Creating a C++ class to read data from a website to a string using libcurl - c++

I am using http://ubuntuforums.org/showthread.php?t=781021 as a guide for how to write a c++ program that use libcurl to check a website and downloads the text to a c++ app. When I copy the code to my visual studio project, it works with only slight modification. However, I hit a snag trying to convert it to class based files.
I created a .h and .cpp files to run the query. What I didn't realize before was that handle_data was not a typical function, since it is not given any arguments or even () in the midway down Viewer.cpp. This is how the above site did it, and it worked, but I'm at a loss as to why or how to convert it now.
Does anyone know whats going on here or how to fix it?
Thanks!
Viewer.h:
#pragma once
#include <string>
#include "curl.h"
class Viewer
{
public:
Viewer(void);
~Viewer(void);
std::string view(std::string q);
private:
size_t handle_data(void *ptr, size_t size, size_t nmemb, void *stream);
std::string contents;
};
Viewer.cpp:
#include "stdafx.h"
#include "Viewer.h"
#include <iostream>
Viewer::Viewer(void)
{
std::cout << "ViewerCreated!\n";
}
Viewer::~Viewer(void)
{
}
size_t Viewer::handle_data(void *ptr, size_t size, size_t nmemb, void *stream)
{
int numbytes = size*nmemb;
// The data is not null-terminated, so get the last character, and replace
// it with '\0'.
char lastchar = *((char *) ptr + numbytes - 1);
*((char *) ptr + numbytes - 1) = '\0';
contents.append((char *)ptr);
contents.append(1,lastchar);
*((char *) ptr + numbytes - 1) = lastchar; // Might not be necessary.
return size*nmemb;
}
std::string Viewer::view(std::string q)
{
char* url = "www.google.com";
CURL* curl = curl_easy_init();
if(curl)
{
// Tell libcurl the URL
curl_easy_setopt(curl,CURLOPT_URL, url);
// Tell libcurl what function to call when it has data
curl_easy_setopt(curl,CURLOPT_WRITEFUNCTION,handle_data);
// Do it!
CURLcode res = curl_easy_perform(curl);
curl_easy_cleanup(curl);
if (res == 0)
std::cout << contents << std::endl;
else
std::cerr << "Error: " << res << std::endl;
}
return contents;
}

You should not replace the last character of the chunk that you have received. Instead you should force that the buffer containing the appended blocks has a '\0' just after the end of the data. This way it can be printed, but if you are going to store that in a file, you should just write the bytes that you have received.
This has always worked for me:
struct MemoryStruct chunk;
chunk.memory=NULL;
chunk.size = 0;
...
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteMemoryCallback);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, (void *)&chunk);
And the callback:
struct MemoryStruct {
char *memory;
size_t size;
};
static void *myrealloc(void *ptr, size_t size)
{
if(ptr)
return realloc(ptr, size);
else
return malloc(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 = (char *)myrealloc(mem->memory, mem->size + realsize + 1);
if (mem->memory) {
memcpy(&(mem->memory[mem->size]), ptr, realsize);
mem->size += realsize;
mem->memory[mem->size] = 0;
}
return realsize;
}

handle_data is used as a parameter for curl_easy_setopt. What that means is that you have to program what handle_data does when it receives the next data chunk (providing the data chunk is what curl will do for you).

handle_data is being passed to curl_easy_setopt as a callback function, which it will call when there's data available. Because of that, handle_data must be called as a static function (that is, one not receiving an object pointer, because cURL doesn't have one). However, you're not declaring it as static. Even if you do, you are accessing contents inside it, which is invalid.

