Xml parsen
import sys
from xml.dom import minidom
minidom.parse(sys.argv[1])
time python /tmp/benchmini.py /mnt/dump/test/bag/gouda/NUM/1005NUM01012010-0001.xml real 0m33.296s user 0m32.788s sys 0m0.502s
import sys
import xml.etree.ElementTree as ET
ET.parse(sys.argv[1])
time python /tmp/benchet.py /mnt/dump/test/bag/gouda/NUM/1005NUM01012010-0001.xml real 0m15.338s user 0m15.184s sys 0m0.152s
import sys
import elementtree.ElementTree as ET
ET.parse(sys.argv[1])
time python /tmp/benchet1.py /mnt/dump/test/bag/gouda/NUM/1005NUM01012010-0001.xml real 0m14.847s user 0m14.688s sys 0m0.156s
import sys
import cElementTree as ET
ET.parse(sys.argv[1])
time python /tmp/benchet2.py /mnt/dump/test/bag/gouda/NUM/1005NUM01012010-0001.xml real 0m1.109s user 0m1.081s sys 0m0.027s
import sys
import lxml.etree as ET
ET.parse(sys.argv[1])
time python /tmp/benchlxml.py /mnt/dump/test/bag/gouda/NUM/1005NUM01012010-0001.xml real 0m0.837s user 0m0.773s sys 0m0.064s
Minidom kunnen we het beste vervangen, maar hoe weten we nu dat bij een beetje Python installatie we een goede ElementTree kiezen?
try:
import lxml.etree as ET
except ImportError:
try:
import cElementTree as ET
except ImportError:
try:
import elementtree.ElementTree as ET
except ImportError:
import xml.etree.ElementTree as ET