Using R to Analyze Balance Sheets and Income Statements

Using R to Analyze Balance Sheets and Income Statements

You are making the common mistake of confusing 'access to Yahoo or Google data' with 'everything I see on Yahoo or Google Finance can be downloaded'.

When R functions download historical stock price data, they almost always access an interface explicitly designed for this purpose as e.g. a cgi handler providing csv files given a stock symbol and start and end date. So this easy as all we need to do is form the appropriate query, hit the webserver, fetch the csv file an dparse it.

Now balance sheet information is (as far as I know) not available in such an interface. So you will need to 'screen scrape' and parse the html directly.

It is not clear that R is the best tool for this. I am aware of some Perl modules for the purpose of getting non-time-series data off Yahoo Finance but have not used them.

importing financial statements from getFin() to data.frame or data.table?

This should give you what you want.

require(quantmod)
setwd("C:/Users/your_path_here/downloads")
stocks <- c("AXP","BA","CAT","CSCO","CVX","DD","DIS","GE","GS","HD","IBM","INTC","JNJ","JPM","KO","MCD","MMM","MRK","MSFT","NKE","PFE","PG","T","TRV","UNH","UTX","V","VZ","WMT","XOM")

# equityList <- read.csv("EquityList.csv", header = FALSE, stringsAsFactors = FALSE)
# names(equityList) <- c ("Ticker")

for (i in 1 : length(stocks)) {   
        temp<-getFinancials(stocks[i],src="google",auto.assign=FALSE)
        write.csv(temp$IS$A,paste(stocks[i],"_Income_Statement(Annual).csv",sep=""))
        write.csv(temp$BS$A,paste(stocks[i],"_Balance_Sheet(Annual).csv",sep=""))
        write.csv(temp$CF$A,paste(stocks[i],"_Cash_Flow(Annual).csv",sep=""))
        write.csv(temp$IS$A,paste(stocks[i],"_Income_Statement(Quarterly).csv",sep=""))
        write.csv(temp$BS$A,paste(stocks[i],"_Balance_Sheet(Quaterly).csv",sep=""))
        write.csv(temp$CF$A,paste(stocks[i],"_Cash_Flow(Quaterly).csv",sep=""))
}

Importing 10-year history of company financials

This will get you 10 years worth of data, where it exists.

stocks <- c("AXP", "BA", "CAT", "CSCO")

for (s in stocks) {
    names(urls) <- sprintf("http://financials.morningstar.com/ajax/exportKR2CSV.html?&t=%s", stocks)
    lst <- lapply(urls, read.csv, header = TRUE, stringsAsFactors = FALSE, skip = 2)
    lst1 <- lapply(lst, `[`, -12)
    write.csv(lst1, file = "C:/Users/your_path/Desktop/files/data.csv", row.names = FALSE, col.names = FALSE, na = "")
}

Web scraping of key stats in Yahoo! Finance with R

I gave up on Excel a long time ago. R is definitely the way to go for things like this.

library(XML)

stocks <- c("AXP","BA","CAT","CSCO")

for (s in stocks) {
      url <- paste0("http://finviz.com/quote.ashx?t=", s)
      webpage <- readLines(url)
      html <- htmlTreeParse(webpage, useInternalNodes = TRUE, asText = TRUE)
      tableNodes <- getNodeSet(html, "//table")

      # ASSIGN TO STOCK NAMED DFS
      assign(s, readHTMLTable(tableNodes[[9]], 
                header= c("data1", "data2", "data3", "data4", "data5", "data6",
                          "data7", "data8", "data9", "data10", "data11", "data12")))

      # ADD COLUMN TO IDENTIFY STOCK 
      df <- get(s)
      df['stock'] <- s
      assign(s, df)
}

# COMBINE ALL STOCK DATA 
stockdatalist <- cbind(mget(stocks))
stockdata <- do.call(rbind, stockdatalist)
# MOVE STOCK ID TO FIRST COLUMN
stockdata <- stockdata[, c(ncol(stockdata), 1:ncol(stockdata)-1)]

# SAVE TO CSV
write.table(stockdata, "C:/Users/your_path_here/Desktop/MyData.csv", sep=",", 
            row.names=FALSE, col.names=FALSE)

# REMOVE TEMP OBJECTS
rm(df, stockdatalist)

---

Related Topics