I'm trying to use libxml to parse through some HTML.
Here's my code:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <libxml/HTMLparser.h>
htmlDocPtr gethtml(char *doclocation,char *encoding) {
htmlDocPtr doc;
doc = htmlReadFile(doclocation, encoding, HTML_PARSE_NOBLANKS | HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING | HTML_PARSE_NONET);
if (doc == NULL) {
fprintf(stderr, "Document not parsed successfully.\n");
return;
}
return doc;
}
void getroot(htmlDocPtr doc) {
xmlNode *cur = NULL;
cur = xmlDocGetRootElement(doc);
if (cur == NULL) {
fprintf(stderr, "empty document\n");
xmlFreeDoc(doc);
return;
}
printf("%s\n", *cur);
}
int main(void) {
char *website = "http://www.google.com/index.html";
char *encoding = "UTF-8";
htmlDocPtr doc;
doc = gethtml(website, encoding);
getroot(doc);
return 0;
}
When I run the program, it always prints out (null). I'm guessing that the document isn't getting parsed c开发者_如何学Goorrected during HtmlReadFile(), but I'm not sure how to correct it.
Any help would be appreciated
精彩评论