如何使用Libxml2从XML解析数据？ LINUX + C代码

编程问答 2022-06-11

问题描述

使用libxml2读取xml文件

我想解析XML文件中的所有数据并将其存储在结构中，以便可以在我的应用程序中的任何地方使用该数据。 我正在使用Libxml2库来解析数据，这是从xml文件中获取数据的最简单代码。

  • 操作系统-> Ubuntu LINUX
  • Lang-> C / C ++

解决方法

  • XML文件：-（用于理解的原始xml文件）

tmp.xml 

<?xml version="1.0" encoding="windows-1252"?>
<firewall-rules>
    <rule name="Telnet &amp; Secure Shell" active="0" action="1" protocol="3" interface="0" enable-process-icmp="0" enable-trusted-mac="0" enable-log="0">
        <ip-source-address type="4" address-1="0.0.0.0" address-2="0.0.0.0"/>
        <ip-source-port type="0" count="0"/>
        <ip-destination-address type="3" address-1="0.0.0.0" address-2="0.0.0.0"/>
        <ip-destination-port type="3" count="2">
            <port>22</port>
            <port>23</port>
        </ip-destination-port>
        <process-icmp>
            <destination-unreachableI>False</destination-unreachableI>
            <echo-replyI>False</echo-replyI>
            <echo-requestI>False</echo-requestI>
            <information-replyI>False</information-replyI>
            <information-requestI>False</information-requestI>
            <parameter-problemI>False</parameter-problemI>
            <redirectI>False</redirectI>
            <source-quenchI>False</source-quenchI>
            <ttl-expiredI>False</ttl-expiredI>
            <destination-unreachableO>False</destination-unreachableO>
            <echo-replyO>False</echo-replyO>
            <echo-requestO>False</echo-requestO>
            <information-replyO>False</information-replyO>
            <information-requestO>False</information-requestO>
            <parameter-problemO>False</parameter-problemO>
            <redirectO>False</redirectO>
            <source-quenchO>False</source-quenchO>
            <ttl-expiredO>False</ttl-expiredO>
        </process-icmp>
    </rule>
</firewall-rules>
  1. 您需要将libxml2库安装到系统中

sudo apt安装libxml2-dev

代码-> main.c 

#include <stdio.h>
#include <unistd.h>
#include <libxml/parser.h>
#include <unistd.h>
#include <string.h>
struct xmlRuleData{
    char rule_name[200],rule_active[5],rule_action[5],rule_protocol[5],rule_interface[5],rule_enableProcessIcmp[5],rule_enableTrustedMac[200],rule_enableLog[200];

    char ipSourceAddress_type[5],ipSourceAddress_address1[200],ipSourceAddress_address2[200];

    char ipSourcePort_type[5],ipSourcePort_count[5];

    char ipDestinationAddress_type[5],ipDestinationAddress_address1[200],ipDestinationAddress_address2[200];

    char ipDestinationPort_type[5],ipDestinationPort_count[5],ipDestinationPort_port[1024];

    char processIcmp_destinationUnreachableI[10],processIcmp_echoReplyI[10],processIcmp_echoRequestI[10],processIcmp_informationReplyI[10],processIcmp_informationRequestI[10],processIcmp_parameterProblemI[10],processIcmp_redirectI[10],processIcmp_sourceQuenchI[10],processIcmp_ttlExpiredI[10],processIcmp_destinationUnreachableO[10],processIcmp_echoReplyO[10],processIcmp_echoRequestO[10],processIcmp_informationReplyO[10],processIcmp_informationRequestO[10],processIcmp_parameterProblemO[10],processIcmp_redirectO[10],processIcmp_sourceQuenchO[10],processIcmp_ttlExpiredO[10];

}obj;

char *fileName = "/home/tmp.xml"; // path of xml file

char subAtt[19][1024]={"destination-unreachableI","echo-replyI","echo-requestI","information-replyI","information-requestI","parameter-problemI","redirectI","source-quenchI","ttl-expiredI","destination-unreachableO","echo-replyO","echo-requestO","information-replyO","information-requestO","parameter-problemO","redirectO","source-quenchO","ttl-expiredO","port"};

char ruleAttribute [8][1024]={"name","active","action","protocol","interface","enable-process-icmp","enable-trusted-mac","enable-log"};

char ipLeafAttributes[4][1024]={"type","address-1","address-2","count"};

