I have a script that works fine for one file. It takes the information from a json file, extracts a list and a sublist of it (A), and then another list B with the third element of list A. It creates a data frame with list B and compares it with a master file. Finally, it provides two numbers: the number of elements in the list B and the number of matching elements of that list when comparing with the master file.
However, I have 180 different json files in a folder and I need to run the script for all of them, and build a data frame with the results for each file. So the final result should be something like this (note that the last line's figures are correct, the first two are fictitious):
The code I have so far is the following:
library(rjson)
library(dplyr)
library(tidyverse)
#load data from file
file <- "./raw_data/whf.json"
json_data <- fromJSON(file = file)
org_name <- json_data$id
# extract lists and the sublist
usernames <- json_data$twitter
following <- usernames$following
# create empty vector to populate
longitud = length(following)
names <- vector(length = longitud)
# loop to populate the empty vector with third element of the sub-list
for(i in 1:longitud){
names[i] <- following[[i]][3]
}
# create a data frame and change column name
names_list <- data.frame(sapply(names, c))
colnames(names_list) <- "usernames"
# create a data frame with the correct formatting ready to comparison
org_handles <- data.frame(paste("#", names_list$usernames, sep=""))
colnames(org_handles) <- "Twitter"
# load master file and select the needed columns
psa_handles <- read_csv(file = "./raw_data/psa_handles.csv") %>%
select(Name, AKA, Twitter)
# merge data frames and present the results
org_list <- inner_join(psa_handles, org_handles)
length(org_list$Twitter)
length(usernames$following)
My first attempt is to include this code at the beginning:
files <- list.files()
for(f in files){
json_data <- fromJSON(file = f)
# the rest of the script for one file here
}
but I do not know how to write the code for the data frame or even how to integrate both ideas -the working script and the loop for the file names. I took the idea from here.
The new code after Alvaro Morales' answer is the following
library(rjson)
library(dplyr)
library(tidyverse)
archivos <- list.files("./raw_data/")
calculate_accounts <- function(archivos){
#load data from file
path <- paste("./raw_data/", archivos, sep = "")
json_data <- fromJSON(file = path)
org_name <- json_data$id
# extract lists and the sublist
usernames <- json_data$twitter
following <- usernames$following
# create empty vector to populate
longitud = length(following)
names <- vector(length = longitud)
# loop to populate the empty vector with third element of the sub-list
for(i in 1:longitud){
names[i] <- following[[i]][3]
}
# create a data frame and change column name
names_list <- data.frame(sapply(names, c))
colnames(names_list) <- "usernames"
# create a data frame with the correct formatting ready to comparison
org_handles <- data.frame(paste("#", names_list$usernames, sep=""))
colnames(org_handles) <- "Twitter"
# load master file and select the needed columns
psa_handles <- read_csv(file = "./psa_handles.csv") %>%
select(Name, AKA, Twitter)
# merge data frames and present the results
org_list <- inner_join(psa_handles, org_handles)
accounts_db_org <- length(org_list$Twitter)
accounts_total_org <- length(usernames$following)
}
table_psa <- map_dfr(archivos, calculate_accounts)
However, now there is an error when Joining, by = "Twitter", it says subindex out of limits.
Links to 3 test files to put together in raw_data folder:
https://drive.google.com/file/d/1ilUHwLjgtZCzh0LneIJEhTryrGumDF1V/view?usp=sharing
https://drive.google.com/file/d/1KM3hRZ8DzgPMEsMFmwBdmMNHrPCttuaB/view?usp=sharing
https://drive.google.com/file/d/17cWXJ9ltGXZ6izkgJv0uyNwStrE95_OA/view?usp=sharing
Link to the master file to compare:
https://drive.google.com/file/d/11fOpYFFfHijhZl_CuWHKvkrI7edkpUNQ/view?usp=sharing
<<<<< UPDATE >>>>>>
I am trying to find the solution and I did the code work and provide a valide output (a 180x3 data frame), but the columns that should be filled with the values of the objects accounts_db_org and accounts_total_org are showing NA. When checking the value stored in those objects, the values are correct (for the last iteration). So the output now is in its right format, but with NA instead of numbers.
