Created
December 6, 2012 14:42
-
-
Save yanping/4224906 to your computer and use it in GitHub Desktop.
获取上海期货交易所数据
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 获取上海期货交易所数据 | |
# 接口举例 http://www.shfe.com.cn/dailydata/kx/kx20121206.html | |
require(XML) | |
require(stringr) | |
shfeDatabase <- NULL | |
for (date in dates) { | |
str <- "http://www.shfe.com.cn/dailydata/kx/kx" | |
url <- paste(str, date, ".html", sep = "") | |
if(!url.exists(url)){ | |
next | |
}else{ | |
text <- htmlParse(url, encoding = "gb2312") | |
node <- getNodeSet(text, "//table[@id='tableInstrument']//td[@class='a1']") | |
data <- sapply(node, xmlValue) | |
data <- iconv(data, "UTF-8", "UTF-8") | |
data <- str_trim(data) | |
m <- matrix(data, nc = 13, byrow = T) | |
m <- data.frame(m) | |
if (nrow(m) == 1) { | |
next | |
} else{ | |
m <- cbind(m, date) | |
colnames(m) <- c("品种", "交割月", "前结算", "今开盘", "最高价", "最低价", "收盘价", "结算价", "涨跌1", "涨跌2", "成交手", "持仓手", "变化", "date") | |
m <- m[(m[, 2] != "小计") & (m[, 1] != "总计"), ] | |
for (i in 2:nrow(m)) { | |
if (m[i, 1] == "") | |
m[i, 1] <- m[i - 1, 1] | |
} | |
m[m == ""] <- NA | |
fileName <- paste("shfe", date, ".csv", sep = "") | |
if(!file.exists(fileName)){ | |
write.csv(m, fileName, row.names = FALSE) | |
} | |
shfeData <- read.csv(fileName) | |
if (is.null(shfeDatabase)) { | |
shfeDatabase <- shfeData | |
} else { | |
shfeDatabase <- rbind(shfeDatabase, shfeData) | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
但是网页的格式也一直在变,不能保证每天的数据都能扒下来