void freeStructData(){
    bzero(obj.processIcmp_echoReplyI,sizeof(obj.processIcmp_echoReplyI ));
    bzero(obj.processIcmp_destinationUnreachableI,sizeof(obj.processIcmp_destinationUnreachableI ));
    bzero(obj.ipDestinationPort_port,sizeof(obj.ipDestinationPort_port ));
    bzero(obj.ipDestinationPort_count,sizeof(obj.ipDestinationPort_count ));
    bzero(obj.ipDestinationPort_type,sizeof(obj.ipDestinationPort_type ));
    bzero(obj.ipDestinationAddress_address2,sizeof(obj.ipDestinationAddress_address2 ));
    bzero(obj.ipDestinationAddress_address1,sizeof(obj.ipDestinationAddress_address1 ));
    bzero(obj.ipDestinationAddress_type,sizeof(obj.ipDestinationAddress_type ));
    bzero(obj.ipSourcePort_count,sizeof(obj.ipSourcePort_count ));
    bzero(obj.ipSourcePort_type,sizeof(obj.ipSourcePort_type ));
    bzero(obj.ipSourceAddress_address2,sizeof(obj.ipSourceAddress_address2 ));
    bzero(obj.ipSourceAddress_address1,sizeof(obj.ipSourceAddress_address1 ));
    bzero(obj.ipSourceAddress_type,sizeof(obj.ipSourceAddress_type ));
    bzero(obj.rule_enableLog,sizeof(obj.rule_enableLog ));
    bzero(obj.rule_enableTrustedMac,sizeof(obj.rule_enableTrustedMac ));
    bzero(obj.rule_enableProcessIcmp,sizeof(obj.rule_enableProcessIcmp ));
    bzero(obj.rule_interface,sizeof(obj.rule_interface ));
    bzero(obj.rule_protocol,sizeof(obj.rule_protocol ));
    bzero(obj.rule_action,sizeof( obj.rule_action));
    bzero(obj.rule_active,sizeof(obj.rule_active ));
    bzero(obj.rule_name,sizeof(obj.rule_name ));
    bzero( obj.processIcmp_echoRequestI,sizeof( obj.processIcmp_echoRequestI));
    bzero( obj.processIcmp_informationReplyI,sizeof( obj.processIcmp_informationReplyI));
    bzero( obj.processIcmp_informationRequestI,sizeof( obj.processIcmp_informationRequestI));
    bzero( obj.processIcmp_parameterProblemI,sizeof( obj.processIcmp_parameterProblemI));
    bzero( obj.processIcmp_redirectI,sizeof( obj.processIcmp_redirectI));
    bzero( obj.processIcmp_sourceQuenchI,sizeof( obj.processIcmp_sourceQuenchI));
    bzero( obj.processIcmp_ttlExpiredI,sizeof( obj.processIcmp_ttlExpiredI));
    bzero( obj.processIcmp_destinationUnreachableO,sizeof( obj.processIcmp_destinationUnreachableO));
    bzero( obj.processIcmp_echoReplyO,sizeof( obj.processIcmp_echoReplyO));
    bzero( obj.processIcmp_echoRequestO,sizeof( obj.processIcmp_echoRequestO));
    bzero( obj.processIcmp_informationReplyO,sizeof( obj.processIcmp_informationReplyO));
    bzero( obj.processIcmp_informationRequestO,sizeof( obj.processIcmp_informationRequestO));
    bzero( obj.processIcmp_parameterProblemO,sizeof( obj.processIcmp_parameterProblemO));
    bzero( obj.processIcmp_redirectO,sizeof( obj.processIcmp_redirectO));
    bzero( obj.processIcmp_sourceQuenchO,sizeof( obj.processIcmp_sourceQuenchO));
    bzero(obj.processIcmp_ttlExpiredO,sizeof(obj.processIcmp_ttlExpiredO ));
}


int is_leaf(xmlNode * node){
    xmlNode * child = node->children;
    while(child){
        if(child->type == XML_ELEMENT_NODE) return 0;
        child = child->next;
    }
    return 1;
}

