Skip to content

Instantly share code, notes, and snippets.

<StartURL>
<url>http://www.yellowpages.com/san-francisco-ca/accountants?g=San+Francisco,+CA&amp;q=Accountants</url>
</StartURL>
<FieldList>
<DATAFIELD> Data Field #1 </DATAFIELD>
<DATAFIELD> Data Field #2 </DATAFIELD>
<DATAFIELD> Data Field #3 </DATAFIELD>
<!-- More Data Fields as required -->
</FieldList>
<?xml version="1.0"?>
<MineParams xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<!-- Configuration Details -->
</MineParams>
<DATAFIELD>
<type>Text</type>
<name>Name</name>
<selector>
#hotellist_inner &gt; DIV:nth-of-type(02) &gt; DIV:nth-of-type(2) &gt; DIV:nth-of-type(1) &gt; DIV:nth-of-type(1) &gt; DIV:nth-of-type(1) &gt; H3 &gt; A &gt; SPAN:nth-of-type(1)
</selector>
<heading />
<pattern>true</pattern>
<regex />
</DATAFIELD>
<CategoryList>
<URLDATA>
<name>URL1</name>
<url>http://www.url1.com/</url>
</URLDATA>
<URLDATA>
<name>URL2</name>
<url>http://www.url2.com/</url>
</URLDATA>
<CategoryList>
<URLDATA>
<name>URL1</name>
<url>http://www.url1.com</url>
</URLDATA>
<URLDATA>
<name>URL2</name>
<url>http://www.url2.com</url>
</URLDATA>
<URLDATA>
@sysnucleus
sysnucleus / WebHarvy Keyword List
Created July 1, 2014 11:32
WebHarvy Keyword List
<KeywordList>
<string>keyword1</string>
<string>keyword2</string>
<string>keyword3</string>
<!-- More keyword strings as required -->
</KeywordList>
@sysnucleus
sysnucleus / Sample Product Details Text
Last active August 29, 2015 14:24
RegEx sample Text
Product Details
Price: 99$
This product comes with absolutely no warranty . .
<address>
356, Street Name, City, Country
</address>
<div class="call-to-action ">
<a title="Website (opens in a new window)"
class="contact contact-main contact-url " href="http://www.canberraeyelaser.com.au" target="_blank" rel="nofollow">
<span class="glyph icon-website border border-dark-blue with-text"></span><span class="contact-text">Website</span>
</a>
</div>