Intro to CS Python

Input > Procedure > Output

#def procedurename():			#if no inputs; input = argument = operand
#	<block of code here>
#	return output1, output2		#if you dont return any output, your variables/values will remain unchanged outside this procedure
								#and print is not the same as returning a value

#def procedurename(input1, input2, ...):
#	<block of code here>
#	return output1, output2


# +		#can sum values; can concatenate strings


#find second occurrence of a particular string
def find_second(search, target):
	first = search.find(target)
	second = search.find(target, first + 1)		#find target string from 'position of previous target string + 1'
	return second


#if <testexpression>:							#execute 0 or 1 time
#	<execute this block of code if expression above is true>
#else
#	<execute this block of code>



#while <testexpression>:						#execute 0 or 1 or a no of times
#	<execute this block of code while expression above is true>


#while <testexpression>:
#	<execute this block of code while expression above is true>
#	if <break test>:
#		break									#ie jump out from the while loop
#<code after while loop>









#if url is not found, return None, 0
def get_next_target(page):
    start_link = page.find('<a href=')

    # if the link tag sequence is not found, find returns a -1
    if start_link == -1:
        # return the error codes of None, 0 now and skip the rest!
        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
	


#print all url
def print_all_links(page):
	while True:
		url, endpos = get_next_target(page)
		if url:
			print url
			page = page[endpos:]
		else:
			break

#to test
#print_all_links('some link 1', ..., 'some link n')
#print_all_links(get_page('page url 1'))






#assertion				#give an assertion error msg if fail
#assert <expression>
#	False => fail

assert not dateIsBefore(year2, month2, day2, year1, month1, day1)
days = 0













##return days between 2 dates
# finish your daysBetweenDates
# procedure. It will need to take into account leap years
# in addition to the correct number of days in each month.

def nextDay(year, month, day):
    """Simple version: assume every month has 30 days"""
    if day < 30:
        return year, month, day + 1
    else:
        if month == 12:
            return year + 1, 1, 1
        else:
            return year, month + 1, 1

#added daysInMonth		
def daysInMonth(year,month):
	if month == 1 or month == 3 or month == 5 or month == 7 or month == 8 or month == 10 or month == 12
		return 31
	else:
		if month == 2:
			if isLeapYear(year):
				return 29
			else:
				return 28	#elseif month is Feb but not a leap year, return 28
	return 30

#added isLeapYear
def isLeapYear(year):
	if year % 400 == 0:
		return True
	if year % 0 == 0:
		return False
	if year % 4 == 0:
		return True
	return False			#ie else return False


def dateIsBefore(year1, month1, day1, year2, month2, day2):
    """Returns True if year1-month1-day1 is before year2-month2-day2. Otherwise, returns False."""
    if year1 < year2:
        return True
    if year1 == year2:
        if month1 < month2:
            return True
        if month1 == month2:
            return day1 < day2
    return False        

def daysBetweenDates(year1, month1, day1, year2, month2, day2):
    """Returns the number of days between year1/month1/day1
       and year2/month2/day2. Assumes inputs are valid dates
       in Gregorian calendar."""
    # program defensively! Add an assertion if the input is not valid!
    assert not dateIsBefore(year2, month2, day2, year1, month1, day1)
    days = 0
    while dateIsBefore(year1, month1, day1, year2, month2, day2):
        year1, month1, day1 = nextDay(year1, month1, day1)
        days += 1
    return days

def test():
    test_cases = [((2012,1,1,2012,2,28), 58), 
                  ((2012,1,1,2012,3,1), 60),
                  ((2011,6,30,2012,6,30), 366),
                  ((2011,1,1,2012,8,8), 585 ),
                  ((1900,1,1,1999,12,31), 36523)]
    
    for (args, answer) in test_cases:
        result = daysBetweenDates(*args)
        if result != answer:
            print "Test with data:", args, "failed"
        else:
            print "Test case passed!"



def mytest():
	#tests with 30-day months
	assert daysBetweenDates(2017,1,1, 2017,1,1) == 0
	assert daysBetweenDates(2017,1,1, 2017,1,2) == 1
	assert nextDay(2017,1,1) == (2017,1,2)
	assert nextDay(2017,4,30) == (2017,5,1)
	assert nextDay(2017,12,31) == (2018,1,1)
	assert nextDay(2017,2,28) == (2017,3,1)
	assert nextDay(2017,9,30) == (2017,10,1)	
	assert nextDay(2016,2,28) == (2016,2,29)			#leap year
	assert daysBetweenDates(2016,1,1, 2017,1,1) == 366	#leap year
	assert daysBetweenDates(2017,1,1, 2018,1,1) == 365
	assert daysBetweenDates(2017,1,24, 2018,6,29) == 156
	print "Tests finished"



test()








#list
list = ['a', 'b', 3]
list[position no]
list[start pos:end pos]
list1 + list2 = [elements in list 1 and 2]
len(listname)		#only count outer elements; dont count elements inside the inner list
len('string')		#length of a string; no of characters
listname.append('element')			#we can append a list within another list





#for loop
#for <name> in <list>:
#	<execute block of code>



#print all elements in a list on separate lines
def print_all_elements(listname):
	for element in listname:		#'element' will be assigned the element at each position of our list
		print element

mylist = [1,2,[3,4]]
print_all_elements(mylist)
#1
#2
#[3,4]




#sum all elements in a list
def sum_list(p):	#input list p
	result = 0
	for e in p:		#for element in list p
		result = result + e
	return result


#count no of elements which start with 'U'
def measure_udacity(p):
    result = 0
    for e in p:
        if e[0] == 'U':
            result += 1
    return result



#return 1st occurrence of target element in a list
#own ans
def find_element(p, t):
    i = 0
    while i < len(p):
        if p[i] == t:
            return i
		return -1
    i += 1

#udacity ans
def find_element(p, t):
    i = 0
    while i < len(p):
        if p[i] == t:
            return i
		i += 1
	return -1
    

def find_element(p, t):
    i = 0
    for e in p:
        if e == t:
            return i
		i += 1
	return -1
    


#<listname>.index(<target element>) 	#returns 1st position of the target element in the list

#<target element> in <listname>			#return True/False whether target element is in the list
#<target element> not in <listname>


#find element using list.index(element) and 'target in list'
def find_element(p, t):
    if t in p:
        return p.index(t)
    else:
		return -1

#find element using list.index(element) and 'target not in list'
def find_element(p, t):
    if t not in p:
        return -1
    return p.index(t)




#append unique elements from list t onto list s
def union(s, t):
    for e in t:
        if e not in s:
            s.append(e)
    return s





