Projected in front of class (teacher explaining her process for grabbing cities and states, making a simple plaintext file for later reuse):
>>> import urllib2 >>> fo = urllib2.urlopen( "http://www.w3.org/2000/10/swap/test/dbork/data/USRegionState.daml";) >>> fo # <-- a file-like object <addinfourl at 21988896 whose fp = <socket._fileobject object at 0x00CA1490>> >>> for i in fo: # grab the strings we'll need to parse if '<capital' in i: allcapitals.append(i) >>> fo.close() >>> def getcities(): # snip off the fat cities = [] for city in allcapitals: st = city.find("#") fn = city.find('"/>') cities.append(city[st+1:fn]) return cities >>> def getcitystate(): # separate city and state citystate=[] global cities for e in cities: city = e[:-2] state = e[-2:] citystate.append((city,state)) return citystate >>> cs = getcitystate() >>> cs [('montgomery', 'al'), ('juneau', 'ak'), ('phoenix', 'az'), ('littlerock', 'ar'), ('sacramento', 'ca'), ('denver', 'co'), ('hartford', 'ct'), ('washington', 'dc'), ('dover', 'de'), ('tallahassee', 'fl'), ('atlanta', 'ga'), ('honolulu', 'hi'), ('boise', 'id'), ('springfield', 'il'), ('indianapolis', 'in'), ('desmoines', 'ia'), ('topeka', 'ks'), ('frankfort', 'ky'), ('batonrouge', 'la'), ('augusta', 'me'), ('annapolis', 'md'), ('boston', 'ma'), ('lansing', 'mi'), ('stpaul', 'mn'), ('jackson', 'ms'), ('jeffersoncity', 'mo'), ('helena', 'mt'), ('lincoln', 'ne'), ('carsoncity', 'nv'), ('concord', 'nh'), ('trenton', 'nj'), ('santafe', 'nm'), ('albany', 'ny'), ('raleighdurham', 'nc'), ('bismarck', 'nd'), ('columbus', 'oh'), ('oklahomacity', 'ok'), ('salem', 'or'), ('harrisburg', 'pa'), ('providence', 'ri'), ('columbia', 'sc'), ('pierre', 'sd'), ('nashville', 'tn'), ('austin', 'tx'), ('saltlakecity', 'ut'), ('montpelier', 'vt'), ('richmond', 'va'), ('olympia', 'wa'), ('charleston', 'wv'), ('madison', 'wi'), ('cheyenne', 'wy')] >>> etc. (still have to hand-space 'jefferson city' etc. once you get your plaintext written out (hey, we humans have a role to play, why not?). Actually, this whole exercise might be fun for the kids to mess with -- I'll forward it to the police in Hillsboro as a lab activity (Red Hat 9 lab, West Precinct). We could show 'em XML parsing and regular expressions (alternative, more sophisticated ways to suck strings) in later lessons. Kirby _______________________________________________ Edu-sig mailing list Edu-sig@python.org http://mail.python.org/mailman/listinfo/edu-sig
