Develop Reference

Parse xml w/ xsd to CSV with Python?

I am trying to parse a very large XML file which I downloaded from OSHA's website and convert it into a CSV so I can use it in a SQLite database along with some other spreadsheets. I would just use an online converter, but the osha file is apparently too big for all of them.
I wrote a script in Python which looks like this:
import csv
import xml.etree.cElementTree as ET
tree = ET.parse('data.xml')
root = tree.getroot()
xml_data_to_csv =open('Out.csv', 'w')
list_head=[]
Csv_writer=csv.writer(xml_data_to_csv)
count=0
for element in root.findall('data'):
List_nodes =[]
if count== 0:
inspection_number = element.find('inspection_number').tag
list_head.append(inspection_number)
establishment_name = element.find('establishment_name').tag
list_head.append(establishment_name)
city = element.find('city')
list_head.append(city)
state = element.find('state')
list_head.append(state)
zip_code = element.find('zip_code')
list_head.append(zip_code)
sic_code = element.find('sic_code')
list_head.append(sic_code)
naics_code = element.find('naics_code')
list_head.append(naics_code)
sampling_number = element.find('sampling_number')
list_head.append(sampling_number)
office_id = element.find('office_id')
list_head.append(office_id)
date_sampled = element.find('date_sampled')
list_head.append(date_sampled)
date_reported = element.find('date_reported')
list_head.append(date_reported)
eight_hour_twa_calc = element.find('eight_hour_twa_calc')
list_head.append(eight_hour_twa_calc)
instrument_type = element.find('instrument_type')
list_head.append(instrument_type)
lab_number = element.find('lab_number')
list_head.append(lab_number)
field_number = element.find('field_number')
list_head.append(field_number)
sample_type = element.find('sample_type')
list_head.append(sample_type)
blank_used = element.find('blank_used')
list_head.append(blank_used)
time_sampled = element.find('time_sampled')
list_head.append(time_sampled)
air_volume_sampled = element.find('air_volume_sampled')
list_head.append(air_volume_sampled)
sample_weight = element.find('sample_weight')
list_head.append(sample_weight)
imis_substance_code = element.find('imis_substance_code')
list_head.append(imis_substance_code)
substance = element.find('substance')
list_head.append(substance)
sample_result = element.find('sample_result')
list_head.append(sample_result)
unit_of_measurement = element.find('unit_of_measurement')
list_head.append(unit_of_measurement)
qualifier = element.find('qualifier')
list_head.append(qualifier)
Csv_writer.writerow(list_head)
count = +1
inspection_number = element.find('inspection_number').text
List_nodes.append(inspection_number)
establishment_name = element.find('establishment_name').text
List_nodes.append(establishment_name)
city = element.find('city').text
List_nodes.append(city)
state = element.find('state').text
List_nodes.append(state)
zip_code = element.find('zip_code').text
List_nodes.append(zip_code)
sic_code = element.find('sic_code').text
List_nodes.append(sic_code)
naics_code = element.find('naics_code').text
List_nodes.append(naics_code)
sampling_number = element.find('sampling_number').text
List_nodes.append(sampling_number)
office_id = element.find('office_id').text
List_nodes.append(office_id)
date_sampled = element.find('date_sampled').text
List_nodes.append(date_sampled)
date_reported = element.find('date_reported').text
List_nodes.append(date_reported)
eight_hour_twa_calc = element.find('eight_hour_twa_calc').text
List_nodes.append(eight_hour_twa_calc)
instrument_type = element.find('instrument_type').text
List_nodes.append(instrument_type)
lab_number = element.find('lab_number').text
List_nodes.append(lab_number)
field_number = element.find('field_number').text
List_nodes.append(field_number)
sample_type = element.find('sample_type').text
List_nodes.append(sample_type)
blank_used = element.find('blank_used').text
List_nodes.append()
time_sampled = element.find('time_sampled').text
List_nodes.append(time_sampled)
air_volume_sampled = element.find('air_volume_sampled').text
List_nodes.append(air_volume_sampled)
sample_weight = element.find('sample_weight').text
List_nodes.append(sample_weight)
imis_substance_code = element.find('imis_substance_code').text
List_nodes.append(imis_substance_code)
substance = element.find('substance').text
List_nodes.append(substance)
sample_result = element.find('sample_result').text
List_nodes.append(sample_result)
unit_of_measurement = element.find('unit_of_measurement').text
List_nodes.append(unit_of_measurement)
qualifier= element.find('qualifier').text
List_nodes.append(qualifier)
Csv_writer.writerow(List_nodes)
xml_data_to_csv.close()
But when I run the code I get a CSV with nothing in it. I suspect this may have something to do with the XSD file associated with the XML, but I'm not totally sure.
Does anyone know what the issue is here?

