Last active
July 21, 2017 20:53
-
-
Save Zoldin/47536af63182a0e8daf37a7b989e2e8d to your computer and use it in GitHub Desktop.
parsingxml.R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/Rscript | |
library(XML) | |
args = commandArgs(trailingOnly=TRUE) | |
if (!length(args)==2) { | |
stop("Two arguments must be supplied (input file name ,output file name - csv ext).n", call.=FALSE) | |
} | |
#read XML line by line | |
con <- file(args[1], "r") | |
lines <- readLines(con, -1) | |
test <- lapply(lines,function(x){return(xmlTreeParse(x,useInternalNodes = TRUE))}) | |
#parsing XML to get variables | |
ID <- as.numeric(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Id"))})) | |
Tags <- sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Tags"))}) | |
Title <- as.character(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Title"))})) | |
Body <- as.character(sapply(test,function(x){return(xpathSApply(x, "//row",xmlGetAttr, "Body"))})) | |
text = paste(Title,Body) | |
label = as.numeric(sapply(Tags,function(x){return(grep("python",x))})) | |
label[is.na(label)]=0 | |
#final data frame for export | |
df <- as.data.frame(cbind(ID,label,text),stringsAsFactors = FALSE) | |
df$ID=as.numeric(df$ID) | |
df$label=as.numeric(df$label) | |
#write to csv | |
write.csv(df, file=args[2],row.names=FALSE) | |
print("output file created....") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment