Create crawl_index.py
Browse files- crawl_index.py +19 -0
crawl_index.py
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from scholarly import scholarly
|
| 2 |
+
import json
|
| 3 |
+
from es_gpt import ESGPT
|
| 4 |
+
|
| 5 |
+
# Create an instance of the ESGPT class
|
| 6 |
+
esgpt = ESGPT(index_name="papers")
|
| 7 |
+
|
| 8 |
+
# Search for papers by author ID
|
| 9 |
+
author = scholarly.search_author_id("JE_m2UgAAAAJ")
|
| 10 |
+
papers = scholarly.fill(author, sections=['publications'])
|
| 11 |
+
# Index each paper in Elasticsearch
|
| 12 |
+
for paper in papers['publications']:
|
| 13 |
+
paper = scholarly.fill(paper, sections=[])
|
| 14 |
+
print(paper)
|
| 15 |
+
paper_dict = paper['bib']
|
| 16 |
+
id = paper['author_pub_id']
|
| 17 |
+
|
| 18 |
+
# Index the paper in Elasticsearch
|
| 19 |
+
esgpt.index(doc_id=id, doc=paper_dict)
|