I'm trying to input a CSV file, but I get the following error:
associatedata <- read.csv("AssociatedSpeciesID_1.csv", header=TRUE, fileEncoding = 'UTF-8-BOM') %>% mutate_all(na_if, "")
Error in read.table(file = file, header = header, sep = sep, quote = quote, :
more columns than column names
Here's the CSV below: I can't find where the number of columns doesn't matched up. I've tried common solutions to other questions, but nothing's worked.
ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
The header has 13 fields and all other records have 15 and examining it we see that there are two trailing commas on the end of each data line.
count.fields("abc.csv", sep = ",")
## [1] 13 15 15 15 15
1) If we remove the two trailing commas then it works. (You may not need the strip.white but it was added because the code in the Note at the end is indented 4 spaces to satisfy SO. It won't hurt.)
L <- "abc.csv" |>
readLines() |>
sub(pattern = ",,$", replacement = "")
DF <- read.csv(text = L, strip.white = TRUE)
giving
> str(DF)
'data.frame': 4 obs. of 13 variables:
$ ObjectID : int 1 2 3 4
$ GlobalID : chr "54e33e7c-1ff1-464f-8872-df027fcfe8ec" "68420bc9-d6c6-4d7f-a149-7306399ce5c1" "88a6807b-b00c-4e58-84bb-4e8cb61409ae" "9fc8ea4a-e197-42cc-bd75-614d5b106364"
$ AssociatedSpeciesKnown : chr "known" "known" "unknown" "known"
$ Associates : chr "Amelanchier utahensis" "NewSpecies" "" "Artemisia nova"
$ NewAssociate : chr "" "Genus species" "" ""
$ UnknownSpecies_Description: chr "" "" "ritiidiwjjviern bg" ""
$ AssociatedSpeciesAbundance: chr "Few" "Occasional" "Common" "Common"
$ Coflowering : chr "no" "yes" "no" "no"
$ ParentGlobalID : chr "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "ea9eb086-89c2-4aa5-a2f6-95519cd35a58"
$ CreationDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Creator : chr "ejob_BLM" "ejob_BLM" "ejob_BLM" "ejob_BLM"
$ EditDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Editor : chr "ejob" "ejob" "ejob" "ejob"
2) Alternately if sed is on your path then:
read.csv(pipe("sed -e s/,,$// abc.csv"), strip.white = TRUE)
3) This would also work.
DF <- read.csv("abc.csv", header = FALSE, skip = 1, strip.white = TRUE)[1:13]
names(DF) <- read.table("abc.csv", sep = ",", strip.white = TRUE, nrows = 1)
Note
Generate file from question.
Lines <- "ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
"
cat(Lines, file = "abc.csv")
Related
I have a file with irregular quotes like the following:
"INDICATOR,""CTY_CODE"",""MGN_CODE"",""EVENT_NR"",""EVENT_NR_CR"",""START_DATE"",""PEAK_DATE"",""END_DATE"",""MAX_EXT_ON"",""DURATION"",""SEVERITY"",""INTENSITY"",""AVERAGE_AREA"",""WIDEST_AREA_PERC"",""SCORE"",""GRP_ID"""
"Spi-3,""AFG"","""",1,1,""1952-10-01"",""1952-11-01"",""1953-06-01"",""1952-11-01"",9,6.98,0.78,19.75,44.09,5,1"
It seems irregular because the first column is only wrapped in single quotes, whereas every subsequent column is wrapped in double quotes. I'd like to read it so that every column is imported without quotes (neither in the header, nor the data).
What I've tried is the following:
# All sorts of tidyverse imports
tib <- readr::read_csv("file.csv")
And I also tried the suggestions offered here:
# Base R import
DF0 <- read.table("file.csv", as.is = TRUE)
DF <- read.csv(text = DF0[[1]])
# Data table import
DT0 <- fread("file.csv", header =F)
DT <- fread(paste(DT0[[1]], collapse = "\n"))
But even when it imports the file in the latter two cases, the variable names and some of the elements are wrapped in quotation marks.
I used data.table::fread with the quote="" option (which is "as is").
Then I cleaned the names and data by eliminating all the quotes.
