XML
Datagrunnlaget er fila all_results.xml med resultater fra sprintøvelsene i olymiske leker de siste årene.
Du vil se av koden nedenfor at metodene find() og findall() er sentrale ii å lokalisere noder i treet. En parameter er et forenklet XPath [1] uttrykk. Mer om XPath i modulen lxml . Og enda mer i materalet om XSLT
Vi tar utgangspunkt i følgende Python modul.
"""
Reading xml, and report
"""
import sys
import xml.etree.ElementTree as TRE
"""
Load data file and establish tree
return the rootnode
"""
def loadIt(filename):
try:
tree = TRE.parse(filename)
return tree.getroot()
except:
res=sys.exc_info()
print (res[1])
return None
"""
All athlet names, unsorted as found
"""
def allAthletNames(root):
all_athlets=root.findall('OlympicGame/event/athlet/name')
for at in all_athlets:
print(at.text)
"""
All olympics, place and year
"""
def allOlympics(root):
all_games=root.findall('OlympicGame')
for ga in all_games:
print(ga.attrib['place'],ga.attrib['year'])
"""
Athlets running a certain dist in a certail year
Using reduced XPAth
"""
def athletsInDistYear(root, dist, year):
print(dist,year)
S=".//OlympicGame[@year='%s']/event[@dist='%s']/athlet/name"%(year,dist)
athletNames=root.findall(S)
for at in athletNames:
print(at.text)
"""
Athlets running a certain dist in a certail year, ordered by result
Using reduced XPAth
"""
def timeused(t):
return float(t[1])
def athletsOrderedInDistYear(root, dist, year):
print(dist,year)
order={}
S=".//OlympicGame[@year='%s']/event[@dist='%s']/athlet"%(year,dist)
athlets=root.findall(S)
for at in athlets:
order[at.find("./name").text] = at.find("./result").text
items=order.items()
sortedtems=sorted(items,key=timeused)
for it in sortedtems:
print(it[0],it[1])
"""
Best result of athlet in a distance, regardless of year
Using reduced XPAth
"""
def athletsOrderedInDist(root, dist):
print(dist,"all olympics")
order={}
S=".//event[@dist='%s']/athlet"%(dist)
athlets=root.findall(S)
for at in athlets:
name=at.find("./name").text
res=at.find("./result").text
if (not name in order) or (float(order[name]) > float(res)):
order[name] = res
items=order.items()
sortedtems=sorted(items,key=timeused)
for it in sortedtems:
print(it[0],it[1])
"""
Best result of athlets in a distance (where and when) , regardless of year
Using reduced XPAth
"""
def timeused2(t):
return float(t[1][0])
def athletsOrderedInDistWhere(root, dist):
print(dist,"all olympics")
order={}
games=root.findall(".//OlympicGame")
for og in games:
athlets=og.findall(".//event[@dist='%s']/athlet"%dist)
for at in athlets:
name=at.find("./name").text
res=at.find("./result").text
if (not name in order) or (float(order[name][0]) > float(res)):
order[name] = [res,og.attrib['place'],og.attrib['year']]
items=order.items()
sortedtems=sorted(items,key=timeused2)
for it in sortedtems:
print(it[1][0],'\t',it[0],',',it[1][1],it[1][2])
root= loadIt('all_results.xml')
if root !=None:
#allAthletNames(root)
#allOlympics(root)
#athletsInDistYear(root, '400m', '2004')
#athletsOrderedInDistYear(root, '100m', '1992')
#athletsOrderedInDist(root, '100m')
athletsOrderedInDistWhere(root, '100m')
Resultatet av metoden athletsOrderedInDistWhere() blir:
100m all olympics 09.63 Usain Bolt , London 2012 09.75 Yohan Blake , London 2012 09.79 Justin Gatlin , London 2012 09.80 Tyson Gay , London 2012 09.84 Donovan Bailey , Atlanta 1996 09.86 Francis Obikwelu , Athens 2004 09.87 Maurice Greene , Sidney 2000 09.88 Ryan Bailey , London 2012 09.89 Shawn Crawford , Athens 2004 09.89 Frank Fredericks , Atlanta 1996 09.89 Richard Thompson , Beijing 2008 09.90 Ato Boldon , Atlanta 1996 09.91 Walter Dix , Beijing 2008 09.93 Churandy Martina , Beijing 2008 09.94 Asafa Powell , Athens 2004 09.96 Linford Christie , Barcelona 1992 09.97 Michael Frater , Beijing 2008 09.99 Dennis Mitchell , Atlanta 1996 10.00 Michael Marsh , Atlanta 1996 10.00 Kim Collins , Athens 2004 10.01 Marc Burns , Beijing 2008 10.03 Darvis Patton , Beijing 2008 10.04 Obadele Thompson , Sidney 2000 10.08 Dwain Chambers , Sidney 2000 10.09 Jonathan Drummond , Sidney 2000 10.09 Bruny Surin , Barcelona 1992 10.10 Leroy Burrell , Barcelona 1992 10.12 Olapade Adeniken , Barcelona 1992 10.13 Darren Campbell , Sidney 2000 10.14 Davidson Ezima , Atlanta 1996 10.16 Michael Green , Atlanta 1996 10.22 Raymond Stewart , Barcelona 1992
Kopier Pythonkoden og datafila som nevnt over, kjør de forskjellige metoden og gjør dine egne eksperimenter.
