new things

This commit is contained in:
ackman678
2021-03-30 00:37:43 -07:00
parent 14f1c48838
commit 6e92164bc3
8 changed files with 235 additions and 16 deletions

View File

@@ -31,13 +31,25 @@ echo "using $bibdFileOut"
#try to extract doi from pdf and retrieve a pubmed id
#for 'DOI:' syntax
doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -i doi: --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#doi:(.+)#\1#")
# doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -i "doi:" --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#doi:(.+)#\1#")
doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -iE "doi:? ?/?10\." --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#.*doi:? ?/?(10.+)#\1#")
#for 'https://doi.org' syntax
if [ -z "$doi" ]; then
doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -i "doi.org/" --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#.+doi\.org\/(.+)#\1#")
doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -iE "doi\.org/10\." --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#.+doi\.org/(10.+)#\1#")
fi
# for 'https://doi.org' syntax
# if [ -z "$doi" ]; then
# doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -i "doi.org/" --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#.+doi\.org\/(.+)#\1#")
# fi
#
# if [ -z "$doi" ]; then
# doi=$(pdftotext -q -f 1 -l 1 $fn - | grep -iE "doi ?" --max-count=1 | tr [:upper:] [:lower:] | sed -E "s#doi ?(.+)#\1#")
# fi
if [ -z "$doi" ]; then
echo "doi not found"
exit 1