NAME = 'InAndOut/Technorati/Python' VERSION = '0.01' # Copyright (C) 2004 Chris Fry # Permission is hereby granted, free of charge, to any person # obtaining a copy of this software and associated documentation files # (the "Software"), to deal in the Software without restriction, # including without limitation the rights to use, copy, modify, merge, # publish, distribute, sublicense, and/or sell copies of the Software, # and to permit persons to whom the Software is furnished to do so, # subject to the following conditions: # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND # NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS # BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN # ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN # CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. import technorati, sys, getopt from pprint import pprint def sort_by_value_and_links(d, weblogs): """ Returns the keys of dictionary d sorted by their values """ items = d.items() backitems = [[v[1], v[0], weblogs[v[0]]['weblog']['inboundlinks']] for v in items] backitems.sort( lambda x, y: y[0]*10000000-x[0]*10000000+y[2]-x[2]) return [backitems[i] for i in range(0, len(backitems))] def perform_query(url): """ Return a list of who else people link to when they link to you """ """ Performs a cosmos query and then a links out query from the cosmos """ technorati.findkey() data = technorati.getCosmos(url, 100) inbound = {} weblogs = {} counts = {} for i in data['inbound']: """ Grab the url from the inbound link list """ in_url = i['weblog']['url'] """ Check if we have already visited this url """ if (inbound.has_key(in_url) == False): inbound[in_url] = i['weblog'] """ For each url grab its outbound list """ for j in technorati.getOutboundBlogs(in_url)['outbound']: out_url = j['weblog']['url'] """ ignore the case where the blog refers to itself """ if in_url != out_url: weblogs[out_url] = j if counts.has_key(out_url): counts[out_url] = counts[out_url]+1 else: counts[out_url] = 1; result = {} result['inbound'] = inbound result['weblogs'] = weblogs result['counts'] = counts return result def format_weblog(weblog, count=None): """ formats a weblog return result in html """ s = "\t<tr><td><a href='"+weblog['url']+"'>"+weblog['name']+"</a></td> " s = s+"<td>"+str(weblog['lastupdate'])+"</td> " s = s+"<td>"+str(weblog['inboundblogs'])+"</td>" s = s+"<td>"+str(weblog['inboundlinks'])+"</td>" if count: s = s+"<td>"+str(count)+"</td>" s = s+"</tr>\n" return s def make_header(outfile, title): outfile.write("<head><meta http-equiv='Content-Type' content='text/html; charset=iso-8859-1' />") outfile.write("<title>Output of the In/Out Query for "); outfile.write(title); outfile.write("</title>\n") outfile.write("<link rel='stylesheet' type='text/css' href='technorati.css'/>") outfile.write("</head>\n") def make_body(outfile, title, counts, inbound, weblogs): outfile.write("<body id='technorati'>") outfile.write("<div id='b'><h1 id='l'><a href='/'><img src='http://www.technorati.com/images/logo200407.gif' alt='Technorati' /></a></h1>") outfile.write("<div id='m'><a href='http://www.technorati.com/help/using-technorati.html' title='Technorati: Help'>Help</a></div>") outfile.write("<form id='searchform' method='get' action='http://www.technorati.com/cosmos/search.html'><div>") outfile.write("<input type='hidden' name='rank' value='' />") outfile.write("<input id='st' type='text' name='url' size='35' maxlength='127' value='"+title+"' />") outfile.write("<input type='submit' class='submit' value='Search' title='Technorati: Search Results' />") outfile.write("<label for='st'>Keyword or URL</label>") outfile.write("</div>") outfile.write("</form>") outfile.write("<div id='cosmbox' class='bodytext'>") outfile.write("<h2> InOut Search for <a href='"+title+"'>"+title+"</a></h2>") outfile.write("<hr style=\"color: 'blue'; height: '15'; text-align: 'left'; width: '50%'\">") outfile.write("<h3>Inbound Bloggers</h3>\n") outfile.write("<table>\n") outfile.write("\t<tr><th><h4>Blog Name/URL</h4></th><th><h4>Last Update</h4></th><th><h4>Inbound Blogs</h4></th><th><h4>Inbound Links</h4></th></tr>") for i in inbound.values(): outfile.write(format_weblog(i)) outfile.write("</table>\n") outfile.write("<hr style=\"color: 'blue'; height: '15'; text-align: 'left'; width: '50%'\">") outfile.write("<h3>Inbound Bloggers Other Connections</h3>\n"); outfile.write("<p>Sorted by number of people who link to you and the blog and number of inbound links from the world</p>") outfile.write("<table>\n") outfile.write("\t<tr><th><h4>Blog Name/URL</h4></th><th><h4>Last Update</h4></th><th><h4>Inbound Blogs</h4></th><th><h4>Inbound Links</h4></th><th><h4>Number of People</h4></th></tr>") for i in counts: outfile.write(format_weblog(weblogs[i[1]]['weblog'], i[0])) outfile.write("</table>\n") def make_footer(outfile): outfile.write("<div id='footer'><div>") outfile.write("<a href='http://www.technorati.com/about/'>About Technorati</a>") outfile.write("| <a href='http://www.technorati.com/about/contact.html' title='Technorati Contact Info'>Contact</a>") outfile.write("| <a href='http://www.technorati.com/legal/privacy.html' title='Technorati Privacy Policy'>Privacy</a>") outfile.write("| <a href='http://www.technorati.com/legal/TOS.html' title='Technorati Terms of Service'>Terms of Service</a>") outfile.write("| <a href='http://www.technorati.com/developers/'>Developers</a>") outfile.write("| <a href='http://www.technorati.com/help/using-technorati.html'>Help</a></div>") outfile.write("<div><span id='copyright'>© 2004 Technorati, Inc.</span>") outfile.write("<span id='badges'><a rel='license' href='http://creativecommons.org/licenses/by-nc/2.0/'>CC by-nc</a> |") outfile.write("<a href='http://validator.w3.org/check/referer'>XHTML Strict</a> | <a href='http://jigsaw.w3.org/css-validator/check/referer'>CSS</a>") outfile.write("</span>") outfile.write("</div>") outfile.write("</div>") outfile.write("</body>") def save_html(title, file, counts, inbound, weblogs): outfile = open(file, 'w'); outfile.write("<html xmlns='http://www.w3.org/1999/xhtml'>") make_header(outfile, title) make_body(outfile, title, counts, inbound, weblogs); make_footer(outfile) outfile.write("</html>") outfile.close(); def run(url, outputfile): result = perform_query(url) inbound = result['inbound'] weblogs = result['weblogs'] counts = sort_by_value_and_links(result['counts'], weblogs) save_html(url, outputfile, counts, inbound, weblogs) def usage(): print>>sys.stderr, "Usage: python inandout.py -u url -o outputfile" def main(): try: opts, args = getopt.getopt(sys.argv[1: ], "hu:o:", ["help", "url=", "output="]) except getopt.GetoptError: # print help information and exit: usage() sys.exit(2) url = "http://www.sifry.com/alerts/" outputfile = "out.html" for o, a in opts: if o in ("-h", "--help"): usage() sys.exit() if o in ("-u", "--url"): url = a if o in ("-o", "--output"): outputfile = a run(url, outputfile) if __name__ == "__main__": sys.exit(main())