The code below is a 'compact' version of your code.
It assumes that the XML structure looks like in the script variable xml. (Based on https://www.osha.gov/opengov/sample_data_2011.zip)
The main difference bwtween this sample code and yours is that I define the fields that I want to collect once (see FIELDS) and I use this definition across the script.
import xml.etree.ElementTree as ET
FIELDS = ['lab_number', 'instrument_type'] # TODO add more fields
xml = '''<main xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="health_sample_data.xsd">
<DATA_RECORD>
<inspection_number>316180165</inspection_number>
<establishment_name>PROFESSIONAL ENGINEERING SERVICES, LLC.</establishment_name>
<city>EUFAULA</city>
<state>AL</state>
<zip_code>36027</zip_code>
<sic_code>1799</sic_code>
<naics_code>238990</naics_code>
<sampling_number>434866166</sampling_number>
<office_id>418600</office_id>
<date_sampled>2011-12-30</date_sampled>
<date_reported>2011-12-30</date_reported>
<eight_hour_twa_calc>N</eight_hour_twa_calc>
<instrument_type>TBD</instrument_type>
<lab_number>L13645</lab_number>
<field_number>S1</field_number>
<sample_type>B</sample_type>
<blank_used>N</blank_used>
<time_sampled></time_sampled>
<air_volume_sampled></air_volume_sampled>
<sample_weight></sample_weight>
<imis_substance_code>S777</imis_substance_code>
<substance>Soil</substance>
<sample_result>0</sample_result>
<unit_of_measurement>AAAAA</unit_of_measurement>
<qualifier></qualifier>
</DATA_RECORD>
<DATA_RECORD>
<inspection_number>315516757</inspection_number>
<establishment_name>MARGUERITE CONCRETE CO.</establishment_name>
<city>WORCESTER</city>
<state>MA</state>
<zip_code>1608</zip_code>
<sic_code>1771</sic_code>
<naics_code>238110</naics_code>
<sampling_number>423259902</sampling_number>
<office_id>112600</office_id>
<date_sampled>2011-12-30</date_sampled>
<date_reported>2011-12-30</date_reported>
<eight_hour_twa_calc>N</eight_hour_twa_calc>
<instrument_type>GRAV</instrument_type>
<lab_number>L13355</lab_number>
<field_number>9831B</field_number>
<sample_type>P</sample_type>
<blank_used>N</blank_used>
<time_sampled>184</time_sampled>
<air_volume_sampled>340.4</air_volume_sampled>
<sample_weight>.06</sample_weight>
<imis_substance_code>9135</imis_substance_code>
<substance>Particulates not otherwise regulated (Total Dust)</substance>
<sample_result>0.176</sample_result>
<unit_of_measurement>M</unit_of_measurement>
<qualifier></qualifier>
</DATA_RECORD></main>'''
root = ET.fromstring(xml)
records = root.findall('.//DATA_RECORD')
with open('out.csv', 'w') as out:
out.write(','.join(FIELDS) + '\n')
for record in records:
values = [record.find(f).text for f in FIELDS]
out.write(','.join(values) + '\n')
out.csv
lab_number,instrument_type
L13645,TBD
L13355,GRAV

