Repository: sewardlee337/finreportr Branch: master Commit: 81b7cc2f2a12 Files: 28 Total size: 39.6 KB Directory structure: gitextract_ethd7a8s/ ├── .Rbuildignore ├── .gitignore ├── .travis.yml ├── DESCRIPTION ├── LICENSE ├── NAMESPACE ├── R/ │ ├── annual_reports.R │ ├── backend_utilities.R │ ├── company_info.R │ ├── data.R │ ├── get_balance_sheet.R │ ├── get_cash_flow.R │ ├── get_financial.R │ └── get_income.R ├── README.md ├── data/ │ ├── siccodes.rda │ └── statecodes.rda ├── finreportr.Rproj ├── man/ │ ├── AnnualReports.Rd │ ├── CompanyInfo.Rd │ ├── GetBalanceSheet.Rd │ ├── GetCashFlow.Rd │ ├── GetIncome.Rd │ ├── siccodes.Rd │ └── statecodes.Rd ├── tests/ │ ├── testthat/ │ │ └── test.R │ └── testthat.R └── vignettes/ └── finreportr.Rmd ================================================ FILE CONTENTS ================================================ ================================================ FILE: .Rbuildignore ================================================ ^.*\.Rproj$ ^\.Rproj\.user$ ^\.travis\.yml$ ^cran-comments\.md$ ^CRAN-RELEASE$ ================================================ FILE: .gitignore ================================================ inst/doc .Rproj.user .Rhistory cran-comments.md ================================================ FILE: .travis.yml ================================================ # Sample .travis.yml for R projects language: r warnings_are_errors: true sudo: required ================================================ FILE: DESCRIPTION ================================================ Package: finreportr Type: Package Title: Financial Data from U.S. Securities and Exchange Commission Version: 1.0.4 Date: 2022-01-16 Author: Seward Lee Maintainer: Seward Lee Description: Download and display company financial data from the U.S. Securities and Exchange Commission's EDGAR database. It contains a suite of functions with web scraping and XBRL parsing capabilities that allows users to extract data from EDGAR in an automated and scalable manner. See for more information. Depends: R (>= 2.10) Imports: xml2, dplyr, httr, rvest, XBRL, curl License: MIT + file LICENSE LazyData: true URL: https://github.com/sewardlee337/finreportr BugReports: https://github.com/sewardlee337/finreportr/issues RoxygenNote: 7.1.0 Suggests: knitr, rmarkdown, testthat VignetteBuilder: knitr ================================================ FILE: LICENSE ================================================ YEAR: 2021 COPYRIGHT HOLDER: Seward Lee ================================================ FILE: NAMESPACE ================================================ # Generated by roxygen2: do not edit by hand export(AnnualReports) export(CompanyInfo) export(GetBalanceSheet) export(GetCashFlow) export(GetIncome) import(curl) import(dplyr) ================================================ FILE: R/annual_reports.R ================================================ #' Acquire listing of company annual reports. #' #' Extracts and displays listing of annual reports filed by a company in a data frame. #' #' @export #' @import dplyr #' @param symbol A character vector specifying the stock symbol of the company of interest. #' @param foreign A logical vector indicating whether the company is domestic or foreign. \code{foreign = FALSE} by default. #' @examples #' \dontrun{ #' AnnualReports("TSLA") #' AnnualReports("BABA", foreign = TRUE) #' } AnnualReports <- function(symbol, foreign = FALSE) { options(stringsAsFactors = FALSE) if(foreign == FALSE) { url <- paste0("http://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=", symbol, "&type=10-k&dateb=&owner=exclude&count=100") } else { url <- paste0("http://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=", symbol, "&type=20-f&dateb=&owner=exclude&count=100") } filings <- xml2::read_html(url) ## Generic function to extract info ExtractInfo <- function(html.node) { info <- filings %>% rvest::html_nodes(html.node) %>% rvest::html_text() return(info) } ## Acquire filing name filing.name <- ExtractInfo("#seriesDiv td:nth-child(1)") ## Error message for function if(length(filing.name) == 0) { stop("invalid company symbol or foreign logical") } ## Acquire filing date filing.date <- ExtractInfo(".small+ td") ## Acquire accession number accession.no.raw <- ExtractInfo(".small") accession.no <- gsub("^.*Acc-no: ", "", accession.no.raw) %>% substr(1, 20) ## Create dataframe info.df <- data.frame(filing.name = filing.name, filing.date = filing.date, accession.no = accession.no) return(info.df) } ================================================ FILE: R/backend_utilities.R ================================================ #' @import dplyr ################################################################################ ##### Backend Utility: Extract Accession No ##### ################################################################################ GetAccessionNo <- function(symbol, year, foreign = FALSE) { ## This is here to please R CMD check filing.year <- NULL filing.name <- NULL accession.no <- NULL year.char <- as.character(year) reports.df <- AnnualReports(symbol, foreign) reports.df <- mutate(reports.df, filing.year = substr(reports.df$filing.date,1,4) ) %>% filter(filing.year == year.char) %>% filter(filing.name == "10-K" | filing.name == "20-F") accession.no.raw <- select(reports.df, accession.no) %>% as.character() ## Error message for function if(accession.no.raw == "character(0)") { stop("no filings available for given year") } return(accession.no.raw) } ################################################################################ ##### Backend Utility: Extract Period of Report ##### ################################################################################ ReportPeriod <- function(symbol, CIK, accession.no, accession.no.raw) { url <- paste0("https://www.sec.gov/Archives/edgar/data/", CIK, "/", accession.no, "/", accession.no.raw, "-index.htm") search.result <- xml2::read_html(url) ## Generic function to extract info ExtractInfo <- function(html.node) { info <- search.result %>% rvest::html_nodes(html.node) %>% rvest::html_text() return(info) } report.period <- ExtractInfo(".formGrouping+ .formGrouping .info:nth-child(2)") return(report.period) } ================================================ FILE: R/company_info.R ================================================ #' Acquire basic company information. #' #' Extracts and displays basic information relating to a given company in a data frame. #' #' @export #' @import dplyr #' @param symbol A character vector specifying the stock symbol of the company of interest. #' @examples #' \dontrun{ #' CompanyInfo("GOOG") #' CompanyInfo("TSLA") #' } CompanyInfo <- function(symbol) { options(stringsAsFactors = FALSE) url <- paste0("https://www.sec.gov/cgi-bin/browse-edgar?CIK=", symbol, "&owner=exclude&action=getcompany&Find=Search") search.result <- xml2::read_html(url) ## Generic function to extract info ExtractInfo <- function(html.node) { info <- search.result %>% rvest::html_nodes(html.node) %>% rvest::html_text() return(info) } ## Acquire company name string company.name.raw <- ExtractInfo(".companyName") %>% strsplit(" CIK") ## Error message for function if(length(company.name.raw) == 0) { stop("invalid company symbol") } ## Parse company name string company.name <- company.name.raw[[1]][1] ## Acquire CIK number CIK.raw <- ExtractInfo(".companyName a") %>% strsplit(" ") CIK <- CIK.raw[[1]][1] ## Acquire SIC code SIC <- ExtractInfo(".identInfo acronym+ a") ## Acquire street address street.address <- ExtractInfo(".mailer:nth-child(1) .mailerAddress:nth-child(1)") ## Acquire city, state, ZIP city.state.raw <- ExtractInfo(".mailer:nth-child(1) .mailerAddress+ .mailerAddress") city.state <- sub("\\s+$", "", city.state.raw) city.state <- gsub("\n", "", city.state) ## Fix problems associated with multiple street address lines if(length(city.state) == 2){ street.address <- paste(street.address, city.state[1]) city.state <- city.state[2] } ## Acquire fiscal year end company.details <- ExtractInfo(".identInfo") fiscal.year.end <- gsub("^.*Fiscal Year End: ", "", company.details) %>% substr(1,4) if(fiscal.year.end == "SIC:"){fiscal.year.end <- NA} ## Fix in case no fiscal year displayed ## Acquire state location state <- gsub("^.*State location: ", "", company.details) %>% substr(1,2) ## Acquire state of incorporation state.inc <- gsub("^.*State of Inc.: ", "", company.details) %>% substr(1,2) if(state.inc == "SI"){state.inc <- NA} ## Fix in case no incorporation year displayed ## Create dataframe info.df <- data.frame(company = company.name, CIK = CIK, SIC = SIC, state = state, state.inc = state.inc, FY.end = fiscal.year.end, street.address = street.address, city.state = city.state) return(info.df) } ================================================ FILE: R/data.R ================================================ #' Standard Industrial Classification Code List #' #' A dataset containing SIC codes and industries that they represent #' #' @format A data frame with 444 rows and 2 variables: #' \itemize{ #' \item SIC: Standard Industrial Classification Code #' \item industry: Industry Title #' } #' #' @source \url{https://www.sec.gov/info/edgar/siccodes.htm} "siccodes" #' EDGAR State and Country Codes #' #' A dataset containing state and country codes used in the SEC EDGAR database. #' #' @format A data frame with 310 rows and 2 variables: #' \itemize{ #' \item state: State or Country Code #' \item state.name: State or Country Name #' } #' #' @source \url{https://www.sec.gov/edgar/searchedgar/edgarstatecodes.htm} "statecodes" ================================================ FILE: R/get_balance_sheet.R ================================================ #' Acquire balance sheet. #' #' Extracts and displays balance sheet from the annual report of a given company. #' This functionality is only available for queries fo balance sheets that belong to domestic companies. #' Note that all data returned by this function comes from the company's Form 10-K, not Form 10-K/A. #' #' @export #' @param symbol A character vector specifying the stock symbol of the company of interest. #' @param year A numeric vector specifying the year during which the annual report was filed. #' @examples #' \dontrun{ #' GetBalanceSheet("FB", 2016) #' } GetBalanceSheet <- function(symbol, year) { balance.sheet.descriptions <- c("CONSOLIDATED BALANCE SHEET", "CONSOLIDATED BALANCE SHEETS", "CONSOLIDATED STATEMENT OF FINANCIAL POSITION", "CONSOLIDATED STATEMENTS OF FINANCIAL POSITION", "BALANCE SHEETS", "CONSOLIDATED FINANCIAL POSITION") GetFinancial(balance.sheet.descriptions, symbol, year) } ================================================ FILE: R/get_cash_flow.R ================================================ #' Acquire statement of cash flow. #' #' Extracts and displays statement of cash flow from the annual report of a given company. #' This functionality is only available for queries of cash flow statements that belong to domestic company. #' Note that all data returned by this function comes from the company's Form 10-K, not Form 10-K/A. #' #' @export #' @param symbol A character vector specifying the stock symbol of the company of interest. #' @param year A numeric vector specifying the year during which the annual report was filed. #' @examples #' \dontrun{ #' GetCashFlow("FB", 2016) #' } GetCashFlow <- function(symbol, year) { cash.flow.descriptions <- c("CONSOLIDATED STATEMENT OF CASH FLOWS", "CONSOLIDATED STATEMENTS OF CASH FLOWS", "CASH FLOWS STATEMENTS", "CONSOLIDATED STATEMENT OF CASH FLOW") GetFinancial(cash.flow.descriptions, symbol, year) } ================================================ FILE: R/get_financial.R ================================================ #' @import dplyr curl GetFinancial <- function(statement.type, symbol, year) { ## This is here to please R CMD check description <- NULL roleId <- NULL labelRole <- NULL labelString <- NULL unitId <- NULL fact <- NULL contextId <- NULL startDate <- NULL endDate <- NULL ## Function to acquire Instance Document URL GetURL <- function(symbol, year) { lower.symbol <- tolower(symbol) accession.no.raw <- GetAccessionNo(symbol, year, foreign = FALSE) accession.no <- gsub("-", "" , accession.no.raw) CIK <- CompanyInfo(symbol) CIK <- as.numeric(CIK$CIK) report.period <- ReportPeriod(symbol, CIK, accession.no, accession.no.raw) report.period <- gsub("-", "" , report.period) inst.url <- paste0("https://www.sec.gov/Archives/edgar/data/", CIK, "/", accession.no, "/", lower.symbol, "-", report.period, ".xml") return(inst.url) } ## Function to download Instance Document GetInstFile <- function(url) { XBRL::xbrlDoAll(url, cache.dir="XBRLcache", prefix.out ="out", verbose=FALSE) } inst.url <- GetURL(symbol, year) ## Check if url exits check <- tryCatch(is.list(httr::GET(inst.url)), error = function(e) {return(FALSE)}) if(check == FALSE) { stop("no XBRL-format filings detected") } ## Download Instance Document instFile <- GetInstFile(inst.url) ## Clear Cache Dir file.remove("out_calculations.csv", "out_contexts.csv", "out_definitions.csv", "out_elements.csv", "out_facts.csv", "out_footnotes.csv", "out_labels.csv", "out_presentations.csv", "out_roles.csv", "out_units.csv") unlink("XBRLcache", recursive = TRUE) ## Get Role ID from Instance Document role.df <- instFile$role %>% filter(toupper(description) %in% statement.type) role.id <- as.character(role.df$roleId) ## Create statement template from Presentation Linkbase statement.skeleton <- instFile$presentation %>% filter(roleId == role.id) rowid <- c(1:nrow(statement.skeleton)) statement.skeleton <- mutate(statement.skeleton, rowid = rowid) ## Merge with Label Linkbase statement <- merge(statement.skeleton, instFile$label, by.x = "toElementId", by.y = "elementId") %>% filter(labelRole == "http://www.xbrl.org/2003/role/label") ## Merge with Fact Linkbase statement <- merge(statement, instFile$fact, by.x = "toElementId", by.y = "elementId") ## Merge with Context Linkbase statement <- merge(statement, instFile$context, by.x = "contextId", by.y = "contextId") %>% arrange(rowid) ## Clean combined table statement <- subset(statement, is.na(statement$dimension1)) clean.statement <- select(statement, labelString, unitId, fact, contextId, startDate, endDate, rowid) clean.statement <- select(clean.statement, -contextId) colnames(clean.statement)[1] <- "Metric" colnames(clean.statement)[2] <- "Units" colnames(clean.statement)[3] <- "Amount" clean.statement <- arrange(clean.statement, rowid) clean.statement <- select(clean.statement, -rowid) return(clean.statement) } ================================================ FILE: R/get_income.R ================================================ #' Acquire income statement. #' #' Extracts and displays income statement from the annual report of a given company. #' This functionality is only available for queries of income statements that belong to domestic companies. #' Note that all data returned by this function comes from the company's 10-K, not 10-K/A. #' #' @export #' @param symbol A character vector specifying the stock symbol of the company of interest. #' @param year A numeric vector specifying the year during which the annual report was filed. #' @examples #' \dontrun{ #' GetIncome("FB", 2016) #' } GetIncome <- function(symbol, year) { income.descriptions <- c("CONSOLIDATED STATEMENTS OF INCOME", "CONSOLIDATED STATEMENT OF INCOME", "CONSOLIDATED STATEMENTS OF OPERATIONS", "CONSOLIDATED STATEMENT OF OPERATIONS", "CONSOLIDATED STATEMENT OF EARNINGS", "CONSOLIDATED STATEMENTS OF EARNINGS", "INCOME STATEMENTS", "CONSOLIDATED RESULTS OF OPERATIONS") GetFinancial(income.descriptions, symbol, year) } ================================================ FILE: README.md ================================================ [![Travis-CI Build Status](https://travis-ci.org/sewardlee337/finreportr.svg?branch=master)](https://travis-ci.org/sewardlee337/finreportr) [![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/finreportr)](https://cran.r-project.org/package=finreportr) ![](http://cranlogs.r-pkg.org/badges/grand-total/finreportr) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.192466.svg)](https://doi.org/10.5281/zenodo.192466) [![status](http://joss.theoj.org/papers/128c974cac2dcf92b673c66f39a2c93e/status.svg)](https://joss.theoj.org/papers/10.21105/joss.00119) # finreportr - Financial Data from U.S. Securities and Exchange Commission * Author/Maintainer: [Seward Lee](https://github.com/sewardlee337) * License: [MIT](https://opensource.org/licenses/MIT) ## Introduction A financial analyst's time is valuable – it shouldn't be wasted performing manual data entry. finreportr is a web scraper written in R that allows analysts to query data from the U.S. Securities and Exchange Commission directly from the R console. It aims to eliminate time wasters from a financial analyst's workflow, such as navigating the SEC EDGAR database, flipping through financial reports, and parsing XBRL-encoded data. finreportr allows you to fetch data from the SEC and load it into your workspace using the following commands: * `CompanyInfo()`: returns basic information about a company * `AnnualReports()`: returns a listing of annual reports filed by a company * `GetIncome()`: returns the income statement for a given company * `GetBalanceSheet()`: returns the balance sheet for a given company * `GetCashFlow()`: returns the cash flow statement for a given company To install CRAN release version of finreportr: ``` install.packages("finreportr") ``` To install bleeding-edge version from GitHub: ``` devtools::install_github("sewardlee337/finreportr") ``` ## CompanyInfo() `CompanyInfo()` returns the following information about a given company based on its stock ticker symbol: * Company Name * [Central Index Key ("CIK")](https://en.wikipedia.org/wiki/Central_Index_Key) * [Standard Industrial Classification ("SIC")](https://en.wikipedia.org/wiki/Standard_Industrial_Classification) * State Location * State of Incorporation * Fiscal Year End (ddmm) * Street Address * City, State, ZIP #### Arguments: `CompanyInfo(symbol)` where * `symbol` is a character string that represents the relevant stock ticker symbol. #### Examples: ``` > CompanyInfo("GOOG") company CIK SIC state state.inc FY.end street.address city.state 1 GOOGLE INC. 0001288776 7370 CA DE 1231 1600 AMPHITHEATRE PARKWAY MOUNTAIN VIEW CA 94043 > CompanyInfo("FB") company CIK SIC state state.inc FY.end street.address city.state 1 Facebook Inc 0001326801 7370 CA DE 1231 1601 WILLOW ROAD MENLO PARK CA 94025 ``` ## AnnualReports() `AnnualReports()` returns a dataframe that summarizes a given company's annual reports based on its stock ticker symbol. Information returned include: * Filing Name * Filing Date * Accession Number `AnnualReports()` will return data relating to a company's [Form 10-Ks](https://www.investopedia.com/terms/1/10-k.asp) if the company is domestic, and [Form 20-Fs](https://www.investopedia.com/terms/s/sec-form-20-f.asp) if the company is foreign. #### Arguments: `AnnualReports(symbol, foreign = FALSE)` where * `symbol` is a character string that represents the relevant stock ticker symbol. * `foreign` is a logical indicating whether the company in question is domestic or foreign. `foreign` is set to `FALSE` by default. #### Examples: ``` > AnnualReports("GOOG") filing.name filing.date accession.no 1 