|
& length(tmp)==0){info$"CLNACC "=" "}
}
info
}
greg_return_string <- function(pattern,stringlist){
#greg_return_stirng 指定匹配全部字符串列表，返回匹配的字符串
#pattern:匹配模式,比如"abc[a-z]*" stringlist:字符串列表，list("abc","abcde","cdfe") return : 列表里字符串匹配结果，"abc""abcde"
findlist <- gregexpr(pattern,stringlist)
needlist <- list()
for (i in which(unlist(findlist)>0)){
preadress <- substr(stringlist[i],findlist[[i]],findlist[[i]]+attr(findlist[[i]],'match.length')-1)
needlist<- c(needlist,list(preadress))
}
return(needlist)
}
greg_return_index <- function(pattern,stringlist){
#greg_return_stirng 指定匹配全部字符串列表，返回存在匹配的字符串列表index
#pattern:匹配模式 stringlst:待匹配字符串列表 return:存在返回匹配的字符串在列表中的index
findlist <- gregexpr(pattern,stringlist)
needlist <- list()
which(unlist(findlist)>0)
}
extradress <- function(strURL){
#将strURL网页里面我们所需要链接提取出来并加工
#strURL:网页链接网址 return:网址列表，包括所有提取加工后的网址链接
pattern <- "/index.php/Rs[0-9]+"
prefix <- "https://snpedia.com" #网址改为https起始
links <- getHTMLLinks(download(strURL)) # getHTMLLinks不能解析https的网址，因此先用download解析网址
needlinks <- gregexpr(pattern,links)
needlinkslist <- list()
for (i in which(unlist(needlinks)>0)){
preadress <- substr(links[i],needlinks[[i]],needlinks[[i]]+attr(needlinks[[i]],'match.length')-1)
needlinkslist<- c(needlinkslist,list(preadress))
adresses <- lapply(needlinkslist,function(x)paste(prefix,x,sep=""))
}
adresses
}
greg <- function(pattern,istring){
#greg函数查看单个字符串istring,并且返回匹配的部分，不匹配返回空
gregout <- gregexpr(pattern,istring)
substr(istring,gregout[[1]],gregout[[1]]+attr(gregout[[1]],'match.length')-1)
}
library(RCurl)
library(XML)
#自定义部分
strURL <- "https://snpedia.com/index.php?title=Special%3ASearch&profile=default&fulltext=Search&search=Congenital+adrenal+hyperplasia" #snpedia网址都已改为https开头
output <- "ouput.txt"
message(paste("[prog]",strURL,output,sep=" "))
strURLs <- extradress(strURL)
pattlistMainTable <- list("Orientation$","Stabilized$","Reference$","Chromosome$","Position$","Gene$")
#此匹配模式列表用于返回该字符串所在index，而对应的值是index是该index+1
pattlistClinvar <- list("Risk\n\n[-A-Za-z0-9_.%;\\(\\), ]+","Alt\n\n[-A-Za-z0-9_.%;\\(\\), ]+",
"Reference\n\n[-A-Za-z0-9_.%;\\(\\) ]+","Significance \n[A-Za-z ]+","Disease \n\n[A-Za-z ]+",
"CLNDBN \n\n[-A-Za-z0-9_.% ]+","Reversed \n\n[0-9]+", "HGVS \n\n[-A-Za-z0-9_.%:> ]+","CLNSRC \n\n[-A-Za-z0-9_.% ]+","CLNACC \n\n[-A-Za-z0-9_.%, ]+")
#此匹配模式列表用于返回相应clinvar
inf <- " "
for ( strURL in strURLs){
dat <- getinf(strURL)
if (inf==" "){
inf <- dat
}else{
inf <- rbind(inf,dat)
}
}
write.table(inf, file = output, row.names = F, col.names=T,quote = F, sep="\t") # tab 分隔的文件
message("完成！")
结果可以用直接打开，也可以用excel的自文本打开，方便查看
|