IndexError when using secrets.choice from dictionary

I have a dictionary of providers, which will contain elements like the one below:
{ 'p_4_0_0': {'technicians': ['683707d2-be18-49b7-bf67-a32048103ca1', '23d06b03-41f4-48cc-b83f-347ebfcb3084']}, 'p_4_0_1': {'technicians': ['d226a9b6-58f3-4f94-bf81-abd4dc825dca']}, ... }
The format used for the keys is string_id_level_pid, and I use secrets.choice to get a random element where the level part of the string is equal to the current level in my loop. However, I get the following error:
Traceback (most recent call last): File
"path/to/file/graph.py",
line 122, in
generate_graph(100) File "path/to/file/graph.py",
line 112, in generate_graph
provider = providers[secrets.choice(list({k:v for (k,v) in providers.items() if (k.split('_'))[2] == str(level)}))] File
"C:\Users\\AppData\Local\Programs\Python\Python37\lib\random.py",
line 261, in choice
raise IndexError('Cannot choose from an empty sequence') from None IndexError: Cannot choose from an empty sequence [Finished in 1.564s]
The full working code is here:
import networkx as nx
import matplotlib.pyplot as plt
from random import randrange,choices,randint
from pathlib import Path
import random
import secrets
import uuid
import math
import json
import os
# ============================================================================ #
# create a technician with id and provider id
def create_technician():
return str(uuid.uuid4())
# create a provider with n technicians
def create_provider(region_id, level, number, n):
id = 'p_'+str(region_id)+'_'+str(level)+'_'+str(number)
# Create n technicians
technicians = []
for i in range(n):
technicians.append(create_technician())
return {id:{'technicians': technicians}}
def create_nmi_technicians(n):
technicians = []
for i in range(n):
technicians.append(create_technician())
return technicians
# Create report with parents + technician
def create_report(device_id, level, technician, parents):
return {'id': device_id, 'level': level, 'technician': technician, 'parents': parents}
# n = number of field devices
def generate_graph(num_field_devices):
max_chain_length = int(2*math.log(num_field_devices, 10))
## Info ##
# ====== #
# Field level = 0
# NMI = max_chain_length-1
nmi_level = str(max_chain_length-1)
regions = {
'USA': {'id': '1', 'NMI': {'level': nmi_level, 'acronym': 'NIST', 'technicians': create_nmi_technicians(5)}},
'UK': {'id': '2', 'NMI': {'level': nmi_level, 'acronym': 'NPL', 'technicians': create_nmi_technicians(4)}},
'China': {'id': '3', 'NMI': {'level': nmi_level, 'acronym': 'NIM', 'technicians': create_nmi_technicians(3)}},
'France': {'id': '4', 'NMI': {'level': nmi_level, 'acronym': 'LNE', 'technicians': create_nmi_technicians(3)}}
}
# For each region, create a set of
# 1 to m calibration service
# providers for each level up to
# the field level
for region, data in regions.items():
# Create providers dict
providers = {}
# For range between field (0) and
# max_chain_length-2, create providers
for i in range(0, max_chain_length-1):
# Choose between 2 and 5 providers
m = randint(2, 5)
x = 0
for j in range(m):
# create provider with 1-3 technicians
providers.update(create_provider(data['id'], i, x, randint(1,3)))
x = x + 1
# Add providers to region
data.update({'providers': providers})
#print(json.dumps(regions, indent=4))
# Cool, now this is done, create the calibration
# reports for the chain!
devices = {}
for level in range(max_chain_length):
devices.update({level: []})
# Field level
if level == 0:
for i in range(num_field_devices):
devices[level].append(str(uuid.uuid4()))
else:
k = int(math.pow((2/3), level) * num_field_devices)
for i in range(k):
devices[level].append(str(uuid.uuid4()))
# Create reports for these devices with parents + technician
reports = {}
for level,devs in devices.items():
for device in devs:
if level == 0:
# Choose 2-3 parents from upper level
parents = choices(devices[level+1], k=randrange(2,4))
elif level == max_chain_length-1:
# NMI level has no parents
parents = []
else:
# Choose 1-2 parents from upper level
parents = choices(devices[level+1], k=randrange(1,3))
# Choose random region
region = regions[secrets.choice(list(regions))]
# Choose random provider at same level
providers = region['providers']
provider = providers[secrets.choice(list({k:v for (k,v) in providers.items() if (k.split('_'))[2] == str(level)}))]
# Choose technician at the same level
technician = secrets.choice(provider['technicians'])
reports.update({'id': create_report(device, level, technician, parents)})
print(reports)
## Run ##
# ===== #
generate_graph(100)
EDIT: the last element in providers is {} (empty dict) - what is the reason for this?

The highest level has its technicians in the NMI region, not in a provider dict. The solution here was the following:
# Choose random region
region = regions[secrets.choice(list(regions))]
# If NMI, use NMI technician, otherwise
# choose a provider from the level
if level == max_chain_length-1:
technician = secrets.choice(region['NMI']['technicians'])
else:
# Choose random provider at same level
providers = region['providers']
provider = providers[secrets.choice(list({k:v for (k,v) in providers.items() if (k.split('_'))[2] == str(level)}))]
# Choose technician at the same level
technician = secrets.choice(provider['technicians'])

Trying to avoid creating numerous variables in python

I am new to python and I have a lot of variables I will be using in this script. These variables are being used to grab data from each column in an uploaded file. I have added variables for each object type and I have about 12 more object types to add. Isn't there a better way I can do this? I have the file it's grabbing data from here:
Action Object Solution ID hostgroup_name alias
Add Host Group ISD-CR ISD-CR_database ISD-CR Database
Add Service ISD-CR ISD-CR_database
Update Service Group ISD-CR ISD-CR Database
Delete Service ISD-CR ISD-CR_database
Here is the script I have so far.
from pynag import Model
from pynag.Parsers import config
def addObject():
# Add hostgroup object
hg = Model.Hostgroup()
hg.set_filename('/etc/nagios/objects/solution1/{0}.cfg'.format(target_hostgroup_name))
# Adding all attributes to allow any to be added if needed
hg.hostgroup_name = target_hostgroup_name
hg.alias = target_alias
hg.members = target_members
hg.hostgroup_members = target_hostgroup_members
hg.notes = target_notes
hg.notes_url = target_notes_url
hg.action_url = target_action_url
# Save
hg.save()
print "hostgroup added"
# Add service object
s = Model.Service()
s.set_filename('/etc/nagios/objects/solution1/{0}.cfg'.format(target_hostgroup_name))
# Adding all attributes to allow any to be added if needed
s.host_name = target_host_name
s.hostgroup_name = target_hostgroup_name
s.service_description = target_service_description
s.display_name = target_display_name
s.servicegroups = target_servicegroups
s.is_volatile = target_is_volatile
s.check_command = target_check_command
s.initial_state = target_initial_state
s.max_check_attempts = target_max_check_attempts
s.check_interval = target_check_interval
s.retry_interval = target_retry_interval
s.active_checks_enabled = target_active_checks_enabled
s.passive_checks_enabled = target_passive_checks_enabled
s.check_period = target_check_period
s.obsess_over_service = target_obsess_over_service
s.check_freshness = target_check_freshness
s.freshness_threshold = target_freshness_threshold
s.event_handler = target_event_handler
s.event_handler_enabled = target_event_handler_enabled
s.low_flap_threshold = target_low_flap_threshold
s.high_flap_threshold = target_high_flap_threshold
s.flap_detection_enabled = target_flap_detection_enabled
s.flap_detection_options = target_flap_detection_options
s.process_perf_data = target_process_perf_data
s.retain_status_information = target_retain_status_information
s.retain_nonstatus_information = target_retain_nonstatus_information
s.notification_interval = target_notification_interval
s.first_notification_delay = target_first_notification_delay
s.notification_period = target_notification_period
s.notification_options = target_notification_options
s.notification_enabled = target_notifications_enabled
s.contacts = target_contacts
s.contact_groups = target_contact_groups
s.stalking_options = target_stalking_options
s.notes = target_notes
s.notes_url = target_notes_url
s.action_url = target_action_url
s.icon_image = target_icon_image
s.icon_image_alt = target_icon_image_alt
# Save
s.save()
print "service added"
# Add servicegroup object
sg = Model.Servicegroup()
sg.set_filename('/etc/nagios/objects/solution1/{0}.cfg'.format(target_hostgroup_name))
# Adding all attributes to allow any to be added if needed
sg.servicegroup_name = target_servicegroup_name
sg.alias = target_alias
sg.members = target_members
sg.servicegroup_members = target_servicegroup_members
sg.notes = target_notes
sg.notes_url = target_notes_url
sg.action_url = '/etc/nagios/objects/solution1/{0}.cfg'.format(target_hostgroup_name)
# Save
sg.save()
print "service group added"
try:
current_file = csv.reader(open(input_file, "rb"), delimiter='\t')
except:
logging.error('No such file or directory. Please try again')
else:
for line in current_file:
for row in current_file:
target_hostgroup_name = row[3]
target_alias = row[4]
target_members = row[5]
target_hostgroup_members = row[6]
target_notes = row[7]
target_notes_url = row[8]
target_action_url = row[9]
target_host_name = row[10]
target_service_description = row[11]
target_display_name = row[12]
target_servicegroups = row[13]
target_is_volatile = row[14]
target_check_command = row[15]
target_initial_state = row[16]
target_max_check_attempts = row[17]
target_check_interval = row[18]
target_retry_interval = row[19]
target_active_checks_enabled = row[20]
target_passive_checks_enabled = row[21]
target_check_period = row[22]
target_obsess_over_service = row[23]
target_check_freshness = row[24]
target_freshness_threshold = row[25]
target_event_handler = row[26]
target_event_handler_enabled = row[27]
target_low_flap_threshold = row[28]
target_high_flap_threshold = row[29]
target_flap_detection_enabled = row[30]
target_flap_detection_options = row[31]
target_process_perf_data = row[32]
target_retain_status_information = row[33]
target_retain_nonstatus_information = row[34]
target_notification_interval = row[35]
target_first_notification_delay = row[36]
target_notification_period = row[37]
target_notification_options = row[38]
target_notifications_enabled = row[39]
target_contacts = row[40]
target_contact_groups = row[41]
target_stalking_options = row[42]
target_icon_image = row[43]
target_icon_image_alt = row[44]
target_servicegroup_name = row[45]
target_servicegroup_members = row[46]

