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：

[plain] view plain copy

1. 1> Xml="<?xml version='1.0' encoding='utf-8'?><root>123</root>".  
2. "<?xml version='1.0' encoding='utf-8'?><root>123</root>"  
3. 2> {Doc,_}=xmerl_scan:string(Xml).  
4. {{xmlElement,root,root,[],  
5.              {xmlNamespace,[],[]},  
6.              [],1,[],  
7.              [{xmlText,[{root,1}],1,[],"123",text}],  
8.              [],"/mnt/hgfs/work/myErlangWork/myErlang1/src",undeclared},  
9.  []}  
10. 3> xmerl_xpath:string("/root",Doc).          
11. [{xmlElement,root,root,[],  
12.              {xmlNamespace,[],[]},  
13.              [],1,[],  
14.              [{xmlText,[{root,1}],1,[],"123",text}],  
15.              [],"/mnt/hgfs/work/myErlangWork/myErlang1/src",undeclared}]  
16. 4> xmerl_xpath:string("/root/text()",Doc).  
17. [{xmlText,[{root,1}],1,[],"123",text}]  

举例：解析购物清单

shopping.xml

[plain] view plain copy

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

xml_test.erl 

[plain] view plain copy

1. -module(xml_test).  
2. -include_lib("xmerl/include/xmerl.hrl").  
3. -export([  
4.     test_xml/0,  
5.     test_xml_file/0  
6.         ]).  
7.   
8. %%读取xml列表为xmlElement，然后解析数据  
9. test_xml() ->  
10.     Xml = "<shopping>  
11.                   <item name=\"bread\" quantity=\"3\" price=\"2.50\">bread</item>  
12.                   <item name=\"milk\" quantity=\"2\" price=\"3.50\">milk</item>  
13.                 </shopping>",  
14.     {XmlDoc,_} = xmerl_scan:string(Xml),  
15.     get_total(XmlDoc),  
16.     get_item_text(XmlDoc).  
17.   
18. %%Parse file containing an XML document，然后解析数据  
19. test_xml_file() ->  
20.     {Doc,_} = xmerl_scan:file("shopping.xml",[{encoding,'utf-8'}]),  
21.     get_total(Doc),  
22.     get_item_text(Doc).  
23.   
24. %%计算得到购物清单的总金额  
25. get_total(XmlDoc) ->  
26.     Items = xmerl_xpath:string("/shopping/item",XmlDoc),  
27.     TotalPrice = lists:foldl(fun(Item,Total)->  
28.                                      [#xmlAttribute{value=PriceString}] = xmerl_xpath:string("/item/@price",Item),  
29.                                      [#xmlAttribute{value=QuantityString}] = xmerl_xpath:string("/item/@quantity",Item),  
30.                                      Price = list_to_float(PriceString),  
31.                                      Quantity = list_to_integer(QuantityString),  
32.                                      Total + Price * Quantity  
33.                              end,  
34.                              0,Items),  
35.     io:format("Price of shopping is $~.2f~n",[TotalPrice]),  
36.     TotalPrice.  
37.   
38. %%获取购物清单上所有商品内容的列表，取item节点的text  
39. get_item_text(XmlDoc) ->  
40.     Items = xmerl_xpath:string("/shopping/item",XmlDoc),  
41.     ItemList = lists:foldl(fun(Item,Result)->  
42.                                    [#xmlText{value=Value}] = xmerl_xpath:string("/item/text()",Item),  
43.                                    io:format("item is ~p~n",[Value]),  
44.                                    Result ++ [Value]        %% 结果是["bread","milk"]  
45.                                    %% 此句如果改为Result ++ Value 结果就变成了"breadmilk"  
46.                            end,  
47.                            [],Items),  
48.     io:format("ItemList is ~p~n",[ItemList]),  
49.     ItemList.  

执行：

[plain] view plain copy

1. 1> c(xml_test).          
2. {ok,xml_test}  
3. 2> xml_test:test_xml().  
4. Price of shopping is $14.50  
5. item is "bread"  
6. item is "milk"  
7. ItemList is ["bread","milk"]  
8. ["bread","milk"]  
9. 3> xml_test:test_xml_file().  
10. Price of shopping is $14.50  
11. item is "bread"  
12. item is "milk"  
13. ItemList is ["bread","milk"]  
14. ["bread","milk"]