ids + list(
|
| 535 |
upload_to_hf(abstract_df, contents_df, processed_arxiv_ids)
|
| 536 |
|
| 537 |
# save as local copy
|
|
|
|
| 445 |
|
| 446 |
|
| 447 |
def main():
|
| 448 |
+
# items = get_zotero_items(debug=True)
|
| 449 |
+
items = get_zotero_items(debug=False)
|
| 450 |
+
|
| 451 |
print(f"# of items fetched from zotero: {len(items)}")
|
| 452 |
arxiv_items = get_arxiv_items(items)
|
| 453 |
print(f"# of arxiv papers: {len(arxiv_items)}")
|
|
|
|
| 533 |
contents_df = contents_df.drop_duplicates(subset=["arxiv_id"], keep="last").reset_index(drop=True)
|
| 534 |
|
| 535 |
# upload to hf
|
| 536 |
+
processed_arxiv_ids = list(set(processed_arxiv_ids + list(existing_arxiv_ids)))
|
| 537 |
upload_to_hf(abstract_df, contents_df, processed_arxiv_ids)
|
| 538 |
|
| 539 |
# save as local copy
|