list_collaborators.py

import string
import urllib
from xml.etree.ElementTree import ElementTree
from StringIO import StringIO

search_author = "Goodman, A."

base_url = '''http://adsabs.harvard.edu/cgi-bin/nph-abs_connect?db_key=AST&'''

parameters = {}
parameters['author'] = search_author.replace(',', '%2C')
parameters['data_type'] = "SHORT_XML"
parameters['jou_pick'] = "NO"
parameters['start_month'] = "10"
parameters['start_year'] = "2007"
parameters['end_month'] = "10"
parameters['end_year'] = "2011"

query = string.join(["%s=%s" % (key, parameters[key])
                    for key in parameters], "&")

f = urllib.urlopen(base_url + query)

# Parse XML
e = ElementTree()
root = e.parse(StringIO(f.read()))

count = {}

# Loop over articles
for record in root.getchildren():

    # Loop over fields
    for field in record.getchildren():

        # Look only at author tags
        if 'author' in field.tag:

            # Split into first and last name
            lastname, firstname = field.text.split(',')[0:2]

            # Keep only first initial of first name
            firstname = firstname.strip()[0]

            # Make author name into the form "Robitaille, T."
            fullname = lastname + ", " + firstname + "."

            # Add author to counter
            if fullname in count:
                count[fullname] += 1
            else:
                count[fullname] = 1

# Print out final list
for author in count:
    if search_author not in author:
        print author + ": " + str(count[author])