added week-05

Author: jsheedy

week-05/serialization_XML/examples/badpicklemodule.py

@@ -0,0 +1,6 @@
+
+def foo():
+    def bar():
+        return 2
+
+    return bar

week-05/serialization_XML/examples/billion_lolz.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python
+
+import bz2
+from xml.dom import minidom 
+
+if __name__ == "__main__":
+    fname = "data/billion_lolz.xml"
+
+    doc = minidom.parse(fname)

week-05/serialization_XML/examples/data/billion_lolz.xml

@@ -0,0 +1,15 @@
+<?xml version="1.0"?>
+<!DOCTYPE lolz [
+ <!ENTITY lol "lol">
+ <!ELEMENT lolz (#PCDATA)>
+ <!ENTITY lol1 "&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;">
+ <!ENTITY lol2 "&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;">
+ <!ENTITY lol3 "&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;">
+ <!ENTITY lol4 "&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;">
+ <!ENTITY lol5 "&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;">
+ <!ENTITY lol6 "&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;">
+ <!ENTITY lol7 "&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;">
+ <!ENTITY lol8 "&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;">
+ <!ENTITY lol9 "&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;">
+]>
+<lolz>&lol9;</lolz>

week-05/serialization_XML/examples/data/enwiki-latest-pages-articles1.xml-p000000010p000010000-shortened.bz2

@@ -0,0 +1,10 @@
+import json
+
+obj = {"key": "value"}
+obj2 = {"key": obj}
+obj["key"] = obj2
+
+print obj["key"]
+print obj2["key"]
+
+print json.dumps(obj2)

week-05/serialization_XML/examples/json_circular.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python
+
+def add_plus_one(values=[]):
+    """adds the values in values together, plus 1"""
+    values.append(1)
+    return sum(values)
+
+print add_plus_one()
+print add_plus_one([1,2,3])
+print add_plus_one()

week-05/serialization_XML/examples/mutable.py

@@ -0,0 +1,10 @@
+import pickle 
+
+from badpicklemodule import foo
+
+
+x = foo()
+
+print x()
+
+print pickle.dumps(x)

week-05/serialization_XML/examples/unpickleable.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+
+import bz2
+import xml.etree.ElementTree as ET
+
+
+if __name__ == "__main__":
+    # fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000.bz2"
+    fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000-shortened.bz2"
+
+    f = bz2.BZ2File(fname)
+
+    # ET.register_namespace('schemaLocation', 'http://www.mediawiki.org/xml/export-0.8/')
+    tree = ET.parse(f)
+    root = tree.getroot()
+
+    # for title in root.findall('page/title'):
+    for title in root.findall('{http://www.mediawiki.org/xml/export-0.8/}page/{http://www.mediawiki.org/xml/export-0.8/}title'):
+        print title.text
+

week-05/serialization_XML/examples/wikipedia-elementtree.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+import bz2
+from lxml import etree
+
+if __name__ == "__main__":
+    # fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000.bz2"
+    fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000-shortened.bz2"
+
+    f = bz2.BZ2File(fname)
+
+    doc = etree.parse(f)
+    
+    for element in doc.findall("{http://www.mediawiki.org/xml/export-0.8/}page/{http://www.mediawiki.org/xml/export-0.8/}title"):
+        
+        print  element.text
+

week-05/serialization_XML/examples/wikipedia-lxml.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python
+
+import bz2
+from xml.dom import minidom 
+
+if __name__ == "__main__":
+    # fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000.bz2"
+    fname = "data/enwiki-latest-pages-articles1.xml-p000000010p000010000-shortened.bz2"
+
+    f = bz2.BZ2File(fname)
+
+    doc = minidom.parse(f)
+
+    for element in doc.getElementsByTagName("title"):
+        
+        text_node = element.childNodes[0]
+        print text_node.data
+