diff options
| author | Jules Laplace <julescarbon@gmail.com> | 2019-02-10 16:16:24 +0100 |
|---|---|---|
| committer | Jules Laplace <julescarbon@gmail.com> | 2019-02-10 16:16:24 +0100 |
| commit | b248ce4f21a94e4d081d93328961aca5942ac8f0 (patch) | |
| tree | 8f082c284e714b36baae4f46c584f7f6439c1d3b /scraper | |
| parent | 4c2952abd847b04827d2465654c6aec24201b23c (diff) | |
citation files
Diffstat (limited to 'scraper')
| -rw-r--r-- | scraper/s2-final-report.py | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/scraper/s2-final-report.py b/scraper/s2-final-report.py index f81d1835..e20b3d98 100644 --- a/scraper/s2-final-report.py +++ b/scraper/s2-final-report.py @@ -24,12 +24,14 @@ def s2_final_report(): def process_paper(row, addresses): aggregate_citations = {} papers = [] + print(row['paper_ids']) for paper_id in row['paper_ids']: - res = process_single_paper(row, addresses, aggregate_citations) + res = process_single_paper(row, paper_id, addresses, aggregate_citations) if res: papers.append(res) if not len(papers): return + print(papers) with open('{}/{}.json'.format(DIR_PUBLIC_CITATIONS, row['key']), 'w') as f: json.dump({ 'id': papers[0]['paper_id'], @@ -39,7 +41,7 @@ def process_paper(row, addresses): 'citations': [aggregate_citations[key] for key in aggregate_citations.keys()], }, f) -def process_single_paper(row, addresses, aggregate_citations): +def process_single_paper(row, paper_id, addresses, aggregate_citations): res = { 'paper_id': '', 'key': '', @@ -62,7 +64,6 @@ def process_single_paper(row, addresses, aggregate_citations): pdf_count = 0 doi_count = 0 address_count = 0 - paper_id = row['paper_id'] fn = file_path('papers', paper_id, 'paper.json') |