User:Renee Oldemonnikhof/Technicalcourse2

Technical course Trimester 2

First assignment

#Looking inside the RSS Feed
import feedparser
# Calling the information from the website and giving it the name "newwork"
newwork = feedparser.parse("http://feeds.feedburner.com/newwork")
import pprint
#pprint.pprint(newwork)
#print(newwork.entries[4]["title"])
print """
<html xmlns="http://www.w3.org/1999/xhtml">
  <head>
    <title>feedbook</title>
    <link type="text/css" rel="stylesheet" media="all" href="stylesheet.css" />
  </head>
  <body>"""
for e in newwork.entries:
    print"<h1>"
    print e["title"].replace("&", "&amp;").encode("utf-8")
    print"</h1>"
    print"<p>"
    print e["summary"].replace("&", "&amp;").encode("utf-8")
    print"</p>"
    print
print"""
  </body>
</html>"""
#(in the terminal to save it as an html) python feed.py > output.html
Makebook.sh

python feed.py > feedbook/OEBPS/content.html

cd feedbook

zip -0Xq feedbook.epub mimetype

zip -Xr9Dq feedbook.epub *

lucidor feedbook.epub

Visual representation of the epub

Second Assignment

a. PALINDROME HEADLINES

import feedparser
newwork = feedparser.parse("http://feeds.feedburner.com/newwork")

for entry in newwork.entries:


    text = entry["title"]
    words = text.split()
    wordstwo = text.split()
    wordstwo.reverse()
    words = words[0:-1]

    print " ".join(words + wordstwo)

Result is:

MTV Rocks MTV
Beauty In Engineering In Beauty
LET’S PLAY A GAME A PLAY LET’S
Demoscene strikes back strikes Demoscene
NY- Z NY-
Mind Control Mind
Walt goes open source open goes Walt
Segmentus
Alex Varanese Alex
Limbo
Milk it! Milk
Friends of Type of Friends
This Too Shall Pass Shall Too This
Stylo
Hello World Hello
Black Box Black
MONOCHRON
New FWA site FWA New
Champion Sound Champion
Radiant Child Radiant
How Your Money Works Money Your How
Vimeo vertising Vimeo
FITC leader FITC
Joe Danger Joe
Givolution
Grindin’
Nozzman app Nozzman
I’M SORRY I’M
Choco snow Choco
Red Bull Red

b. Chicken Comic

import urllib2, urlparse, html5lib

def absolutizeURL (href, base):
    if not href.lower().startswith("http://"):
        return urlparse.urljoin(base, href)
    return href

def openURL (url):
    """
    returns (page, actualurl)
    sets user_agent and resolves possible redirection
    realurl maybe different than url in the case of a redirect
    """    
    request = urllib2.Request(url)
    user_agent = "Mozilla/5.0 (X11; U; Linux x86_64; fr; rv:1.9.1.5) Gecko/20091109 Ubuntu/9.10 (karmic) Firefox/3.5.5"
    request.add_header("User-Agent", user_agent)
    pagefile=urllib2.urlopen(request)
    realurl = pagefile.geturl()
    return (pagefile, realurl)

parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder("dom"))

(f,bamiurl)=openURL("http://images.google.com/images?hl=en&source=hp&q=bami&gbv=2&aq=f&aqi=g10&aql=&oq=")
tree1 = parser.parse(f)
f.close()
tree1.normalize()
bamiimgs = tree1.getElementsByTagName("img")
# print tags

(f,naziurl)=openURL("http://images.google.nl/images?q=chicken&oe=utf-8&rls=com.ubuntu:en-US:unofficial&client=firefox-a&um=1&ie=UTF-8&sa=N&hl=nl&tab=wi")
tree2 = parser.parse(f)
f.close()
tree2.normalize()
naziimgs = tree2.getElementsByTagName("img")
# print tags

print """<html><body>"""


for (bami, nazi) in zip (bamiimgs, naziimgs):
    var=bami.getAttribute("src")
    var=absolutizeURL(var,bamiurl)
    if var != "http://images.google.com/images/nav_logo7.png":
        print "<img src='" + var + "' height='200' />"
    var=nazi.getAttribute("src")
    var=absolutizeURL(var,naziurl)
    if var != "http://images.google.com/images/nav_logo7.png":
        print "<img src='" + var + "' height='200' />"
	
print """</html></body>"""

c. Regular Expressions

import re

text = open("romeo_and_juliet.txt").read()

You = re.findall(r"\bYou [a-z']+\b", text)
Me = re.findall(r"\bI [a-z']+\b", text)
The = re.findall(r"\bthe [a-z']+", text)

You = list(set(You))
Me = list(set(Me))

import random
random.shuffle(You)
random.shuffle(Me)
random.shuffle(The)

for (x,y,z) in zip(You,Me,The):
    print x,z,"-",y,z