diff options
| author | jules@lens <julescarbon@gmail.com> | 2019-05-03 19:18:29 +0200 |
|---|---|---|
| committer | jules@lens <julescarbon@gmail.com> | 2019-05-03 19:18:29 +0200 |
| commit | b3117f6a558bf0c9d00aa0d3039f9d3672774d90 (patch) | |
| tree | 11e6cd2edb2e2db016458168cf5c61c337992c03 /scraper | |
| parent | 44c3cd19655db3877ec3b8e2fbcab23302973f27 (diff) | |
| parent | 715cad30012b1530f2316c80c8d6594e9d7b4f25 (diff) | |
erge branch 'master' of asdf.us:megapixels_dev
Diffstat (limited to 'scraper')
| -rw-r--r-- | scraper/s2-final-report.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/scraper/s2-final-report.py b/scraper/s2-final-report.py index 854aa940..8d42a52b 100644 --- a/scraper/s2-final-report.py +++ b/scraper/s2-final-report.py @@ -134,6 +134,9 @@ def process_single_paper(row, paper_id, addresses, aggregate_citations, unknown_ if paper_id == 'search': dataset = row['key'] fn = 'datasets/s2/search_papers/{}.json'.format(dataset) + if not os.path.exists(fn): + return + print('>> {} {}'.format(data['paperId'], 'search results')) with open(fn, 'r') as f: citations = json.load(f) data = { 'citations': [ { 'paperId': paperId } for paperId in citations ] } |
