1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313
|
/***************************************************************************
* _ _ ____ _
* Project ___| | | | _ \| |
* / __| | | | |_) | |
* | (__| |_| | _ <| |___
* \___|\___/|_| \_\_____|
*
* Copyright (C) 1998 - 2011, Daniel Stenberg, <daniel@haxx.se>, et al.
*
* This software is licensed as described in the file COPYING, which
* you should have received as part of this distribution. The terms
* are also available at http://curl.haxx.se/docs/copyright.html.
*
* You may opt to use, copy, modify, merge, publish, distribute and/or sell
* copies of the Software, and permit persons to whom the Software is
* furnished to do so, under the terms of the COPYING file.
*
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
***************************************************************************/
// Get a web page, parse it with libxml.
//
// Written by Lars Nilsson
//
// GNU C++ compile command line suggestion (edit paths accordingly):
//
// g++ -Wall -I/opt/curl/include -I/opt/libxml/include/libxml2 htmltitle.cpp \
// -o htmltitle -L/opt/curl/lib -L/opt/libxml/lib -lcurl -lxml2
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <string>
#include <curl/curl.h>
#include <libxml/HTMLparser.h>
//
// 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 = (Context *)voidContext;
if (COMPARE((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 = (Context *)voidContext;
if (COMPARE((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((char *)chars, length);
}
//
// libxml PCDATA callback function
//
static void Characters(void *voidContext,
const xmlChar *chars,
int length)
{
Context *context = (Context *)voidContext;
handleCharacters(context, chars, length);
}
//
// libxml CDATA callback function
//
static void cdata(void *voidContext,
const xmlChar *chars,
int length)
{
Context *context = (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;
}
|