I am really close, but I am not being able to make the code to show the right numbers. My last attempt is:
library(rjson)
library(dplyr)
library(tidyverse)
archivos <- list.files("./raw_data", pattern = "json", full.names = TRUE)
psa_handles <- read_csv(file = "./raw_data/psa_handles.csv", show_col_types = FALSE) %>%
select(Name, AKA, Twitter)
nr_archivos <- length(archivos)
psa_result <- matrix(nrow = nr_archivos, ncol = 3)
# loop for working with all files, one by one
for(f in 1:nr_archivos){
# load file
json_data <- fromJSON(file = archivos[f])
org_name <- json_data$id
# extract lists and the sublist
usernames <- json_data$twitter
following <- usernames$following
# empty vector
longitud = length(following)
names <- vector(length = longitud)
# loop to populate with the third element of each i item of the sublist
for(i in 1:longitud){
names[i] <- following[[i]][3]
}
# convert the list into a data frame
names_list <- data.frame(sapply(names, c))
colnames(names_list) <- "usernames"
# applying some format prior to comparison
org_handles <- data.frame(paste("#", names_list$usernames, sep=""))
colnames(org_handles) <- "Twitter"
# merge tables and calculate the results for each iteration
org_list <- inner_join(psa_handles, org_handles)
accounts_db_org <- length(org_list$Twitter)
accounts_total_org <- length(usernames$following)
# populate the matrix row by row
psa_result[f] <- c(org_name, accounts_db_org, accounts_total_org)
}
# create a data frame from the matrix and save the result
psa_result <- data.frame(psa_result)
write_csv(psa_result, file = "./outputs/cuentas_seguidas_en_psa.csv")
The subscript out of bounds error was caused by a json file with 0 records. That was fixed deleting the file.
You can do it with purrr::map or purrr::map_dfr.
Is this what you looking for?
archivos <- list.files("./raw_data", pattern = "json", full.names = TRUE)
# load master file and select the needed columns. This needs to be out of "calculate_accounts" because you only read it once.
psa_handles <- read_csv(file = "./raw_data/psa_handles.csv") %>%
select(Name, AKA, Twitter)
# calculate accounts
calculate_accounts <- function(archivo){
json_data <- rjson::fromJSON(file = archivo)
org_handles <- json_data %>%
pluck("twitter", "following") %>%
map_chr("username") %>%
as_tibble() %>%
rename(usernames = value) %>%
mutate(Twitter = str_c("#", usernames)) %>%
select(Twitter)
org_list <- inner_join(psa_handles, org_handles)
org_list %>%
mutate(accounts_db_org = length(Twitter),
accounts_total_org = nrow(org_handles)) %>%
select(-Twitter)
}
table_psa <- map_dfr(archivos, calculate_accounts)
#output:
# A tibble: 53 x 4
Name AKA accounts_db_org accounts_total_org
<chr> <chr> <int> <int>
1 Association of American Medical Colleges AAMC 20 2924
2 American College of Cardiology ACC 20 2924
3 American Heart Association AHA 20 2924
4 British Association of Dermatologists BAD 20 2924
5 Canadian Psoriasis Network CPN 20 2924
6 Canadian Skin Patient Alliance CSPA 20 2924
7 European Academy of Dermatology and Venereology EADV 20 2924
8 European Society for Dermatological Research ESDR 20 2924
9 US Department of Health and Human Service HHS 20 2924
10 International Alliance of Dermatology Patients Organisations (Global Skin) IADPO 20 2924
# ... with 43 more rows
Unfortunately, the answer provided by Álvaro does not work as expected, since the output repeats the same number with different organisation names, making it really difficult to read. Actually, the number 20 is repeated 20 times, the number 11, 11 times, and so on. The information is there, but it is not accessible without further data treatment.
I was doing my own research in the meantime and I got to the following code. Finally I made it to work, but the data format was "matrix" "array", really confusing. Fortunately, I wrote the last lines to transpose the data, unlist the array and convert in a matrix, which is able to be converted in a data frame and manipulated as usual.
