Scrape Yahoo Finance Financial Ratios

Question

I have been trying to scrap the value of the Current Ratio (as shown below) from Yahoo Finance using Beautiful Soup, but it keeps returning an empty value.

Inte

Answer 1

Maybe this is not the answer you are looking for, but R can do this very easily and very quickly. See the link below.

http://allthingsr.blogspot.com/2012/10/pull-yahoo-finance-key-statistics.html

#######################################################################
# Script to download key metrics for a set of stock tickers using the quantmod package
#######################################################################
require(quantmod)
require("plyr")
what_metrics <- yahooQF(c("Price/Sales", 
                          "P/E Ratio",
                          "Price/EPS Estimate Next Year",
                          "PEG Ratio",
                          "Dividend Yield", 
                          "Market Capitalization"))

tickers <- c("AAPL", "FB", "GOOG", "HPQ", "IBM", "MSFT", "ORCL", "SAP")
# Not all the metrics are returned by Yahoo.
metrics <- getQuote(paste(tickers, sep="", collapse=";"), what=what_metrics)

#Add tickers as the first column and remove the first column which had date stamps
metrics <- data.frame(Symbol=tickers, metrics[,2:length(metrics)]) 

#Change colnames
colnames(metrics) <- c("Symbol", "Revenue Multiple", "Earnings Multiple", 
                       "Earnings Multiple (Forward)", "Price-to-Earnings-Growth", "Div Yield", "Market Cap")

#Persist this to the csv file
write.csv(metrics, "FinancialMetrics.csv", row.names=FALSE)

#######################################################################

#######################################################################
##Alternate method to download all key stats using XML and x_path - PREFERRED WAY
#######################################################################

setwd("C:/Users/i827456/Pictures/Blog/Oct-25")
require(XML)
require(plyr)
getKeyStats_xpath <- function(symbol) {
  yahoo.URL <- "http://finance.yahoo.com/q/ks?s="
  html_text <- htmlParse(paste(yahoo.URL, symbol, sep = ""), encoding="UTF-8")

  #search for  nodes anywhere that have class 'yfnc_tablehead1'
  nodes <- getNodeSet(html_text, "/*//td[@class='yfnc_tablehead1']")

  if(length(nodes) > 0 ) {
   measures <- sapply(nodes, xmlValue)

   #Clean up the column name
   measures <- gsub(" *[0-9]*:", "", gsub(" \\(.*?\\)[0-9]*:","", measures))   

   #Remove dups
   dups <- which(duplicated(measures))
   #print(dups) 
   for(i in 1:length(dups)) 
     measures[dups[i]] = paste(measures[dups[i]], i, sep=" ")

   #use siblings function to get value
   values <- sapply(nodes, function(x)  xmlValue(getSibling(x)))

   df <- data.frame(t(values))
   colnames(df) <- measures
   return(df)
  } else {
    break
  }
}

tickers <- c("AAPL")
stats <- ldply(tickers, getKeyStats_xpath)
rownames(stats) <- tickers
write.csv(t(stats), "FinancialStats_updated.csv",row.names=TRUE)  

#######################################################################