With package XML this can be drastically shortened –
# get blogger urls with XML: library(RCurl) library(XML) script <- getURL("www.r-bloggers.com") doc <- htmlParse(script) li <- getNodeSet(doc, "//ul[@class='xoxo blogroll']//a") urls <- sapply(li, xmlGetAttr, "href")
With only a few lines of code this gives the same result as in the original post! Here I will also process the urls for retrieving links to each blog's start page:
# get ids for those with only 2 slashes (no 3rd in the end): id <- which(nchar(gsub("[^/]", "", urls )) == 2) slash_2 <- urls[id] # find position of 3rd slash occurrence in strings: slash_stop <- unlist(lapply(str_locate_all(urls, "/"),"[[", 3)) slash_3 <- substring(urls, first = 1, last = slash_stop - 1) # final result, replace the ones with 2 slashes, # which are lacking in slash_3: blogs <- slash_3; blogs[id] <- slash_2
p.s.: Thanks to Vincent Zoonekynd for helping out with the XML syntax.