The dates could be converted too, but I didn't do that.
library(data.table)
library(magrittr)
DT0 <- fread('file.csv', quote = "")
DT0 %>% setnames(names(.), gsub('"', '', names(.)))
string_cols <- which(sapply(DT0, class) == 'character')
DT0[, (string_cols) := lapply(.SD, function(x) gsub('\\"', '', x)),
.SDcols = string_cols]
str(DT0)
Classes ‘data.table’ and 'data.frame': 1 obs. of 16 variables:
$ INDICATOR : chr "Spi-3"
$ CTY_CODE : chr "AFG"
$ MGN_CODE : chr ""
$ EVENT_NR : int 1
$ EVENT_NR_CR : int 1
$ START_DATE : chr "1952-10-01"
$ PEAK_DATE : chr "1952-11-01"
$ END_DATE : chr "1953-06-01"
$ MAX_EXT_ON : chr "1952-11-01"
$ DURATION : int 9
$ SEVERITY : num 6.98
$ INTENSITY : num 0.78
$ AVERAGE_AREA : num 19.8
$ WIDEST_AREA_PERC: num 44.1
$ SCORE : int 5
$ GRP_ID : chr "1"
- attr(*, ".internal.selfref")=<externalptr>
I have a .txt file and am using Rstudio.
200416657210340 1665721 20040608 20090930 20060910 20070910 20080827 20090804
200416657210345 1665721 20040907 20090203 20070331 20080719
200416657210347 1665721 20040914 20091026 20070213 20080114 20090302
200416657210352 1665721 20041111 20100315 20070123 20071205 20081202
I am trying to read in the .txt file using read.fwf :
gripalisti <- read.fwf(file = "gripalisti.txt",
widths = c(15,8,9,9,9,9,9,9),
header = FALSE,
#stringsAsFactors = FALSE,
col.names = c("einst","bu","faeding","forgun","burdur1",
"burdur2","burdur3","burdur4"))
This works and the columns are the correct lenght.
However the "einst" and "bu" are supposed to be integer values and the rest are supposed to be dates.
When imported all the values in the first column (ID variables) look like this:
2.003140e+14
I have been trying to search for a way to change the imported column to integer (or character?) values and I have not found anything that does not result in an error.
An example, that I tried after a google:
gripalisti <- read.fwf(file = "gripalisti.txt",
widths = c(15,8,9,9,9,9,9,9),
header = FALSE,
#stringsAsFactors = FALSE,
col.names = c("einst","bu","faeding","forgun","burdur1",
"burdur2","burdur3","burdur4"),
colclasses = c("integer", "integer", "Date", "Date",
"Date", "Date", "Date", "Date"))
results in the error:
Error in read.table(file = FILE, header = header, sep = sep, row.names = row.names, :
unused argument (colclasses = c("integer", "integer", "Date", "Date", "Date", "Date", "Date", "Date"))
There are many missing values in the dataset that is over 100.000 lines. So other ways of importing have not worked for me. The dataset is NOT tab delimited.
Sorry if this is obvious, I am a very new R user.
edit:
Thanks for the help, I changed it to:
colClasses = c("character",
And now it look good.
As suggested in the comments:
it is colClasses=, not colclasses=, typo;
that first field cannot be stored as "integer", it must either be "numeric" or "character";
(additionally) those dates are not in the default format of %Y-%m-%d, you will need to convert them after reading in the data.
Prep:
writeLines("200416657210340 1665721 20040608 20090930 20060910 20070910 20080827 20090804\n200416657210345 1665721 20040907 20090203 20070331 20080719 \n200416657210347 1665721 20040914 20091026 20070213 20080114 20090302 \n200416657210352 1665721 20041111 20100315 20070123 20071205 20081202",
con = "gripalisti.txt")
Execution:
dat <- read.fwf("gripalisti.txt", widths = c(15,8,9,9,9,9,9,9), header = FALSE,
col.names = c("einst","bu","faeding","forgun","burdur1", "burdur2","burdur3","burdur4"),
colClasses = c("character", "integer", "character", "character", "character", "character", "character", "character"))
str(dat)
