GPL4381_正则提取

https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL4381

image.png

options(stringsAsFactors = F)
kk=data.table::fread("C:/Users/Administrator/Downloads/GPL4381-4306.txt")
patten=".*\\((.*?)\\),.*"
patten2="[a-zA-Z0-9 ]*\\((.*?)\\),.*"
res=str_match(kk$GB_DEFINITION,pattern = patten)
res2=str_match(kk$GB_DEFINITION,pattern = patten2)
k1=data.frame(res[,2])
k2=data.frame(res2[,2])

image.png
image.png