Related

VS2013 ERROR 0xC0000005: when using libcurl

I'm trying to use libcurl (http://curl.haxx.se/libcurl/c/) for downloading data from a web, and store these data in a txt file , and here is my code:
// CLASS SinaStk
size_t save_data(char *buffer, size_t size, size_t nmemb, FILE* userdata){
locale loc = std::locale::global(std::locale("")); //TRY TO OPEN FILE WITH CHINESE
userdata = fopen(fpath.c_str(), "w");
if (userdata == NULL)
printf("File not open!\n");
locale::global(loc);
size_t writelen=size * nmemb;
fwrite(buffer, size, nmemb, userdata);
return writelen;
};
virtual void downloadUrl()
{
CURL* stkCURL=NULL;
CURLcode res;
FILE * fp=NULL;
curl_global_init(CURL_GLOBAL_WIN32);
stkCURL = curl_easy_init();
curl_easy_setopt(stkCURL, CURLOPT_URL,"http://hq.sinajs.cn/list=s_sh000001");
curl_easy_setopt(stkCURL, CURLOPT_WRITEFUNCTION, &SinaStk::save_data);
curl_easy_setopt(stkCURL, CURLOPT_WRITEDATA,fp);
res=curl_easy_perform(stkCURL); //<-STOP!!!!
fclose(fp);
curl_easy_cleanup(stkCURL);
curl_global_cleanup();
return;
};
and when I debug my code, it always stop and then jump to xstring:
size_type size() const _NOEXCEPT
{ // return length of sequence
return (this->_Mysize); // <-STOP!!!
}
0xC0000005: Access violation reading location 0x0000009E
I have no idea about the problem for almost a week. I am upset, I asked people around me and nobody knows why.
Thanks for reading, I am really confused.
=============
Problem is solved! Thanks you guys! now my code is:
//CLASS StkApiInfo
size_t writeData(char* buffer, size_t size, size_t nmemb){
if (stkFile.is_open()){
stkFile.close();
stkFile.clear();
};
fpath = "D:\\Code\\代码\\数据文件\\" + fname + ".txt";
stkFile.open(fpath.c_str(), ios::out);
//if (stkFile.is_open())
cout << buffer<<size<<nmemb;
stkFile << buffer<<endl;
stkFile.close();
stkFile.clear();
return size*nmemb;
};
//CLASS SinaStk : public StkApiInfo
static size_t save_data(char *buffer, size_t size, size_t nmemb, void* userdata){
SinaStk* self = (SinaStk*)userdata;
return self->writeData(buffer, size, nmemb);
};
virtual void downloadUrl()
{
CURL* stkCURL = NULL;
CURLcode res;
curl_global_init(CURL_GLOBAL_WIN32);
stkCURL = curl_easy_init();
if (stkCURL)
{
curl_easy_setopt(stkCURL, CURLOPT_URL, stkUrl.c_str());
curl_easy_setopt(stkCURL, CURLOPT_WRITEFUNCTION, &SinaStk::save_data);
curl_easy_setopt(stkCURL, CURLOPT_WRITEDATA, this);
res = curl_easy_perform(stkCURL);
//if (res != CURLE_OK)
curl_easy_cleanup(stkCURL);
curl_global_cleanup();
}
return;
};
Callback passed with CURLOPT_WRITEFUNCTION argument should be of type write_callback (with exact that signature) and therefore cannot be non-static class method. Usual workaround is to define callback as non-member or static method and pass this as an argument:
static size_t save_data(char *buffer, size_t size, size_t nmemb, void* userdata)
{
SinaStk* self = (SinaStk*) userdata;
return self->doStuff(buffer, size, nmemb);
}
virtual void downloadUrl()
{
//...
curl_easy_setopt(stkCURL, CURLOPT_WRITEFUNCTION, &SinaStk::save_data);
curl_easy_setopt(stkCURL, CURLOPT_WRITEDATA, this);
//...
}
If you need to access additional data (like FILE* in your example) you can either store it as class field or introduce temporary structure that would contain this and additional data fields and pass it's address as callback argument.