#<listname>.pop()		#removes and returns the last element



#web crawler for links starting from a seed page

def get_page(url):
    # This is a simulated get_page procedure so that you can test your
    # code on two pages "http://xkcd.com/353" and "http://xkcd.com/554".
    # A procedure which actually grabs a page from the web will be 
    # introduced in unit 4.
    try:
        if url == "http://xkcd.com/353":
            return  '<?xml version="1.0" encoding="utf-8" ?><?xml-stylesheet href="http://imgs.xkcd.com/s/c40a9f8.css" type="text/css" media="screen" ?><!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"><html xmlns="http://www.w3.org/1999/xhtml"> <head> <title>xkcd: Python</title> <link rel="stylesheet" type="text/css" href="http://imgs.xkcd.com/s/c40a9f8.css" media="screen" title="Default" /> <!--[if IE]><link rel="stylesheet" type="text/css" href="http://imgs.xkcd.com/s/ecbbecc.css" media="screen" title="Default" /><![endif]--> <link rel="alternate" type="application/atom+xml" title="Atom 1.0" href="/atom.xml" /> <link rel="alternate" type="application/rss+xml" title="RSS 2.0" href="/rss.xml" /> <link rel="icon" href="http://imgs.xkcd.com/s/919f273.ico" type="image/x-icon" /> <link rel="shortcut icon" href="http://imgs.xkcd.com/s/919f273.ico" type="image/x-icon" /> </head> <body> <div id="container"> <div id="topContainer"> <div id="topLeft" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s">\t<ul> <li><a href="http://xkcd.com/554"">Archive</a><br /></li>\t <li><a href="http://blag.xkcd.com/">News/Blag</a><br /></li> <li><a href="http://store.xkcd.com/">Store</a><br /></li> <li><a href="/about/">About</a><br /></li> <li><a href="http://forums.xkcd.com/">Forums</a><br /></li> </ul> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> <div id="topRight" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <div id="topRightContainer"> <div id="logo"> <a href="/"><img src="http://imgs.xkcd.com/s/9be30a7.png" alt="xkcd.com logo" height="83" width="185"/></a> <h2><br />A webcomic of romance,<br/> sarcasm, math, and language.</h2> <div class="clearleft"></div> <br />XKCD updates every Monday, Wednesday, and Friday. </div> </div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> </div> <div id="contentContainer"> <div id="middleContent" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"><h1>Python</h1><br/><br /><div class="menuCont"> <ul> <li><a href="/1/">|&lt;</a></li> <li><a href="/352/" accesskey="p">&lt; Prev</a></li> <li><a href="http://dynamic.xkcd.com/random/comic/" id="rnd_btn_t">Random</a></li> <li><a href="/354/" accesskey="n">Next &gt;</a></li> <li><a href="/">&gt;|</a></li> </ul></div><br/><br/><img src="http://imgs.xkcd.com/comics/python.png" title="I wrote 20 short programs in Python yesterday. It was wonderful. Perl, Im leaving you." alt="Python" /><br/><br/><div class="menuCont"> <ul> <li><a href="/1/">|&lt;</a></li> <li><a href="/352/" accesskey="p">&lt; Prev</a></li> <li><a href="http://dynamic.xkcd.com/random/comic/" id="rnd_btn_b">Random</a></li> <li><a href="/354/" accesskey="n">Next &gt;</a></li> <li><a href="/">&gt;|</a></li> </ul></div><h3>Permanent link to this comic: http://xkcd.com/353/</h3><h3>Image URL (for hotlinking/embedding): http://imgs.xkcd.com/comics/python.png</h3><div id="transcript" style="display: none">[[ Guy 1 is talking to Guy 2, who is floating in the sky ]]Guy 1: You39;re flying! How?Guy 2: Python!Guy 2: I learned it last night! Everything is so simple!Guy 2: Hello world is just 39;print &quot;Hello, World!&quot; 39;Guy 1: I dunno... Dynamic typing? Whitespace?Guy 2: Come join us! Programming is fun again! It39;s a whole new world up here!Guy 1: But how are you flying?Guy 2: I just typed 39;import antigravity39;Guy 1: That39;s it?Guy 2: ...I also sampled everything in the medicine cabinet for comparison.Guy 2: But i think this is the python.