C语言读HTML文档算法/考研复试

C语言读HTML文档算法

#include <stdio.h>
#include <stdlib.h>
int main(int argc,char *argv[]){
	char c,tag[7];
	int status,len;
	FILE *fin,*fout;
	if(argc!=3){
		printf("参数错误！");
		exit(1);
	}
	if((fin=fopen(argv[1],"r"))== NULL){
			printf("文件无法读取！");
		exit(1);
	}
		if((fin=fopen(argv[2],"w"))==NULL){
			printf("文件无法存储！");
		fclose(fin);
		exit(1);
	}
	status=0;
	
	while((c=fgetc(fin))!=EOF){		
		switch(c){
			case '<':
				status=1;
				len=0;
				break;
			case'>':				
			status=0;
			
			if(len<=6)
			tag[len]='\0';
			if(!strcmp(tag,"/title")||!strcmp(tag,"BR"))
				fputc('\n',fout);
			
			break;
			case '\n':
				break;//遇到换行去掉，只有换行符才真正换行 
			defaut:
				if(!status)
				fput(c,fout);	
				else{
						len++;
				if(len<=6) 
				tag[len-1]=c;	
					break;
				}
				
		}
	}
fclose(fin);
fclose(fout);
}