digest-html | Converts HTML to plaintext-with-links. |
| download: http://git.y1.nz/archives/digest-html.tar.gz | |
| README | Files | Log | Refs |
test/2.html
1 <!DOCTYPE html>
2 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
3 <head>
4 <meta http-equiv="content-type" content="text/html; charset=utf-8" />
5 <link rel="author" href="mailto:webmasters@gnu.org" />
6 <link rel="icon" type="image/png" href="/graphics/gnu-head-mini.png" />
7 <meta name="ICBM" content="42.355469,-71.058627" />
8 <link rel="stylesheet" type="text/css" href="/layout.min.css" media="screen" />
9 <link rel="stylesheet" type="text/css" href="/print.min.css" media="print" />
10
11
12
13 <!-- Parent-Version: 1.79 -->
14 <title>Wget - GNU Project - Free Software Foundation</title>
15 <style type="text/css">
16 body ul#wget-feature-list {
17 padding-top: 0;
18 padding-bottom: 0;
19 margin-left: 2em;
20 }
21 ul#wget-feature-list li {
22 line-height: 1.2em;
23 margin-top: 0.5em;
24 margin-bottom: 0.5em;
25 padding-top: 0;
26 padding-bottom: 0;
27 }
28 </style>
29 <!-- begin /server/gnun/initial-translations-list.html -->
30 <!-- HTML head: set a flag for further expansion in body-include*.html. -->
31 <!-- end /server/gnun/initial-translations-list.html -->
32
33 <!-- start of server/banner.html -->
34 <!-- start of head-include-2.html -->
35 <meta name="viewport" content="width=device-width, initial-scale=1" />
36
37
38
39 <link rel="stylesheet" type="text/css" href="/server/banners/fundraiser.css" media="screen" />
40 <style type="text/css" media="screen"><!--
41 .progress-bar
42 {
43 width: 41%;
44 }
45 --></style>
46
47 <style type="text/css" media="screen">
48 <!-- TRANSLATORS: Change direction to rtl if you translate
49 the fundraiser and your script is right-to-left. -->
50 #fundraiser { direction: ltr; }
51 </style>
52 <!-- end of head-include-2.html -->
53
54 </head>
55 <body>
56 <div class="inner">
57 <!-- start of server/body-include-1.html -->
58 <div id="top">
59 <p><a class="skip" href="#content"><b>Skip to main text</b></a></p>
60 </div>
61 <div id='fundraiser'>
62 <div class="message">
63 <p class="headline"><b>Commit to freedom</b></p>
64 <p><a href="https://my.fsf.org/join?mtm_campaign=summer26&mtm_source=banner">
65 The FSF empowers users with <em>free software</em>, technology built
66 through global collaboration, mutual respect, and above all,
67 freedom. We won't be stopped: the FSF does not compromise when it
68 comes to your freedom. Commit to freedom. Join us by July 10
69 and help us reach our goal of 175 new associate members!
70 <span class="gnun-split"></span></a></p>
71 <p class="button"><a href="https://my.fsf.org/join?mtm_campaign=summer26&mtm_source=banner">Join<span class="gnun-split"></span></a> <a href="https://www.fsf.org/appeal?mtm_campaign=summer26&mtm_source=banner">Read more<span class="gnun-split"></span></a>
72 </p>
73 <div style="clear: both"></div>
74 </div><!-- .message -->
75 <div class="progress">
76 <div class="progress-bar"><span class="percentage">72</span></div>
77
78 <span class="goal">175<span class="gnun-split"></span>
79 </span>
80
81 </div><!-- .progress -->
82 </div><!-- #fundraiser -->
83 <div style="clear: both"></div>
84
85 <div id="header" role="banner">
86 <p id="gnu-banner">
87 <a href="/">
88 <img src="/graphics/heckert_gnu.transp.small.png" height="48" width="49"
89 alt=" [A GNU head] " /><strong>GNU</strong> <span
90 class="hide">Operating System</span></a><br />
91 <small id="fsf-support">Supported by the
92 <a href="#mission-statement">Free Software Foundation</a></small>
93 </p>
94
95 <div id="switches">
96 <!-- begin search button -->
97 <div id="search-button" class="switch">
98 <a href="//www.gnu.org/cgi-bin/estseek.cgi">
99 <img id="search-icon" height="30" width="30"
100 src="/graphics/icons/search.png"
101 alt=" [Search www.gnu.org] " /></a>
102 </div>
103 <!-- end search button -->
104
105 </div><!-- #switches -->
106 </div><!-- #header -->
107 <!-- end of server/body-include-1.html -->
108
109 <!-- start of server/body-include-2 -->
110
111
112 <div style="clear: both"></div>
113
114 <div id="navigation" role="navigation">