{{ I wrote 20 short programs in Python yesterday. It was wonderful. Perl, I39;m leaving you. }}</div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> <div id="middleFooter" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <img src="http://imgs.xkcd.com/s/a899e84.jpg" width="520" height="100" alt="Selected Comics" usemap=" comicmap" /> <map name="comicmap"> <area shape="rect" coords="0,0,100,100" href="/150/" alt="Grownups" /> <area shape="rect" coords="104,0,204,100" href="/730/" alt="Circuit Diagram" /> <area shape="rect" coords="208,0,308,100" href="/162/" alt="Angular Momentum" /> <area shape="rect" coords="312,0,412,100" href="/688/" alt="Self-Description" /> <area shape="rect" coords="416,0,520,100" href="/556/" alt="Alternative Energy Revolution" /> </map><br/><br />Search comic titles and transcripts:<br /><script type="text/javascript" src="//www.google.com/jsapi"></script><script type="text/javascript"> google.load(\"search\", \"1\"); google.setOnLoadCallback(function() { google.search.CustomSearchControl.attachAutoCompletion( \"012652707207066138651:zudjtuwe28q\", document.getElementById(\"q\"), \"cse-search-box\"); });</script><form action="//www.google.com/cse" id="cse-search-box"> <div> <input type="hidden" name="cx" value="012652707207066138651:zudjtuwe28q" /> <input type="hidden" name="ie" value="UTF-8" /> <input type="text" name="q" id="q" autocomplete="off" size="31" /> <input type="submit" name="sa" value="Search" /> </div></form><script type="text/javascript" src="//www.google.com/cse/brand?form=cse-search-box&lang=en"></script><a href="/rss.xml">RSS Feed</a> - <a href="/atom.xml">Atom Feed</a><br /> <br/> <div id="comicLinks"> Comics I enjoy:<br/> <a href="http://www.qwantz.com">Dinosaur Comics</a>, <a href="http://www.asofterworld.com">A Softer World</a>, <a href="http://pbfcomics.com/">Perry Bible Fellowship</a>, <a href="http://www.boltcity.com/copper/">Copper</a>, <a href="http://questionablecontent.net/">Questionable Content</a>, <a href="http://achewood.com/">Achewood</a>, <a href="http://wondermark.com/">Wondermark</a>, <a href="http://thisisindexed.com/">Indexed</a>, <a href="http://www.buttercupfestival.com/buttercupfestival.htm">Buttercup Festival</a> </div> <br/> Warning: this comic occasionally contains strong language (which may be unsuitable for children), unusual humor (which may be unsuitable for adults), and advanced mathematics (which may be unsuitable for liberal-arts majors).<br/> <br/> <h4>We did not invent the algorithm. The algorithm consistently finds Jesus. The algorithm killed Jeeves. <br />The algorithm is banned in China. The algorithm is from Jersey. The algorithm constantly finds Jesus.<br />This is not the algorithm. This is close.</h4><br/> <div class="line"></div> <br/> <div id="licenseText"> <!-- <a rel="license" href="http://creativecommons.org/licenses/by-nc/2.5/"><img alt="Creative Commons License" style="border:none" src="http://imgs.xkcd.com/static/somerights20.png" /></a><br/> --> This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-nc/2.5/">Creative Commons Attribution-NonCommercial 2.5 License</a>.<!-- <rdf:RDF xmlns="http://web.resource.org/cc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns "><Work rdf:about=""><dc:creator>Randall Munroe</dc:creator><dcterms:rightsHolder>Randall Munroe</dcterms:rightsHolder><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:source rdf:resource="http://www.xkcd.com/"/><license rdf:resource="http://creativecommons.org/licenses/by-nc/2.5/" /></Work><License rdf:about="http://creativecommons.org/licenses/by-nc/2.5/"><permits rdf:resource="http://web.resource.org/cc/Reproduction" /><permits rdf:resource="http://web.resource.org/cc/Distribution" /><requires rdf:resource="http://web.resource.org/cc/Notice" /><requires rdf:resource="http://web.resource.org/cc/Attribution" /><prohibits rdf:resource="http://web.resource.org/cc/CommercialUse" /><permits rdf:resource="http://web.resource.org/cc/DerivativeWorks" /></License></rdf:RDF> --> <br/> This means you\"re free to copy and share these comics (but not to sell them). <a href="/license.html">More details</a>.<br/> </div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> </div> </div> </body></html> '
