Print Extents from EADs

printextents.py

import lxml
from lxml import etree
import os
from os.path import join

# Enter the path to the folder containing your EADs
path = 'path/to/EADs'

# Check each file in the EAD folder
for filename in os.listdir(path):
    tree = etree.parse(join(path, filename))
    extents = tree.xpath('//ead/archdesc/did//physdesc/extent') # Check each collection level extent
    for e in extents: # Output the contents of each extent
        extent = e.text
        print 'The extent of ' + filename + ' is: ' + extent