mirror of
https://github.com/moparisthebest/curl
synced 2024-11-14 05:25:06 -05:00
3a6563d668
All plain C examples now (mostly) adhere to the curl code style. While they are only examples, they had diverted so much and contained all sorts of different mixed code styles by now. Having them use a unified style helps users and readability. Also, as they get copy-and-pasted widely by users, making sure they're clean and nice is a good idea. 573 checksrc warnings were addressed.
87 lines
2.6 KiB
C
87 lines
2.6 KiB
C
/***************************************************************************
|
|
* _ _ ____ _
|
|
* Project ___| | | | _ \| |
|
|
* / __| | | | |_) | |
|
|
* | (__| |_| | _ <| |___
|
|
* \___|\___/|_| \_\_____|
|
|
*
|
|
* Copyright (C) 2012 - 2016, 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 https://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.
|
|
*
|
|
***************************************************************************/
|
|
|
|
/* <DESC>
|
|
* Uses the "Streaming HTML parser" to extract the href pieces in a streaming
|
|
* manner from a downloaded HTML.
|
|
* </DESC>
|
|
*/
|
|
/*
|
|
* The HTML parser is found at http://code.google.com/p/htmlstreamparser/
|
|
*/
|
|
|
|
#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;
|
|
for(p = 0; p < realsize; p++) {
|
|
html_parser_char_parse(hsp, ((char *)buffer)[p]);
|
|
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)) {
|
|
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;
|
|
|
|
if(argc != 2) {
|
|
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);
|
|
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
|
|
|
|
curl_easy_perform(curl);
|
|
|
|
curl_easy_cleanup(curl);
|
|
|
|
html_parser_cleanup(hsp);
|
|
|
|
return EXIT_SUCCESS;
|
|
}
|