Question

html可能很脏例如标签

中的数据过早结束

我该怎么办？感谢

Answer 1

使用libxml2 HTML解析器，它将标准化＆＃34;脏＆＃34; HTML成为规范化树。见htmlDocPtr htmlParseFile(const char * filename, const char * encoding)

http://xmlsoft.org/html/libxml-HTMLparser.html

Answer 2

由于缺乏知识，我遇到了很多麻烦。所以我编写完整的演示程序来解析使用libxml2库的HTML。

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <libxml/HTMLparser.h>

void traverse_dom_trees(xmlNode * a_node)
{
    xmlNode *cur_node = NULL;

    if(NULL == a_node)
    {
        //printf("Invalid argument a_node %p\n", a_node);
        return;
    }

    for (cur_node = a_node; cur_node; cur_node = cur_node->next) 
    {
        if (cur_node->type == XML_ELEMENT_NODE) 
        {
            /* Check for if current node should be exclude or not */
            printf("Node type: Text, name: %s\n", cur_node->name);
        }
        else if(cur_node->type == XML_TEXT_NODE)
        {
            /* Process here text node, It is available in cpStr :TODO: */
            printf("node type: Text, node content: %s,  content length %d\n", (char *)cur_node->content, strlen((char *)cur_node->content));
        }
        traverse_dom_trees(cur_node->children);
    }
}

int main(int argc, char **argv) 
{
    htmlDocPtr doc;
    xmlNode *roo_element = NULL;

    if (argc != 2)  
    {
        printf("\nInvalid argument\n");
        return(1);
    }

    /* Macro to check API for match with the DLL we are using */
    LIBXML_TEST_VERSION    

    doc = htmlReadFile(argv[1], NULL, HTML_PARSE_NOBLANKS | HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING | HTML_PARSE_NONET);
    if (doc == NULL) 
    {
        fprintf(stderr, "Document not parsed successfully.\n");
        return 0;
    }

    roo_element = xmlDocGetRootElement(doc);

    if (roo_element == NULL) 
    {
        fprintf(stderr, "empty document\n");
        xmlFreeDoc(doc);
        return 0;
    }

    printf("Root Node is %s\n", roo_element->name);
    traverse_dom_trees(roo_element);

    xmlFreeDoc(doc);       // free document
    xmlCleanupParser();    // Free globals
    return 0;
}

如何使用libxml2来解析C编程中的脏HTML

2 个答案: