Getting Started
with WebHarvest

# Download from SourceForge
# Extract the ZIP file
unzip webharvest-2.2.0.zip

# Navigate to CLI directory
cd webharvest-cli

# Verify installation
java -jar webharvest-cli-2.2.0.jar --version
# Output: WebHarvest v2.2.0

<?xml version="1.0" encoding="UTF-8"?>
<config xmlns="http://org.webharvest/schema/2.1/core">

    <!-- Step 1: Fetch the webpage -->
    <def var="html">
        <http url="https://example.com"/>
    </def>

    <!-- Step 2: Convert HTML to XML for parsing -->
    <def var="page">
        <html-to-xml>
            <get var="html"/>
        </html-to-xml>
    </def>

    <!-- Step 3: Extract the title -->
    <def var="title">
        <xpath expression="//title/text()">
            <get var="page"/>
        </xpath>
    </def>

    <!-- Step 4: Extract first paragraph -->
    <def var="firstPara">
        <xpath expression="//p[1]/text()">
            <get var="page"/>
        </xpath>
    </def>

    <!-- Step 5: Save results to file -->
    <file action="write" path="results.txt">
        Title: ${title}
        
        First Paragraph: ${firstPara}
    </file>

    <!-- Step 6: Print to console -->
    <template>
        ✅ Scraping complete!
        Title: ${title}
    </template>

</config>

# Run the scraper
java -jar webharvest-cli-2.2.0.jar my-first-scraper.xml

# Expected output:
# ✅ Scraping complete!
# Title: Example Domain

# Check the results file
cat results.txt

# Output:
# Title: Example Domain
# 
# First Paragraph: This domain is for use in illustrative examples...