If the values are in the same order every time, you could consider populating a list that you then could loop over, instead of doing it one by one.
For the "target" portion of your script, you could nest another loop for range(3, 46) as well, and pass the index to your list instead of manually for every number from 3 to 46.

Why do you do this?
for line in current_file:
for row in current_file:
If the first row is a header row and you're skipping it on purpose, you can use a DictReader instead.
It doesn't look like you'll be able to do much to clean this up, but you could factor out each "section" into its own function:
def save_hostgroup(name, alias, members, hostgroup_members, notes, notes_url, action_url):
hg = Model.Hostgroup()
hg.set_filename('/etc/nagios/objects/solution1/{0}.cfg'.format(target_hostgroup_name))
# Adding all attributes to allow any to be added if needed
hg.hostgroup_name = target_hostgroup_name
hg.alias = target_alias
hg.members = target_members
hg.hostgroup_members = target_hostgroup_members
hg.notes = target_notes
hg.notes_url = target_notes_url
hg.action_url = target_action_url
hg.save()

Behind the scenes all the member names of an object are stored in a dict. You can access this dict with vars(obj) or obj.__dict__. You can then use the update method of the dict to add a set of names to your object.
eg.
class SomeClass:
def __str__(self):
return "SomeClass({})".format(
", ".join(
"{}={!r}".format(key, value)
for key, value in self.__dict__.items()
)
)
__repr__ = __str__
target_names = ['var_a', 'var_b', 'var_c']
target_values = [1, 2, 3]
target = dict(zip(target_names, target_values))
assert target == {'var_a': 1, 'var_b': 2, 'var_c': 3}
s = SomeClass()
vars(s).update(target)
assert hasattr(s, 'var_a')
assert s.var_a == 1
print(s) # prints SomeClass(var_c=3, var_a=1, var_b=2)

What Should Be In My Return?

