vs2022 c++使用curl+libxml2庫獲取網站標題demo

開發環境 windows10 64位

  • 首先需要安裝vcpkg工具。 開始使用 vcpkg
  • 創建項目
  • 打開CMD進行安裝curllibxml2
vcpkg install curl:x64-windows
vcpkg install libxml2:x64-windows
  • 安裝完成后執行vcpkg integrate install,讓vs2022可以識別該lib庫。
  • 先填一下坑,使用VS2022,打開X:\vcpkg\vcpkg\installed\x64-windows\include\iconv.h文件,然后Ctrl+A全選代碼,菜單文件->iconv.h 另存為-> 選擇編碼保存->選擇UNICODE 代碼頁 1200 確定保存。
    編碼保存
UNICODE 代碼頁 1200
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <string>
#include<curl/curl.h>
#include <libxml/HTMLparser.h>

# pragma warning (disable:4819)

//
//  Case-insensitive string comparison
//

#ifdef _MSC_VER
#define COMPARE(a, b) (!_stricmp((a), (b)))
#else
#define COMPARE(a, b) (!strcasecmp((a), (b)))
#endif

//
//  libxml callback context structure
//

struct Context
{
    Context() : addTitle(false) { }

    bool addTitle;
    std::string title;
};

//
//  libcurl variables for error strings and returned data

static char errorBuffer[CURL_ERROR_SIZE];
static std::string buffer;

//
//  libcurl write callback function
//

static int writer(char* data, size_t size, size_t nmemb,
    std::string* writerData)
{
    if (writerData == NULL)
        return 0;

    writerData->append(data, size * nmemb);

    return size * nmemb;
}

//
//  libcurl connection initialization
//

static bool init(CURL*& conn, char* url)
{
    CURLcode code;

    conn = curl_easy_init();

    if (conn == NULL) {
        fprintf(stderr, "Failed to create CURL connection\n");
        exit(EXIT_FAILURE);
    }

    code = curl_easy_setopt(conn, CURLOPT_ERRORBUFFER, errorBuffer);
    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to set error buffer [%d]\n", code);
        return false;
    }

    code = curl_easy_setopt(conn, CURLOPT_URL, url);
    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to set URL [%s]\n", errorBuffer);
        return false;
    }

    code = curl_easy_setopt(conn, CURLOPT_FOLLOWLOCATION, 1L);
    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to set redirect option [%s]\n", errorBuffer);
        return false;
    }

    code = curl_easy_setopt(conn, CURLOPT_WRITEFUNCTION, writer);
    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to set writer [%s]\n", errorBuffer);
        return false;
    }

    code = curl_easy_setopt(conn, CURLOPT_WRITEDATA, &buffer);
    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to set write data [%s]\n", errorBuffer);
        return false;
    }

    return true;
}

//
//  libxml start element callback function
//

static void StartElement(void* voidContext,
    const xmlChar* name,
    const xmlChar** attributes)
{
    Context* context = static_cast<Context*>(voidContext);

    if (COMPARE(reinterpret_cast<const char*>(name), "TITLE")) {
        context->title = "";
        context->addTitle = true;
    }
    (void)attributes;
}

//
//  libxml end element callback function
//

static void EndElement(void* voidContext,
    const xmlChar* name)
{
    Context* context = static_cast<Context*>(voidContext);

    if (COMPARE(reinterpret_cast<const char*>(name), "TITLE"))
        context->addTitle = false;
}

//
//  Text handling helper function
//

static void handleCharacters(Context* context,
    const xmlChar* chars,
    int length)
{
    if (context->addTitle)
        context->title.append(reinterpret_cast<const char*>(chars), length);
}

//
//  libxml PCDATA callback function
//

static void Characters(void* voidContext,
    const xmlChar* chars,
    int length)
{
    Context* context = static_cast<Context*>(voidContext);

    handleCharacters(context, chars, length);
}

//
//  libxml CDATA callback function
//

static void cdata(void* voidContext,
    const xmlChar* chars,
    int length)
{
    Context* context = static_cast<Context*>(voidContext);

    handleCharacters(context, chars, length);
}

//
//  libxml SAX callback structure
//

static htmlSAXHandler saxHandler =
{
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  StartElement,
  EndElement,
  NULL,
  Characters,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  NULL,
  cdata,
  NULL
};

//
//  Parse given (assumed to be) HTML text and return the title
//

static void parseHtml(const std::string& html,
    std::string& title)
{
    htmlParserCtxtPtr ctxt;
    Context context;

    ctxt = htmlCreatePushParserCtxt(&saxHandler, &context, "", 0, "",
        XML_CHAR_ENCODING_NONE);

    htmlParseChunk(ctxt, html.c_str(), html.size(), 0);
    htmlParseChunk(ctxt, "", 0, 1);

    htmlFreeParserCtxt(ctxt);

    title = context.title;
}

int main(int argc, char* argv[])
{
    CURL* conn = NULL;
    CURLcode code;
    std::string title;

    // Ensure one argument is given

    if (argc != 2) {
        fprintf(stderr, "Usage: %s <url>\n", argv[0]);
        exit(EXIT_FAILURE);
    }

    curl_global_init(CURL_GLOBAL_DEFAULT);

    // Initialize CURL connection

    if (!init(conn, argv[1])) {
        fprintf(stderr, "Connection initializion failed\n");
        exit(EXIT_FAILURE);
    }

    // Retrieve content for the URL

    code = curl_easy_perform(conn);
    curl_easy_cleanup(conn);

    if (code != CURLE_OK) {
        fprintf(stderr, "Failed to get '%s' [%s]\n", argv[1], errorBuffer);
        exit(EXIT_FAILURE);
    }

    // Parse the (assumed) HTML code
    parseHtml(buffer, title);

    // Display the extracted title
    printf("Title: %s\n", title.c_str());

    return EXIT_SUCCESS;
}

項目->屬性->如下圖設置。關閉所有警告

關閉所有警告

  • 測試結果


    測試結果
?著作權歸作者所有,轉載或內容合作請聯系作者
平臺聲明:文章內容(如有圖片或視頻亦包括在內)由作者上傳并發布,文章內容僅代表作者本人觀點,簡書系信息發布平臺,僅提供信息存儲服務。

推薦閱讀更多精彩內容