Erlang的Xml解析

Erlang的Xml解析常用函数：

xmerl_scan库：

string(Text::list()) -> {xmlElement(),Rest} Parse string containing an XML document,将字符串列表，解析成XML树

file(Filename::string()) -> {xmlElement(),Rest} Parse file containing an XML document

xmerl_xpath库：

string(Str,Doc) -> [docEntity()] | Scalar 根据XPath，从已经解析好的XML树中提取出节点

基础练习：

1> Xml="<?xml version='1.0' encoding='utf-8'?><root>123</root>".
"<?xml version='1.0' encoding='utf-8'?><root>123</root>"
2> {Doc,_}=xmerl_scan:string(Xml).
{{xmlElement,root,[],{xmlNamespace,[]},1,[{xmlText,[{root,1}],"123",text}],"/mnt/hgfs/work/myErlangWork/myErlang1/src",undeclared},[]}
3> xmerl_xpath:string("/root",Doc).        
[{xmlElement,undeclared}]
4> xmerl_xpath:string("/root/text()",Doc).
[{xmlText,text}]

举例：解析购物清单

shopping.xml

<?xml version="1.0" encoding="UTF-8"?>
<shopping>
    <item name="bread" quantity="3" price="2.50">bread</item>
    <item name="milk" quantity="2" price="3.50">milk</item>
</shopping>

xml_test.erl

-module(xml_test).
-include_lib("xmerl/include/xmerl.hrl").
-export([
    test_xml/0,test_xml_file/0
        ]).

%%读取xml列表为xmlElement，然后解析数据
test_xml() ->
    Xml = "<shopping>
                  <item name=\"bread\" quantity=\"3\" price=\"2.50\">bread</item>
                  <item name=\"milk\" quantity=\"2\" price=\"3.50\">milk</item>
                </shopping>",{XmlDoc,_} = xmerl_scan:string(Xml),get_total(XmlDoc),get_item_text(XmlDoc).

%%Parse file containing an XML document，然后解析数据
test_xml_file() ->
    {Doc,_} = xmerl_scan:file("shopping.xml",[{encoding,'utf-8'}]),get_total(Doc),get_item_text(Doc).

%%计算得到购物清单的总金额
get_total(XmlDoc) ->
    Items = xmerl_xpath:string("/shopping/item",XmlDoc),TotalPrice = lists:foldl(fun(Item,Total)->
                                     [#xmlAttribute{value=PriceString}] = xmerl_xpath:string("/item/@price",Item),[#xmlAttribute{value=QuantityString}] = xmerl_xpath:string("/item/@quantity",Price = list_to_float(PriceString),Quantity = list_to_integer(QuantityString),Total + Price * Quantity
                             end,Items),io:format("Price of shopping is $~.2f~n",[TotalPrice]),TotalPrice.

%%获取购物清单上所有商品内容的列表，取item节点的text
get_item_text(XmlDoc) ->
    Items = xmerl_xpath:string("/shopping/item",ItemList = lists:foldl(fun(Item,Result)->
                                   [#xmlText{value=Value}] = xmerl_xpath:string("/item/text()",io:format("item is ~p~n",[Value]),Result ++ [Value]        %% 结果是["bread","milk"]
                                   %% 此句如果改为Result ++ Value 结果就变成了"breadmilk"
                           end,io:format("ItemList is ~p~n",[ItemList]),ItemList.

执行：

1> c(xml_test).        
{ok,xml_test}
2> xml_test:test_xml().
Price of shopping is $14.50
item is "bread"
item is "milk"
ItemList is ["bread","milk"]
["bread","milk"]
3> xml_test:test_xml_file().
Price of shopping is $14.50
item is "bread"
item is "milk"
ItemList is ["bread","milk"]