mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
*) changed regex that is created for crawling filter (see http://forum.yacy-websuche.de/viewtopic.php?t=83)
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@3945 6c8d7289-2bf4-0310-a012-ef5d649a1542
This commit is contained in:
parent
28baecd41b
commit
51800539b2
|
@ -71,10 +71,10 @@
|
|||
</tr>
|
||||
<tr valign="top" class="TableCellDark">
|
||||
<td><label for="crawlingFilter">Crawling Filter</label>:</td>
|
||||
<td>
|
||||
<input name="crawlingFilter" id="crawlingFilter" type="text" size="20" maxlength="100" value="#[crawlingFilter]#" />
|
||||
<input type="button" value="only one domain" onclick='var domain=prompt("please enter domain without \"www.\" (i.e. \"yacy.net\").");if(domain!=null){document.getElementById("crawlingFilter").value=".*\\."+domain.replace("\.", "\\.")+"/.*"}' />
|
||||
</td>
|
||||
<td>
|
||||
<input name="crawlingFilter" id="crawlingFilter" type="text" size="20" maxlength="100" value="#[crawlingFilter]#" />
|
||||
<input type="button" value="only one domain" onclick='var domain=prompt("please enter domain without \"www.\" (i.e. \"yacy.net\").");if(domain!=null){document.getElementById("crawlingFilter").value="(^|.*\\.)"+domain.replace("\.", "\\.")+"/.*"}' />
|
||||
</td>
|
||||
<td>
|
||||
This is an emacs-like regular expression that must match with the URLs which are used to be crawled.
|
||||
Use this i.e. to crawl a single domain. If you set this filter it makes sense to increase
|
||||
|
@ -216,7 +216,7 @@
|
|||
<td colspan="5"><input type="submit" name="crawlingstart" value="Start New Crawl" /></td>
|
||||
</tr>
|
||||
</table>
|
||||
</form>
|
||||
</form>
|
||||
|
||||
#%env/templates/footer.template%#
|
||||
</body>
|
||||
|
|
Loading…
Reference in New Issue
Block a user