diff --git a/pom.xml b/pom.xml
index c4d09052..bbb9761a 100644
--- a/pom.xml
+++ b/pom.xml
@@ -344,6 +344,29 @@
         <artifactId>build-helper-maven-plugin</artifactId>
         <version>${build-helper.plugin.version}</version>
       </plugin>
+
+      <!-- this is to create a zip of PySpark modules -->
+      <plugin>
+        <artifactId>maven-assembly-plugin</artifactId>
+        <version>2.6</version>
+        <configuration>
+          <descriptors>
+            <descriptor>src/main/assembly/python.xml</descriptor>
+          </descriptors>
+          <finalName>aut</finalName>
+          <appendAssemblyId>false</appendAssemblyId>
+        </configuration>
+        <executions>
+          <execution>
+            <id>make-assembly</id>
+            <phase>package</phase>
+            <goals>
+              <goal>single</goal>
+            </goals>
+          </execution>
+        </executions>
+      </plugin>
+
     </plugins>
   </build>
 
diff --git a/src/main/assembly/python.xml b/src/main/assembly/python.xml
new file mode 100644
index 00000000..57b09aef
--- /dev/null
+++ b/src/main/assembly/python.xml
@@ -0,0 +1,13 @@
+<assembly xmlns="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://maven.apache.org/plugins/maven-assembly-plugin/assembly/1.1.0 http://maven.apache.org/xsd/assembly-1.1.0.xsd">
+  <id>python</id>
+  <formats>
+    <format>zip</format>
+  </formats>
+  <fileSets>
+    <fileSet>
+      <directory>src/main/python/aut/</directory>
+      <outputDirectory>/</outputDirectory>
+    </fileSet>
+  </fileSets>
+</assembly>
diff --git a/src/main/python/aut/__init__.py b/src/main/python/aut/__init__.py
new file mode 100644
index 00000000..18028104
--- /dev/null
+++ b/src/main/python/aut/__init__.py
@@ -0,0 +1,5 @@
+from aut.common import WebArchive
+from aut.udfs import extract_domain
+
+__all__ = ['WebArchive', 'extract_domain']
+
diff --git a/src/main/python/aut/common.py b/src/main/python/aut/common.py
new file mode 100644
index 00000000..1c053a4c
--- /dev/null
+++ b/src/main/python/aut/common.py
@@ -0,0 +1,15 @@
+from pyspark.sql import DataFrame
+
+class WebArchive:
+    def __init__(self, sc, sqlContext, path):
+        self.sc = sc
+        self.sqlContext = sqlContext
+        self.loader = sc._jvm.io.archivesunleashed.DataFrameLoader(sc._jsc.sc())
+        self.path = path
+
+    def pages(self):
+        return DataFrame(self.loader.extractValidPages(self.path), self.sqlContext)
+
+    def links(self):
+        return DataFrame(self.loader.extractHyperlinks(self.path), self.sqlContext)
+
diff --git a/src/main/python/aut/udfs.py b/src/main/python/aut/udfs.py
new file mode 100644
index 00000000..eab46e55
--- /dev/null
+++ b/src/main/python/aut/udfs.py
@@ -0,0 +1,11 @@
+from pyspark.sql.functions import udf
+from pyspark.sql.types import StringType
+
+def extract_domain_func(url):
+    url = url.replace('http://', '').replace('https://', '')
+    if '/' in url:
+        return url.split('/')[0].replace('www.', '')
+    else:
+        return url.replace('www.', '')
+
+extract_domain = udf(extract_domain_func, StringType())
diff --git a/src/main/scala/io/archivesunleashed/DataFrameLoader.scala b/src/main/scala/io/archivesunleashed/DataFrameLoader.scala
new file mode 100644
index 00000000..95f2cc2e
--- /dev/null
+++ b/src/main/scala/io/archivesunleashed/DataFrameLoader.scala
@@ -0,0 +1,16 @@
+package io.archivesunleashed
+
+import org.apache.spark.SparkContext
+import org.apache.spark.sql._
+
+class DataFrameLoader(sc: SparkContext) {
+  def extractValidPages(path: String): DataFrame = {
+    RecordLoader.loadArchives(path, sc)
+      .extractValidPagesDF()
+  }
+
+  def extractHyperlinks(path: String): DataFrame = {
+    RecordLoader.loadArchives(path, sc)
+      .extractHyperlinksDF()
+  }
+}