boxtec
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server
4
1
Fork 0
Code Issues Projects Releases Wiki Activity

Fixed CrawlStartExpert.html HTML validation errors

Browse Source 
Validated with Nu Html Checker 17.11.1
pull/167/head
luccioman 7 years ago
parent 519fc9a600
commit 7c644090ff
10 changed files with 41 additions and 29 deletions
Show Stats Download Patch File Download Diff File

59
htroot/CrawlStartExpert.html
Unescape View File

@ -1,5 +1,5 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >
<!DOCTYPE html>
<html lang="en">
<head>
<title>YaCy '#[clientname]#': Crawl Start</title>
#%env/templates/metas.template%#
@ -231,8 +231,8 @@
Each of these URLs are the root for a crawl start, existing start URLs are always re-loaded.
Other already visited URLs are sorted out as "double", if they are not allowed using the re-crawl option.
</span></span>
<input type="radio" align="top" name="crawlingMode" id="url" value="url" #(crawlingMode_url)#::checked="checked"#(/crawlingMode_url)# />
<textarea name="crawlingURL" id="crawlingURL" cols="64" rows="3" size="41" onkeypress="changed()">#[starturl]#</textarea>
<input type="radio" style="vertical-align: top" name="crawlingMode" id="url" value="url" #(crawlingMode_url)#::checked="checked"#(/crawlingMode_url)# />
<textarea name="crawlingURL" id="crawlingURL" cols="64" rows="3" onkeypress="changed()">#[starturl]#</textarea>
&nbsp;
<span id="robotsOK"></span>
<span id="title"><br/></span>
@ -247,7 +247,7 @@
<input type="radio" name="crawlingMode" id="sitelist" value="sitelist" #(has_url)#disabled="disabled"::#(/has_url)# #(crawlingMode_sitelist)#::checked="checked"#(/crawlingMode_sitelist)#/><br />
<div id="sitelistURLs"></div>
<button id="expandSiteListBtn" style="visibility:hidden" type="button" onclick="this.disabled = true;loadInfos(true);" class="btn btn-default btn-xs" title="Show all links">
<span class="glyphicon glyphicon-option-horizontal"/>
<span class="glyphicon glyphicon-option-horizontal"></span>
</button>
</dd>
<dt>From Sitemap</dt>
@ -293,7 +293,7 @@
<input name="crawlingDomMaxPages" id="crawlingDomMaxPages" type="text" size="6" maxlength="6" value="#[crawlingDomMaxPages]#" />
</dd>
<dt><label for="Constraints">misc. Constraints</label></dt>
<dt><label>misc. Constraints</label></dt>
<dd>
<span class="info" style="float:right"><img src="env/grafics/i16.gif" width="16" height="16" alt="info"/><span style="right:0px;">
A questionmark is usually a hint for a dynamic page. URLs pointing to dynamic content should usually not be crawled.
@ -311,25 +311,25 @@
The filter is a <b><a href="https://docs.oracle.com/javase/8/docs/api/java/util/regex/Pattern.html" target="_blank">regular expression</a></b>.
Example: to allow only urls that contain the word 'science', set the must-match filter to '.*science.*'.
You can also use an automatic domain-restriction to fully crawl a single domain.
Attention: you can test the functionality of your regular expressions using the <a href="RegexTest.html">Regular Expression Tester</a> within YaCy</a>.
Attention: you can test the functionality of your regular expressions using the <a href="RegexTest.html">Regular Expression Tester</a> within YaCy.
</span></span>
<table border="0">
<tr><td width="110"><img src="env/grafics/plus.gif"> must-match</td><td></td></tr>
<table style="border-width: 0px">
<tr><td style="width:110px"><img src="env/grafics/plus.gif" alt=""> must-match</td><td></td></tr>
<tr><td colspan="2"><input type="radio" name="range" id="rangeDomain" value="domain" #(range_domain)#::checked="checked"#(/range_domain)#/><div id="rangeDomainDescription" style="display:inline">Restrict to start domain(s)</div></td></tr>
<tr><td colspan="2"><input type="radio" name="range" id="rangeSubpath" value="subpath" #(range_subpath)#::checked="checked"#(/range_subpath)#/><div id="rangeSubpathDescription" style="display:inline">Restrict to sub-path(s)</div></td></tr>
<tr><td><input type="radio" name="range" id="rangeWide" value="wide" #(range_wide)#::checked="checked"#(/range_wide)#/>Use filter</td>
