2012-10-18 10:45:51 -04:00
|
|
|
/***************************************************************************
|
|
|
|
* _ _ ____ _
|
|
|
|
* Project ___| | | | _ \| |
|
|
|
|
* / __| | | | |_) | |
|
|
|
|
* | (__| |_| | _ <| |___
|
|
|
|
* \___|\___/|_| \_\_____|
|
|
|
|
*
|
2020-11-05 02:22:10 -05:00
|
|
|
* Copyright (C) 2012 - 2020, Daniel Stenberg, <daniel@haxx.se>, et al.
|
2012-10-18 10:45:51 -04:00
|
|
|
*
|
|
|
|
* This software is licensed as described in the file COPYING, which
|
|
|
|
* you should have received as part of this distribution. The terms
|
2020-11-04 08:02:01 -05:00
|
|
|
* are also available at https://curl.se/docs/copyright.html.
|
2012-10-18 10:45:51 -04:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
***************************************************************************/
|
|
|
|
|
2015-06-18 05:38:54 -04:00
|
|
|
/* <DESC>
|
|
|
|
* Uses the "Streaming HTML parser" to extract the href pieces in a streaming
|
|
|
|
* manner from a downloaded HTML.
|
|
|
|
* </DESC>
|
|
|
|
*/
|
2012-10-18 10:45:51 -04:00
|
|
|
/*
|
2018-09-23 05:20:26 -04:00
|
|
|
* The HTML parser is found at https://github.com/arjunc77/htmlstreamparser
|
2012-10-18 10:45:51 -04:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <curl/curl.h>
|
|
|
|
#include <htmlstreamparser.h>
|
|
|
|
|
|
|
|
|
|
|
|
static size_t write_callback(void *buffer, size_t size, size_t nmemb,
|
|
|
|
void *hsp)
|
|
|
|
{
|
|
|
|
size_t realsize = size * nmemb, p;
|
2016-02-11 03:42:38 -05:00
|
|
|
for(p = 0; p < realsize; p++) {
|
2012-10-18 10:45:51 -04:00
|
|
|
html_parser_char_parse(hsp, ((char *)buffer)[p]);
|
2016-02-11 03:42:38 -05:00
|
|
|
if(html_parser_cmp_tag(hsp, "a", 1))
|
|
|
|
if(html_parser_cmp_attr(hsp, "href", 4))
|
|
|
|
if(html_parser_is_in(hsp, HTML_VALUE_ENDED)) {
|
2012-10-18 10:45:51 -04:00
|
|
|
html_parser_val(hsp)[html_parser_val_length(hsp)] = '\0';
|
|
|
|
printf("%s\n", html_parser_val(hsp));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return realsize;
|
|
|
|
}
|
|
|
|
|
|
|
|
int main(int argc, char *argv[])
|
|
|
|
{
|
|
|
|
char tag[1], attr[4], val[128];
|
|
|
|
CURL *curl;
|
|
|
|
HTMLSTREAMPARSER *hsp;
|
|
|
|
|
2016-02-11 03:42:38 -05:00
|
|
|
if(argc != 2) {
|
2012-10-18 10:45:51 -04:00
|
|
|
printf("Usage: %s URL\n", argv[0]);
|
|
|
|
return EXIT_FAILURE;
|
|
|
|
}
|
|
|
|
|
|
|
|
curl = curl_easy_init();
|
|
|
|
|
|
|
|
hsp = html_parser_init();
|
|
|
|
|
|
|
|
html_parser_set_tag_to_lower(hsp, 1);
|
|
|
|
html_parser_set_attr_to_lower(hsp, 1);
|
|
|
|
html_parser_set_tag_buffer(hsp, tag, sizeof(tag));
|
|
|
|
html_parser_set_attr_buffer(hsp, attr, sizeof(attr));
|
|
|
|
html_parser_set_val_buffer(hsp, val, sizeof(val)-1);
|
|
|
|
|
|
|
|
curl_easy_setopt(curl, CURLOPT_URL, argv[1]);
|
|
|
|
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_callback);
|
|
|
|
curl_easy_setopt(curl, CURLOPT_WRITEDATA, hsp);
|
2014-07-02 05:49:08 -04:00
|
|
|
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
|
2012-10-18 10:45:51 -04:00
|
|
|
|
|
|
|
curl_easy_perform(curl);
|
|
|
|
|
|
|
|
curl_easy_cleanup(curl);
|
|
|
|
|
|
|
|
html_parser_cleanup(hsp);
|
|
|
|
|
|
|
|
return EXIT_SUCCESS;
|
|
|
|
}
|