115 <a id="more-links" href="#navigation" title="More...">
116 <span>Site navigation</span></a>
117 <a id="less-links" href="#content"><b>Skip</b></a>
118 <ul>
119
120 <li id="tabAboutGNU"><a href="/gnu/gnu.html">ABOUT GNU</a></li>
121
122
123 <li id="tabPhilosophy"><a href="/philosophy/philosophy.html">PHILOSOPHY</a></li>
124
125
126 <li id="tabLicenses"><a href="/licenses/licenses.html">LICENSES</a></li>
127
128
129 <li id="tabEducation"><a href="/education/education.html">EDUCATION</a></li>
130
131
132 <li id="tabSoftware" class="active">
133 <span class='no-display'>=</span>
134 <a href="/software/software.html">SOFTWARE</a>
135 <span class="gnun-split"></span>
136 <span class='no-display'>=</span>
137 </li>
138
139
140 <li id="tabDistros"><a href="/distros/distros.html">DISTROS</a></li>
141
142
143 <li id="tabDoc"><a href="/doc/doc.html">DOCS</a></li>
144
145
146 <li id="tabMalware"><a href="/proprietary/proprietary.html">MALWARE</a></li>
147
148
149 <li id="tabHelp"><a href="/help/help.html">HELP GNU</a></li>
150
151
152 <li id="tabAV"><a href="/audio-video/audio-video.html">AUDIO & VIDEO</a></li>
153
154
155 <li id="tabArt"><a href="/graphics/graphics.html">GNU ART</a></li>
156
157
158 <li id="tabFun"><a href="/fun/humor.html">FUN</a></li>
159
160
161 <li id="tabPeople"><a href="/people/people.html">GNU'S WHO?</a></li>
162
163 <li><a href="//directory.fsf.org">SOFTWARE DIRECTORY</a></li>
164 <li><a href="https://h-node.org/">HARDWARE</a></li>
165 <li><a href="/server/sitemap.html">SITEMAP</a></li>
166 </ul>
167 <div style="clear: both"></div>
168 </div><!-- /"navigation -->
169 <!-- end of server/body-include-2 -->
170
171 <div id="content" role="main">
172
173
174 <!-- end of server/banner.html -->
175
176 <div class="reduced-width">
177
178 <h2>GNU Wget</h2>
179 <hr class="thin" />
180
181 <p>
182 GNU Wget is a <a href="/philosophy/free-sw">free software</a>
183 package for retrieving files using HTTP, HTTPS, FTP and FTPS, the most widely used
184 Internet protocols. It is a non-interactive commandline tool, so it may
185 easily be called from scripts, <code>cron</code> jobs, terminals without
186 X-Windows support, etc.
187 </p>
188
189 <p>
190 GNU Wget has many features to make retrieving large files or mirroring
191 entire web or FTP sites easy, including:
192 </p>
193
194 <ul id="wget-feature-list">
195 <li>Can resume aborted downloads, using <code>REST</code> and <code>RANGE</code></li>
196 <li>Can use filename wild cards and recursively mirror directories</li>
197 <li>NLS-based message files for many different languages</li>
198 <li>
199 Optionally converts absolute links in downloaded documents to relative,
200 so that downloaded documents may link to each other
201 locally
202 </li>
203 <li>Runs on most UNIX-like operating systems as well as Microsoft Windows</li>
204 <li>Supports HTTP proxies</li>
205 <li>Supports HTTP cookies</li>
206 <li>Supports persistent HTTP connections</li>
207 <li>Unattended / background operation</li>
208 <li>Uses local file timestamps to determine whether documents need to be re-downloaded when mirroring</li>
209 <li>GNU Wget is distributed under the <a href="/licenses/gpl.html">GNU General Public License</a>.</li>
210 </ul>
211
212
213 <h3>Downloading GNU Wget</h3>
214
215 <p>
216 The source code for GNU Wget can be found on the main <a
217 href="https://ftp.gnu.org/gnu/wget/">GNU download server</a> or (better)
218 on a <a href="http://ftpmirror.gnu.org/wget">GNU mirror</a> near you.<br />
219 For more download options, see the <a href="http://wget.addictivecode.org/FrequentlyAskedQuestions.html#download">FAQ</a>.
220 </p>
221
222
223 <h3>Documentation</h3>
224
225 <p>
226 <a href="/software/wget/manual/">GNU Wget documentation</a> is available online,
227 as are the <a href="/manual/">manuals of other GNU packages</a>.
228 </p>
229
230
231 <h3>Additional Information</h3>
232
233 <p>
234 Currently GNU Wget2 is being developed.<br />
235 Please help us if you can with testing, docs, organization, development, etc. See you at the <a href="https://gitlab.com/gnuwget/wget2">Wget2 collaboration site</a>.