Pass extra arguments to libcurl CURLOPT_READFUNCTION callback

The program
Reads out a textfile and emails it's contents
The original code (with help of Sehe)
https://gist.github.com/1342118#file_test.cpp
The problem:
I am trying to run the application multiple times using threading, using a different textfile for each thread. This means I can no longer use a global vector because thread 3 may add to / alter this vector while thread 1 is still working on it. This means this line is becoming problematic:
curl_easy_setopt(curl, CURLOPT_READFUNCTION, read_callback);
This calls this function:
static size_t read_callback(void *ptr, size_t size, size_t nmemb, void *userp)
{
struct WriteThis *pooh = (struct WriteThis *)userp;
if(size*nmemb < 1)
return 0;
if (pooh->counter < text.size())
{
const std::string& data = text[pooh->counter];
memcpy(ptr, data.data(), data.length());
pooh->counter++; /* advance pointer */
return data.length();
}
return 0; /* no more data left to deliver */
}
As you can see it uses the globally defined vector "text". I thought I could fix it by simply making the vector inside that function (read_callback) but since I'm using threading now, the filename is no longer hard coded so I end up having to pass a variable anyway.
Curl seems to fill in the variables that read_callback accepts automatically so how is this done?
Just to clarify, here's what I have now:
std::vector<string> read_text(char* fname)
{
std::ifstream myfile (fname);
std::vector<string> text;
std::string line;
while (std::getline(myfile, line))
{
text.push_back(line + '\n');
}
return text;
}
static size_t read_callback(void *ptr, size_t size, size_t nmemb, void *userp)
{
std::vector<string> text;
text = read_text(textfilename);
struct WriteThis *pooh = (struct WriteThis *)userp;
if(size*nmemb < 1)
return 0;
if (pooh->counter < text.size())
{
const std::string& data = text[pooh->counter];
memcpy(ptr, data.data(), data.length());
pooh->counter++; /* advance pointer */
return data.length();
}
return 0; /* no more data left to deliver */
}
But read_text doesn't work because textfilename hasn't been passed to the function.
Read carefully again curl_easy_setopt's documentation. You might set the CURLOPT_READDATA to your textfilename and cast the userp to get it inside your read_callback
edit
Your userp is actually used; so you should add the textfilename in a new field of your WriteThis struct. Most callback functions take only one user data, but it should be enough (since you can pack arbitrary stuff in it).

a multiple definition error in c++

I have 2 files, grabURL.cpp and grabURL.hpp. When I compile the both with gcc it gives me multiple definitions errors.
grabURL.cpp
#include "grabURL.hpp"
size_t buffer(void *ptr, size_t size, size_t nmemb, void *stream) {
int numbytes = size*nmemb;
char lastchar = *((char *) ptr + numbytes - 1);
*((char *) ptr + numbytes - 1) = '\0';
ret.append((char *)ptr);
ret.append(1,lastchar);
*((char *) ptr + numbytes - 1) = lastchar;
return size*nmemb;
}
void grabURL(std::string url, std::string *theRet){
curl_easy_setopt(curl,CURLOPT_URL,url.c_str());
curl_easy_setopt(curl,CURLOPT_WRITEFUNCTION, buffer);
res = curl_easy_perform(curl);
*theRet = ret;
}
grabURL.hpp:
#ifndef CURLURLGRAB_HPP
#define CURLURLGRAB_HPP
#include <string>
#include <curl/curl.h>
CURL * curl;
CURLcode res;
std::string ret;
size_t buffer(void *ptr, size_t size, size_t nmemb, void *stream);
void grabURL(std::string url,std::string* theRet);
#endif
I have no idea what I am doing wrong, I thought I did the ifndef thing correctly. What exactly is wrong?
This definitions in your header file:
CURL * curl;
CURLcode res;
std::string ret;
get defined when you include the file from the cpp file, and pressumably some other translation unit (perhaps main.cpp?)
They don't look like something that should be in a header file, but if they do then you can declare them extern within the header file and move the actual definitions to the cpp file.

