我有以下代码:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>
char * return_next(char *link, int rand_flag);
char* strip_parens(char* string);
char* strip_itals(char* string);
char* strip_tables(char* string);
struct MemoryStruct {
char *memory;
size_t size;
};
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! */
printf("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;
}
int main(void)
{
char *page = malloc(1000);
page = strcpy(page, "http://en.wikipedia.org/wiki/Literature");
char *start = malloc(1000);
start = strcpy(start, page);
printf("%s\n\n", page);
int i = 0, rand_flag = 0;
while(strcmp(page, "http://en.wikipedia.org/wiki/Philosophy")){
i++;
page = return_next(page, rand_flag);
printf("deep: %d, %s\n\n", i, page);
rand_flag = 0;
}
printf("start link: %s, is %d clicks from philosophy", start, i);
return 0;
}
char * return_next(char *link, int rand_flag){
CURL *curl_handle;
struct MemoryStruct chunk;
chunk.memory = malloc(1);
chunk.size = 0;
curl_global_init(CURL_GLOBAL_ALL);
curl_handle = curl_easy_init();
curl_easy_setopt(curl_handle, CURLOPT_URL, link);
curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);
curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *)&chunk);
curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/2.0.0.1");
if(rand_flag){
curl_easy_setopt(curl_handle, CURLOPT_FOLLOWLOCATION, 1);
}
curl_easy_perform(curl_handle);
curl_easy_cleanup(curl_handle);
char *theString = malloc(strlen(chunk.memory)+1);
char *theString1 = malloc(strlen(theString) + 1);
theString = strstr(chunk.memory, "div id=\"body");
theString1 = strip_tables(theString);
if(chunk.memory)
free(chunk.memory);
theString = strstr(theString1, "<p>");
theString1 = strip_itals(theString);
theString = strip_parens(theString1);
curl_global_cleanup();
return theString;
}
char* strip_parens(char* string) {
long len = strlen(string);
char* result = malloc(len + 1);
int num_parens = 0;
int i, j = 0;
for(i=0; i < len; i++) {
char c = string[i];
if(c == '(') {
num_parens++;
}
else if(c == ')' && num_parens > 0) {
num_parens--;
}
else if(num_parens == 0) {
if(c == '<'){
if (string[i+1] == 'a'){
if (string[i+2] == ' ') {
if(string[i+3] == 'h'){
i = i+9;
for(;string[i] != '"'; i++){
result[j] = string[i];
j++;
}
result[j] = '\0';
len = strlen("http://en.wikipedia.org");
char *final = malloc(j+len);
final = strcpy(final, "http://en.wikipedia.org");
return strcat(final, result);
}
}
}
}
}
}
result[j] = '\0';
return result;
}
char* strip_itals(char* string) {
long len = strlen(string);
char* result = malloc(len + 1);
int inside = 0;
int i, j = 0;
for(i=0; i < len; i++) {
//printf(".%d, %c, %d\n", i, string[i], inside);
char c = string[i];
if(c == '<' && inside == 0) {
if (string[i+1] == 'i'){
if (string[i+2] == '>') {
inside++;
i = i+2;
}
}
}
else if(c == '<' && inside > 0) {
//printf("first if\n");
if (string[i+1] == '/'){
if (string[i+2] == 'i') {
inside--;
i=i+3;
}
}
}
if(inside == 0) {
result[j] = c;
j++;
}
}
result[j] = '\0';
return result;
}
char* strip_tables(char* string) {
//printf("%s\n", string);
long len = strlen(string);
//long len = 1000000;
char* result = malloc(len + 1);
int inside = 0;
int i, j = 0;
for(i=0; i < len; i++) {
//printf(".%d, %c, %d\n", i, string[i], inside);
char c = string[i];
if(c == '<' && inside == 0) {
if (string[i+1] == 't'){
if (string[i+2] == 'a') {
if (string[i+3] == 'b') {
if (string[i+4] == 'l') {
inside++;
i = i+4;
}
}
}
}
}
else if(c == '<' && inside > 0) {
//printf("first if\n");
if (string[i+1] == '/'){
if (string[i+2] == 't') {
if (string[i+3] == 'a') {
if (string[i+4] == 'b') {
if (string[i+5] == 'l') {
inside--;
i=i+7;
}
}
}
}
}
}
if(inside == 0) {
result[j] = c;
j++;
}
}
result[j] = '\0';
return result;
}
给定一个wiki文章的链接将返回第一个链接,然后在main我循环这个函数,直到我到达指定的文章。我从一些随机文章中发现并发现当它通过“文学”时它将“Art”作为下一页但是当它进入搜索时Art curl返回一个空白字符串 - 如果我打印(“%s”,chunk.memory)通话结束后我得到(null)。如果我手动强制该功能从艺术开始它工作正常,一直落后于哲学。对于我的生活,我看不出任何差异......我把一些诊断printfs放入并得到以下内容 -
这是地址〜&gt; !http://en.wikipedia.org/wiki/Art !, rand flag = 0
使用感叹号之间的链接,所以我知道它正在正确解析链接,并且rand_flag此时始终设置为0。
非常感谢任何提示,指示或解决方案。
答案 0 :(得分:1)
如果您拥有的只是一段无法编译的代码,通常无法对程序说任何话。所以我打算给出一些通用的建议。
curl -v
一样 - 如果需要指导,请查看其来源)。 答案 1 :(得分:0)
代码完整borked,将无法正常工作。让我通过剪断一段代码和评论来说明:
char * theString = 的malloc(strlen的(chunk.memory)+1);
char * theString1 = malloc(strlen(theString)+ 1);
执行strlen(theString)将在指向未初始化内存的指针上调用strlen()。可以是任何东西。然后你分配那个大小并放入第二个指针...
theString = strstr(chunk.memory,“div ID = \ “体”);
...然后你再次将'theString'分配到'chunk.memory'内存区域内的位置。
theString1 = strip_tables(theString);
然后再将'theString1'分配给'theString'中的某个位置。
你现在已经泄露了两个mallocs。
如果(chunk.memory) 自由(chunk.memory);
看,你现在释放了你的两个指针所指向的数据。他们现在指向垃圾。
theString = strstr(theString1,“
”);
...现在您搜索已经释放的数据。
我需要说更多吗?