void insertIntoStruct(xmlChar * str,xmlNode * node,char *attName){
    struct xmlRuleData *ptr = &obj;
    if ((!xmlStrcmp(node->name,(const xmlChar *)"rule"))) {
        if(strcmp(attName,"name") == 0){
            strcpy(((ptr)->rule_name),str);
        }else if(strcmp(attName,"active") == 0){
            strcpy(((ptr)->rule_active),"action") == 0){
            strcpy(((ptr)->rule_action),"protocol") == 0){
            strcpy(((ptr)->rule_protocol),"interface") == 0){
            strcpy(((ptr)->rule_interface),"enable-process-icmp") == 0){
            strcpy(((ptr)->rule_enableProcessIcmp),"enable-trusted-mac") == 0){
            strcpy(((ptr)->rule_enableTrustedMac),"enable-log") == 0){
            strcpy(((ptr)->rule_enableLog),str);
        }
    }else if ((!xmlStrcmp(node->name,(const xmlChar *)"ip-source-address"))) {
        if(strcmp(attName,"type") == 0){
            strcpy(((ptr)->ipSourceAddress_type),"address-1") == 0){
            strcpy(((ptr)->ipSourceAddress_address1),"address-2") == 0){
            strcpy(((ptr)->ipSourceAddress_address2),(const xmlChar *)"ip-source-port"))) {
        if(strcmp(attName,"type") == 0){
            strcpy(((ptr)->ipSourcePort_type),"count") == 0){
            strcpy(((ptr)->ipSourcePort_count),(const xmlChar *)"ip-destination-address"))) {
        if(strcmp(attName,"type") == 0){
            strcpy(((ptr)->ipDestinationAddress_type),"address-1") == 0){
            strcpy(((ptr)->ipDestinationAddress_address1),"address-2") == 0){
            strcpy(((ptr)->ipDestinationAddress_address2),str);
        }

    }else if ((!xmlStrcmp(node->name,(const xmlChar *)"ip-destination-port"))) {
        if(strcmp(attName,"type") == 0){
            strcpy(((ptr)->ipDestinationPort_type),"count") == 0){
            strcpy(((ptr)->ipDestinationPort_count),(const xmlChar *)"port"))) {
        strcat(((ptr)->ipDestinationPort_port),str);
        strcat(((ptr)->ipDestinationPort_port),",");
    }else if ((!xmlStrcmp(node->name,(const xmlChar *)"destination-unreachableI"))) {
        strcpy(((ptr)->processIcmp_destinationUnreachableI),str);
    }else if ((!xmlStrcmp(node->name,(const xmlChar *)"echo-replyI"))) {
        strcpy(((ptr)->processIcmp_echoReplyI),(const xmlChar *)"echo-requestI"))) {
        strcpy(((ptr)->processIcmp_echoRequestI),(const xmlChar *)"information-replyI"))) {
        strcpy(((ptr)->processIcmp_informationReplyI),(const xmlChar *)"information-requestI"))) {
        strcpy(((ptr)->processIcmp_informationRequestI),(const xmlChar *)"parameter-problemI"))) {
        strcpy(((ptr)->processIcmp_parameterProblemI),(const xmlChar *)"redirectI"))) {
        strcpy(((ptr)->processIcmp_redirectI),(const xmlChar *)"source-quenchI"))) {
        strcpy(((ptr)->processIcmp_sourceQuenchI),(const xmlChar *)"ttl-expiredI"))) {
        strcpy(((ptr)->processIcmp_ttlExpiredI),(const xmlChar *)"destination-unreachableO"))) {
        strcpy(((ptr)->processIcmp_destinationUnreachableO),(const xmlChar *)"echo-replyO"))) {
        strcpy(((ptr)->processIcmp_echoReplyO),(const xmlChar *)"echo-requestO"))) {
        strcpy(((ptr)->processIcmp_echoRequestO),(const xmlChar *)"information-replyO"))) {
        strcpy(((ptr)->processIcmp_informationReplyO),(const xmlChar *)"information-requestO"))) {
        strcpy(((ptr)->processIcmp_informationRequestO),(const xmlChar *)"parameter-problemO"))) {
        strcpy(((ptr)->processIcmp_parameterProblemO),(const xmlChar *)"redirectO"))) {
        strcpy(((ptr)->processIcmp_redirectO),(const xmlChar *)"source-quenchO"))) {
        strcpy(((ptr)->processIcmp_sourceQuenchO),(const xmlChar *)"ttl-expiredO"))) {
        strcpy(((ptr)->processIcmp_ttlExpiredO),str);
    }