I am using Python to parse an XML response from a SOAP web-service. The Customer returns about 40 values as you can see below. I would like to know if there is a way to make it so I only have to type one thing into my return statement and get all of the values returned? I tried to use for customer in doc.findall('.//Customer').itervalues() and that did not work as I believe that call is for dictionaries. Same results and reasoning behind .iteritems.
doc = ET.fromstring(response_xml)
for customer in doc.findall('.//Customer'):
customer_number = customer.findtext('CustomerNumber')
customer_first_name = customer.findtext('FirstName')
customer_last_name = customer.findtext('LastName')
customer_middle_name = customer.findtext('MiddleName')
customer_salutation = customer.findtext('Salutation')
customer_gender = customer.findtext('Gender')
customer_language = customer.findtext('Language')
customer_address1 = customer.findtext('Address1')
customer_address2 = customer.findtext('Address2')
customer_address3 = customer.findtext('Address3')
customer_city = customer.findtext('City')
customer_county = customer.findtext('County')
customer_state_code = customer.findtext('StateCode')
customer_zip_code = customer.findtext('ZipCode')
customer_phone_number = customer.findtext('PhoneNumber')
customer_business_phone = customer.findtext('BusinessPhone')
customer_business_ext = customer.findtext('BusinessExt')
customer_fax_number = customer.findtext('FaxNumber')
customer_birth_date = customer.findtext('BirthDate')
customer_drivers_license = customer.findtext('DriversLicense')
customer_contact = customer.findtext('Contact')
customer_preferred_contact = customer.findtext('PreferredContact')
customer_mail_code = customer.findtext('MailCode')
customer_tax_exempt_Number = customer.findtext('TaxExmptNumber')
customer_assigned_salesperson = customer.findtext('AssignedSalesperson')
customer_type = customer.findtext('CustomerType')
customer_preferred_phone = customer.findtext('PreferredPhone')
customer_cell_phone = customer.findtext('CellPhone')
customer_page_phone = customer.findtext('PagePhone')
customer_other_phone = customer.findtext('OtherPhone')
customer_other_phone_desc = customer.findtext('OtherPhoneDesc')
customer_email1 = customer.findtext('Email1')
customer_email2 = customer.findtext('Email2')
customer_optional_field = customer.findtext('OptionalField')
customer_allow_contact_postal = customer.findtext('AllowContactByPostal')
customer_allow_contact_phone = customer.findtext('AllowContactByPhone')
customer_allow_contact_email = customer.findtext('AllowContactByEmail')
customer_business_phone_ext = customer.findtext('BusinessPhoneExtension')
customer_internatinol_bus_phone = customer.findtext('InternationalBusinessPhone')
customer_international_cell = customer.findtext('InternationalCellPhone')
customer_external_x_reference_key = customer.findtext('ExternalCrossReferenceKey')
customer_international_fax = customer.findtext('InternationalFaxNumber')
customer_international_other_phone = customer.findtext('InternationalOtherPhone')
customer_international_home_phone = customer.findtext('InternationalHomePhone')
customer_preferred_name = customer.findtext('CustomerPreferredName')
customer_international_pager = customer.findtext('InternationalPagerPhone')
customer_preferred_lang = customer.findtext('PreferredLanguage')
customer_last_change_date = customer.findtext('LastChangeDate')
customer_vehicles = customer.findtext('Vehicles')
customer_ccid = customer.findtext('CCID')
customer_cccd = customer.findtext('CCCD')
webservice.close()
return

I would write that as a generator function yielding dicts where the key matches the findtext argument, e.g.:
fields = ['CustomerNumber', 'FirstName', 'LastName',
# ...
]
for customer in doc.findall('.//Customer'):
yield dict((f, customer.findtext(f)) for f in fields)

You either want to return a list of dicts:
customers = []
for customer in doc.findall('.//Customer'):
customer_dict = {}
customer_dict['number'] = customer.findtext('CustomerNumber')
customer_dict['first_name'] = customer.findtext('FirstName')
customer_dict['last_name'] = customer.findtext('LastName')
# ad nauseum
customers.append(customer_dict)
webservice.close()
return customers
Or you make a Customer class that handles this, and you return a list of customer instances.

I would use a dictionary of dictionaries:
doc = ET.fromstring(response_xml)
customers = {}
cust_dict = {}
for customer in doc.findall('.//Customer'):
cust_dict['customer_number'] = customer.findtext('CustomerNumber')
cust_dict['customer_first_name'] = customer.findtext('FirstName')
cust_dict['customer_last_name'] = customer.findtext('LastName')
snip snip...
customers[customer_number] = cust_dict # or whatever property you want to use to identify each customer, I'm assuming customer_number is some sort of id number
webservice.close()
return customers
That is if you don't have a class you can use to create a Customer object.

How to specify multiple author(s) / email(s) in setup.py

We wrote a small wrapper to a twitter app and published this information to http://pypi.python.org. But setup.py just contained a single field for specifying email / name of the author. How do I specify multiple contributors / email list, to the following fields since we would like this package to be listed under our names, much similar to how it shows up in http://rubygems.org.
author='foo',
author_email='foo.bar#gmail.com',

As far as I know, setuptools doesn't support using a list of strings in order to specify multiple authors. Your best bet is to list the authors in a single string:
author='Foo Bar, Spam Eggs',
author_email='foobar#baz.com, spameggs#joe.org',
I'm not sure if PyPI validates the author_email field, so you may run into trouble with that one. In any case, I would recommend you limit these to a single author and mention all contributors in the documentation or description.
Some sources:
This has been registered as a bug, actually, but it seems like support for multiple authors was not implemented. Here is an alternative solution. Here is an idea for how to provide a contact email for a project with multiple authors.