<td valign="bottom"><input name="mustmatch" id="mustmatch" type="text" size="55" maxlength="100000" value="#[mustmatch]#" onblur="if (this.value=='') this.value='.*';"/></td><td>(must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif"> must-not-match</td><td><input name="mustnotmatch" id="mustnotmatch" type="text" size="55" maxlength="100000" value="#[mustnotmatch]#" /></td></tr>
<td style="vertical-align: bottom"><input name="mustmatch" id="mustmatch" type="text" size="55" maxlength="100000" value="#[mustmatch]#" onblur="if (this.value=='') this.value='.*';"/> (must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif" alt=""> must-not-match</td><td><input name="mustnotmatch" id="mustnotmatch" type="text" size="55" maxlength="100000" value="#[mustnotmatch]#" /></td></tr>
</table>
</dd>
<dt>Load Filter on IPs</dt>
<dd>
<table border="0">
<tr><td width="110"><img src="env/grafics/plus.gif"> must-match</td><td><input name="ipMustmatch" id="ipMustmatch" type="text" size="55" maxlength="100000" value="#[ipMustmatch]#" onblur="if (this.value=='') this.value='.*';"/></td><td>(must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif"> must-not-match</td><td><input name="ipMustnotmatch" id="ipMustnotmatch" type="text" size="55" maxlength="100000" value="#[ipMustnotmatch]#" /></td></tr>
<table style="border-width: 0px">
<tr><td style="width:110px"><img src="env/grafics/plus.gif" alt=""> must-match</td><td><input name="ipMustmatch" id="ipMustmatch" type="text" size="55" maxlength="100000" value="#[ipMustmatch]#" onblur="if (this.value=='') this.value='.*';"/> (must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif" alt=""> must-not-match</td><td><input name="ipMustnotmatch" id="ipMustnotmatch" type="text" size="55" maxlength="100000" value="#[ipMustnotmatch]#" /></td></tr>
</table>
</dd>
<dt><label for="crawlingCountryMustMatch">Must-Match List for Country Codes</label>
<dt><label>Must-Match List for Country Codes</label>
</dt>
<dd><span class="info" style="float:right"><img src="env/grafics/i16.gif" width="16" height="16" alt="info"/><span style="right:0px;">
Crawls can be restricted to specific countries. This uses the country code that can be computed from
@ -350,18 +350,18 @@
<span class="info" style="float:right"><img src="env/grafics/i16.gif" width="16" height="16" alt="info"/><span style="right:0px;">
The filter is a <b><a href="https://docs.oracle.com/javase/8/docs/api/java/util/regex/Pattern.html" target="_blank">regular expression</a></b>
that <b>must not match</b> with the URLs to allow that the content of the url is indexed.
Attention: you can test the functionality of your regular expressions using the <a href="RegexTest.html">Regular Expression Tester</a> within YaCy</a>.
Attention: you can test the functionality of your regular expressions using the <a href="RegexTest.html">Regular Expression Tester</a> within YaCy.
</span></span>
<table border="0">
<tr><td width="110"><img src="env/grafics/plus.gif"> must-match</td><td><input name="indexmustmatch" id="indexmustmatch" type="text" size="55" maxlength="100000" value="#[indexmustmatch]#" onblur="if (this.value=='') this.value='.*';"/></td><td>(must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif"> must-not-match</td><td><input name="indexmustnotmatch" id="indexmustnotmatch" type="text" size="55" maxlength="100000" value="#[indexmustnotmatch]#" /></td></tr>
<table style="border-width: 0px">
<tr><td style="width:110px"><img src="env/grafics/plus.gif" alt=""> must-match</td><td><input name="indexmustmatch" id="indexmustmatch" type="text" size="55" maxlength="100000" value="#[indexmustmatch]#" onblur="if (this.value=='') this.value='.*';"/> (must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif" alt=""> must-not-match</td><td><input name="indexmustnotmatch" id="indexmustnotmatch" type="text" size="55" maxlength="100000" value="#[indexmustnotmatch]#" /></td></tr>
</table>
</dd>
<dt>Filter on Content of Document<br/>(all visible text, including camel-case-tokenized url and title)</dt>
<dd>
<table border="0">
