我正在用 C++ 编写一个爬虫,该函数crawler
下载一个网站并从中提取所有链接。我希望它crawler
在多个线程中运行该函数,每个线程具有不同的参数,并且我想指定线程的数量。所以在程序开始时我想指定多个线程,然后在程序启动时我需要每个线程以不同的参数运行,这样我就可以同时下载指定数量的网站。我知道如何进行基本的多线程,但我需要在程序开始时指定多个线程。那么有没有图书馆可以让我这样做?或者有可能std::thread
吗?
#include <sstream>
#include <iostream>
#include <string>
#include "gumbo.h"
#include <curl/curl.h>
using namespace std;
//extract links
static void search_for_links(GumboNode* node) {
if (node->type != GUMBO_NODE_ELEMENT) {
return;
}
GumboAttribute* href;
if (node->v.element.tag == GUMBO_TAG_A &&
(href = gumbo_get_attribute(&node->v.element.attributes, "href"))) {
std::cout << href->value << std::endl;
}
GumboVector* children = &node->v.element.children;
for (int i = 0; i < children->length; ++i) {
search_for_links(static_cast<GumboNode*>(children->data[i]));
}
}
//turn the output from libcurl in to a string
size_t write_to_string(void *ptr, size_t size, size_t count, void *stream) {
((string*)stream)->append((char*)ptr, 0, size*count);
return size*count;
}
int crawler(char url[60])
{
curl_global_init( CURL_GLOBAL_ALL );
CURL * myHandle = curl_easy_init ( );
//set the 'libcurl' parameters
curl_easy_setopt(myHandle, CURLOPT_USERAGENT, "Mozilla/5.0 (iPhone; U; CPU iPhone OS 3_0 like Mac OS X; en-us) AppleWebKit/528.18 (KHTML, like Gecko) Version/4.0 Mobile/7A341 Safari/528.16");
curl_easy_setopt(myHandle, CURLOPT_AUTOREFERER, 1 );
curl_easy_setopt(myHandle, CURLOPT_FOLLOWLOCATION, 1 );
curl_easy_setopt(myHandle, CURLOPT_COOKIEFILE, "");
//set the url
curl_easy_setopt(myHandle, CURLOPT_URL, url);
//turn the output in to a string using a function
string response;
curl_easy_setopt(myHandle, CURLOPT_WRITEFUNCTION, write_to_string);
curl_easy_setopt(myHandle, CURLOPT_WRITEDATA, &response);
curl_easy_perform( myHandle );
//HTML parsing
GumboOutput* output = gumbo_parse(response.c_str());
search_for_links(output->root);
return 0;
}
int main()
{
crawler("http://wikipedia.org");
return 0;
}