10-K 2015-02-09 0001288776-15-000008 2 10-K 2014-02-12 0001288776-14-000020 3 10-K 2013-01-29 0001193125-13-028362 4 10-K/A 2012-04-23 0001193125-12-174477 5 10-K 2012-01-26 0001193125-12-025336 6 10-K 2011-02-11 0001193125-11-032930 7 10-K 2010-02-12 0001193125-10-030774 8 10-K 2009-02-13 0001193125-09-029448 9 10-K 2008-02-15 0001193125-08-032690 10 10-K 2007-03-01 0001193125-07-044494 11 10-K 2006-03-16 0001193125-06-056598 12 10-K 2005-03-30 0001193125-05-065298 > AnnualReports("HTHIY", foreign = TRUE) filing.name filing.date accession.no 1 20-F/A 2011-07-21 0001193125-11-192990 2 20-F 2011-06-24 0001193125-11-172867 3 20-F/A 2010-07-29 0001193125-10-169851 4 20-F 2010-06-29 0001193125-10-149406 5 20-F 2009-07-27 0001193125-09-155317 6 20-F 2008-06-20 0001193125-08-137042 7 20-F/A 2008-04-28 0001193125-08-091853 8 20-F/A 2007-11-30 0001193125-07-256746 9 20-F 2007-06-26 0001193125-07-142357 10 20-F 2006-08-07 0001193125-06-163031 11 20-F 2005-08-26 0001193125-05-174960 12 20-F 2004-08-20 0001193125-04-144223 13 20-F 2003-09-30 0001193125-03-056135 14 20-F 2002-09-26 0001145549-02-000252 ``` ## GetIncome() `GetIncome()` returns a company's income statement from the annual report of a given filing year as a dataframe. This functionality is only available for queries of income statements that belong to domestic companies. Note that all data returned by this function comes from the company's 10-K, not 10-K/A. #### Arguments: `GetIncome(symbol, year)` where * `symbol` is a character string that represents the relevant stock ticker symbol. * `year` is the year during which the annual report was filed. *(Note: This is not necessarily identical to the fiscal year for which the annual report was filed)* #### Example: ``` ### Fetch first 20 lines of Google's income statement in the Form 10-K published in 2016. > head(GetIncome("GOOG", 2016), 20) Metric Units Amount startDate endDate 1 Revenues usd 55519000000 2013-01-01 2013-12-31 2 Revenues usd 66001000000 2014-01-01 2014-12-31 3 Revenues usd 74989000000 2015-01-01 2015-12-31 4 Cost of Revenue usd 21993000000 2013-01-01 2013-12-31 5 Cost of Revenue usd 25691000000 2014-01-01 2014-12-31 6 Cost of Revenue usd 28164000000 2015-01-01 2015-12-31 7 Research and Development Expense usd 7137000000 2013-01-01 2013-12-31 8 Research and Development Expense usd 9832000000 2014-01-01 2014-12-31 9 Research and Development Expense usd 12282000000 2015-01-01 2015-12-31 10 Selling and Marketing Expense usd 6554000000 2013-01-01 2013-12-31 11 Selling and Marketing Expense usd 8131000000 2014-01-01 2014-12-31 12 Selling and Marketing Expense usd 9047000000 2015-01-01 2015-12-31 13 General and Administrative Expense usd 4432000000 2013-01-01 2013-12-31 14 General and Administrative Expense usd 5851000000 2014-01-01 2014-12-31 15 General and Administrative Expense usd 6136000000 2015-01-01 2015-12-31 16 Costs and Expenses usd 40116000000 2013-01-01 2013-12-31 17 Costs and Expenses usd 49505000000 2014-01-01 2014-12-31 18 Costs and Expenses usd 55629000000 2015-01-01 2015-12-31 19 Operating Income (Loss) usd 15403000000 2013-01-01 2013-12-31 20 Operating Income (Loss) usd 16496000000 2014-01-01 2014-12-31 ``` ## GetBalanceSheet() `GetBalanceSheet()` returns a company's balance sheet from the annual report of a given filing year as a dataframe. This functionality is only available for queries of balance sheets that belong to domestic companies. Note that all data returned by this function comes from the company's 10-K, not 10-K/A. #### Arguments: `GetBalanceSheet(symbol, year)` where * `symbol` is a character string that represents the relevant stock ticker symbol. * `year` is the year during which the annual report was filed. *(Note: This is not necessarily identical to the fiscal year for which the annual report was filed)* #### Example: ``` ### Fetch first 20 lines of Google's balance sheet in the Form 10-K published in 2016. > head(GetBalanceSheet("GOOG", 2016), 20) Metric Units Amount startDate endDate 1 Cash and Cash Equivalents, at Carrying Value usd 14778000000 2012-12-31 2 Cash and Cash Equivalents, at Carrying Value usd 18898000000 2013-12-31 3 Cash and Cash Equivalents, at Carrying Value usd 18347000000 2014-12-31 4 Cash and Cash Equivalents, at Carrying Value usd 16549000000 2015-12-31 5 Available-for-sale Securities, Current usd 46048000000 2014-12-31 6 Available-for-sale Securities, Current usd 56517000000 2015-12-31 7 Cash, Cash Equivalents, and Short-term Investments usd 64395000000 2014-12-31 8 Cash, Cash Equivalents, and Short-term Investments usd 73066000000 2015-12-31 9 Accounts Receivable, Net, Current usd 9383000000 2014-12-31 10 Accounts Receivable, Net, Current usd 11556000000 2015-12-31 11 Receivable Under Reverse Repurchase Agreements usd 875000000 2014-12-31 12 Receivable Under Reverse Repurchase Agreements