cs101 ยป

Unit 4 Challenge Questions

'Challenge questions' are labeled with Gold Stars and are intentionally more difficult than the normal homework questions.

Not every student is expected to correctly solve every problem. Challenge questions are intended to take more time, and provoke more thought than the normal questions. The more difficult the question is, the more Gold Stars it will be labeled with. You shouldn't be discouraged if you don't solve them.

Question 4 - Better Splitting (1 Gold Star)

# 1 Gold Star

# The built-in <string>.split() procedure works
# okay, but fails to find all the words on a page
# because it only uses whitespace to split the
# string. To do better, we should also use punctuation
# marks to split the page into words.

# Define a procedure, split_string, that takes two
# inputs: the string to split and a string containing
# all of the characters considered separators. The
# procedure should return a list of strings that break
# the source string up by the characters in the
# splitlist.

def split_string(source,splitlist):

#out = split_string("This is a test-of the,string separation-code!"," ,!-")
#print out
#>>> ['This', 'is', 'a', 'test', 'of', 'the', 'string', 'separation', 'code']

#out = split_string("After  the flood   ...  all the colors came out.", " .")
#print out
#>>> ['After', 'the', 'flood', 'all', 'the', 'colors', 'came', 'out']

#out = split_string("First Name,Last Name,Street Address,City,State,Zip Code",",")
#print out
#>>>['First Name', 'Last Name', 'Street Address', 'City', 'State', 'Zip Code']

Question 6 - Counting Clicks (2 Gold Stars)

# 2 Gold Stars

# One way search engines rank pages
# is to count the number of times a
# searcher clicks on a returned link.
# This indicates that the person doing
# the query thought this was a useful
# link for the query, so it should be
# higher in the rankings next time.

# (In Unit 6, we will look at a different
# way of ranking pages that does not depend
# on user clicks.)

# Modify the index such that for each url in a
# list for a keyword, there is also a number
# that counts the number of times a user
# clicks on that link for this keyword.

# The result of lookup(index,keyword) should
# now be a list of url entries, where each url
# entry is a list of a url and a number
# indicating the number of times that url
# was clicked for this query keyword.

# You should define a new procedure to simulate
# user clicks for a given link:

# record_user_click(index,word,url)

# that modifies the entry in the index for
# the input word by increasing the count associated
# with the url by 1.

# You also will have to modify add_to_index
# in order to correctly create the new data
# structure.

def record_user_click(index,keyword,url):

def add_to_index(index, keyword, url):
    for entry in index:
        if entry[0] == keyword:
    # not found, add new keyword to index
    index.append([keyword, [url]])

def get_page(url):
        if url == "http://www.udacity.com/cs101x/index.html":
            return '''<html> <body> This is a test page for learning to crawl!
<p> It is a good idea to
<a href="http://www.udacity.com/cs101x/crawling.html">
learn to crawl</a> before you try to
<a href="http://www.udacity.com/cs101x/walking.html">walk</a> or
<a href="http://www.udacity.com/cs101x/flying.html">fly</a>.</p></body></html>'''

        elif url == "http://www.udacity.com/cs101x/crawling.html":
            return '''<html> <body> I have not learned to crawl yet, but I am
quite good at  <a href="http://www.udacity.com/cs101x/kicking.html">kicking</a>.
</body> </html>'''

        elif url == "http://www.udacity.com/cs101x/walking.html":
            return '''<html> <body> I cant get enough
<a href="http://www.udacity.com/cs101x/index.html">crawling</a>!</body></html>'''

        elif url == "http://www.udacity.com/cs101x/flying.html":
            return '<html><body>The magic words are Squeamish Ossifrage!</body></html>'
        return ""
    return ""

def union(a, b):
    for e in b:
        if e not in a:

def get_next_target(page):
    start_link = page.find('<a href=')
    if start_link == -1:
        return None, 0
    start_quote = page.find('"', start_link)
    end_quote = page.find('"', start_quote + 1)
    url = page[start_quote + 1:end_quote]
    return url, end_quote

def get_all_links(page):
    links = []
    while True:
        url, endpos = get_next_target(page)
        if url:
            page = page[endpos:]
    return links

def crawl_web(seed):
    tocrawl = [seed]
    crawled = []
    index = []
    while tocrawl:
        page = tocrawl.pop()
        if page not in crawled:
            content = get_page(page)
            add_page_to_index(index, page, content)
            union(tocrawl, get_all_links(content))
    return index

def add_page_to_index(index, url, content):
    words = content.split()
    for word in words:
        add_to_index(index, word, url)

def lookup(index, keyword):
    for entry in index:
        if entry[0] == keyword:
            return entry[1]
    return None

#Here is an example showing a sequence of interactions:
index = crawl_web('http://www.udacity.com/cs101x/index.html')
print lookup(index, 'good')
#>>> [['http://www.udacity.com/cs101x/index.html', 0],
#>>> ['http://www.udacity.com/cs101x/crawling.html', 0]]

record_user_click(index, 'good', 'http://www.udacity.com/cs101x/crawling.html')
print lookup(index, 'good')
#>>> [['http://www.udacity.com/cs101x/index.html', 0],
#>>> ['http://www.udacity.com/cs101x/crawling.html', 1]]