    ptr = NULL;
    free(ptr);
}

void printStruct(){
    printf("\nrule_name->> %s",obj.rule_name);
    printf("\nrule_active -->> %s",obj.rule_active);
    printf("\nrule_action -->> %s",obj.rule_action);
    printf("\nrule_action -->> %s",obj.rule_action);
    printf("\nrule_protocol -->> %s",obj.rule_protocol);
    printf("\nrule_interface -->> %s",obj.rule_interface);
    printf("\nrule_enableProcessIcmp -->> %s",obj.rule_enableProcessIcmp);
    printf("\nrule_enableTrustedMac -->> %s",obj.rule_enableTrustedMac);
    printf("\nrule_enableLog -->> %s",obj.rule_enableLog);
    printf("\nipSourceAddress_type -->> %s",obj.ipSourceAddress_type);
    printf("\nipSourceAddress_address1 -->> %s",obj.ipSourceAddress_address1);
    printf("\nipSourceAddress_address2 -->> %s",obj.ipSourceAddress_address2);
    printf("\nipSourcePort_type-->> %s",obj.ipSourcePort_type);
    printf("\nipSourcePort_count-->> %s",obj.ipSourcePort_count);
    printf("\nipDestinationAddress_type-->> %s",obj.ipDestinationAddress_type);
    printf("\nipDestinationAddress_address1-->> %s",obj. ipDestinationAddress_address1);
    printf("\nipDestinationAddress_address2-->> %s",obj.ipDestinationAddress_address2);
    printf("\nipDestinationPort_type -->> %s",obj.ipDestinationPort_type);
    printf("\nipDestinationPort_count -->> %s",obj.ipDestinationPort_count);
    printf("\nipDestinationPort_port -->> %s",obj.ipDestinationPort_port);
    printf("\nprocessIcmp_destinationUnreachableI -->> %s",obj.processIcmp_destinationUnreachableI);
    printf("\nprocessIcmp_echoReplyI -->> %s",obj.processIcmp_echoReplyI);
    printf("\nprocessIcmp_echoRequestI -->> %s",obj.processIcmp_echoRequestI);
    printf("\nprocessIcmp_informationReplyI -->> %s",obj.processIcmp_informationReplyI);
    printf("\nprocessIcmp_informationRequestI-->> %s",obj.processIcmp_informationRequestI);
    printf("\nprocessIcmp_parameterProblemI -->> %s",obj.processIcmp_parameterProblemI);
    printf("\nprocessIcmp_redirectI -->> %s",obj.processIcmp_redirectI);
    printf("\nprocessIcmp_sourceQuenchI -->> %s",obj.processIcmp_sourceQuenchI);
    printf("\nprocessIcmp_ttlExpiredI -->> %s",obj.processIcmp_ttlExpiredI);
    printf("\nprocessIcmp_destinationUnreachableO -->> %s",obj.processIcmp_destinationUnreachableO);
    printf("\nprocessIcmp_echoReplyO -->> %s",obj.processIcmp_echoReplyO);
    printf("\nprocessIcmp_echoRequestO -->> %s",obj.processIcmp_echoRequestO);
    printf("\nprocessIcmp_informationReplyO-->> %s",obj.processIcmp_informationReplyO);
    printf("\nprocessIcmp_informationRequestO -->> %s",obj.processIcmp_informationRequestO);
    printf("\nprocessIcmp_parameterProblemO -->> %s",obj.processIcmp_parameterProblemO);
    printf("\nprocessIcmp_redirectO -->> %s",obj.processIcmp_redirectO);
    printf("\nprocessIcmp_sourceQuenchO -->> %s",obj.processIcmp_sourceQuenchO);
    printf("\nprocessIcmp_ttlExpiredO -->> %s",obj.processIcmp_ttlExpiredO);

}
void print_xml(xmlNode * node){
    xmlChar *uri,*tmp,*key;
    xmlNode *cur;
    xmlDocPtr doc = xmlParseFile(fileName);
    while(node){
        if(node->type == XML_ELEMENT_NODE){
            if(is_leaf(node) == 1){
                struct xmlRuleData *objPtr = &obj;
                xmlNodeGetContent(node);
                tmp = xmlGetProp(node,"firewall-rules");
                for(int j=0; j<4; j++){
                    if((xmlGetProp(node,ipLeafAttributes[j])) != NULL){
                        uri = xmlGetProp(node,ipLeafAttributes[j]);
                        insertIntoStruct(uri,node,ipLeafAttributes[j]);
                        xmlFree(tmp);
                    }
                }