usd 450000000 2015-12-31 13 Income Taxes Receivable, Current usd 591000000 2014-12-31 14 Income Taxes Receivable, Current usd 1903000000 2015-12-31 15 Prepaid Revenue Share Expenses And Other Assets Current usd 3412000000 2014-12-31 16 Prepaid Revenue Share Expenses And Other Assets Current usd 3139000000 2015-12-31 17 Assets, Current usd 78656000000 2014-12-31 18 Assets, Current usd 90114000000 2015-12-31 19 Prepaid Revenue Share Expenses And Other Assets Noncurrent usd 3187000000 2014-12-31 20 Prepaid Revenue Share Expenses And Other Assets Noncurrent usd 3181000000 2015-12-31 ``` ## GetCashFlow() `GetCashFlow()` returns a company's statement of cash flow from the annual report of a given filing year as a dataframe. This functionality is only available for queries of cash flow statements that belong to domestic companies. Note that all data returned by this function comes from the company's 10-K, not 10-K/A. #### Arguments: `GetCashFlow(symbol, year)` where * `symbol` is a character string that represents the relevant stock ticker symbol. * `year` is the year during which the annual report was filed. *(Note: This is not necessarily identical to the fiscal year for which the annual report was filed)* #### Example: ``` ### Fetch first 20 lines of Google's cash flow statement in the Form 10-K published in 2016. > head(GetCashFlow("GOOG", 2016), 20) Metric Units Amount startDate endDate 1 Net Income (Loss) Attributable to Parent usd 12733000000 2013-01-01 2013-12-31 2 Net Income (Loss) Attributable to Parent usd 14136000000 2014-01-01 2014-12-31 3 Net Income (Loss) Attributable to Parent usd 16348000000 2015-01-01 2015-12-31 4 Depreciation and Impairment on Disposition of Property and Equipment usd 2781000000 2013-01-01 2013-12-31 5 Depreciation and Impairment on Disposition of Property and Equipment usd 3523000000 2014-01-01 2014-12-31 6 Depreciation and Impairment on Disposition of Property and Equipment usd 4132000000 2015-01-01 2015-12-31 7 Amortization and Impairment of Intangible and Other Assets usd 1158000000 2013-01-01 2013-12-31 8 Amortization and Impairment of Intangible and Other Assets usd 1456000000 2014-01-01 2014-12-31 9 Amortization and Impairment of Intangible and Other Assets usd 931000000 2015-01-01 2015-12-31 10 Share-based Compensation usd 3343000000 2013-01-01 2013-12-31 11 Share-based Compensation usd 4279000000 2014-01-01 2014-12-31 12 Share-based Compensation usd 5203000000 2015-01-01 2015-12-31 13 Excess Tax Benefit from Share-based Compensation, Operating Activities usd 481000000 2013-01-01 2013-12-31 14 Excess Tax Benefit from Share-based Compensation, Operating Activities usd 648000000 2014-01-01 2014-12-31 15 Excess Tax Benefit from Share-based Compensation, Operating Activities usd 548000000 2015-01-01 2015-12-31 16 Deferred Income Taxes and Tax Credits usd -437000000 2013-01-01 2013-12-31 17 Deferred Income Taxes and Tax Credits usd -104000000 2014-01-01 2014-12-31 18 Deferred Income Taxes and Tax Credits usd -179000000 2015-01-01 2015-12-31 19 Gain (Loss) on Sale of Business, Including Discontinued Operations usd 700000000 2013-01-01 2013-12-31 20 Gain (Loss) on Sale of Business, Including Discontinued Operations usd 740000000 2014-01-01 2014-12-31 ``` ## Bug Reports and Feedback Please use the GitHub issue tracker for bug reports, feature request, or general discussions. ================================================ FILE: finreportr.Rproj ================================================ Version: 1.0 RestoreWorkspace: Default SaveWorkspace: Default AlwaysSaveHistory: Default EnableCodeIndexing: Yes UseSpacesForTab: Yes NumSpacesForTab: 5 Encoding: UTF-8 RnwWeave: Sweave LaTeX: pdfLaTeX BuildType: Package PackageUseDevtools: Yes PackageInstallArgs: --no-multiarch --with-keep.source PackageRoxygenize: rd,collate,namespace ================================================ FILE: man/AnnualReports.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/annual_reports.R \name{AnnualReports} \alias{AnnualReports} \title{Acquire listing of company annual reports.} \usage{ AnnualReports(symbol, foreign = FALSE) } \arguments{ \item{symbol}{A character vector specifying the stock symbol of the company of interest.} \item{foreign}{A logical vector indicating whether the company is domestic or foreign. \code{foreign = FALSE} by default.} } \description{ Extracts and displays listing of annual reports filed by a company in a data frame. } \examples{ \dontrun{ AnnualReports("TSLA") AnnualReports("BABA", foreign = TRUE) } } ================================================ FILE: man/CompanyInfo.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/company_info.R \name{CompanyInfo} \alias{CompanyInfo} \title{Acquire basic company information.} \usage{ CompanyInfo(symbol) } \arguments{ \item{symbol}{A character vector specifying the stock symbol of the company of interest.