I'm sort of just piggybacking off of #modocache's answer, in case you want some specifics.
Throughout this answer, I'll be refering to a python3.6 version of the FOO-PYTHON-ENV\Lib\distutils\dist.py file
To reiterate, you cannot use a list in the author field. Here's why:
Spoiler: Two methods belonging to the DistributionMetadata class are the reason --
def _read_field(name):
value = msg[name]
if value == 'UNKNOWN':
return None
return value
def _read_list(name):
values = msg.get_all(name, None)
if values == []:
return None
return values
Here's where you'll hit an error if you try to stick a list in the author field:
class DistributionMetadata:
#*...(R E D A C T E D)...*#
def read_pkg_file(self, file):
"""Reads the metadata values from a file object."""
#*...(R E D A C T E D)...*#
# ####################################
# Note the usage of _read_field() here
# ####################################
self.name = _read_field('name')
self.version = _read_field('version')
self.description = _read_field('summary')
# we are filling author only.
self.author = _read_field('author')
self.maintainer = None
self.author_email = _read_field('author-email')
self.maintainer_email = None
self.url = _read_field('home-page')
self.license = _read_field('license')
#*...(R E D A C T E D)...*#
# ###################################
# Note the usage of _read_list() here
# ###################################
self.platforms = _read_list('platform')
self.classifiers = _read_list('classifier')
#*...(R E D A C T E D)...*#
& Here's the whole thing:
class DistributionMetadata:
"""Dummy class to hold the distribution meta-data: name, version,
author, and so forth.
"""
_METHOD_BASENAMES = ("name", "version", "author", "author_email",
"maintainer", "maintainer_email", "url",
"license", "description", "long_description",
"keywords", "platforms", "fullname", "contact",
"contact_email", "classifiers", "download_url",
# PEP 314
"provides", "requires", "obsoletes",
)
def __init__(self, path=None):
if path is not None:
self.read_pkg_file(open(path))
else:
self.name = None
self.version = None
self.author = None
self.author_email = None
self.maintainer = None
self.maintainer_email = None
self.url = None
self.license = None
self.description = None
self.long_description = None
self.keywords = None
self.platforms = None
self.classifiers = None
self.download_url = None
# PEP 314
self.provides = None
self.requires = None
self.obsoletes = None
def read_pkg_file(self, file):
"""Reads the metadata values from a file object."""
msg = message_from_file(file)
def _read_field(name):
value = msg[name]
if value == 'UNKNOWN':
return None
return value
def _read_list(name):
values = msg.get_all(name, None)
if values == []:
return None
return values
metadata_version = msg['metadata-version']
self.name = _read_field('name')
self.version = _read_field('version')
self.description = _read_field('summary')
# we are filling author only.
self.author = _read_field('author')
self.maintainer = None
self.author_email = _read_field('author-email')
self.maintainer_email = None
self.url = _read_field('home-page')
self.license = _read_field('license')
if 'download-url' in msg:
self.download_url = _read_field('download-url')
else:
self.download_url = None
self.long_description = _read_field('description')
self.description = _read_field('summary')
if 'keywords' in msg:
self.keywords = _read_field('keywords').split(',')
self.platforms = _read_list('platform')
self.classifiers = _read_list('classifier')
# PEP 314 - these fields only exist in 1.1
if metadata_version == '1.1':
self.requires = _read_list('requires')
self.provides = _read_list('provides')
self.obsoletes = _read_list('obsoletes')
else:
self.requires = None
self.provides = None
self.obsoletes = None

Consider using flit to build the package, as this build system supports multiple authors and maintainers. Store this metadata in pyproject.toml as follows:
[build-system]
requires = ["flit_core >=3.2,<4"]
build-backend = "flit_core.buildapi"
[project]
...
authors = [
{name = "First1 Last1", email = "name1#foo.bar"},
{name = "First2 Last2", email = "name2#foo.bar"},
]
maintainers = [
{name = "First1 Last1", email = "name1#foo.bar"},
{name = "First2 Last2", email = "name2#foo.bar"},
]