From 6deb5ce1eb1461e7a7ef37d41eb43517e0eefebb Mon Sep 17 00:00:00 2001 From: petermr Date: Thu, 24 Mar 2022 10:26:25 +0000 Subject: [PATCH] Update arxiv.py --- pygetpapers/repository/arxiv.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/pygetpapers/repository/arxiv.py b/pygetpapers/repository/arxiv.py index 0010836..40206dc 100644 --- a/pygetpapers/repository/arxiv.py +++ b/pygetpapers/repository/arxiv.py @@ -50,7 +50,17 @@ from pygetpapers.repositoryinterface import RepositoryInterface class Arxiv(RepositoryInterface): - """Arxiv class which handles arxiv repository""" + ""arxiv.org repository + + This uses a PyPI code `arxiv` to download metadata. It is not clear whether this is + created by the `arXiv` project or layered on top of the public API. + + `arXiv` current practice for bulk data download (e.g. PDFs) is described in +https://arxiv.org/help/bulk_data. Please be considerate and also include a rate limit. + + + + """ def __init__(self): self.download_tools = DownloadTools(ARXIV) @@ -176,4 +186,4 @@ def apipaperdownload(self, query_namespace): makecsv=query_namespace["makecsv"], makexml=query_namespace["xml"], makehtml=query_namespace["makehtml"], - ) \ No newline at end of file + )