summaryrefslogtreecommitdiff
path: root/htroot/CrawlStartExpert.html
diff options
context:
space:
mode:
authorMichael Peter Christen <mc@yacy.net>2023-01-16 14:50:30 +0100
committerMichael Peter Christen <mc@yacy.net>2023-01-16 14:50:30 +0100
commit9fcd8f1bdac38beb18e00e7ed37c6532ea5bd416 (patch)
treed2328e22e15adde4b67cf40a0a880fdf107a20a1 /htroot/CrawlStartExpert.html
parent5a52b01c0995c439aee36c63ad0c75dca5ad20e1 (diff)
added canonical filter
attention: this is on by default! (it should do the right thing)
Diffstat (limited to 'htroot/CrawlStartExpert.html')
-rw-r--r--htroot/CrawlStartExpert.html5
1 files changed, 4 insertions, 1 deletions
diff --git a/htroot/CrawlStartExpert.html b/htroot/CrawlStartExpert.html
index c3e60c1b8..9917cd7e1 100644
--- a/htroot/CrawlStartExpert.html
+++ b/htroot/CrawlStartExpert.html
@@ -412,6 +412,9 @@
<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>
+ <tr>
+ <td colspan="2"><input type="checkbox" name="noindexWhenCanonicalUnequalURL" id="noindexWhenCanonicalUnequalURL" #(noindexWhenCanonicalUnequalURLChecked)#::checked="checked"#(/noindexWhenCanonicalUnequalURLChecked)#/> No Indexing when Canonical present and Canonical != URL</td>
+ </tr>
</table>
</dd>
<dt>Filter on Content of Document<br/>(all visible text, including camel-case-tokenized url and title)</dt>
@@ -470,7 +473,7 @@
<tr>
<td style="width:110px"><img src="env/grafics/minus.gif" alt=""> must-not-match</td>
<td>
- <input name="indexSolrQueryMustNotMatch" id="indexSolrQueryMustNotMatch" type="text" size="55" maxlength="100000" value="#[indexSolrQueryMustNotMatch]#" aria-describedby="indexSolrQueryInfo" />
+ <input name="indexSolrQueryMustNotMatch" id="indexSolrQueryMustNotMatch" type="text" size="55" maxlength="100000" value="#[indexSolrQueryMustNotMatch]#" aria-describedby="indexSolrQueryInfo" enabled="false"/>
</td>
</tr>
#(/embeddedSolrConnected)#