initial import of material for public archive into git
We're creating a fresh archive because the history for our old chapter includes API keys, data files, and other material we can't share.
This commit is contained in:
24
code/data_collection/00_get_search_results.py
Normal file
24
code/data_collection/00_get_search_results.py
Normal file
@@ -0,0 +1,24 @@
|
||||
import argparse
|
||||
from request_functions import *
|
||||
|
||||
'''
|
||||
This script takes in a search query and an output file. It queries the scopus API to find all papers that match the search query, and saves them to the output file.
|
||||
|
||||
Unlike some of the other scripts in this directory, it does not try to determine the state - if you restart the script, it will start over and blow away whatever you had saved before.
|
||||
'''
|
||||
|
||||
years = range(2004, 2017)
|
||||
|
||||
def main():
|
||||
|
||||
parser = argparse.ArgumentParser(description='Output JSON of all articles matching search query')
|
||||
parser.add_argument('-q', help='Search query', required=True)
|
||||
parser.add_argument('-o', help='Where to append JSON results')
|
||||
args = parser.parse_args()
|
||||
|
||||
with open(args.o, 'w') as out_file:
|
||||
for year in years:
|
||||
get_search_results(args.q, out_file, year=year)
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user