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Wiki文章的链接将返回第一个链接,然后在主循环中遍历此函数,直到到达指定的文章为止。我从一些随机文章中跑出来,发现当它经过“文学”时,它会变成“艺术”作为下一页,但是当它进行搜索时,艺术卷曲会返回一个空字符串-如果我print(“%s”,chunk.memory)通话后,我得到(空)。如果我手动强制该功能从艺术开始,那么它就可以正常工作,一直到哲学。对于我的一生,我看不到任何区别...我放入了一些诊断printfs并获得了以下内容:
这是地址〜>!http://en.wikipedia.org/wiki/Art !,兰德标志= 0
链接位于感叹号之间,因此我知道它可以正确解析链接,并且rand_flag始终设置为0。
任何提示,指针或解决方案表示赞赏。
最佳答案
如果您所拥有的只是一段不可编译的代码,通常就不可能对程序说任何话。因此,我将提出一些一般性建议。
检查函数的返回值。
设置libcurl的回调,以便您可以通过轻按一下开关来打印出入和出出的每个字节(很像curl -v
一样-如果需要指导,请查看其来源)。
嗅探您的网络流量。
如果发现根本没有发送请求,或者发送了请求但没有返回数据,则说明问题范围有所缩小。