Maybe my explanation is not very useful, and since I am a newbie, I am sure the code is far from being elegant and optimised. Anyway, please review the code below:
library(purrr)
library(rjson)
library(dplyr)
library(tidyverse)
setwd("~/documentos/varios/proyectos/programacion/R/psa_twitter")
# Load data from files.
archivos <- list.files("./raw_data/json_files",
pattern = ".json",
full.names = TRUE)
psa_handles <- read_csv(file = "./raw_data/psa_handles.csv") %>%
select(Name, AKA, Twitter)
nr_archivos <- length(archivos)
calcula_cuentas <- function(a){
# Extract lists
json_data <- fromJSON(file = a)
org_aka <- json_data$id
org_meta <- json_data$metadata
org_name <- org_meta$company
twitter <- json_data$twitter
following <- twitter$following
# create an empty vector to populate
longitud = length(following)
names <- vector(length = longitud)
# loop to populate the empty vector with third element of the sub-list
for(i in 1:longitud){
names[i] <- following[[i]][3]
}
# create a data frame and change column name
names_list <- data.frame(sapply(names, c))
colnames(names_list) <- "usernames"
# Create a data frame with the correct formatting ready to comparison
org_handles <- data.frame(paste("#",
names_list$usernames,
sep="")
)
colnames(org_handles) <- "Twitter"
# merge tables
org_list <- inner_join(psa_handles, org_handles)
cuentas_db_org <- length(org_list$Twitter)
cuentas_total_org <- length(twitter$following)
results <- data.frame(Name = org_name,
AKA = org_aka,
Cuentas_db = cuentas_db_org,
Total = cuentas_total_org)
results
}
# apply function to list of files and unlist the result
psa <- sapply(archivos, calcula_cuentas)
psa1 <- t(as.data.frame(psa))
psa2 <- matrix(unlist(psa1), ncol = 4) %>%
as.data.frame()
colnames(psa2) <- c("Name", "AKA", "tw_int_outbound", "tw_ext_outbound")
# Save the results.
saveRDS(psa2, file = "rda/psa.RDS")
I am new to web scraping. I am trying to scrape a table with the following code. But I am unable to get it. The source of data is
https://www.investing.com/stock-screener/?sp=country::6|sector::a|industry::a|equityType::a|exchange::a%3Ceq_market_cap;1
url <- "https://www.investing.com/stock-screener/?sp=country::6|sector::a|industry::a|equityType::a|exchange::a%3Ceq_market_cap;1"
urlYAnalysis <- paste(url, sep = "")
webpage <- readLines(urlYAnalysis)
html <- htmlTreeParse(webpage, useInternalNodes = TRUE, asText = TRUE)
tableNodes <- getNodeSet(html, "//table")
Tab <- readHTMLTable(tableNodes[[1]])
I copied this apporach from the link (Web scraping of key stats in Yahoo! Finance with R) where it is applied on yahoo finance data.
In my opinion, in readHTMLTable(tableNodes[[12]]), it should be Table 12. But when I try giving tableNodes[[12]], it always gives me an error.
Error in do.call(data.frame, c(x, alis)) :
variable names are limited to 10000 bytes
Please suggest me the way to extract the table and combine the data from other tabs as well (Fundamental, Technical and Performance).
This data is returned dynamically as json. In R (behaves differently from Python requests) you get html from which you can extract a given page's results as json. A page includes all the tabs info and 50 records. From the first page you are given the total record count and therefore can calculate the total number of pages to loop over to get all results. Perhaps combine them info a final dataframe during a loop to total number of pages; where you alter the pn param of the XHR POST body to the appropriate page number for desired results in each new POST request. There are two required headers.
Probably a good idea to write a function that accepts a page number in signature and returns a given page's json as a dataframe. Apply that via a tidyverse package to handle loop and combining of results to final dataframe?