Adding to char array isn't working

I'm trying to read a text file line by line, and add each line to a char array. But the lines aren't added, at all.
//This is the default char array that comes with the cURL code.
char *text[]={
"one\n",
"two\n",
"three\n",
" Hello, this is CURL email SMTP\n",
NULL
};
/*Now we're going to replace that char array, with an array that holds the contents of a textfile.
We'll read a textfile out line by line, and add each line to the char array.
*/
void makemailmessage()
{
text[0] = '\0'; //Clear text
text[0] = "testy\n"; //First line in new char array
//Read the text file, add each line to the char array.
string line;
ifstream myfile ("C:\\Users\\admin\\Downloads\\bbb.txt");
int counter;
counter = 1;
if (myfile.is_open())
{
while ( myfile.good() )
{
getline (myfile,line);
//Convert the string variable "line" to a char (a)
char *a=new char[line.size()+1];
a[line.size()]=0;
memcpy(a,line.c_str(),line.size());
//Add \n to the end of "a" (new char will be "str")
char str[80];
strcpy (str,a);
strcat (str,"\n");
//Add "str" to the char array "text"
text[counter] = str;
text[counter+1] = "test\n"; //Also added this for testing purposes
write_data("C:\\Users\\admin\\Downloads\\checkit.txt", str); //Also for testing purposes
//Increase counter by 2 because we added two new items to the char array "text"
counter++;
counter++;
}
myfile.close();
text[counter-1] = "testy2\n"; //Ad another text line
text[counter] = NULL; //End char array
}
Each str is written correctly to checkit.txt but for some reason it is not added to the char array because I end up with the char array looking like this:
testy
test
test
testy2
What am I doing wrong?
UPDATE2:
The reason I am trying to make a char array is because the cURL function I am using needs a char array to form the email body. This is the important part of the cURL code.
static size_t read_callback(void *ptr, size_t size, size_t nmemb, void *userp)
{
struct WriteThis *pooh = (struct WriteThis *)userp;
const char *data;
if(size*nmemb < 1)
return 0;
data = text[pooh->counter]; //This part is using the char array.
if(data) {
size_t len = strlen(data);
memcpy(ptr, data, len);
pooh->counter++;
return len;
}
return 0;
}
Here's the full code
Okay, after chatting on this a bit more, here is a fix:
C++ version
Full code file here: https://gist.github.com/1342118#file_test.cpp
Replace the relevant code with:
#include <vector>
#include <fstream>
// ...
std::vector<std::string> text;
static int read_text(char* fname)
{
//Read the text file, add each line to the char array.
std::ifstream myfile (fname);
std::string line;
while (std::getline(myfile, line))
text.push_back(line + '\n');
return 0;
}
static size_t read_callback(void *ptr, size_t size, size_t nmemb, void *userp)
{
/* This was already in. */
struct WriteThis *pooh = (struct WriteThis *)userp;
if(size*nmemb < 1)
return 0;
if (pooh->counter < text.size())
{
const std::string& data = text[pooh->counter];
memcpy(ptr, data.data(), data.length());
pooh->counter++; /* advance pointer */
return data.length();
}
return 0; /* no more data left to deliver */
}
Pure C version
Full code file here: https://gist.github.com/1342118#file_test.c
Replace
//This is the default char array that comes with the cURL code.
char *text[]={
"one\n",
"two\n",
"three\n",
" Hello, this is CURL email SMTP\n",
NULL
};
With
char **text = 0;
static int read_text(char* fname)
{
unsigned capacity = 10;
int linecount = 0;
// free_text(); see below
text = realloc(text, capacity*sizeof(*text));
FILE* file = fopen(fname, "r");
if (!file)
{ perror("Opening file"); return 1; }
char buf[2048];
char* line = 0;
while (line = fgets(buf, sizeof(buf), file))