# 'data.frame': 4 obs. of 8 variables:
# $ einst : chr "200416657210340" "200416657210345" "200416657210347" "200416657210352"
# $ bu : int 1665721 1665721 1665721 1665721
# $ faeding: chr " 20040608" " 20040907" " 20040914" " 20041111"
# $ forgun : chr " 20090930" " 20090203" " 20091026" " 20100315"
# $ burdur1: chr " 20060910" " 20070331" " 20070213" " 20070123"
# $ burdur2: chr " 20070910" " 20080719" " 20080114" " 20071205"
# $ burdur3: chr " 20080827" " " " 20090302" " "
# $ burdur4: chr " 20090804" " " " " " 20081202"
dat[,3:8] <- lapply(dat[,3:8], as.Date, format = "%Y%m%d")
dat
# einst bu faeding forgun burdur1 burdur2 burdur3 burdur4
# 1 200416657210340 1665721 2004-06-08 2009-09-30 2006-09-10 2007-09-10 2008-08-27 2009-08-04
# 2 200416657210345 1665721 2004-09-07 2009-02-03 2007-03-31 2008-07-19 <NA> <NA>
# 3 200416657210347 1665721 2004-09-14 2009-10-26 2007-02-13 2008-01-14 2009-03-02 <NA>
# 4 200416657210352 1665721 2004-11-11 2010-03-15 2007-01-23 2007-12-05 <NA> 2008-12-02
str(dat)
# 'data.frame': 4 obs. of 8 variables:
# $ einst : chr "200416657210340" "200416657210345" "200416657210347" "200416657210352"
# $ bu : int 1665721 1665721 1665721 1665721
# $ faeding: Date, format: "2004-06-08" "2004-09-07" "2004-09-14" "2004-11-11"
# $ forgun : Date, format: "2009-09-30" "2009-02-03" "2009-10-26" "2010-03-15"
# $ burdur1: Date, format: "2006-09-10" "2007-03-31" "2007-02-13" "2007-01-23"
# $ burdur2: Date, format: "2007-09-10" "2008-07-19" "2008-01-14" "2007-12-05"
# $ burdur3: Date, format: "2008-08-27" NA "2009-03-02" NA
# $ burdur4: Date, format: "2009-08-04" NA NA "2008-12-02"
here the number in the first column is very large number, if you import it in term of integer or numeric it will automatically shown in exponent format. The way to resolve this to set scipen before reading the file. use below code :
options(scipen = 999)
I think this should resolve your problem.
Below is code I run, of course for date columns you need to to work. For that you can use simple command like as.Date(gripalisti$burdur1, format = "%Y%m%d")
I'm trying to pull data directly from an API into R using the httr package. The API doesn't require any authentication, and accepts JSON strings of lat, long, elevation, variable sets, and time period to estimate climate variables for any location. This is my first time using an API, but the code below is what I've cobbled together from various Stack Overflow posts.
library(jsonlite)
library(httr)
url = "http://apibc.climatewna.com/api/clmApi"
body <- data.frame(lat = c(48.98,50.2), ##two example locations
lon = c(-115.02, -120),
el = c(1000,100),
prd = c("Normal_1961_1990.nrm","Normal_1961_1990.nrm"),
varYSM = c("Y","SST"))
requestBody <- toJSON(list("output" = body),auto_unbox = TRUE) ##convert to JSON string
result <- POST("http://apibc.climatewna.com/api/clmApi", ##post to API
body = requestBody,
add_headers(`Content-Type`="application/json"))
content(result)
I've tried various different versions of this (e.g. writing the JSON string manually, putting the body as a list in POST with encode = "json"), and it always runs, but the content always contains the below error message:
$Message
[1] "An error has occurred."
$ExceptionMessage
[1] "Object reference not set to an instance of an object."
$ExceptionType
[1] "System.NullReferenceException"
If I use GET and specify the variables directly in the URL
url = "http://apibc.climatewna.com/api/clmApi/LatLonEl?lat=48.98&lon=-115.02&el=1000&prd=Normal_1961_1990&varYSM=Y"
result <- GET(url)
content(result)
it produces the correct output, but then I can only obtain information for one location at a time. There isn't currently any public documentation about this API as it's very new, but I've attached a draft of the section explaining it using JS below. I would very much appreciate any help/suggestions on what I'm doing wrong!
Thank you!
The main problem is that jQuery.ajax encodes the data using jQuery.param before sending it to the API, so what it's sending looks something like [0][lat]=48.98&[0][lon]=-115.02.... I don't know of a package in R that does a similar encoding as jQuery.param, so we'll have to hack something together.
