diff options
| author | Jules Laplace <julescarbon@gmail.com> | 2018-11-03 19:08:17 +0100 |
|---|---|---|
| committer | Jules Laplace <julescarbon@gmail.com> | 2018-11-03 19:08:17 +0100 |
| commit | 0af672923232b53b2cdd3c41cb6768a64e200e68 (patch) | |
| tree | 7ecc63d58c80528c393fdeef792dd5d27956f8fb | |
| parent | 8299124ecc34fd4885e7b525b849a44083ab334b (diff) | |
| parent | cbd96aeca32dcfd37acdf5f6b7e3a2997311783c (diff) | |
Merge branch 'master' of asdf.us:megapixels_dev
| -rw-r--r-- | s2-extract-papers.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/s2-extract-papers.py b/s2-extract-papers.py index 00301433..bd30c24b 100644 --- a/s2-extract-papers.py +++ b/s2-extract-papers.py @@ -22,7 +22,7 @@ def search_dataset_shard(fn, ids): if (i % 1000) == 0: print("{}...".format(i)) for line in f.readlines(): - process_paper(str(line)[2:-3], ids) + process_paper(line.decode('UTF-8'), ids) def process_paper(line, ids): paper_id = line.split('"id":"', 2)[1].split('"', 2)[0] |
