diff options
Diffstat (limited to 'scraper')
| -rw-r--r-- | scraper/s2-final-report.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/scraper/s2-final-report.py b/scraper/s2-final-report.py index a3209d24..2ebd516c 100644 --- a/scraper/s2-final-report.py +++ b/scraper/s2-final-report.py @@ -27,14 +27,15 @@ def process_paper(row): aggregate_citations = {} unknown_citations = {} address = None + address_list = [] papers = [] - print(row['paper_ids']) + # print(row['paper_ids']) for paper_id in row['paper_ids']: res = process_single_paper(row, paper_id, addresses, aggregate_citations, unknown_citations) if res: papers.append(res) if res['address']: - address = res['address'] + address_list.append(res['address']) if not len(papers): return with open('{}/{}.json'.format(DIR_PUBLIC_CITATIONS, row['key']), 'w') as f: @@ -43,7 +44,7 @@ def process_paper(row): 'dataset': row['dataset'], 'statistics': row['statistics'], 'paper': papers[0], - 'address': address, + 'addresses': address_list, 'additional_papers': papers[1:], 'citations': [aggregate_citations[key] for key in aggregate_citations.keys()], }, f) @@ -94,7 +95,7 @@ def process_single_paper(row, paper_id, addresses, aggregate_citations, unknown_ paper_institutions = load_institutions(paper.paper_id, paper_location_lookup) paper_address = None for inst in sorted(paper_institutions, key=operator.itemgetter(1)): - print(inst[1]) + #print(inst[1]) institution = inst[1] if paper_address is None: paper_address = addresses.findObject(institution) |