1 거래주식 업체코드

코스피(KOSPI)는 한국거래소 유가증권시장의 종합주가지수를 이른다. 코스닥(KOSDAQ)은 한국거래소(KRX)의 코스닥시장본부가 운영하는 주식시장을 통칭한다. KIND - 상장법인목록 웹사이트에서 유가증권, 코스닥별로 나눠서 검색하고 엑셀파일로 다운로드 받는다.

library(tidyverse)
library(readxl)

kospi_code <- read_excel("data/유가증권.xlsx", sheet="유가증권")
kosdaq_code <- read_excel("data/코스닥.xlsx", sheet="코스닥")

kospi_df <- kospi_code %>% 
  mutate(`구분`="코스피")

kosdaq_df <- kosdaq_code %>% 
  mutate(`구분`="코스닥")

stock_code_df <- bind_rows(kospi_df, kosdaq_df)

stock_code_df %>% 
  select(`구분`, everything()) %>% 
  mutate(`홈페이지` = paste0("<a href='", `홈페이지`, "' target='_blank'>", `홈페이지`, "</a>")) %>% 
  DT::datatable(escape = FALSE,  filter = 'top')

# stock_code_df %>% write_rds("data/stock_code_df.rds")
kospi_df %>% write_rds("data/kospi_df.rds")
kosdaq_df %>% write_rds("data/kosdaq_df.rds")

library(lubridate)
library(extrafont)
loadfonts()

stock_code_df %>% 
  mutate(`상장년` = year(`상장일`)) %>% 
  count(`구분`, `상장년`) %>% 
  ggplot(aes(x=`상장년`, y=n, color=`구분`)) +
    geom_point() +
    geom_line() +
    theme_minimal(base_family = "NanumGothic") +
    labs(x="", y="상장업체수", title="연도별 상장업체수") +
    theme(legend.position = "top")

stock_code_df %>% 
  filter(!str_detect(`결산월`, "12월")) %>% 
  group_by(`결산월`) %>% 
  summarise(`회사명` = str_c(`회사명`, collapse=", "),
            `종목코드` = str_c(`종목코드`, collapse=", "),) %>% 
  DT::datatable()

2 주식투자를 위한 기업정보

NICE 평가정보 상장코스탁분석 웹사이트에서 앞서 준비한 코스피/코스탁 업체코드를 넣어 Highlight에서 “Financial Summary” 정보를 가져온다.

library(tidyverse)
library(rvest)

# kisline_url <- "http://media.kisline.com/highlight/mainHighlight.nice?paper_stock=293940"
kisline_url <- "http://media.kisline.com/highlight/mainHighlight.nice?paper_stock=069080"

stock_dat <- kisline_url %>% 
  read_html() %>% 
  html_node(xpath = '//*[@id="summarytp1"]/table[1]') %>% 
  html_table()

stock_df <- stock_dat %>% 
  set_names(make.names(stock_dat[1,], unique = TRUE)) %>% 
  filter(row_number() != 1) 

stock_df %>% 
  DT::datatable()

3 야후 파이낸스 기업정보

• 손익계산서(income statement): https://finance.yahoo.com/quote/AAPL/financials?p=AAPL
• 대차대조표(balance sheet): https://finance.yahoo.com/quote/AAPL/balance-sheet?p=AAPL
• 현금유동성: https://finance.yahoo.com/quote/AAPL/cash-flow?p=AAPL

library(tidyverse)
library(rvest)

is_df <- "https://finance.yahoo.com/quote/AAPL/financials?p=APPL" %>% 
  read_html() %>% 
  html_table() %>% 
  map_df(bind_cols) %>% 
  as_tibble()

is_df

# A tibble: 28 x 5
   X1                    X2           X3           X4           X5         
   <chr>                 <chr>        <chr>        <chr>        <chr>      
 1 Revenue               9/29/2018    9/30/2017    9/24/2016    9/26/2015  
 2 Total Revenue         265,595,000  229,234,000  215,639,000  233,715,000
 3 Cost of Revenue       163,756,000  141,048,000  131,376,000  140,089,000
 4 Gross Profit          101,839,000  88,186,000   84,263,000   93,626,000 
 5 Operating Expenses    Operating E~ Operating E~ Operating E~ Operating ~
 6 Research Development  14,236,000   11,581,000   10,045,000   8,067,000  
 7 Selling General and ~ 16,705,000   15,261,000   14,194,000   14,329,000 
 8 Non Recurring         -            -            -            -          
 9 Others                -            -            -            -          
10 Total Operating Expe~ 194,697,000  167,890,000  155,615,000  162,485,000
# ... with 18 more rows

4 네이버 파이낸스 기업정보 ¹

• cmp_cd(종목코드) → 005930
• fin_typ(재무제표 유형) → 0: 주재무제표, 1: GAAP개별, 2: GAAP연결, 3: IFRS별도, 4:IFRS연결
• freq_typ(기간): → Y:년, Q:분기

library(janitor)

kospi_df <- read_rds("data/kospi_df.rds")

company_url <- 'http://companyinfo.stock.naver.com/v1/company/cF1001.aspx?cmp_cd=005930&fin_typ=0&freq_typ=Y'

company_dat <- company_url %>% 
  read_html() %>% 
  html_nodes(xpath='//*[@id="cTB26"]') %>% 
  html_table(fill = TRUE) %>% 
  .[[1]]

company_df <- company_dat %>% 
  clean_names() %>% 
  select(`주_요_재_무_정_보`, contains("연_간")) 
  
company_df <- company_df %>% 
  set_names(company_df[1,]) %>% 
  filter(row_number() != 1) %>% 
  gather(`연도`, `값`, -`주요재무정보`) %>% 
  mutate(`연도` = str_extract(`연도`, "[0-9]{4}")) %>% 
  mutate(`값` = parse_number(`값`))

company_df %>% 
  DT::datatable()