| 1 |
/*************************************************************************** |
| 2 |
* _ _ ____ _ |
| 3 |
* Project ___| | | | _ \| | |
| 4 |
* / __| | | | |_) | | |
| 5 |
* | (__| |_| | _ <| |___ |
| 6 |
* \___|\___/|_| \_\_____| |
| 7 |
* |
| 8 |
* Copyright (C) 2012 - 2019, Daniel Stenberg, <[email protected]>, et al. |
| 9 |
* |
| 10 |
* This software is licensed as described in the file COPYING, which |
| 11 |
* you should have received as part of this distribution. The terms |
| 12 |
* are also available at https://curl.haxx.se/docs/copyright.html. |
| 13 |
* |
| 14 |
* You may opt to use, copy, modify, merge, publish, distribute and/or sell |
| 15 |
* copies of the Software, and permit persons to whom the Software is |
| 16 |
* furnished to do so, under the terms of the COPYING file. |
| 17 |
* |
| 18 |
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY |
| 19 |
* KIND, either express or implied. |
| 20 |
* |
| 21 |
***************************************************************************/ |
| 22 |
|
| 23 |
/* <DESC> |
| 24 |
* Uses the "Streaming HTML parser" to extract the href pieces in a streaming |
| 25 |
* manner from a downloaded HTML. |
| 26 |
* </DESC> |
| 27 |
*/ |
| 28 |
/* |
| 29 |
* The HTML parser is found at https://github.com/arjunc77/htmlstreamparser |
| 30 |
*/ |
| 31 |
|
| 32 |
#include <stdio.h> |
| 33 |
#include <curl/curl.h> |
| 34 |
#include <htmlstreamparser.h> |
| 35 |
|
| 36 |
|
| 37 |
static size_t write_callback(void *buffer, size_t size, size_t nmemb, |
| 38 |
void *hsp) |
| 39 |
{ |
| 40 |
size_t realsize = size * nmemb, p; |
| 41 |
for(p = 0; p < realsize; p++) { |
| 42 |
html_parser_char_parse(hsp, ((char *)buffer)[p]); |
| 43 |
if(html_parser_cmp_tag(hsp, "a", 1)) |
| 44 |
if(html_parser_cmp_attr(hsp, "href", 4)) |
| 45 |
if(html_parser_is_in(hsp, HTML_VALUE_ENDED)) { |
| 46 |
html_parser_val(hsp)[html_parser_val_length(hsp)] = '\0'; |
| 47 |
printf("%s\n", html_parser_val(hsp)); |
| 48 |
} |
| 49 |
} |
| 50 |
return realsize; |
| 51 |
} |
| 52 |
|
| 53 |
int main(int argc, char *argv[]) |
| 54 |
{ |
| 55 |
char tag[1], attr[4], val[128]; |
| 56 |
CURL *curl; |
| 57 |
HTMLSTREAMPARSER *hsp; |
| 58 |
|
| 59 |
if(argc != 2) { |
| 60 |
printf("Usage: %s URL\n", argv[0]); |
| 61 |
return EXIT_FAILURE; |
| 62 |
} |
| 63 |
|
| 64 |
curl = curl_easy_init(); |
| 65 |
|
| 66 |
hsp = html_parser_init(); |
| 67 |
|
| 68 |
html_parser_set_tag_to_lower(hsp, 1); |
| 69 |
html_parser_set_attr_to_lower(hsp, 1); |
| 70 |
html_parser_set_tag_buffer(hsp, tag, sizeof(tag)); |
| 71 |
html_parser_set_attr_buffer(hsp, attr, sizeof(attr)); |
| 72 |
html_parser_set_val_buffer(hsp, val, sizeof(val)-1); |
| 73 |
|
| 74 |
curl_easy_setopt(curl, CURLOPT_URL, argv[1]); |
| 75 |
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_callback); |
| 76 |
curl_easy_setopt(curl, CURLOPT_WRITEDATA, hsp); |
| 77 |
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L); |
| 78 |
|
| 79 |
curl_easy_perform(curl); |
| 80 |
|
| 81 |
curl_easy_cleanup(curl); |
| 82 |
|
| 83 |
html_parser_cleanup(hsp); |
| 84 |
|
| 85 |
return EXIT_SUCCESS; |
| 86 |
} |