        elif url == "http://xkcd.com/554":
            return  '<?xml version="1.0" encoding="utf-8" ?> <?xml-stylesheet href="http://imgs.xkcd.com/s/c40a9f8.css" type="text/css" media="screen" ?> <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <title>xkcd: Not Enough Work</title> <link rel="stylesheet" type="text/css" href="http://imgs.xkcd.com/s/c40a9f8.css" media="screen" title="Default" /> <!--[if IE]><link rel="stylesheet" type="text/css" href="http://imgs.xkcd.com/s/ecbbecc.css" media="screen" title="Default" /><![endif]--> <link rel="alternate" type="application/atom+xml" title="Atom 1.0" href="/atom.xml" /> <link rel="alternate" type="application/rss+xml" title="RSS 2.0" href="/rss.xml" /> <link rel="icon" href="http://imgs.xkcd.com/s/919f273.ico" type="image/x-icon" /> <link rel="shortcut icon" href="http://imgs.xkcd.com/s/919f273.ico" type="image/x-icon" /> </head> <body> <div id="container"> <div id="topContainer"> <div id="topLeft" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <ul> <li><a href="/archive/">Archive</a><br /></li> <li><a href="http://blag.xkcd.com/">News/Blag</a><br /></li> <li><a href="http://store.xkcd.com/">Store</a><br /></li> <li><a href="/about/">About</a><br /></li> <li><a href="http://forums.xkcd.com/">Forums</a><br /></li> </ul> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> <div id="topRight" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <div id="topRightContainer"> <div id="logo"> <a href="/"><img src="http://imgs.xkcd.com/s/9be30a7.png" alt="xkcd.com logo" height="83" width="185"/></a> <h2><br />A webcomic of romance,<br/> sarcasm, math, and language.</h2> <div class="clearleft"></div> XKCD updates every Monday, Wednesday, and Friday. <br /> Blag: Remember geohashing? <a href="http://blog.xkcd.com/2012/02/27/geohashing-2/">Something pretty cool</a> happened Sunday. </div> </div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> </div> <div id="contentContainer"> <div id="middleContent" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <h1>Not Enough Work</h1><br/> <br /> <div class="menuCont"> <ul> <li><a href="/1/">|&lt;</a></li> <li><a href="/553/" accesskey="p">&lt; Prev</a></li> <li><a href="http://dynamic.xkcd.com/random/comic/" id="rnd_btn_t">Random</a></li> <li><a href="/555/" accesskey="n">Next &gt;</a></li> <li><a href="/">&gt;|</a></li> </ul> </div> <br/> <br/> <img src="http://imgs.xkcd.com/comics/not_enough_work.png" title="It39;s even harder if you39;re an asshole who pronounces &lt;&gt; brackets." alt="Not Enough Work" /><br/> <br/> <div class="menuCont"> <ul> <li><a href="/1/">|&lt;</a></li> <li><a href="/553/" accesskey="p">&lt; Prev</a></li> <li><a href="http://dynamic.xkcd.com/random/comic/" id="rnd_btn_b">Random</a></li> <li><a href="/555/" accesskey="n">Next &gt;</a></li> <li><a href="/">&gt;|</a></li> </ul> </div> <h3>Permanent link to this comic: http://xkcd.com/554/</h3> <h3>Image URL (for hotlinking/embedding): http://imgs.xkcd.com/comics/not_enough_work.png</h3> <div id="transcript" style="display: none">Narration: Signs your coders don39;t have enough work to do: [[A man sitting at his workstation; a female co-worker behind him]] Man: I39;m almost up to my old typing speed in dvorak [[Two men standing by a server rack]] Man  1: Our servers now support gopher. Man  1: Just in case. [[A woman standing near her workstation speaking to a male co-worker]] Woman: Our pages are now HTML, XHTML-STRICT, and haiku-compliant Man: Haiku? Woman: &lt;div class=&quot;main&quot;&gt; Woman: &lt;span id=&quot;marquee&quot;&gt; Woman: Blog!&lt; span&gt;&lt; div&gt; [[A woman sitting at her workstation]] Woman: Hey! Have you guys seen this webcomic? {{title text: It39;s even harder if you39;re an asshole who pronounces &lt;&gt; brackets.