test.py

from urllib import urlopen
import subprocess
import pandas as pd
from xml.etree import ElementTree as ET
from time import sleep
import datetime
import base64

root = ET.parse(urlopen('http://webservice.wikipathways.org/listPathways')).getroot()
list_of_pathways = [list(i)[0].text for i in root]
pathway_names = [list(i)[2].text.replace(" ", "_") for i in root]
pathway_species = [list(i)[3].text.replace(" ", "_") for i in root]                                                               
api_out = []
api = []
fails = []
more = []
more1 = []

trash = []
trash1 = []
count = 0
for pathway, pathway_name, specie in zip(list_of_pathways, pathway_names, pathway_species):
	if pathway == 'WP3617':
	    try:
	        temp = ET.parse(urlopen('http://webservice.wikipathways.org/getPathway?pwId={}'.format(pathway))).getroot()
	        for i in temp:
	            gpml_text = i[0].text
		    gpml_text = base64.b64decode(gpml_text)
	            name = i[1].text
	        with open("output.gpml", "w") as text_file:
	            text_file.write(gpml_text)
	        file = "http://159.203.176.220/api/users/[email protected]/graph/add/{}_{}_{}_api.gpml/".format(name, pathway_name, specie)
	        location = 'graphname=@"/home/test/output.gpml"'
	        proc = subprocess.Popen(["curl", "-X", "POST",  file, "-F", "[email protected]", "-F", "password=test" , "-F",  location], stdout=subprocess.PIPE)
	        (out, err) = proc.communicate()
	        print(out)
	        if out[-6:] == b' 400\n}':
	            more.append(out)
	            more1.append(pathway)
	        elif out[-6:] == b' 201\n}':
	            api_out.append(out)
	            api.append(pathway)
	        else:
	            trash.append(out)
	            trash1.append(pathway)
	    except:
	        fails.append(pathway)
	    print pathway, count
	    count += 1
	    print datetime.datetime.now()
	    sleep(0.3)
# success = pd.DataFrame({'WP': api, 'Return Message': api_out})
# failure = pd.DataFrame({'WP': more1, 'Return Message': more})
# trash = pd.DataFrame({'WP': trash1, 'Return Message': trash})
# api_fail = pd.DataFrame({'WP':fails, 'Return Message': 'API fail'})

# result = pd.concat([success, failure, trash, api_fail])
# result.to_csv('testing.csv')

# print '========================'
# with open("list.txt", "w") as text_file:
#             text_file.write("{0}".format(list_of_pathways))
# with open("failure_due_toerror.txt", "w") as text_file:
#             text_file.write("{0} \n {1}".format(more, more1))
# with open("something.txt", "w") as text_file:
#             text_file.write("{0} \n {1}".format(trash, trash1))
# with open("notabletoparse.txt", "w") as text_file:
#             text_file.write("{0} ".format(fails))
# with open("api_out.txt", "w") as text_file:
#             text_file.write("{0} \n {1}".format(api_out, api))