使用 XML 包将 html 表抓取到 R 数据帧中

Question

如何使用 XML 包抓取 html 表？

以巴西足球队的维基百科页面为例。我想在 R 中阅读它并获取“巴西与 FIFA 认可球队对阵的所有比赛列表”表作为数据框。我该怎么做？

Answer 1

…或更短的尝试：

library(XML)
library(RCurl)
library(rlist)
theurl <- getURL("https://en.wikipedia.org/wiki/Brazil_national_football_team",.opts = list(ssl.verifypeer = FALSE) )
tables <- readHTMLTable(theurl)
tables <- list.clean(tables, fun = is.null, recursive = FALSE)
n.rows <- unlist(lapply(tables, function(t) dim(t)[1]))

所选表格是页面上最长的表格

tables[[which.max(n.rows)]]

Answer 2

library(RCurl)
library(XML)

# Download page using RCurl
# You may need to set proxy details, etc.,  in the call to getURL
theurl <- "http://en.wikipedia.org/wiki/Brazil_national_football_team"
webpage <- getURL(theurl)
# Process escape characters
webpage <- readLines(tc <- textConnection(webpage)); close(tc)

# Parse the html tree, ignoring errors on the page
pagetree <- htmlTreeParse(webpage, error=function(...){})

# Navigate your way through the tree. It may be possible to do this more efficiently using getNodeSet
body <- pagetree$children$html$children$body 
divbodyContent <- body$children$div$children[[1]]$children$div$children[[4]]
tables <- divbodyContent$children[names(divbodyContent)=="table"]

#In this case, the required table is the only one with class "wikitable sortable"  
tableclasses <- sapply(tables, function(x) x$attributes["class"])
thetable  <- tables[which(tableclasses=="wikitable sortable")]$table

#Get columns headers
headers <- thetable$children[[1]]$children
columnnames <- unname(sapply(headers, function(x) x$children$text$value))

# Get rows from table
content <- c()
for(i in 2:length(thetable$children))
{
   tablerow <- thetable$children[[i]]$children
   opponent <- tablerow[[1]]$children[[2]]$children$text$value
   others <- unname(sapply(tablerow[-1], function(x) x$children$text$value)) 
   content <- rbind(content, c(opponent, others))
}

# Convert to data frame
colnames(content) <- columnnames
as.data.frame(content)

编辑添加：

示例输出

                     Opponent Played Won Drawn Lost Goals for Goals against  % Won
    1               Argentina     94  36    24   34       148           150  38.3%
    2                Paraguay     72  44    17   11       160            61  61.1%
    3                 Uruguay     72  33    19   20       127            93  45.8%
    ...

Answer 3

rvest 和 xml2 是另一个用于解析 html 网页的流行包。

library(rvest)
theurl <- "http://en.wikipedia.org/wiki/Brazil_national_football_team"
file<-read_html(theurl)
tables<-html_nodes(file, "table")
table1 <- html_table(tables[4], fill = TRUE)

该语法比 xml 包更易于使用，并且对于大多数网页，该包提供了人们需要的所有选项。

Answer 4

另一种选择是使用 Xpath。

library(RCurl)
library(XML)

theurl <- "http://en.wikipedia.org/wiki/Brazil_national_football_team"
webpage <- getURL(theurl)
webpage <- readLines(tc <- textConnection(webpage)); close(tc)

pagetree <- htmlTreeParse(webpage, error=function(...){}, useInternalNodes = TRUE)

# Extract table header and contents
tablehead <- xpathSApply(pagetree, "//*/table[@class='wikitable sortable']/tr/th", xmlValue)
results <- xpathSApply(pagetree, "//*/table[@class='wikitable sortable']/tr/td", xmlValue)

# Convert character vector to dataframe
content <- as.data.frame(matrix(results, ncol = 8, byrow = TRUE))

# Clean up the results
content[,1] <- gsub(" ", "", content[,1])
tablehead <- gsub(" ", "", tablehead)
names(content) <- tablehead

产生这个结果

> head(content)
   Opponent Played Won Drawn Lost Goals for Goals against % Won
1 Argentina     94  36    24   34       148           150 38.3%
2  Paraguay     72  44    17   11       160            61 61.1%
3   Uruguay     72  33    19   20       127            93 45.8%
4     Chile     64  45    12    7       147            53 70.3%
5      Peru     39  27     9    3        83            27 69.2%
6    Mexico     36  21     6    9        69            34 58.3%