}}</div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> <div id="middleFooter" class="dialog"> <div class="hd"><div class="c"></div></div> <div class="bd"> <div class="c"> <div class="s"> <img src="http://imgs.xkcd.com/s/a899e84.jpg" width="520" height="100" alt="Selected Comics" usemap=" comicmap" /> <map name="comicmap"> <area shape="rect" coords="0,0,100,100" href="/150/" alt="Grownups" /> <area shape="rect" coords="104,0,204,100" href="/730/" alt="Circuit Diagram" /> <area shape="rect" coords="208,0,308,100" href="/162/" alt="Angular Momentum" /> <area shape="rect" coords="312,0,412,100" href="/688/" alt="Self-Description" /> <area shape="rect" coords="416,0,520,100" href="/556/" alt="Alternative Energy Revolution" /> </map><br/><br /> Search comic titles and transcripts:<br /> <script type="text/javascript" src="//www.google.com/jsapi"></script> <script type="text/javascript"> google.load("search", "1"); google.search.CustomSearchControl.attachAutoCompletion( "012652707207066138651:zudjtuwe28q", document.getElementById("q"), "cse-search-box"); }); </script> <form action="//www.google.com/cse" id="cse-search-box"> <div> <input type="hidden" name="cx" value="012652707207066138651:zudjtuwe28q" /> <input type="hidden" name="ie" value="UTF-8" /> <input type="text" name="q" id="q" autocomplete="off" size="31" /> <input type="submit" name="sa" value="Search" /> </div> </form> <script type="text/javascript" src="//www.google.com/cse/brand?form=cse-search-box&lang=en"></script> <a href="/rss.xml">RSS Feed</a> - <a href="/atom.xml">Atom Feed</a> <br /> <br/> <div id="comicLinks"> Comics I enjoy:<br/> <a href="http://threewordphrase.com/">Three Word Phrase</a>, <a href="http://oglaf.com/">Oglaf</a> (nsfw), <a href="http://www.smbc-comics.com/">SMBC</a>, <a href="http://www.qwantz.com">Dinosaur Comics</a>, <a href="http://www.asofterworld.com">A Softer World</a>, <a href="http://buttersafe.com/">Buttersafe</a>, <a href="http://pbfcomics.com/">Perry Bible Fellowship</a>, <a href="http://questionablecontent.net/">Questionable Content</a>, <a href="http://www.buttercupfestival.com/buttercupfestival.htm">Buttercup Festival</a> </div> <br/> Warning: this comic occasionally contains strong language (which may be unsuitable for children), unusual humor (which may be unsuitable for adults), and advanced mathematics (which may be unsuitable for liberal-arts majors).<br/> <br/> <h4>We did not invent the algorithm. The algorithm consistently finds Jesus. The algorithm killed Jeeves. <br />The algorithm is banned in China. The algorithm is from Jersey. The algorithm constantly finds Jesus.<br />This is not the algorithm. This is close.</h4><br/> <div class="line"></div> <br/> <div id="licenseText"> <!-- <a rel="license" href="http://creativecommons.org/licenses/by-nc/2.5/"><img alt="Creative Commons License" style="border:none" src="http://imgs.xkcd.com/static/somerights20.png" /></a><br/> --> This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-nc/2.5/">Creative Commons Attribution-NonCommercial 2.5 License</a>. <!-- <rdf:RDF xmlns="http://web.resource.org/cc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns "><Work rdf:about=""><dc:creator>Randall Munroe</dc:creator><dcterms:rightsHolder>Randall Munroe</dcterms:rightsHolder><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:source rdf:resource="http://www.xkcd.com/"/><license rdf:resource="http://creativecommons.org/licenses/by-nc/2.5/" /></Work><License rdf:about="http://creativecommons.org/licenses/by-nc/2.5/"><permits rdf:resource="http://web.resource.org/cc/Reproduction" /><permits rdf:resource="http://web.resource.org/cc/Distribution" /><requires rdf:resource="http://web.resource.org/cc/Notice" /><requires rdf:resource="http://web.resource.org/cc/Attribution" /><prohibits rdf:resource="http://web.resource.org/cc/CommercialUse" /><permits rdf:resource="http://web.resource.org/cc/DerivativeWorks" /></License></rdf:RDF> --> <br/> This means you"re free to copy and share these comics (but not to sell them). <a href="/license.html">More details</a>.<br/> </div> </div> </div> </div> <div class="ft"><div class="c"></div></div> </div> </div> </div> </body> </html> '
    except:
        return ""
    return ""