<tr><td width="110"><img src="env/grafics/plus.gif"> must-match</td><td><input name="indexcontentmustmatch" id="indexcontentmustmatch" type="text" size="55" maxlength="100000" value="#[indexcontentmustmatch]#" onblur="if (this.value=='') this.value='.*';"/></td><td>(must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif"> must-not-match</td><td><input name="indexcontentmustnotmatch" id="indexcontentmustnotmatch" type="text" size="55" maxlength="100000" value="#[indexcontentmustnotmatch]#" /></td></tr>
<table style="border-width: 0px">
<tr><td style="width:110px"><img src="env/grafics/plus.gif" alt=""> must-match</td><td><input name="indexcontentmustmatch" id="indexcontentmustmatch" type="text" size="55" maxlength="100000" value="#[indexcontentmustmatch]#" onblur="if (this.value=='') this.value='.*';"/> (must not be empty)</td></tr>
<tr><td><img src="env/grafics/minus.gif" alt=""> must-not-match</td><td><input name="indexcontentmustnotmatch" id="indexcontentmustnotmatch" type="text" size="55" maxlength="100000" value="#[indexcontentmustnotmatch]#" /></td></tr>
</table>
</dd>
</dl>
@ -372,8 +372,8 @@
<dl>
<dt>Filter div class names</dt>
<dd>
<table border="0">
<tr><td width="110">set of CSS class names</td><td><input name="ignoreclassname" id="ignoreclassname" type="text" size="55" maxlength="100000" value="#[ignoreclassname]#" onblur="if (this.value=='') this.value='';"/></td><td>comma-separated list of &lt;div&gt; element class names which should be filtered out</td></tr>
<table style="border-width: 0px">
<tr><td style="width:110px">set of CSS class names</td><td><input name="ignoreclassname" id="ignoreclassname" type="text" size="55" maxlength="100000" value="#[ignoreclassname]#" onblur="if (this.value=='') this.value='';"/></td><td>comma-separated list of &lt;div&gt; element class names which should be filtered out</td></tr>
</table>
</dd>
</dl>
@ -512,7 +512,7 @@
<fieldset>
<legend>Snapshot Creation</legend>
<dl>
<dt><label for="snapshotMaxdepth">Max Depth for Snapshots</label></dt>
<dt><label>Max Depth for Snapshots</label></dt>
<dd>
<span class="info" style="float:right"><img src="env/grafics/i16.gif" width="16" height="16" alt="info"/><span style="right:0px;">
Snapshots are xml metadata and pictures of web pages that can be created during crawling time.
@ -523,16 +523,16 @@
</span></span>
<input type="text" name="snapshotsMaxDepth" id="snapshotsMaxDepth" size="2" maxlength="2" value="#[snapshotsMaxDepth]#" />
</dd>
<dt><label for="snapshotVersion">Multiple Snapshot Versions</label></dt>
<dt><label>Multiple Snapshot Versions</label></dt>
<dd>
<input type="radio" name="snapshotsReplaceOld" value="on" checked="checked"/> replace old snapshots with new one&nbsp;&nbsp;&nbsp;
<input type="radio" name="snapshotsReplaceOld" value="off" /> add new versions for each crawl
</dd>
<dt><label for="<label for="snapshotVersion">must-not-match filter for snapshot generation</label></dt>
<dt><label for="snapshotsMustnotmatch">must-not-match filter for snapshot generation</label></dt>
<dd><input name="snapshotsMustnotmatch" id="snapshotsMustnotmatch" type="text" size="55" maxlength="100000" value="#[snapshotsMustnotmatch]#" /></dd>
#(snapshotEnableImages)#
<input type="hidden" name="snapshotsLoadImage" id="snapshotsLoadImage" value="false"/>::
<dt><label for="snapshotImage">Image Creation</label></dt>
<dt><label>Image Creation</label></dt>
<dd>
<input type="checkbox" name="snapshotsLoadImage" id="snapshotsLoadImage"#(snapshotsLoadImageChecked)#:: checked="checked"#(/snapshotsLoadImageChecked)#/>
</dd>
@ -563,7 +563,7 @@
<strong>A YaCyNews message will be created to inform all peers about a global crawl</strong>,
so they can omit starting a crawl with the same start point.
</span></span>
<table border="0">
<table style="border-width: 0px">
<tr>
<td>
<input type="checkbox" name="crawlOrder" id="crawlOrder" #(crawlOrderChecked)#::checked="checked"#(/crawlOrderChecked)# />
@ -602,6 +602,7 @@
</dl>
</fieldset>
<dl>
<dt><input type="hidden" name="crawlingstart" value="1"/><input type="submit" value="Start New Crawl Job" class="btn btn-primary"/></dt><dd></dd>
</dl>
</fieldset>

