J1975
Reputation: 79
Parsing JSONP files using R
JSON newbie here. Could you please help with parsing JSON files using R. I did try jsonlite & rjson, but keep getting errors.
Below is the data retrieved via the api.
data <- GET("http://svcs.ebay.com/services/search/FindingService/v1?OPERATION-NAME=findItemsByKeywords&SERVICE-VERSION=1.0.0&SECURITY-APPNAME=GLOBAL-ID=EBAY-US&RESPONSE-DATA-FORMAT=JSON&callback=_cb_findItemsByKeywords&REST-PAYLOAD&keywords=harry%20potter&paginationInput.entriesPerPage=10")
The JSON looks like this:
/**/_cb_findItemsByKeywords({
"findItemsByKeywordsResponse":[
{
"ack":[
"Success"
],
"version":[
"1.13.0"
],
"timestamp":[
"2016-01-29T16:36:25.984Z"
],
"searchResult":[
{
"@count":"1",
"item":[
{
"itemId":[
"371533364795"
],
"title":[
"Harry Potter: Complete 8-Film Collection (DVD, 2011, 8-Disc Set)"
],
"globalId":[
"EBAY-US"
],
"primaryCategory":[
{
"categoryId":[
"617"
],
"categoryName":[
"DVDs & Blu-ray Discs"
]
}
],
"galleryURL":[
"http:\/\/thumbs4.ebaystatic.com\/m\/mn5Agt0HFD89L7_-lqfrZZw\/140.jpg"
],
"viewItemURL":[
"http:\/\/www.ebay.com\/itm\/Harry-Potter-Complete-8-Film-Collection-DVD-2011-8-Disc-Set-\/371533364795"
],
"productId":[
{
"@type":"ReferenceID",
"__value__":"110258144"
}
],
"paymentMethod":[
"PayPal"
],
"autoPay":[
"false"
],
"postalCode":[
"60131"
],
"location":[
"Franklin Park,IL,USA"
],
"country":[
"US"
],
"shippingInfo":[
{
"shippingServiceCost":[
{
"@currencyId":"USD",
"__value__":"0.0"
}
],
"shippingType":[
"FlatDomesticCalculatedInternational"
],
"shipToLocations":[
"US",
"CA",
"GB",
"AU",
"AT",
"BE",
"FR",
"DE",
"IT",
"JP",
"ES",
"TW",
"NL",
"CN",
"HK",
"MX",
"DK",
"RO",
"SK",
"BG",
"CZ",
"FI",
"HU",
"LV",
"LT",
"MT",
"EE",
"GR",
"PT",
"CY",
"SI",
"SE",
"KR",
"ID",
"ZA",
"TH",
"IE",
"PL",
"RU",
"IL"
],
"expeditedShipping":[
"false"
],
"oneDayShippingAvailable":[
"false"
],
"handlingTime":[
"1"
]
}
],
"sellingStatus":[
{
"currentPrice":[
{
"@currencyId":"USD",
"__value__":"26.95"
}
],
"convertedCurrentPrice":[
{
"@currencyId":"USD",
"__value__":"26.95"
}
],
"sellingState":[
"Active"
],
"timeLeft":[
"P16DT3H12M6S"
]
}
],
"listingInfo":[
{
"bestOfferEnabled":[
"false"
],
"buyItNowAvailable":[
"false"
],
"startTime":[
"2016-01-15T19:43:31.000Z"
],
"endTime":[
"2016-02-14T19:48:31.000Z"
],
"listingType":[
"StoreInventory"
],
"gift":[
"false"
]
}
],
"returnsAccepted":[
"true"
],
"condition":[
{
"conditionId":[
"1000"
],
"conditionDisplayName":[
"Brand New"
]
}
],
"isMultiVariationListing":[
"false"
],
"topRatedListing":[
"true"
]
}
]
}
],
"paginationOutput":[
{
"pageNumber":[
"1"
],
"entriesPerPage":[
"1"
],
"totalPages":[
"138112"
],
"totalEntries":[
"138112"
]
}
],
"itemSearchURL":[
"http:\/\/www.ebay.com\/sch\/i.html?_nkw=harry+potter&_ddo=1&_ipg=1&_pgn=1"
]
}
]
})
Upvotes: 3
Views: 433
Answers (2)
Jeroen Ooms
Reputation: 32988
The problem is that your data is not json, but it is JavaScript, jsonp to be exactly. If you just want to parse the JSON data you have to strip off the padding callback function.
req <- httr::GET("http://svcs.ebay.com/services/search/FindingService/v1?OPERATION-NAME=findItemsByKeywords&SERVICE-VERSION=1.0.0&SECURITY-APPNAME=YOUR-APP-123456&GLOBAL-ID=EBAY-US&RESPONSE-DATA-FORMAT=JSON&callback=_cb_findItemsByKeywords&REST-PAYLOAD&keywords=harry%20potter&paginationInput.entriesPerPage=10")
txt <- content(req, "text")
json <- sub("/**/_cb_findItemsByKeywords(", "", txt, fixed = TRUE)
json <- sub(")$", "", json)
mydata <- jsonlite::fromJSON(json)
Extra credit: alternatively you could use an actual JavaScript engine to parse the JavaScript:
library(V8)
ctx <- V8::v8()
ctx$eval("var out;")
ctx$eval("function _cb_findItemsByKeywords(x){out = x;}")
ctx$source("http://svcs.ebay.com/services/search/FindingService/v1?OPERATION-NAME=findItemsByKeywords&SERVICE-VERSION=1.0.0&SECURITY-APPNAME=YOUR-APP-123456&GLOBAL-ID=EBAY-US&RESPONSE-DATA-FORMAT=JSON&callback=_cb_findItemsByKeywords&REST-PAYLOAD&keywords=harry%20potter&paginationInput.entriesPerPage=10")
mydata <- ctx$get("out")
Upvotes: 4
Fernando Macedo
Reputation: 29
First, your json file seems to have a little issue. It should have started in the opening bracket "[".
I removed the text before it and I've tried this code, which worked perfectly:
library(rjson)
obj <- fromJSON(file = "v2.json")
That returned a list in obj with the contents of v2.json.
EDITED: Including a full functional soltion:
library(rjson)
library(stringr)
obj <- read.table("v2.json", sep = "\n", stringsAsFactors = FALSE, quote = "")
# Gets the first line with the string "[" ("\\" for scape)
firstline <- grep("\\[", obj[,1])[1]
# Gets the position of the string "[" in the line
fpos <- which(strsplit(obj[firstline, 1], "")[[1]] == "[")
# Gets the last line with the string "]"
lastline <- grep("\\]", obj[,1])
lastline <- lastline[length(lastline)]
# Gets the position of the string "]" in the line
lpos <- which(strsplit(obj[lastline, 1], "")[[1]] == "]")
# Changes the lines with the first "[" and the last "]" to keep the text
# between both (after "[" and before "]") if there is any.
obj[firstline, 1] <- str_sub(obj[firstline, 1], fpos)
obj[lastline, 1] <- str_sub(obj[lastline, 1], 1, lpos)
obj2 <- data.frame(obj[firstline:lastline, 1])
write.table(obj2, "v3.json", row.names = FALSE, col.names = FALSE, quote = FALSE)
obj3 <- fromJSON(file = "v3.json")
Upvotes: -1