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 union(p,q):
    for e in q:
        if e not in p:
            p.append(e)


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

	
#depth first search
def crawl_web(seed):
	tocrawl = [seed]	#seed page as input
	crawled = []		#empty list initially
	while tocrawl:		#while listname = while there are elements in listname
		page = tocrawl.pop()	#pop allows us to do breadth first search, ie start from the last link on a seed page, then go to the last link of subsequent links,..., then move on to second last link, ... , move on to first link on seed page at the end
		if page not in crawled:
			union(tocrawl, get_all_links(get_page(page)))		#union procedure was defined by us	#union links from any new pages we find to the tocrawl list
			crawled.append(page)
	return crawled




#crawl up to a max no of pages
def crawl_web(seed,max_pages):
	tocrawl = [seed]	
	crawled = []		
	while tocrawl:		
		page = tocrawl.pop()	
		if page not in crawled and len(crawled) < max_pages:	#no of crawled pages/elements < the max no of pages you want to crawl
			union(tocrawl, get_all_links(get_page(page)))		
			crawled.append(page)
	return crawled





#crawl up to a max depth, ie take the shortest path to get to subsequent webpages
def crawl_web(seed,max_depth):
	tocrawl = [seed]	
	crawled = []		
	next_depth= []
	depth = ()
	while tocrawl and depth <= max_depth:		
		page = tocrawl.pop()	
		if page not in crawled:										#existing page/pages not found in crawled
			union(next_depth, get_all_links(get_page(page)))		#get all links to subsequent pages and add it to our next_depth list
			crawled.append(page)									#existing page/pages are added to crawled
		if not tocrawl:	
			tocrawl, next_depth = next_depth, []		#links from next_depth move to tocrawl if havent crawled(above) or not in tocrawl(here)
			depth = depth + 1							#next_depth becomes empty after moving; increase depth of next round/iteration of search
	return crawled















#sudoku digit checker
correct = [[1,2,3],
           [2,3,1],
           [3,1,2]]

incorrect = [[1,2,3,4],
             [2,3,1,3],
             [3,1,2,3],
             [4,4,4,4]]

incorrect2 = [[1,2,3,4],
             [2,3,1,4],
             [4,1,2,3],
             [3,4,1,2]]

incorrect3 = [[1,2,3,4,5],
              [2,3,1,5,6],
              [4,5,2,1,3],
              [3,4,5,2,1],
              [5,6,4,3,2]]

incorrect4 = [['a','b','c'],
              ['b','c','a'],
              ['c','a','b']]

incorrect5 = [ [1, 1.5],
               [1.5, 1]]
               
def check_sudoku(p):
	n = len(p)	#extract size of grid
	digit = 1	#start with 1
	
	while digit <= n:	#go through each digit
		i=0
		
		while i<n:		#go through every row and col
			row_count = 0	#initialise counters
			col_count = 0
			j = 0
			
			while j <= n:	# for each entry in ith row/ith col
				if p[i][j] == digit:	#row i
					row_count += 1
				if p[j][i] == digit:	#col j
					col_count += 1
				j += 1					#go through every col on row i + every row on col i
			if row_count != 1 or col_count != 1:
				return False
			i += 1						#next set of ith row/col
	
		digit += 1				#next digit; and go through the whole grid again
		
	return True					#nothing was wrong

#inner loop looks at 1 digit before going through the whole grid; return False at any time that the digit test in a row/col is False
#then middle loop will increment digit till the last digit; take the number and go through the inner loop
#once digit is greater than the last digit, stop loops and return True

