Mercurial > hgrepos > Python2 > PyMuPDF
comparison mupdf-source/thirdparty/curl/docs/examples/htmltidy.c @ 2:b50eed0cc0ef upstream
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4.
The directory name has changed: no version number in the expanded directory now.
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Mon, 15 Sep 2025 11:43:07 +0200 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| 1:1d09e1dec1d9 | 2:b50eed0cc0ef |
|---|---|
| 1 /*************************************************************************** | |
| 2 * _ _ ____ _ | |
| 3 * Project ___| | | | _ \| | | |
| 4 * / __| | | | |_) | | | |
| 5 * | (__| |_| | _ <| |___ | |
| 6 * \___|\___/|_| \_\_____| | |
| 7 * | |
| 8 * Copyright (C) 1998 - 2017, Daniel Stenberg, <daniel@haxx.se>, 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 /* <DESC> | |
| 23 * Download a document and use libtidy to parse the HTML. | |
| 24 * </DESC> | |
| 25 */ | |
| 26 /* | |
| 27 * LibTidy => https://www.html-tidy.org/ | |
| 28 */ | |
| 29 | |
| 30 #include <stdio.h> | |
| 31 #include <tidy.h> | |
| 32 #include <tidybuffio.h> | |
| 33 #include <curl/curl.h> | |
| 34 | |
| 35 /* curl write callback, to fill tidy's input buffer... */ | |
| 36 uint write_cb(char *in, uint size, uint nmemb, TidyBuffer *out) | |
| 37 { | |
| 38 uint r; | |
| 39 r = size * nmemb; | |
| 40 tidyBufAppend(out, in, r); | |
| 41 return r; | |
| 42 } | |
| 43 | |
| 44 /* Traverse the document tree */ | |
| 45 void dumpNode(TidyDoc doc, TidyNode tnod, int indent) | |
| 46 { | |
| 47 TidyNode child; | |
| 48 for(child = tidyGetChild(tnod); child; child = tidyGetNext(child) ) { | |
| 49 ctmbstr name = tidyNodeGetName(child); | |
| 50 if(name) { | |
| 51 /* if it has a name, then it's an HTML tag ... */ | |
| 52 TidyAttr attr; | |
| 53 printf("%*.*s%s ", indent, indent, "<", name); | |
| 54 /* walk the attribute list */ | |
| 55 for(attr = tidyAttrFirst(child); attr; attr = tidyAttrNext(attr) ) { | |
| 56 printf(tidyAttrName(attr)); | |
| 57 tidyAttrValue(attr)?printf("=\"%s\" ", | |
| 58 tidyAttrValue(attr)):printf(" "); | |
| 59 } | |
| 60 printf(">\n"); | |
| 61 } | |
| 62 else { | |
| 63 /* if it doesn't have a name, then it's probably text, cdata, etc... */ | |
| 64 TidyBuffer buf; | |
| 65 tidyBufInit(&buf); | |
| 66 tidyNodeGetText(doc, child, &buf); | |
| 67 printf("%*.*s\n", indent, indent, buf.bp?(char *)buf.bp:""); | |
| 68 tidyBufFree(&buf); | |
| 69 } | |
| 70 dumpNode(doc, child, indent + 4); /* recursive */ | |
| 71 } | |
| 72 } | |
| 73 | |
| 74 | |
| 75 int main(int argc, char **argv) | |
| 76 { | |
| 77 if(argc == 2) { | |
| 78 CURL *curl; | |
| 79 char curl_errbuf[CURL_ERROR_SIZE]; | |
| 80 TidyDoc tdoc; | |
| 81 TidyBuffer docbuf = {0}; | |
| 82 TidyBuffer tidy_errbuf = {0}; | |
| 83 int err; | |
| 84 | |
| 85 curl = curl_easy_init(); | |
| 86 curl_easy_setopt(curl, CURLOPT_URL, argv[1]); | |
| 87 curl_easy_setopt(curl, CURLOPT_ERRORBUFFER, curl_errbuf); | |
| 88 curl_easy_setopt(curl, CURLOPT_NOPROGRESS, 0L); | |
| 89 curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L); | |
| 90 curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_cb); | |
| 91 | |
| 92 tdoc = tidyCreate(); | |
| 93 tidyOptSetBool(tdoc, TidyForceOutput, yes); /* try harder */ | |
| 94 tidyOptSetInt(tdoc, TidyWrapLen, 4096); | |
| 95 tidySetErrorBuffer(tdoc, &tidy_errbuf); | |
| 96 tidyBufInit(&docbuf); | |
| 97 | |
| 98 curl_easy_setopt(curl, CURLOPT_WRITEDATA, &docbuf); | |
| 99 err = curl_easy_perform(curl); | |
| 100 if(!err) { | |
| 101 err = tidyParseBuffer(tdoc, &docbuf); /* parse the input */ | |
| 102 if(err >= 0) { | |
| 103 err = tidyCleanAndRepair(tdoc); /* fix any problems */ | |
| 104 if(err >= 0) { | |
| 105 err = tidyRunDiagnostics(tdoc); /* load tidy error buffer */ | |
| 106 if(err >= 0) { | |
| 107 dumpNode(tdoc, tidyGetRoot(tdoc), 0); /* walk the tree */ | |
| 108 fprintf(stderr, "%s\n", tidy_errbuf.bp); /* show errors */ | |
| 109 } | |
| 110 } | |
| 111 } | |
| 112 } | |
| 113 else | |
| 114 fprintf(stderr, "%s\n", curl_errbuf); | |
| 115 | |
| 116 /* clean-up */ | |
| 117 curl_easy_cleanup(curl); | |
| 118 tidyBufFree(&docbuf); | |
| 119 tidyBufFree(&tidy_errbuf); | |
| 120 tidyRelease(tdoc); | |
| 121 return err; | |
| 122 | |
| 123 } | |
| 124 else | |
| 125 printf("usage: %s <url>\n", argv[0]); | |
| 126 | |
| 127 return 0; | |
| 128 } |
