R语言操作XML文件实例分析

install.packages("XML")

<RECORDS>
   <EMPLOYEE>
      <ID>1</ID>
      <NAME>Rick</NAME>
      <SALARY>623.3</SALARY>
      <STARTDATE>1/1/2012</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>
	
   <EMPLOYEE>
      <ID>2</ID>
      <NAME>Dan</NAME>
      <SALARY>515.2</SALARY>
      <STARTDATE>9/23/2013</STARTDATE>
      <DEPT>Operations</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>3</ID>
      <NAME>Michelle</NAME>
      <SALARY>611</SALARY>
      <STARTDATE>11/15/2014</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>4</ID>
      <NAME>Ryan</NAME>
      <SALARY>729</SALARY>
      <STARTDATE>5/11/2014</STARTDATE>
      <DEPT>HR</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>5</ID>
      <NAME>Gary</NAME>
      <SALARY>843.25</SALARY>
      <STARTDATE>3/27/2015</STARTDATE>
      <DEPT>Finance</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>6</ID>
      <NAME>Nina</NAME>
      <SALARY>578</SALARY>
      <STARTDATE>5/21/2013</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>7</ID>
      <NAME>Simon</NAME>
      <SALARY>632.8</SALARY>
      <STARTDATE>7/30/2013</STARTDATE>
      <DEPT>Operations</DEPT>
   </EMPLOYEE>
   
   <EMPLOYEE>
      <ID>8</ID>
      <NAME>Guru</NAME>
      <SALARY>722.5</SALARY>
      <STARTDATE>6/17/2014</STARTDATE>
      <DEPT>Finance</DEPT>
   </EMPLOYEE>
	
</RECORDS>

# Load the package required to read XML files.
library("XML")

# Also load the other required package.
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Print the result.
print(result)

    1
    Rick
    623.3
    1/1/2012
    IT
  
  
    2
    Dan
    515.2
    9/23/2013
    Operations
  
  
    3
    Michelle
    611
    11/15/2014
    IT
  
  
    4
    Ryan
    729
    5/11/2014
    HR
  
  
    5
    Gary
    843.25
    3/27/2015
    Finance
  
  
    6
    Nina
    578
    5/21/2013
    IT
  
  
    7
    Simon
    632.8
    7/30/2013
    Operations
  
  
    8
    Guru
    722.5
    6/17/2014
    Finance

# Load the packages required to read XML files.
library("XML")
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Exract the root node fORM the xml file.
rootnode <- xmlRoot(result)

# Find number of nodes in the root.
rootsize <- xmlSize(rootnode)

# Print the result.
print(rootsize)

output
[1] 8

# Load the packages required to read XML files.
library("XML")
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Exract the root node form the xml file.
rootnode <- xmlRoot(result)

# Print the result.
print(rootnode[1])

$EMPLOYEE
  1
  Rick
  623.3
  1/1/2012
  IT
 

attr(,"class")
[1] "XMLInternalNodeList" "XMLNodeList" 

# Load the packages required to read XML files.
library("XML")
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Exract the root node form the xml file.
rootnode <- xmlRoot(result)

# Get the first element of the first node.
print(rootnode[[1]][[1]])

# Get the fifth element of the first node.
print(rootnode[[1]][[5]])

# Get the second element of the third node.
print(rootnode[[3]][[2]])

1 
IT 
Michelle 

# Load the packages required to read XML files.
library("XML")
library("methods")

# Convert the input xml file to a data frame.
xmldataframe <- xmlToDataFrame("input.xml")
print(xmldataframe)

      ID    NAME     SALARY    STARTDATE       DEPT 
1      1    Rick     623.30    2012-01-01      IT
2      2    Dan      515.20    2013-09-23      Operations
3      3    Michelle 611.00    2014-11-15      IT
4      4    Ryan     729.00    2014-05-11      HR
5     NA    Gary     843.25    2015-03-27      Finance
6      6    Nina     578.00    2013-05-21      IT
7      7    Simon    632.80    2013-07-30      Operations
8      8    Guru     722.50    2014-06-17      Finance