236 </p>
237
238
239 <h3>Maintainer</h3>
240
241 <p>
242 GNU Wget is currently being maintained
243 by Tim Rühsen, Darshit Shah and <a href="https://www.scrivano.org">Giuseppe Scrivano</a>.<br />
244 The original author of GNU Wget is Hrvoje Nikšić.<br />
245 <strong>Please</strong> do <em>not</em> directly contact either of these
246 individuals with bug reports, or requests for help with Wget: that is
247 what the <a href="https://lists.gnu.org/mailman/listinfo/bug-wget">mailing
248 list</a> is for; please use it instead.
249 </p>
250
251 <h3>Donators</h3>
252
253 <p>
254 We thank the TYPO3 & Magento partner <a href="https://www.aoe.com/en">AOE media</a> for donating to the Wget project.
255 </p>
256
257 </div>
258 </div><!-- for id="content", starts in the include above -->
259
260 <!-- begin server/footer-text.html -->
261
262
263
264
265
266
267 <div style="clear:both"></div>
268
269
270
271 <div id="mission-statement" role="complementary">
272 <div class="backtotop">
273 <hr class="no-display" />
274 <a href="#header"><span>BACK TO TOP </span>▲</a>
275 </div>
276 <div style="clear: both"></div>
277 <blockquote>
278 <p style="direction:ltr; text-align:left"><a href="//www.fsf.org"><img id="fsfbanner"
279 src="/graphics/fsf-logo-notext-small.png" alt=" [FSF logo] "
280 width="75" height="25" /></a><strong>
281 “The Free Software Foundation (FSF) is a nonprofit with a worldwide
282 mission to promote computer user freedom. We defend the rights of all
283 software users.”</strong></p>
284 </blockquote>
285
286 <div id="support-the-fsf" class="button">
287 <a class="join" href="//www.fsf.org/associate/support_freedom?referrer=4052">JOIN</a>
288 <a class="donate" href="//donate.fsf.org/">DONATE</a>
289 <a class="shop" href="//shop.fsf.org/">SHOP</a>
290 </div>
291 </div>
292 <!-- end server/footer-text.html -->
293
294
295 <div id="footer">
296 <div class="unprintable">
297
298 <p>Please send general FSF & GNU inquiries to
299 <a href="mailto:gnu@gnu.org"><gnu@gnu.org></a>.
300 There are also <a href="/contact/">other ways to contact</a>
301 the FSF. Broken links and other corrections or suggestions can be sent
302 to <a href="mailto:bug-wget@gnu.org">bug-wget@gnu.org</a>.
303 </p>
304
305 <p>Please see the <a
306 href="/server/standards/README.translations.html">Translations
307 README</a> for information on coordinating and contributing translations
308 of this article.</p>
309 </div>
310
311 <!-- Regarding copyright, in general, standalone pages (as opposed to
312 files generated as part of manuals) on the GNU web server should
313 be under CC BY-ND 4.0. Please do NOT change or remove this
314 without talking with the webmasters or licensing team first.
315 Please make sure the copyright date is consistent with the
316 document. For web pages, it is ok to list just the latest year the
317 document was modified, or published.
318
319 If you wish to list earlier years, that is ok too.
320 Either "2001, 2002, 2003" or "2001-2003" are ok for specifying
321 years, as long as each year in the range is in fact a copyrightable
322 year, i.e., a year in which the document was published (including
323 being publicly visible on the web or in a revision control system).
324
325 There is more detail about copyright years in the GNU Maintainers
326 Information document, www.gnu.org/prep/maintain. -->
327
328 <p>Copyright © 2017 Free Software Foundation, Inc.</p>
329
330 <p>This page is licensed under a <a rel="license"
331 href="https://creativecommons.org/licenses/by-nd/4.0/">Creative
332 Commons Attribution-NoDerivatives 4.0 International License</a>.</p>
333
334 <!-- start of server/bottom-notes.html -->
335 <div id="bottom-notes" class="unprintable">
336 <p><a href="//www.fsf.org/about/dmca-notice">Copyright Infringement Notification</a></p>
337 <div id="generic">
338
339
340 </div>
341 </div>
342 <!-- end of server/bottom-notes.html -->
343
344
345 <p class="unprintable">Updated:
346 <!-- timestamp start -->
347 $Date: 2020/08/04 09:29:54 $
348 <!-- timestamp end -->
349 </p>
350 </div>
351 </div><!-- for class="inner", starts in the banner include -->
352 </body>
353 </html>
This webpage is intended to be an accessible preview of this repository. To get a fuller picture, clone it and use the git CLI.