1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
|
import os
import sys
import csv
import subprocess
import time
import random
import re
import simplejson as json
import click
from s2 import SemanticScholarAPI
from util import *
'''
s2 search API format:
results
matchedAuthors
matchedPresentations
query
querySuggestions
results
stats
totalPages
totalResults
'''
s2 = SemanticScholarAPI()
@click.command()
@click.option('--index', '-n', default=0, help='Index of CSV (query,)')
@click.option('--depth', '-d', default=1, help='Depth to recurse (not implemented).')
def fetch_papers(index, depth):
keys, lines = read_citation_list(index)
for line in lines:
label = line[0]
title = re.sub(r'[^-0-9a-zA-Z ]+', '', line[1])
entry_fn = './datasets/s2/entries/{}.json'.format(title)
if not os.path.exists(entry_fn):
print('not found: {}'.format(entry_fn))
continue
result = read_json(entry_fn)
paper_id = result['id']
paper = fetch_paper(paper_id)
# get all of the paper's citations
def fetch_paper(paper_id):
os.makedirs('./datasets/s2/papers/{}/{}'.format(paper_id[0:2], paper_id), exist_ok=True)
paper_fn = './datasets/s2/papers/{}/{}/paper.json'.format(paper_id[0:2], paper_id)
if os.path.exists(paper_fn):
return read_json(paper_fn)
print(paper_id)
paper = s2.paper(paper_id)
if paper is None:
print("Got none paper??")
time.sleep(random.randint(20, 30))
paper = s2.paper(paper_id)
if paper is None:
print("Paper not found")
return None
write_json(paper_fn, paper)
time.sleep(random.randint(5, 10))
return paper
if __name__ == '__main__':
fetch_papers()
|
