search from the command line

google_search.c

/*
 * main.c
 *
 *  Created on: 11/03/2011
 *      Author: adam
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>
#include "cJSON.h"

#define USER_AGENT "ConsoleSearch/1.0 (like GoogleCL/1.0)"
#define REFERER "Console-based Google Search Client"
#define USE_ANSI 1

#if USE_ANSI
#define RESULT_FORMAT "%2i. \x1b[1m%s\x1b[0m\n   %s\n   <\x1b[4m%s\x1b[0m>\n\n"
#else
#define RESULT_FORMAT "%2i. %s\n   %s\n   <%s>\n\n"
#endif

struct MemoryStruct {
	char *memory;
	size_t size;
};

/**
 * Callback for cURL to write response into memory
 *
 * Copied from libcurl example <http://curl.haxx.se/libcurl/c/getinmemory.html>
 */
static size_t WriteMemoryCallback(void *ptr, size_t size, size_t nmemb, void *data)
{
  size_t realsize = size * nmemb;
  struct MemoryStruct *mem = (struct MemoryStruct *)data;

  mem->memory = realloc(mem->memory, mem->size + realsize + 1);
  if (mem->memory == NULL) {
    /* out of memory! */
    fprintf(stderr,"not enough memory (realloc returned NULL)\n");
    exit(EXIT_FAILURE);
  }

  memcpy(&(mem->memory[mem->size]), ptr, realsize);
  mem->size += realsize;
  mem->memory[mem->size] = 0;

  return realsize;
}

char* convertHtmlEntities(char* str) {
    size_t length = strlen(str);
    size_t i;
    char *endchar = malloc(sizeof(char));
    long charCode;
    if (!endchar) {
        fprintf(stderr,"not enough memory");
        exit(EXIT_FAILURE);
    }
    for (i=0;i<length;i++) {
        if (*(str+i) == '&' && *(str+i+1) == '#' && *(str+i+2) >= '0' && *(str+i+2) <= '9' && *(str+i+3) >= '0' && *(str+i+3) <= '9' && *(str+i+4) == ';') {
            charCode = strtol(str+i+2,&endchar,0);
            *(str+i) = charCode;
            memmove(str+i+1,str+i+5,length - (i+5) + 1);

        } else if (*(str+i) == '&' && *(str+i+1) == 'q' && *(str+i+2) == 'u' && *(str+i+3) == 'o' && *(str+i+4) == 't' && *(str+i+5) == ';') {
            *(str+i) = '"';
            memmove(str+i+1,str+i+6,length - (i+6) + 1);
        }
    }
    return str;
}

char* convertHtmlTags(char* str) {
    size_t length = strlen(str);
    char *start = str;
    while ((start = strstr(start, "<b>"))) {
        memmove(start,start+3, length - 3 + 1);
        start = strstr(start, "</b>");
        memmove(start,start+4, length - 4 + 1);
        if (!*(start+1)) {
            break;
        } else {
            start++;
        }
    }
    return str;
}

int main(int argc, char *argv[])
{
    const char baseUrl[] = "https://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=";
    const int baseUrlLength = strlen(baseUrl);

	CURL *curl;
	CURLcode res;
	cJSON *json;
	struct MemoryStruct chunk;
	char* searchQuery;
	char* searchUrl;

	chunk.memory = malloc(1);
	chunk.size = 0;
	
	/* Get search query */
	if (argc > 1) {
        int count;
        int searchQueryLength = (argc - 2);
        char sepChar[] = "+";
        for (count = 1; count < argc; count++) {
            searchQueryLength += strlen(argv[count]);
        }
        searchQuery = malloc(sizeof(char) * searchQueryLength + 1);
        if (!searchQuery) {
            fprintf(stderr,"not enough memory\n");
            return -1;
        }
        for (count = 1; count < argc; count++) {
            strcat(searchQuery, argv[count]);
            if (count != (argc-1)) {
                strcat(searchQuery, sepChar);
            }
        }
	} else {
	    searchQuery = malloc(sizeof(char) * 255);
	    printf("Enter a search query: ");
	    scanf("%[^\n]s", searchQuery);
	}
	    /* Free memory used by response */
	if(chunk.memory)
	{
		free(chunk.memory);
	}
	
	/* Get search url */
	searchUrl = malloc(sizeof(char) * (baseUrlLength + strlen(searchQuery) + 1));
	if (!searchUrl) {
        fprintf(stderr,"not enough memory\n");
        return -1;
    }
    memmove(searchUrl,baseUrl,baseUrlLength);
    memmove(searchUrl+baseUrlLength,searchQuery,strlen(searchQuery));
    *(searchUrl+baseUrlLength+strlen(searchQuery)) = 0;

	/* Initialise cURL */
	curl_global_init(CURL_GLOBAL_ALL);
	curl = curl_easy_init();
	if (!curl) {
        fprintf(stderr,"Error Initalising cURL\n");
		return -1;
	}

	/* Set cURL options */
	curl_easy_setopt(curl, CURLOPT_URL, searchUrl);
	curl_easy_setopt(curl, CURLOPT_USERAGENT, USER_AGENT);
	curl_easy_setopt(curl, CURLOPT_REFERER, REFERER);
	curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);
	curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *)&chunk);


	/* Perform cURL request */
	res = curl_easy_perform(curl);
	if (res != CURLE_OK || (long)chunk.size == 0) {
		curl_easy_cleanup(curl);
        fprintf(stderr,"Error Performing Request\n");
		return -1;
	}

	/* Clean up */
	curl_easy_cleanup(curl);

	/* Decode JSON */
	json=cJSON_Parse(chunk.memory);
	if (!json) {
        fprintf(stderr,"Error Parsing JSON\n");
	    return -1;
    }
    
    /* Check response status */
    if (cJSON_GetObjectItem(json,"responseStatus")->valueint != 200) {
        fprintf(stderr,"Service Error: %s\n", cJSON_GetObjectItem(json,"responseDetails")->valuestring);
        return -1;
    }
    
    /* Get number of results */
    cJSON *data = cJSON_GetObjectItem(json,"responseData");
    cJSON *results = cJSON_GetObjectItem(data,"results");
    int numResults = cJSON_GetArraySize(results);
    
    /* Print each result */
    cJSON *result;
    int resultIndex;
    for (resultIndex = 0; resultIndex < numResults; resultIndex++) {
        result = cJSON_GetArrayItem(results, resultIndex);
        printf(RESULT_FORMAT, resultIndex + 1, convertHtmlEntities(cJSON_GetObjectItem(result,"titleNoFormatting")->valuestring), convertHtmlTags(convertHtmlEntities(cJSON_GetObjectItem(result,"content")->valuestring)), cJSON_GetObjectItem(result,"unescapedUrl")->valuestring);

    }
    
    /* Free memory used by response */
	if(chunk.memory)
	{
		free(chunk.memory);
	}
    
    /*printf("%s",cJSON_Print(json));*/
	return 0;
}