从URL获取html文件
library("httr")
library("XML")
URL <- "https://www.fantasypros.com/nfl/rankings/consensus-cheatsheets.php"
temp <- tempfile(fileext = ".html")
GET(url = URL, user_agent("Mozilla/5.0"), write_disk(temp))
解析 HTML 文件
doc <- htmlParse(temp)
XPath 查询是通过选择table
元素与class = "player-table"
和它的孩子tr
元素具有class = 'mpb-player-'
xpexpr <- "//table[contains(@class, 'player-table')]/tbody/tr[contains(@class, 'mpb-player-')]"
从 doc 获取 xpath 表达式的节点列表
listofTableNodes <- getNodeSet(doc, xpexpr)
listofTableNodes
使用节点列表的 xmlvalues 创建一个数据框
df <- xmlToDataFrame(listofTableNodes, stringsAsFactors = FALSE)
# alternatively xpathSApply can be used to get the same data frame
# df <- xmlToDataFrame(xpathSApply(doc, xpexpr), stringsAsFactors = FALSE)
删除空列
df <- df[, seq(1, length(df), by = 2)]
添加列名称
xpexpr <- "//table[contains(@class, 'player-table')]/thead/tr/th"
listofTableNodes <- getNodeSet(doc, xpexpr)
listofTableNodes
colnames(df) <- gsub("[\r\n ]*$", '', xmlSApply(listofTableNodes, xmlValue))
head(df)
# Rank Player (Team) Pos Bye Best Worst Avg Std Dev ADP vs. ADP
# 1 1 Antonio Brown PIT WR1 8 1 5 1.3 0.8 1.0 0.0
# 2 2 Odell Beckham Jr. NYG WR2 8 1 9 3.1 1.6 2.0 0.0
# 3 3 Julio Jones ATL WR3 11 1 6 3.4 1.1 4.0 +1.0
# 4 4 Todd Gurley LA RB1 8 1 11 4.5 2.3 3.0 -1.0
# 5 5 David Johnson ARI RB2 9 1 19 6.1 3.5 6.0 +1.0
# 6 6 Adrian Peterson MIN RB3 6 1 22 7.6 3.8 5.0 -1.0