From 078574a7b827106ff1130b7c12320c69202394a9 Mon Sep 17 00:00:00 2001 From: "jules@lens" Date: Wed, 20 Feb 2019 17:19:42 +0100 Subject: new reports --- scraper/s2-scrape.sh | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'scraper/s2-scrape.sh') diff --git a/scraper/s2-scrape.sh b/scraper/s2-scrape.sh index e1df67c5..3f548e6e 100644 --- a/scraper/s2-scrape.sh +++ b/scraper/s2-scrape.sh @@ -2,19 +2,40 @@ # These are the pertinent scripts for updating an existing S2 citation scrape. +echo ">> s2-papers.py" python s2-papers.py + +echo ">> s2-dump-ids.py" python s2-dump-ids.py + +echo ">> s2-dump-ids.py" #python s2-extract-papers.py + +echo ">> s2-dump-missing-paper-ids.py" python s2-dump-missing-paper-ids.py + +echo ">> s2-raw-papers.py" python s2-raw-papers.py + +echo ">> s2-dump-db-pdf-urls.py" python s2-dump-db-pdf-urls.py + +echo ">> s2-fetch-pdf.py" python s2-fetch-pdf.py + +echo ">> s2-fetch-doi.py" python s2-fetch-doi.py + +echo ">> s2-extract-pdf-txt.py" python s2-extract-pdf-txt.py + +echo ">> s2-citation-report.py" python s2-citation-report.py + +echo ">> s2-final-report.py" python s2-final-report.py -rm s2-final-all-papers.tar -tar cf s2-final-all-papers.tar datasets/s2/papers/ datasets/s2/raw_papers/ datasets/s2/pdf/*/*/*.txt -scp s2-final-all-papers.tar lens@neural.garden:www/files/ +#rm s2-final-all-papers.tar +#tar cf s2-final-all-papers.tar datasets/s2/papers/ datasets/s2/raw_papers/ datasets/s2/pdf/*/*/*.txt +#scp s2-final-all-papers.tar lens@neural.garden:www/files/ -- cgit v1.2.3-70-g09d2