s2 scripts

1 files changed, 68 insertions, 0 deletions

diff --git a/s2-search.py b/s2-search.py
new file mode 100644
index 00000000..1804207b
--- /dev/null
+++ b/s2-search.py
@@ -0,0 +1,68 @@
+import os
+import sys
+import csv
+import subprocess
+import time
+import random
+import re
+import json
+import click
+from s2 import SemanticScholarAPI
+
+'''
+s2 search API format:
+results
+matchedAuthors
+matchedPresentations
+query
+querySuggestions
+results
+stats
+totalPages
+totalResults
+'''
+
+@click.command()
+@click.option('--index', '-n', default=0, help='Index of CSV.')
+def fetch_entries(index):
+  keys, lines = read_citation_list(index)
+  s2 = SemanticScholarAPI()
+  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):
+      results = s2.search(title)
+      write_json(dump_fn, results)
+      if len(results['results']) == 0:
+        print("No results for {}".format(title))
+      else:
+        print(title)
+        write_json(entry_fn, results['results'][0])
+      time.sleep(random.randint(10, 20))
+
+def read_citation_list(index=0):
+  filename = './datasets/citations.csv'
+  if index > 0:
+    fn, ext = os.path.splitext(filename)
+    filename = fn + '-' + str(index) + ext
+  with open(filename, 'r') as f:
+    reader = csv.reader(f)
+    lines = list(reader)
+    keys = lines[0]
+    lines = lines[1:]
+    return keys, lines
+
+def write_json(fn, data):
+  with open(fn, 'w') as outfile:
+    json.dump(data, outfile)
+def write_csv(fn, keys, rows):
+  with open(fn, 'w') as f:
+    writer = csv.writer(f)
+    if keys is not None:
+      writer.writerow(keys)
+    for row in rows:
+      writer.writerow(row)
+
+if __name__ == '__main__':
+  fetch_entries()