#this script captures the current posted links from a del.icio.us webpage
import urllib
import os

#creates list of delicious webpages to pull links from
webpageList = ["http://del.icio.us/popular/mapping","http://del.icio.us/popular/design", "http://del.icio.us/popular/webdesign", "http://del.icio.us/popular/web2.0",
               "http://del.icio.us/popular/technology", "http://del.icio.us/popular/geography"]

outfile = open('../includes/linkgrabber.php', 'wt') #opens/creates the linkgrabber.php file

#function that opens the file, copies it as a list, and strips the links from it
def grabLinks(webpage):
    sock = urllib.urlopen(webpage)
    htmlSource = sock.readlines()
    sock.close()
    i=0
    lines = []
    links = []
    
    for i in htmlSource:
        if 'nofollow' in i:
            j = i.find('<a')
            k = i.find('a>')
            lines.append(i[j:k])
    outfile.write('<ul>')
    h = 0
    for i in lines:
        l = i.find('http:')
        m = i.find('" ')
        n = i.find('">')
        o = i.find('</a>')
        linkText = i[n+2:o-1]
        if h < 7 and linkText != 'save this':
            links = '<li><a href="',i[l:m],'">',linkText,'</a></li>'
            outfile.writelines(links) #writes the links to the linkgrabber.php file
            h+=1
    outfile.write('</ul>') 

#loops through the webpageList and executes the grabLinks function using each page
for i in webpageList:
    webpage = i
    p = i.find('r/')
    name = i[p+2:]
    headers = '<h3><a href="',webpage,'">',name,'</a></h3>'
    outfile.writelines(headers) #writes the name of the tag header to file
    grabLinks(webpage)

outfile.close()