Modifying your example slightly:
library(httr)
body <- data.frame(lat = c(48.98,50.2), ##two example locations
lon = c(-115.02, -120),
el = c(1000,100),
prd = c("Normal_1961_1990","Normal_1961_1990"),
varYSM = c("Y","Y"))
Now, we do the encoding, like so:
out <- sapply(1:nrow(body), function(i) {
paste(c(
paste0(sprintf("[%d][lat]", i - 1), "=", body$lat[i]),
paste0(sprintf("[%d][lon]", i - 1), "=", body$lon[i]),
paste0(sprintf("[%d][el]", i - 1), "=", body$el[i]),
paste0(sprintf("[%d][prd]", i - 1), "=", body$prd[i]),
paste0(sprintf("[%d][varYSM]", i - 1), "=", body$varYSM[i])
), collapse = "&")
})
out <- paste(out, collapse = "&")
so now out is in a form that the API likes. Finally
result <- POST(url = "http://apibc.climatewna.com/api/clmApi", ##post to API
body = out,
add_headers(`Content-Type`="application/x-www-form-urlencoded"))
noting the Content-Type. We get
df <- do.call(rbind, lapply(content(result), as.data.frame, stringsAsFactors = FALSE))
str(df)
# 'data.frame': 2 obs. of 29 variables:
# $ lat : chr "48.98" "50.2"
# $ lon : chr "-115.02" "-120"
# $ elev : chr "1000" "100"
# $ prd : chr "Normal_1961_1990" "Normal_1961_1990"
# $ varYSM : chr "Y" "Y"
# $ MAT : chr "5.2" "8"
# $ MWMT : chr "16.9" "20.2"
# $ MCMT : chr "-6.7" "-5.6"
# $ TD : chr "23.6" "25.7"
# $ MAP : chr "617" "228"
# $ MSP : chr "269" "155"
# $ AHM : chr "24.7" "79.1"
# $ SHM : chr "62.9" "130.3"
# $ DD_0 : chr "690" "519"
# $ DD5 : chr "1505" "2131"
# $ DD_18 : chr "4684" "3818"
# $ DD18 : chr "60" "209"
# $ NFFD : chr "165" "204"
# $ bFFP : chr "150" "134"
# $ eFFP : chr "252" "254"
# $ FFP : chr "101" "120"
# $ PAS : chr "194" "34"
# $ EMT : chr "-36.3" "-32.7"
# $ EXT : chr "37.1" "41.2"
# $ Eref : chr "14.7" "13.6"
# $ CMD : chr "721" "862"
# $ MAR : chr "347" "679"
# $ RH : chr "57" "57"
# $ Version: chr "ClimateBC_API_v5.51" "ClimateBC_API_v5.51"
I am trying to find a way to retrieve data from Harvard Dataverse website through R. I am using "dataverse" and "dvn" packages, among others. Many of the data files end with ".tab", although they are not formatted as normal tab-delimited text.
I have done this:
library(dataverse)
## 01. Using the dataverse server and making a search
Sys.setenv("DATAVERSE_SERVER" ="dataverse.harvard.edu")
## 02. Loading the dataset that I chose, by url
doi_url <- "https://doi.org/10.7910/DVN/ZTCWYQ"
my_dataset <- get_dataset(doi_url)
## 03. Grabbing the first file of the dataset
## which is named "001_AppendixC.tab"
my_files <- my_dataset$files$label
my_file <- get_file(my_files[1], doi_url)
AppendixC <- tempfile()
writeBin(my_file, AppendixC)
read.table(AppendixC)
> Error in scan(file = file, what = what, sep = sep, quote = quote, dec = dec, :
> line 1 did not have 2 elements
> In addition: Warning message:
> In read.table(AppendixC) :
> line 1 appears to contain embedded nulls
Any hint?
The problem is that dataverse::get_file() returns the file in a raw binary format. The easiest way to load it into memory is to write it to a tempfile with writeBin() and then read that file with the appropriate import/read function.
Here is a function that should automagically read it into memory:
# Uses rio, which automatically chooses the appropriate import/read
# function based on file type.
library(rio)
install_formats() # only needs to run once after
# pkg installation
load_raw_file <- function(raw, type) {
match.arg(
arg = type,
choices = c(
"csv", "tab", "psc", "tsv", "sas7bdat",
"sav", "dta", "xpt", "por", "xls", "xlsx",
"R", "RData", "rda", "rds", "rec", "mtb",
"feather", "csv.gz", "fwf"
)
)
tmp <- tempfile(fileext = paste0(".", type))
writeBin(as.vector(raw), tmp)
out <- import(tmp)
unlink(tmp)
out
}
Let's try it out with your file, which is a an excel file.
library(dataverse)
raw <- get_file(
"001_AppendixC.tab",
"https://doi.org/10.7910/DVN/ZTCWYQ"
)
data <- load_raw_file(raw, "xlsx")
And look at the data:
str(data)
> 'data.frame': 132 obs. of 17 variables:
> $ Country : chr "Afghanistan" "Albania" "Algeria" "Angola" ...
> $ UN_9193 : chr "37.4" "7.7" "9.1" "65.400000000000006" ...
> $ UN_9901 : chr "46.1" "7.2" "10.7" "50" ...
> $ UN_0709 : chr "24.6" "9.6999999999999993" "7.5" "23.7" ...
> $ UN_1416 : chr "23" "4.9000000000000004" "4.5999999999999996" "14" ...
> $ stu90_94 : chr "51.3" "37.200000000000003" "22.9" "52.9" ...
> $ stu98_02 : chr "54.7" "39.200000000000003" "23.6" "47.1" ...
> $ stu06_10 : chr "51.3" "23.1" "13.2" "29.2" ...
