diff options
author | Kirill Volinsky <mataes2007@gmail.com> | 2013-11-10 18:02:01 +0000 |
---|---|---|
committer | Kirill Volinsky <mataes2007@gmail.com> | 2013-11-10 18:02:01 +0000 |
commit | ac48668a549fe76648e0ac3f93c9943383e043f5 (patch) | |
tree | bcfcf258bd003db20b1ee41fbbff173c8f340031 /plugins/FTPFileYM/curl/docs/examples/htmltidy.c | |
parent | 64e1340acd813704c9e9009b0a4e6fc9a3fb5adf (diff) |
curl folder renamed
git-svn-id: http://svn.miranda-ng.org/main/trunk@6858 1316c22d-e87f-b044-9b9b-93d7a3e3ba9c
Diffstat (limited to 'plugins/FTPFileYM/curl/docs/examples/htmltidy.c')
-rw-r--r-- | plugins/FTPFileYM/curl/docs/examples/htmltidy.c | 130 |
1 files changed, 130 insertions, 0 deletions
diff --git a/plugins/FTPFileYM/curl/docs/examples/htmltidy.c b/plugins/FTPFileYM/curl/docs/examples/htmltidy.c new file mode 100644 index 0000000000..a36e331bfe --- /dev/null +++ b/plugins/FTPFileYM/curl/docs/examples/htmltidy.c @@ -0,0 +1,130 @@ +/*************************************************************************** + * _ _ ____ _ + * 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. + * + ***************************************************************************/ +/* Download a document and use libtidy to parse the HTML. + * Written by Jeff Pohlmeyer + * + * LibTidy => http://tidy.sourceforge.net + * + * gcc -Wall -I/usr/local/include tidycurl.c -lcurl -ltidy -o tidycurl + * + */ + +#include <stdio.h> +#include <tidy/tidy.h> +#include <tidy/buffio.h> +#include <curl/curl.h> + +/* curl write callback, to fill tidy's input buffer... */ +uint write_cb(char *in, uint size, uint nmemb, TidyBuffer *out) +{ + uint r; + r = size * nmemb; + tidyBufAppend( out, in, r ); + return(r); +} + +/* Traverse the document tree */ +void dumpNode(TidyDoc doc, TidyNode tnod, int indent ) +{ + TidyNode child; + for ( child = tidyGetChild(tnod); child; child = tidyGetNext(child) ) + { + ctmbstr name = tidyNodeGetName( child ); + if ( name ) + { + /* if it has a name, then it's an HTML tag ... */ + TidyAttr attr; + printf( "%*.*s%s ", indent, indent, "<", name); + /* walk the attribute list */ + for ( attr=tidyAttrFirst(child); attr; attr=tidyAttrNext(attr) ) { + printf(tidyAttrName(attr)); + tidyAttrValue(attr)?printf("=\"%s\" ", + tidyAttrValue(attr)):printf(" "); + } + printf( ">\n"); + } + else { + /* if it doesn't have a name, then it's probably text, cdata, etc... */ + TidyBuffer buf; + tidyBufInit(&buf); + tidyNodeGetText(doc, child, &buf); + printf("%*.*s\n", indent, indent, buf.bp?(char *)buf.bp:""); + tidyBufFree(&buf); + } + dumpNode( doc, child, indent + 4 ); /* recursive */ + } +} + + +int main(int argc, char **argv ) +{ + CURL *curl; + char curl_errbuf[CURL_ERROR_SIZE]; + TidyDoc tdoc; + TidyBuffer docbuf = {0}; + TidyBuffer tidy_errbuf = {0}; + int err; + if ( argc == 2) { + curl = curl_easy_init(); + curl_easy_setopt(curl, CURLOPT_URL, argv[1]); + curl_easy_setopt(curl, CURLOPT_ERRORBUFFER, curl_errbuf); + curl_easy_setopt(curl, CURLOPT_NOPROGRESS, 0L); + curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L); + curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb); + + tdoc = tidyCreate(); + tidyOptSetBool(tdoc, TidyForceOutput, yes); /* try harder */ + tidyOptSetInt(tdoc, TidyWrapLen, 4096); + tidySetErrorBuffer( tdoc, &tidy_errbuf ); + tidyBufInit(&docbuf); + + curl_easy_setopt(curl, CURLOPT_WRITEDATA, &docbuf); + err=curl_easy_perform(curl); + if ( !err ) { + err = tidyParseBuffer(tdoc, &docbuf); /* parse the input */ + if ( err >= 0 ) { + err = tidyCleanAndRepair(tdoc); /* fix any problems */ + if ( err >= 0 ) { + err = tidyRunDiagnostics(tdoc); /* load tidy error buffer */ + if ( err >= 0 ) { + dumpNode( tdoc, tidyGetRoot(tdoc), 0 ); /* walk the tree */ + fprintf(stderr, "%s\n", tidy_errbuf.bp); /* show errors */ + } + } + } + } + else + fprintf(stderr, "%s\n", curl_errbuf); + + /* clean-up */ + curl_easy_cleanup(curl); + tidyBufFree(&docbuf); + tidyBufFree(&tidy_errbuf); + tidyRelease(tdoc); + return(err); + + } + else + printf( "usage: %s <url>\n", argv[0] ); + + return(0); +} |