{
if (linecount>=capacity)
{
capacity *= 2;
text = realloc(text, capacity*sizeof(*text));
}
text[linecount++] = strdup(line);
}
fclose(file);
return 0;
}
Hook it up in you main function, e.g. like so
if (argc<2)
{
printf("Usage: %s <email.eml>\n", argv[0]);
exit(255);
} else
{
printf("Reading email body from %s\n", argv[1]);
if (0 != read_text(argv[1]))
exit(254);
}
Or, if you so prefer, just calling read_text("C:\\Users\\admin\\Downloads\\bbb.txt") :)
To really top things off, don't forget to reclaim memory when you're done - properly:
#include "curl/curl.h"
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <memory.h>
#include <string.h>
#define GetCurrentDir getcwd
#define USERNAME "obscured#gmail.com"
#define PASSWORD "obscured"
#define SMTPSERVER "smtp.gmail.com"
#define SMTPPORT ":587"
#define RECIPIENT "<obscured#gmail.com>"
#define MAILFROM "<obscured#gmail.com>"
#define MULTI_PERFORM_HANG_TIMEOUT 60 * 1000
/* Note that you should include the actual meta data headers here as well if
you want the mail to have a Subject, another From:, show a To: or whatever
you think your mail should feature! */
char **text = 0;
void free_text()
{
if (text)
{
char** it;
for (it = text; *it; ++it)
free(*it);
free(text);
text = 0;
}
}
static int read_text(char* fname)
{
unsigned capacity = 10;
int linecount = 0;
free_text();
text = realloc(text, capacity*sizeof(*text));
FILE* file = fopen(fname, "r");
if (!file)
{ perror("Opening file"); return 1; }
char buf[2048];
char* line = 0;
while (line = fgets(buf, sizeof(buf), file))
{
if (linecount>=capacity)
{
capacity *= 2;
text = realloc(text, capacity*sizeof(*text));
}
text[linecount++] = strdup(line);
}
if (linecount>=capacity)
text = realloc(text, (++capacity)*sizeof(*text));
text[linecount] = 0; // terminate
fclose(file);
return 0;
}
struct WriteThis {
int counter;
};
static size_t read_callback(void *ptr, size_t size, size_t nmemb, void *userp)
{
/* This was already in. */
struct WriteThis *pooh = (struct WriteThis *)userp;
const char *data;
if(size*nmemb < 1)
return 0;
data = text[pooh->counter];
if(data) {
size_t len = strlen(data);
memcpy(ptr, data, len);
pooh->counter++; /* advance pointer */
return len;
}
return 0; /* no more data left to deliver */
}
static struct timeval tvnow(void)
{
/*
** time() returns the value of time in seconds since the Epoch.
*/
struct timeval now;
now.tv_sec = (long)time(NULL);
now.tv_usec = 0;
return now;
}
static long tvdiff(struct timeval newer, struct timeval older)
{
return (newer.tv_sec-older.tv_sec)*1000+
(newer.tv_usec-older.tv_usec)/1000;
}
int main(int argc, char** argv)
{
if (argc<2)
{
printf("Usage: %s <email.eml>\n", argv[0]);
exit(255);
} else
{
printf("Reading email body from %s\n", argv[1]);
if (0 != read_text(argv[1]))
exit(254);
}
CURL *curl;
CURLM *mcurl;
int still_running = 1;
struct timeval mp_start;
char mp_timedout = 0;
struct WriteThis pooh;
struct curl_slist* rcpt_list = NULL;
pooh.counter = 0;
curl_global_init(CURL_GLOBAL_DEFAULT);
curl = curl_easy_init();
if(!curl)
return 1;
mcurl = curl_multi_init();
if(!mcurl)
return 2;
rcpt_list = curl_slist_append(rcpt_list, RECIPIENT);
/* more addresses can be added here
rcpt_list = curl_slist_append(rcpt_list, "<others#example.com>");
*/
curl_easy_setopt(curl, CURLOPT_URL, "smtp://" SMTPSERVER SMTPPORT);
curl_easy_setopt(curl, CURLOPT_USERNAME, USERNAME);
curl_easy_setopt(curl, CURLOPT_PASSWORD, PASSWORD);
curl_easy_setopt(curl, CURLOPT_READFUNCTION, read_callback);
curl_easy_setopt(curl, CURLOPT_MAIL_FROM, MAILFROM);
curl_easy_setopt(curl, CURLOPT_MAIL_RCPT, rcpt_list);
curl_easy_setopt(curl, CURLOPT_USE_SSL, CURLUSESSL_ALL);
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER,0);
curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0);
curl_easy_setopt(curl, CURLOPT_READDATA, &pooh);
curl_easy_setopt(curl, CURLOPT_VERBOSE, 1);
curl_easy_setopt(curl, CURLOPT_SSLVERSION, 0);
curl_easy_setopt(curl, CURLOPT_SSL_SESSIONID_CACHE, 0);
curl_multi_add_handle(mcurl, curl);
mp_timedout = 0;
mp_start = tvnow();
/* we start some action by calling perform right away */
curl_multi_perform(mcurl, &still_running);
while(still_running) {
struct timeval timeout;
int rc; /* select() return code */
fd_set fdread;
fd_set fdwrite;
fd_set fdexcep;
int maxfd = -1;
long curl_timeo = -1;
FD_ZERO(&fdread);
FD_ZERO(&fdwrite);
FD_ZERO(&fdexcep);
/* set a suitable timeout to play around with */
timeout.tv_sec = 1;
timeout.tv_usec = 0;
curl_multi_timeout(mcurl, &curl_timeo);
if(curl_timeo >= 0) {
timeout.tv_sec = curl_timeo / 1000;
if(timeout.tv_sec > 1)
timeout.tv_sec = 1;
else
timeout.tv_usec = (curl_timeo % 1000) * 1000;
}
/* get file descriptors from the transfers */
curl_multi_fdset(mcurl, &fdread, &fdwrite, &fdexcep, &maxfd);
/* In a real-world program you OF COURSE check the return code of the
function calls. On success, the value of maxfd is guaranteed to be
greater or equal than -1. We call select(maxfd + 1, ...), specially in
case of (maxfd == -1), we call select(0, ...), which is basically equal
to sleep. */
//rc = select(maxfd+1, &fdread, &fdwrite, &fdexcep, &timeout);
if (tvdiff(tvnow(), mp_start) > MULTI_PERFORM_HANG_TIMEOUT) {
fprintf(stderr, "ABORTING TEST, since it seems "
"that it would have run forever.\n");
break;
}
switch(rc) {
case -1:
/* select error */
break;
case 0: /* timeout */
default: /* action */
curl_multi_perform(mcurl, &still_running);
break;
}
}
curl_slist_free_all(rcpt_list);
curl_multi_remove_handle(mcurl, curl);
curl_multi_cleanup(mcurl);
curl_easy_cleanup(curl);
curl_global_cleanup();
free_text();
return 0;
}
I'm trying to read a text file line by line, and add each line to a
char array.
Since this is C++, why not use an std::vector<string> and use the std::string version of getline?
The std::string class will look after the memory needed to hold a string of any sort of length, and the std::vector class will worry about the memory needed to hold an "array", so to speak, of strings.
EDIT: Actually looking at your code again, you do use an std::string and then allocate memory to store it as an array of chars, and then store pointers to those strings in some fixed sized array, test. Why go to all that trouble when, as I mentioned above, you can use an std::vector<string> to hold all your std::string objects? Mind = boggled.
EDIT2: Couldn't you also use cURLpp as a C++ wrapper for cURL? I haven't used either so I can't comment on the effectiveness of it.
What am I doing wrong?
For one, this:
char str[80];
strcpy (str,a);
strcat (str,"\n");
//Add "str" to the char array "text"
text[counter] = str;
str is allocated on the stack, with block-wide scope. Then you enter that pointer in an array with a greater scope. This is usually a recipe for disaster - a rather impressive segmentation fault or whatever the equivalent is on your platform.
In this case, due to its use in a loop, your program will either crash, or - if the stars have the proper alignment - you will end up with all pointers in your array pointing to the same out-of-scope string, namely the one that was last read.
Why do you even go into that trouble, when you have already dynamically allocated a in the heap?
By the way, mixing char[] arrays (and the associated standard C library functions) with C++ strings is NOT a good idea. Not even an acceptable one. OK, it a bad idea. Just stick to C++ strings...