> $ stu12_16 : chr "40.9" "17.899999999999999" "11.7" "37.6" ...
> $ wast90_94: chr "11.5" "9.4" "7.1" "7.9" ...
> $ wast98_02: chr "13.4" "12.2" "3.1" "8.6999999999999993" ...
> $ wast06_10: chr "8.9" "9.4" "4.0999999999999996" "8.1999999999999993" ...
> $ wast12_16: chr "9.5" "6.2" "4.0999999999999996" "4.9000000000000004" ...
> $ UM1992 : chr "16.8" "3.7" "4.5" "22.6" ...
> $ UM2000 : chr "13.7" "2.6" "4" "21.7" ...
> $ UM2008 : chr "11" "1.8" "2.9" "19.2" ...
> $ UM2015 : chr "9.1" "1.4" "2.6" "15.7" ...
I'm trying to use this code:
require(RSelenium)
checkForServer()
startServer()
remDr<-remoteDriver()
remDr$open()
appURL <- 'http://www.mtmis.excise-punjab.gov.pk'
remDr$navigate(appURL)
remDr$findElement("name", "vhlno")$sendKeysToElement(list("ria-07-777"))
Can't figure out css selector
remDr$findElements("class", "ent-button-div")[[1]]$clickElement()
after searching query
elem <- remDr$findElement(using="class", value="result-div")
elemtxt <- elem$getElementAttribute("outerHTML")[[1]]
elemxml <- htmlTreeParse(elemtxt, useInternalNodes=T)
final <- readHTMLTable(elemxml)
remDr$close()
rD[["server"]]$stop()
What I want is to create an automated "for loop" with different vehicles from list and merge all into one final table with unique identifier, e.g., "ria-07-777".
list <- c("ria-07-776", "ria-07-777", "ria-07-778")
Why do you need Selenium?
library(httr)
library(rvest)
clean_cols <- function(x) {
x <- tolower(x)
x <- gsub("[[:punct:][:space:]]+", "_", x)
x <- gsub("_+", "_", x)
x <- gsub("(^_|_$)", "", x)
make.unique(x, sep = "_")
}
get_vehicle_info <- function(vhlno) {
POST(
url = 'http://www.mtmis.excise-punjab.gov.pk/',
set_cookies(has_js=1),
body = list(vhlno=vhlno)
) -> res
stop_for_status(res)
pg <- content(res)
rows <- html_nodes(pg, xpath=".//div[contains(#class, 'result-div')]/table/tr[td[not(#colspan)]]")
cbind.data.frame(
as.list(
setNames(
html_text(html_nodes(rows, xpath=".//td[2]")),
clean_cols(html_text(html_nodes(rows, xpath=".//td[1]")))
)
),
stringsAsFactors=FALSE
)
}
Now use ^^:
vehicles <- c("ria-07-776", "ria-07-777", "ria-07-778")
Reduce(
rbind.data.frame,
lapply(vehicles, function(v) {
Sys.sleep(5) # your desire to steal a bunch of vehicle info to make a sketch database does not give you the right to hammer the server, and you'll very likely remove this line anyway, but I had to try
get_vehicle_info(v)
})
) -> vehicle_df
str(vehicle_df)
## 'data.frame': 3 obs. of 12 variables:
## $ registration_number: chr "ria-07-776" "ria-07-777" "ria-07-778"
## $ chassis_number : chr "KZJ95-0019869" "NFBFD15746R101101" "NZE1206066278"
## $ engine_number : chr "1KZ-0375851" "R18A11981105" "X583994"
## $ make_name : chr "LAND - CRUISER" "HONDA - CIVIC" "TOYOTA - COROLLA"
## $ registration_date : chr "17-Dec-2007 12:00 AM" "01-Aug-2007 12:00 AM" "01-Jan-1970 12:00 AM"
## $ model : chr "1997" "2006" "2007"
## $ vehicle_price : chr "1,396,400" "1,465,500" "0"
## $ color : chr "MULTI" "GRENDA B.P" "SILVER"
## $ token_tax_paid_upto: chr "June 2015" "June 2011" "June 2016"
## $ owner_name : chr "FATEH DIN AWAN" "M BILAL YASIN" "MUHAMMAD ALTAF"
## $ father_name : chr "HAFIZ ABDUL HAKEEM AWAN" "CH M. YASIN" "NAZAR MUHAMMAD"
## $ owner_city : chr "RAWALPINDI" "ISLAMABAD" "SARGODHA"
You'll need to handle network and scraping errors on your own. I can't justify any more time for this likely unethical endeavour (the answer was more to help others with similar q's).