#print check_sudoku(incorrect)
#>>> False

#print check_sudoku(correct)
#>>> True

#print check_sudoku(incorrect2)
#>>> False

#print check_sudoku(incorrect3)
#>>> False

#print check_sudoku(incorrect4)
#>>> False

#print check_sudoku(incorrect5)
#>>> False















#compile a list of (lists of [keyword and list of urls])
# Define a procedure, add_to_index,
# that takes 3 inputs:

# - an index: [[<keyword>,[<url>,...]],...]
# - a keyword: String
# - a url: String

# If the keyword is already
# in the index, add the url
# to the list of urls associated
# with that keyword.

# If the keyword is not in the index,
# add an entry to the index: [keyword,[url]]

index = []          #initialise empty list

def add_to_index(index,keyword,url):
    for entry in index:
        if entry[0] == keyword:				#do not use index[entry][0]
            entry[1].append(url)	#when keyword == existing entry, only insert url in the 2nd element, ie the url list of the entry
			return					#return exits from for loop; doesnt end the whole procedure like 'break' does
	index.append([keyword,[url]])	#since keyword was not found after running through our index list, add keyword and url as a new entry to our index list



#add_to_index(index,'udacity','http://udacity.com')
#add_to_index(index,'computing','http://acm.org')
#add_to_index(index,'udacity','http://npr.org')
#print index
#>>> [['udacity', ['http://udacity.com', 'http://npr.org']], 
#>>> ['computing', ['http://acm.org']]]















#Lookup a keyword from an index list; then return list of url
# Define a procedure, lookup,
# that takes two inputs:

# - an index
# - keyword

# The procedure should return a list
# of the urls associated
# with the keyword. If the keyword
# is not in the index, the procedure
# should return an empty list.

index = [['udacity', ['http://udacity.com', 'http://npr.org']],
         ['computing', ['http://acm.org']]]

def lookup(index,keyword):
    for entry in index:
        if entry[0] == keyword:
            return entry[1]
    return []



print lookup(index,'udacity')
#>>> ['http://udacity.com','http://npr.org']









#stringname.split()		#will split all the words in a string into individual elements in a list






















#from a web page, add all keywords + url that can appear in a page to our index list
#then look up another webpage and add keywords + url to our index page
# Define a procedure, add_page_to_index,
# that takes three inputs:

#   - index
#   - url (String)
#   - content (String)

# It should update the index to include
# all of the word occurences found in the
# page content by adding the url to the
# word's associated url list.

index = []


def add_to_index(index,keyword,url):
    for entry in index:
        if entry[0] == keyword:
            entry[1].append(url)
            return
    index.append([keyword,[url]])

def add_page_to_index(index,url,content):
	words = content.split()
    for word in words:
		add_to_index(index,word,url)		#use our previously defined procedure
		
#just modify index; dont need to return anything



add_page_to_index(index,'fake.text',"This is a test")
print index
#>>> [['This', ['fake.text']], ['is', ['fake.text']], ['a', ['fake.text']],
#>>> ['test',['fake.text']]]









#web crawler [L15]
def crawl_web(seed):
	tocrawl = [seed]	
	crawled = []		
	index = []
	
	while tocrawl:					#links on seed page
		page = tocrawl.pop()		#
		if page not in crawled:
			content = get_page(page)
			add_page_to_index(index,page,content)		#for each page, add content to index
			union(tocrawl, get_all_links(content))		
			crawled.append(page)									
	return index