1
locales/de.lng
Unescape View File

@ -1172,6 +1172,7 @@ Showing latest #[count]# lines from a stack of #[all]# entries.==Zeigt die letzt
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="de">
Expert Crawl Start==Experten Crawl Start
Start Crawling Job:==Starte Crawling Job:
You can define URLs as start points for Web page crawling and start crawling here.==Sie können hier URLs angeben, die gecrawlt werden sollen und dann das Crawling starten.

1
locales/fr.lng
Unescape View File

@ -832,6 +832,7 @@ Word-Hash:</td>==Mot-Hash:</td>
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="fr">
Index Creation==Cr&eacute;er un index
Start Crawling Job:==T&acirc;che de d&eacute;marrage du crawl:
You can define URLs as start points for Web page crawling and start crawling here. "Crawling" means that YaCy will download the given website, extract all links in it and then download the content behind these links. This is repeated as long as specified under "Crawling Depth".==Vous pouvez d&eacute;finir les URLs de d&eacute;part et d&eacute;marrer le crawl ici. Crawler signifie que YaCy t&eacute;l&eacute;chargera les sites de d&eacute;part et extraira tous leurs liens ainsi que leur contenu. Cela sera r&eacute;p&eacute;t&eacute; jusqu'a ce que la "profondeur de crawl" soit atteinte.

1
locales/hi.lng
Unescape View File

@ -943,6 +943,7 @@ Showing latest #[count]# lines from a stack of #[all]# entries.==नवीनत
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="hi">
Expert Crawl Start==विशेषज्ञ क्रॉल प्रारंभ
Start Crawling Job:==नौकरी रेंगने प्रारंभ:
You can define URLs as start points for Web page crawling and start crawling here. "Crawling" means that YaCy will download the given website, extract all links in it and then download the content behind these links. This is repeated as long as specified under "Crawling Depth".==आप वेब पेज रेंगने के लिए प्रारंभ बिंदु के रूप में यूआरएल को परिभाषित करने और यहां रेंगने शुरू कर सकते हैं. "क्रॉलिंग " YaCy, किसी वेबसाइट डाउनलोड कर इसमें सभी लिंक निकालें और फिर इन कड़ियों के पीछे सामग्री डाउनलोड जाएगा. लंबे समय के रूप में "क्रॉलिंग गहराई के तहत निर्दिष्ट के रूप में यह दोहराया है.

1
locales/ja.lng
Unescape View File

@ -755,6 +755,7 @@ Crawl Results<==クロールの結果<
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="ja">
Expert Crawl Start==エキスパート クロールの開始
Start Crawling Job:==クローリングのジョブを開始する:
>Crawl Job<==>クロール ジョブ<

3
locales/master.lng.xlf
Unescape View File

@ -3065,6 +3065,9 @@
<file original="CrawlStartExpert.html" source-language="en" datatype="html">
<body>
<trans-unit id="b3979711" xml:space="preserve" approved="no" translate="yes">
<source>&lt;html lang="en"&gt;</source>
</trans-unit>
<trans-unit id="51586213" xml:space="preserve" approved="no" translate="yes">
<source>Expert Crawl Start</source>
</trans-unit>

1
locales/ru.lng
Unescape View File

@ -1263,6 +1263,7 @@ Blacklist to use==Используется чёрный список
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="ru">
Expert Crawl Start==Расширенное индексирование
Start Crawling Job:==Запустить индексирование:
You can define URLs as start points for Web page crawling and start crawling here.==Здесь можете указать начальные ссылки и запустить индексирование.

1
locales/sk.lng
Unescape View File

@ -452,6 +452,7 @@ Word-Hash:</td>==Hash-slovo:</td>
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="sk">
Index Creation==Tvorba indexu
Start Crawling Job:==Odstartuj crawling:
You can define URLs as start points for Web page crawling and start crawling here. "Crawling" means that YaCy will download the given website, extract all links in it and then download the content behind these links. This is repeated as long as specified under "Crawling Depth".==Tu mozete zadat URL adresy web stranok ktore budu preliezane (crawled) a z ktorych sa preliezanie (crawling) odstartuje. "Crawling" znamena, ze YaCy siahne zvolenu web stranku, extrahuje vsetky odkazy a nasledne stiahne web stranky pod tymito odkazmi. Toto sa opakuje do hlbky zadanej v policku "Hlbka crawlingu".

1
locales/uk.lng
Unescape View File

@ -1025,6 +1025,7 @@ Initiator==Зачинщик
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="uk">
Crawl Start<==Запуск сканування<
Expert Crawl Start==Розширений запуск сканування
Start Crawling Job:==Завдання запуску сканування:

1
locales/zh.lng
Unescape View File

@ -1384,6 +1384,7 @@ Showing latest #[count]# lines from a stack of #[all]# entries.==显示栈中 #[
#File: CrawlStartExpert.html
#---------------------------
<html lang="en">==<html lang="zh">
Expert Crawl Start==Crawl高级设置
Start Crawling Job:==开始Crawl任务:
You can define URLs as start points for Web page crawling and start crawling here. "Crawling" means that YaCy will download the given website, extract all links in it and then download the content behind these links. This is repeated as long as specified under "Crawling Depth".==您可以将指定URL作为网页crawling的起始点. "Crawling"意即YaCy会下载指定的网站, 并解析出网站中链接的所有内容, 其深度由"Crawling深度"指定.

Write Preview
Loading…
Cancel
Save