library(httr)
library(jsonlite)
library(magrittr)
library(rvest)
library(stringr)
headers = c(
'User-Agent' = 'Mozilla/5.0',
'X-Requested-With' = 'XMLHttpRequest'
)
data = list(
'country[]' = '6',
'sector' = '7,5,12,3,8,9,1,6,2,4,10,11',
'industry' = '81,56,59,41,68,67,88,51,72,47,12,8,50,2,71,9,69,45,46,13,94,102,95,58,100,101,87,31,6,38,79,30,77,28,5,60,18,26,44,35,53,48,49,55,78,7,86,10,1,34,3,11,62,16,24,20,54,33,83,29,76,37,90,85,82,22,14,17,19,43,89,96,57,84,93,27,74,97,4,73,36,42,98,65,70,40,99,39,92,75,66,63,21,25,64,61,32,91,52,23,15,80',
'equityType' = 'ORD,DRC,Preferred,Unit,ClosedEnd,REIT,ELKS,OpenEnd,Right,ParticipationShare,CapitalSecurity,PerpetualCapitalSecurity,GuaranteeCertificate,IGC,Warrant,SeniorNote,Debenture,ETF,ADR,ETC,ETN',
'exchange[]' = '109',
'exchange[]' = '127',
'exchange[]' = '51',
'exchange[]' = '108',
'pn' = '1', # this is page number and should be altered in a loop over all pages. 50 results per page i.e. rows
'order[col]' = 'eq_market_cap',
'order[dir]' = 'd'
)
r <- httr::POST(url = 'https://www.investing.com/stock-screener/Service/SearchStocks', httr::add_headers(.headers=headers), body = data)
s <- r %>%read_html()%>%html_node('p')%>% html_text()
page1_data <- jsonlite::fromJSON(str_match(s, '(\\[.*\\])' )[1,2])
total_rows <- str_match(s, '"totalCount\":(\\d+),' )[1,2]%>%as.integer()
num_pages <- ceiling(total_rows/50)
My current attempt at combining which I would welcome feedback on. This is all the returned columns, for all pages, and I have to handle missing columns and different ordering of columns as well as 1 column being a data.frame. As the returned number is far greater than those visible on page, you could simply revise to subset returned columns with a mask just for the columns present in the tabs.
library(httr)
library(jsonlite)
library(magrittr)
library(rvest)
library(stringr)
library(tidyverse)
library(data.table)
headers = c(
'User-Agent' = 'Mozilla/5.0',
'X-Requested-With' = 'XMLHttpRequest'
)
data = list(
'country[]' = '6',
'sector' = '7,5,12,3,8,9,1,6,2,4,10,11',
'industry' = '81,56,59,41,68,67,88,51,72,47,12,8,50,2,71,9,69,45,46,13,94,102,95,58,100,101,87,31,6,38,79,30,77,28,5,60,18,26,44,35,53,48,49,55,78,7,86,10,1,34,3,11,62,16,24,20,54,33,83,29,76,37,90,85,82,22,14,17,19,43,89,96,57,84,93,27,74,97,4,73,36,42,98,65,70,40,99,39,92,75,66,63,21,25,64,61,32,91,52,23,15,80',
'equityType' = 'ORD,DRC,Preferred,Unit,ClosedEnd,REIT,ELKS,OpenEnd,Right,ParticipationShare,CapitalSecurity,PerpetualCapitalSecurity,GuaranteeCertificate,IGC,Warrant,SeniorNote,Debenture,ETF,ADR,ETC,ETN',
'exchange[]' = '109',
'exchange[]' = '127',
'exchange[]' = '51',
'exchange[]' = '108',
'pn' = '1', # this is page number and should be altered in a loop over all pages. 50 results per page i.e. rows
'order[col]' = 'eq_market_cap',
'order[dir]' = 'd'
)
get_data <- function(page_number){
data['pn'] = page_number
r <- httr::POST(url = 'https://www.investing.com/stock-screener/Service/SearchStocks', httr::add_headers(.headers=headers), body = data)
s <- r %>% read_html() %>% html_node('p') %>% html_text()
if(page_number==1){ return(s) }
else{return(data.frame(jsonlite::fromJSON(str_match(s, '(\\[.*\\])' )[1,2])))}
}
clean_df <- function(df){
interim <- df['viewData']
df_minus <- subset(df, select = -c(viewData))
df_clean <- cbind.data.frame(c(interim, df_minus))
return(df_clean)
}
initial_data <- get_data(1)
df <- clean_df(data.frame(jsonlite::fromJSON(str_match(initial_data, '(\\[.*\\])' )[1,2])))
total_rows <- str_match(initial_data, '"totalCount\":(\\d+),' )[1,2] %>% as.integer()
num_pages <- ceiling(total_rows/50)
dfs <- map(.x = 2:num_pages,
.f = ~clean_df(get_data(.)))
r <- rbindlist(c(list(df),dfs),use.names=TRUE, fill=TRUE)
write_csv(r, 'data.csv')