Despite there being a section in RFC 7231 https://tools.ietf.org/html/rfc7231#section-5.5.3 defining a suggested structure for âUser-Agentâ headers this data is notoriously difficult to parse consistently. Tools are provided that will take in user agent strings and return structured R objects. This is a âV8â-backed package based on the âua-parserâ project https://github.com/ua-parser.
NOTE: there is a C++-backed R package but it has issues compiling on a few platforms and is dependent upon Boost regex. This version is definitely slower but it works on all platforms.
install.packages("uaparserjs", repos = c("https://cinc.rud.is", "https://cloud.r-project.org/"))
# or
remotes::install_git("https://git.rud.is/hrbrmstr/uaparserjs.git")
# or
remotes::install_git("https://git.sr.ht/~hrbrmstr/uaparserjs")
# or
remotes::install_gitlab("hrbrmstr/uaparserjs")
# or
remotes::install_bitbucket("hrbrmstr/uaparserjs")
# or
remotes::install_github("hrbrmstr/uaparserjs")NOTE: To use the âremotesâ install options you will need to have the {remotes} package installed.
library(uaparserjs)
# current version
packageVersion("uaparserjs")
## [1] '0.3.5'
dplyr::glimpse(ua_parse("Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.2 (KHTML, like Gecko) Ubuntu/11.10 Chromium/15.0.874.106 Chrome/15.0.874.106 Safari/535.2"))
## Rows: 1
## Columns: 9
## $ userAgent <chr> "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.2 (KHTML, like Gecko) Ubuntu/11.10 Chromium/15â¦
## $ ua.family <chr> "Chromium"
## $ ua.major <chr> "15"
## $ ua.minor <chr> "0"
## $ ua.patch <chr> "874"
## $ os.family <chr> "Ubuntu"
## $ os.major <chr> "11"
## $ os.minor <chr> "10"
## $ device.family <chr> "Other"
agents <- readLines(system.file("extdat", "agents.txt", package = "uaparserjs"))
dplyr::glimpse(ua_parse(agents))
## Rows: 1,091
## Columns: 13
## $ userAgent <chr> "Mozilla/5.0 (Windows; U; en-US) AppleWebKit/531.9 (KHTML, like Gecko) AdobeAIR/2.5.1", "Mozillâ¦
## $ ua.family <chr> "AdobeAIR", "Amazon Silk", "Amazon Silk", "Amazon Silk", "Amazon Silk", "Amazon Silk", "Androidâ¦
## $ ua.major <chr> "2", "1", "2", "2", "2", "3", "2", "2", "2", "2", "3", "4", "4", "4", "4", "1", "1", "6", "7", â¦
## $ ua.minor <chr> "5", "1", "0", "1", "2", "25", "2", "3", "3", "3", "0", "0", "0", "0", "0", NA, NA, "13", "6", â¦
## $ ua.patch <chr> "1", "0-80", NA, NA, NA, NA, "2", "3", "4", "5", "1", "3", "3", "3", "4", NA, NA, "13719", "214â¦
## $ os.family <chr> "Windows", "Android", "Android", "Android", "Android", "Android", "Android", "Android", "Androiâ¦
## $ device.family <chr> "Other", "Kindle", "Kindle Fire HD", "Kindle Fire", "Kindle Fire HD", "Kindle Fire HD", "HTC Deâ¦
## $ device.brand <chr> NA, "Amazon", "Amazon", "Amazon", "Amazon", "Amazon", "HTC", "HTC", "Amazon", "Tecno", "Samsungâ¦
## $ device.model <chr> NA, "Kindle", "Kindle Fire HD 7\"", "Kindle Fire", "Kindle Fire HD 7\"", "Kindle Fire HD 7\"", â¦
## $ os.major <chr> NA, NA, NA, NA, NA, "4", "2", "2", "2", "2", "3", "4", "4", "4", "4", "7", "7", "XP", "8", "4",â¦
## $ os.minor <chr> NA, NA, NA, NA, NA, "0", "2", "3", "3", "3", "0", "0", "0", "0", "0", NA, NA, NA, NA, "1", "0",â¦
## $ os.patch <chr> NA, NA, NA, NA, NA, "3", "2", "3", "4", "5", "1", "3", "3", "3", "4", NA, NA, NA, NA, "1", "6",â¦
## $ os.patchMinor <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,â¦
set.seed(100)
batch_100 <- sample(agents, 100)
microbenchmark::microbenchmark(
ua_parse(batch_100)
)
## Unit: milliseconds
## expr min lq mean median uq max neval
## ua_parse(batch_100) 708.7338 721.5558 737.8894 730.8626 742.9891 928.1393 100Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4