                for(int i=0; i<19; i++){
                    if ((!xmlStrcmp(node->name,(const xmlChar *)subAtt[i]))) {
                        key = xmlNodeListGetString(doc,node->xmlChildrenNode,1);
                        insertIntoStruct(key,subAtt[i]);
                        xmlFree(key);
                    }
                }
            }else{
                tmp = xmlGetProp(node,"firewall-rules");
                if ((!xmlStrcmp(node->name,(const xmlChar *)"rule"))) {
                    printf("\n <Start of the rule> \n");
                    struct xmlRuleData *objPtr = &obj;
                    for(int j=0; j<8; j++){
                        uri = xmlGetProp(node,ruleAttribute[j]);
                        insertIntoStruct(uri,ruleAttribute[j]);
                        xmlFree(tmp);
                    }
                }
                if ((!xmlStrcmp(node->name,(const xmlChar *)"ip-destination-port"))) {
                    struct xmlRuleData *objPtr = &obj;
                    for(int j=0; j<4; j++){
                        if((xmlGetProp(node,ipLeafAttributes[j])) != NULL){
                            uri = xmlGetProp(node,ipLeafAttributes[j]);
                            insertIntoStruct(uri,ipLeafAttributes[j]);
                            xmlFree(tmp);
                        }
                    }
                }
            }
        }
        if ((!xmlStrcmp(node->name,(const xmlChar *)"ttl-expiredO"))) {
            printStruct();          
            freeStructData();
            printf("\n <End of the rule> \n");
        }
        print_xml(node->children);
        node = node->next;
    }
}

int main(){
    xmlDoc *doc = NULL;
    xmlNode *root_element = NULL;
    doc = xmlReadFile(fileName,NULL,0);
    if (doc == NULL) {
        printf("Could not parse the XML file");
    }
    root_element = xmlDocGetRootElement(doc);
    print_xml(root_element);
    xmlFreeDoc(doc);
    xmlCleanupParser();
}
  • 命令

gcc tmp.c -I / usr / include / libxml2 -lxml2 -o tmp

  • 输出
<Start of the rule> 
rule_name->> Telnet & Secure Shell
rule_active -->> 0
rule_action -->> 1
rule_action -->> 1
rule_protocol -->> 3
rule_interface -->> 0
rule_enableProcessIcmp -->> 0
rule_enableTrustedMac -->> 0
rule_enableLog -->> 0
ipSourceAddress_type -->> 4
ipSourceAddress_address1 -->> 0.0.0.0
ipSourceAddress_address2 -->> 0.0.0.0
ipSourcePort_type-->> 0
ipSourcePort_count-->> 0
ipDestinationAddress_type-->> 3
ipDestinationAddress_address1-->> 0.0.0.0
ipDestinationAddress_address2-->> 0.0.0.0
ipDestinationPort_type -->> 3
ipDestinationPort_count -->> 2
ipDestinationPort_port -->> 22,23,processIcmp_destinationUnreachableI -->> False
processIcmp_echoReplyI -->> False
processIcmp_echoRequestI -->> False
processIcmp_informationReplyI -->> False
processIcmp_informationRequestI-->> False
processIcmp_parameterProblemI -->> False
processIcmp_redirectI -->> False
processIcmp_sourceQuenchI -->> False
processIcmp_ttlExpiredI -->> False
processIcmp_destinationUnreachableO -->> False
processIcmp_echoReplyO -->> False
processIcmp_echoRequestO -->> False
processIcmp_informationReplyO-->> False
processIcmp_informationRequestO -->> False
processIcmp_parameterProblemO -->> False
processIcmp_redirectO -->> False
processIcmp_sourceQuenchO -->> False
processIcmp_ttlExpiredO -->> False
<End of the rule>

这是您可以使用libxml2解析器简单地从xml文件中读取xml数据并将其存储到strucutre中的方法，对于进一步使用此struct数据，您可以将结构对象地址传递给任何函数。

clibxml2libxml2parsexmlreadxmlxmlxmlxmlxmlxmlxml

相关问答

matplotlib报错：AttributeError: module 'backend_interagg' has no attribute 'FigureCanvas'. Did you mean: 'FigureCanvasAgg'?
使用本地python环境可以成功执行 import pandas as pd impor...
gitlab登录失败，报错：This challenge page was accidentally cached by an intermediary and is no longer available.
设置时间 控制面板
后端开发常见错误
错误1：Request method ‘DELETE‘ not supported 错误还原：...
docker常见错误
错误1：启动docker镜像时报错：Error response from daemon:...
idea常见错误
错误1：private field ‘xxx‘ is never assigned 按Alt...
pip安装依赖失败
报错如下，通过源不能下载，最后警告pip需升级版本 Requirem...