Script to query OpenDoar for science sites in English that allow free access to their metadata; parses the XML into JSON

get_oai_free_science_sites.py

import urllib2
import xml.etree.ElementTree as etree
import json

# Query for sites in English that have science data, an OAI URL, and allow free access to metadata. 
resp = urllib2.urlopen('http://opendoar.org/api13.php?la=en&oai=y&pograde=11,12&subject=Ca,Ce,Cur,Cuv')
data = resp.read()
tree = etree.fromstring(data)
l = []
for child in tree.iter('repository'):
    d = {}
    for item in child:
        if item.tag in ['rUrl', 'rOaiBaseUrl', 'rName']:
            d[item.tag] = item.text
    l.append(d)

# Prints a list of all returned repositories' names, URLs, OAI URLs in JSON format (list of dicts)
print json.dumps(l)