} } \description{ Extracts and displays basic information relating to a given company in a data frame. } \examples{ \dontrun{ CompanyInfo("GOOG") CompanyInfo("TSLA") } } ================================================ FILE: man/GetBalanceSheet.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/get_balance_sheet.R \name{GetBalanceSheet} \alias{GetBalanceSheet} \title{Acquire balance sheet.} \usage{ GetBalanceSheet(symbol, year) } \arguments{ \item{symbol}{A character vector specifying the stock symbol of the company of interest.} \item{year}{A numeric vector specifying the year during which the annual report was filed.} } \description{ Extracts and displays balance sheet from the annual report of a given company. This functionality is only available for queries fo balance sheets that belong to domestic companies. Note that all data returned by this function comes from the company's Form 10-K, not Form 10-K/A. } \examples{ \dontrun{ GetBalanceSheet("FB", 2016) } } ================================================ FILE: man/GetCashFlow.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/get_cash_flow.R \name{GetCashFlow} \alias{GetCashFlow} \title{Acquire statement of cash flow.} \usage{ GetCashFlow(symbol, year) } \arguments{ \item{symbol}{A character vector specifying the stock symbol of the company of interest.} \item{year}{A numeric vector specifying the year during which the annual report was filed.} } \description{ Extracts and displays statement of cash flow from the annual report of a given company. This functionality is only available for queries of cash flow statements that belong to domestic company. Note that all data returned by this function comes from the company's Form 10-K, not Form 10-K/A. } \examples{ \dontrun{ GetCashFlow("FB", 2016) } } ================================================ FILE: man/GetIncome.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/get_income.R \name{GetIncome} \alias{GetIncome} \title{Acquire income statement.} \usage{ GetIncome(symbol, year) } \arguments{ \item{symbol}{A character vector specifying the stock symbol of the company of interest.} \item{year}{A numeric vector specifying the year during which the annual report was filed.} } \description{ Extracts and displays income statement from the annual report of a given company. This functionality is only available for queries of income statements that belong to domestic companies. Note that all data returned by this function comes from the company's 10-K, not 10-K/A. } \examples{ \dontrun{ GetIncome("FB", 2016) } } ================================================ FILE: man/siccodes.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/data.R \docType{data} \name{siccodes} \alias{siccodes} \title{Standard Industrial Classification Code List} \format{ A data frame with 444 rows and 2 variables: \itemize{ \item SIC: Standard Industrial Classification Code \item industry: Industry Title } } \source{ \url{https://www.sec.gov/info/edgar/siccodes.htm} } \usage{ siccodes } \description{ A dataset containing SIC codes and industries that they represent } \keyword{datasets} ================================================ FILE: man/statecodes.Rd ================================================ % Generated by roxygen2: do not edit by hand % Please edit documentation in R/data.R \docType{data} \name{statecodes} \alias{statecodes} \title{EDGAR State and Country Codes} \format{ A data frame with 310 rows and 2 variables: \itemize{ \item state: State or Country Code \item state.name: State or Country Name } } \source{ \url{https://www.sec.gov/edgar/searchedgar/edgarstatecodes.htm} } \usage{ statecodes } \description{ A dataset containing state and country codes used in the SEC EDGAR database. } \keyword{datasets} ================================================ FILE: tests/testthat/test.R ================================================ # Test CompanyInfo() context("Data output dimensions") skip_on_cran() test_that("CompanyInfo returning correct dimensions", { expect_equal(dim(CompanyInfo("GOOG")), c(1, 8)) expect_equal(dim(CompanyInfo("TSLA")), c(1, 8)) expect_equal(dim(CompanyInfo("FB")), c(1, 8)) }) ================================================ FILE: tests/testthat.R ================================================ library(testthat) library(finreportr) test_check("finreportr") ================================================ FILE: vignettes/finreportr.Rmd ================================================ --- title: "finreportr – Querying Data from the U.S. Securities and Exchange Commission" author: "Seward Lee" date: "`r Sys.Date()`" output: rmarkdown::html_vignette vignette: > %\VignetteIndexEntry{finreportr} %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- A financial analyst's time is valuable – it shouldn't be