Multithreaded curl application has memory allocation problems

I'm working on an application in C++ that threads and hands a bunch of threads URLs for cURL to download in parallel.
I'm employing a method that should be safe to download images and videos, etc. I uses memcpy instead of assuming the data is a string or character array.
I pass each thread a structure, thread_status, for a number of things. The structure lets the parent process know the thread is done downloading. It also stores the data cURL is downloading and keeps track of it's size as cURL returns more buffers for writing.
I pass a (void *) pointer that points to each structure that's allocated at initialization to each thread that does the downloading. The first page is downloaded properly, after that I keep getting errors from realloc().
Here is the simplest example that illustrates my problem. This sample is not multi-threaded but uses a similar structure to keep track of itself.
#include <string>
#include <assert.h>
#include <iostream>
#include <curl/curl.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#define NOT_READY 1
#define READY 0
using namespace std;
struct thread_status {
int id;
pthread_t *pid;
int readyState;
char *url;
void *data;
size_t bufferlen;
size_t writepos;
int initialized;
} ;
size_t static
writefunction( void *ptr, size_t size,
size_t nmemb, void *userdata)
{
size_t nbytes = size*nmemb;
struct thread_status **this_status;
this_status = (struct thread_status **) userdata;
if (!(*this_status)->initialized){
(*this_status)->data = (void *)malloc(1024);
(*this_status)->bufferlen = 1024;
(*this_status)->writepos = 0;
(*this_status)->initialized = true;
}
if ((*this_status)->bufferlen < ((*this_status)->writepos + nbytes)){
(*this_status)->bufferlen = (*this_status)->bufferlen + nbytes;
(*this_status)->data = realloc((*this_status)->data, (size_t) ((*this_status)->writepos + nbytes));
}
assert((*this_status)->data != NULL);
memcpy((*this_status)->data + (*this_status)->writepos, ptr, nbytes);
(*this_status)->writepos += nbytes;
return nbytes;
}
void *pull_data (void *my_struct){
struct thread_status *this_struct;
this_struct = (struct thread_status *) my_struct;
this_struct->initialized = false;
cout<<(char *)this_struct->url<<"\n";
CURL *curl;
curl = curl_easy_init();
size_t rc = 0;
while(true){
curl_easy_setopt(curl,
CURLOPT_WRITEFUNCTION, writefunction);
curl_easy_setopt(curl,
CURLOPT_WRITEDATA, (void *) &this_struct);
curl_easy_setopt(curl,
CURLOPT_NOSIGNAL, true);
curl_easy_setopt(curl,
CURLOPT_URL, (char *)this_struct->url);
if (curl_easy_perform(curl) != 0){
cout<<"curl did not perform\n";
exit(1);
} else {
if (this_struct->data != NULL){
// Use a binary write.
rc = fwrite(this_struct->data, this_struct->writepos, 1, stdout);
free(this_struct->data);
} else {
cout<<"Data is NULL\n";
}
}
// Tell the babysitter the thread is ready.
this_struct->readyState = READY;
// This would pause the thread until the parent thread has processed the data in it.
// while(this_struct->readyState == READY){;}
// Now get ready for another round!
this_struct->writepos = (size_t) 0;
this_struct->initialized = false;
this_struct->bufferlen = (size_t) 0;
break;
}
curl_easy_cleanup(curl);
return (void *)"a";
}
int main(){
char *urls[] = { "http://www.example.com/", "http://www.google.com", "http://www.touspassagers.com/", "http://www.facebook.com/" };
int i=0;
struct thread_status mystatuses[4];
for (i=0;i<4;i++){
struct thread_status my_status;
char *data;
my_status.id = i;
my_status.readyState = NOT_READY;
my_status.url = urls[i];
my_status.data = data;
my_status.bufferlen = 0;
my_status.writepos = 0;
my_status.initialized = false;
mystatuses[i] = my_status;
}
for (i=0;i<4;i++){
cout<<"pulling #"<<i<<"\n";
pull_data((void *)&mystatuses[i]);
}
}
If anyone can enlighten me as to the source of my error or a remedy for it I would appreciate it.
You might consider using valgrind to help locate the source of the memory problems.
Got it!
Apparently 1KB isn't enough memory to handle the first cURL buffer. I changed 1024 to nbytes and it works!
Before the memory memcpy put in the buffer ran over the allocated memory resulting in corruptions.
I did a post about it if anyone cares to see the full implementation:
http://www.touspassagers.com/2011/01/a-working-curlopt_writefunction-function-for-libcurl/