Remove/Replace/Extract URLs

Usage

rm_url(text.var, trim = !extract, clean = TRUE, pattern = "@rm_url", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)
rm_twitter_url(text.var, trim = !extract, clean = TRUE, pattern = "@rm_twitter_url", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)

Arguments

text.var

The text variable.

trim

logical. If TRUE removes leading and trailing white spaces.

clean

trim logical. If TRUE extra white spaces and escaped character will be removed.

pattern

A character string containing a regular expression (or character string for fixed = TRUE) to be matched in the given character vector. Default, @rm_url uses the rm_url regex from the regular expression dictionary from the dictionary argument.

replacement

Replacement for matched pattern.

extract

logical. If TRUE the URLs are extracted into a list of vectors.

dictionary

A dictionary of canned regular expressions to search within if pattern begins with "@rm_".

...

Other arguments passed to gsub.

Examples

x <- " I like www.talkstats.com and http://stackoverflow.com"
rm_url(x)

[1] "I like and"

rm_url(x, replacement = '<a href="\\1" target="_blank">\\1</a>')

[1] "I like <a href=\"\" target=\"_blank\"></a> and <a href=\"http://stackoverflow.com\" target=\"_blank\">http://stackoverflow.com</a>"

rm_url(x, extract=TRUE)

[[1]]
[1] "www.talkstats.com"        "http://stackoverflow.com"



rm_url(x, pattern = "@rm_url2", extract=TRUE)

[[1]]
[1] "www.talkstats.com"        "http://stackoverflow.com"


rm_url(x, pattern = "@rm_url3", extract=TRUE)

[[1]]
[1] "http://stackoverflow.com"



## Remove Twitter Short URL
x <- c("download file from http://example.com",
         "this is the link to my website http://example.com",
         "go to http://example.com from more info.",
         "Another url ftp://www.example.com",
         "And https://www.example.net",
         "twitter type: t.co/N1kq0F26tG",
         "still another one https://t.co/N1kq0F26tG :-)")

rm_twitter_url(x)

[1] "download file from http://example.com"             "this is the link to my website http://example.com"
[3] "go to http://example.com from more info."          "Another url ftp://www.example.com"                
[5] "And https://www.example.net"                       "twitter type:"                                    
[7] "still another one :-)"                            

rm_twitter_url(x, extract=TRUE)

[[1]]
[1] NA

[[2]]
[1] NA

[[3]]
[1] NA

[[4]]
[1] NA

[[5]]
[1] NA

[[6]]
[1] "t.co/N1kq0F26tG"

[[7]]
[1] "https://t.co/N1kq0F26tG"



## Combine removing Twitter URLs and standard URLs
rm_twitter_n_url <- rm_(pattern=pastex("@rm_twitter_url", "@rm_url"))
rm_twitter_n_url(x)

[1] "download file from"             "this is the link to my website" "go to from more info."         
[4] "Another url"                    "And"                            "twitter type:"                 
[7] "still another one :-)"         

rm_twitter_n_url(x, extract=TRUE)

[[1]]
[1] "http://example.com"

[[2]]
[1] "http://example.com"

[[3]]
[1] "http://example.com"

[[4]]
[1] "ftp://www.example.com"

[[5]]
[1] "https://www.example.net"

[[6]]
[1] "t.co/N1kq0F26tG"

[[7]]
[1] "https://t.co/N1kq0F26tG"

See also