library(rvest) library(httr) library(dplyr) library(stringr)

1. Fetch data from TWSE ISIN page for listed stocks (strMode=2)

url_twse <- “https://isin.twse.com.tw/isin/C_public.jsp?strMode=2” response_twse <- GET(url_twse) content_twse <- content(response_twse, as = “text”, encoding = “Big5”)

Parse HTML table

df_raw <- html_table(read_html(content_twse), fill = TRUE)[[1]]

2. Clean and format TWSE data

colnames(df_raw) <- df_raw[1, ] df_twse_clean <- df_raw[-1, ] %>% rename(security = 1, listing_date = 3, industry = 5) %>% mutate( stock_id = str_extract(security, “¹+”), name = str_trim(str_remove(security, “²+\s*“)) ) %>% filter( !is.na(stock_id), str_length(stock_id) == 4, !str_detect(name,”ETF|基金|受益證券|存託憑證”) ) %>% select(stock_id, name, listing_date, industry)

head(df_twse_clean)

---

1. 0-9↩︎

2. 0-9↩︎