wasted on performing manual data entry. **finreportr** is a web scraper written in R that allows analysts to query data from the U.S. Securities and Exchange Commission directly from the R console. It aims to eliminate time wasters from a financial analyst's workflow, such as navigating the SEC EDGAR database, flipping through financial reports, and parsing XBRL-encoded data. **finreportr** allows you to fetch data from the SEC and load it into your workspace using the following commands: * `CompanyInfo()`: returns basic information about a company * `AnnualReports()`: returns a listing of annual reports filed by a company * `GetIncome()`: returns the income statement for a given company * `GetBalanceSheet()`: returns the balance sheet for a given company * `GetCashFlow()`: returns the cash flow statement for a given company ## Querying Company Information **finreportr** provides two functions that allow users to acquire background information relating to publicly-listed companies. The function `CompanyInfo()` returns the following information about a company based on its stock ticker symbol: * Name * [Central Index Key ("CIK")](https://en.wikipedia.org/wiki/Central_Index_Key) * [Standard Industrial Classification ("SIC")](https://en.wikipedia.org/wiki/Standard_Industrial_Classification) * State Location * State of Incorporation * Fiscal Year End * Address For example, suppose we want to do a quick search on Google/Alphabet (symbol: `GOOG`): ``` > CompanyInfo("GOOG") company CIK SIC state state.inc FY.end street.address city.state 1 GOOGLE INC. 0001288776 7370 CA DE 1231 1600 AMPHITHEATRE PARKWAY MOUNTAIN VIEW CA 94043 ``` The function `AnnualReports()` returns a data frame that summarizes a company's annual reports based on its stock ticker symbol. It will return data relating to a company's [Form 10-Ks](https://www.investopedia.com/terms/1/10-k.asp) if the company is domestic, and [Form 20-Fs](https://www.investopedia.com/terms/s/sec-form-20-f.asp) if the company is foreign. For example, suppose we want to display the annual reports filed by Facebook (symbol: `FB`): ``` > AnnualReports("FB") filing.name filing.date accession.no 1 10-K 2016-01-28 0001326801-16-000043 2 10-K/A 2015-02-13 0001326801-15-000010 3 10-K 2015-01-29 0001326801-15-000006 4 10-K 2014-01-31 0001326801-14-000007 5 10-K 2013-02-01 0001326801-13-000003 ``` ## Querying Financial Data The main benefit of **finreportr** comes from allowing users to download and display financial data without having to manually inspect filings from the SEC EDGAR database. This creates opportunities for users to introduce automation, scalability, and reproducibility to their analysis. The function `GetIncome()` returns a company's income statement from a given filing year. Suppose we want the income statement of Tesla Motors (symbol: `TSLA`) from the annual report filed in 2015: ``` > head(GetIncome("TSLA", 2015)) Metric Units Amount startDate endDate 1 Sales Revenue Goods Net U_iso4217USD 385699000 2012-01-01 2012-12-31 2 Sales Revenue Goods Net U_iso4217USD 1997786000 2013-01-01 2013-12-31 3 Sales Revenue Goods Net U_iso4217USD 3192723000 2014-01-01 2014-12-31 4 Sales Revenue Services Net U_iso4217USD 27557000 2012-01-01 2012-12-31 5 Sales Revenue Services Net U_iso4217USD 15710000 2013-01-01 2013-12-31 6 Sales Revenue Services Net U_iso4217USD 5633000 2014-01-01 2014-12-31 ``` The function `GetBalanceSheet()` returns a company's balance sheet from a given filing year. Suppose we want the balance sheet of Apple (symbol: `AAPL`) from the annual report filed in 2012: ``` > head(GetBalanceSheet("AAPL", 2012)) Metric Units Amount startDate endDate 1 Available For Sale Securities Noncurrent iso4217_USD 55618000000 2011-09-24 2 Available For Sale Securities Noncurrent iso4217_USD 92122000000 2012-09-29 3 Property Plant And Equipment Net iso4217_USD 7777000000 2011-09-24 4 Property Plant And Equipment Net iso4217_USD 15452000000 2012-09-29 5 Goodwill iso4217_USD 896000000 2011-09-24 6 Goodwill iso4217_USD 1135000000 2012-09-29 ``` The function `GetCashFlow()` returns a company's cash flow statement from a given filing year. Suppose we want the cash flow statement of LinkedIn (symbol: `LNKD`) from the annual report filed in 2014: ``` > head(GetCashFlow("LNKD", 2014)) Metric Units Amount startDate endDate 1 Net Income (Loss) Attributable to Parent usd 11912000 2011-01-01 2011-12-31 2 Net Income (Loss) Attributable to Parent usd 21610000 2012-01-01 2012-12-31 3 Net Income (Loss) Attributable to Parent usd 26769000 2013-01-01 2013-12-31 4 Depreciation, Depletion and Amortization, Nonproduction usd 43100000 2011-01-01 2011-12-31 5 Depreciation, Depletion and Amortization, Nonproduction usd 79849000 2012-01-01 2012-12-31 6 Depreciation, Depletion and Amortization, Nonproduction usd 134516000 2013-01-01 2013-12-31 ```