kbquery3

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import requests
import re
import string
import csv
import xml.etree.ElementTree as ET

inputFile  = input("Input File: ")
outputFile = input("Name of file to save results: ")
queryType = input('What are you searching on? ISSN, ISBN, OCN, or Title: ')
collectionID = input("To search in a particular collection, enter its ID otherwise type 'no': ")
fieldNames = ["publication_title", "print_identifier", "online_identifier", "date_first_issue_online", "num_first_vol_online", "num_first_issue_online", "date_last_issue_online", "num_last_vol_online", "num_last_issue_online", "title_url", "first_author", "title_id", "embargo_info", "coverage_depth",	"coverage_notes", "publisher_name", "location", "title_notes", "staff_notes", "vendor_id", "oclc_collection_name", "oclc_collection_id", "oclc_entry_id", "oclc_linkscheme", "oclc_number",	"ACTION"]
completeKbartCheck = 0

#Add your API key below, assigned to the "key" variable

key = ''
ns = {'kb' : 'http://worldcat.org/kb', 'atom' : 'http://www.w3.org/2005/Atom', 'os' : 'http://a9.com/-/spec/opensearch/1.1/'}
#ns variable is used for namespaces for the XML that the KB API returns
if queryType == 'ISSN':
	searcher = 'issn='
elif queryType == 'ISBN':
	searcher = 'isbn='
elif queryType == 'Title':
	searcher = "title="
elif queryType == 'OCN':
	searcher = 'oclcnum='
else:
	searcher = 'q='	
	
if collectionID == 'no':
	collectionSearch = ''
else:
	collectionSearch = "collection_uid="+collectionID

with open(inputFile, 'r') as f:
	with open(outputFile, 'a+') as o:
		o.write('number'+'	'+'status'+'	'+'title' + '	' + 'ISBN or ISSN' + '	' + 'ocn' + '	' + 'Collection Name' + '	' + 'KB ID' +'	' + 'coverage'+ '	' +'Search Term'+'	'+'\n')
		termCount = 0
		for terms in f:
			if queryType == 'Title':
				term = '"'+terms.strip()+'"'
				if "&" in term:
					term = term.replace('&', '&')
			else:
				term = terms.strip()
			termCount +=1
			print('Search number: ' +str(termCount)+'    Search term: '+term)
			if term == '\n':
				o.write('blank'+'\n')
				print('no search term')
			else:			
				url ='http://worldcat.org/webservices/kb/rest/entries/search?'+collectionSearch+'&'+searcher+term+'&wskey='+key
				print(url)
				r = requests.get(url.strip()).text
				results = r.encode('utf-8')
				root = ET.fromstring(results)
				resultCheck = root.find('os:totalResults', ns)
				emptyCheck = resultCheck.text
				if emptyCheck == "0":
					if collectionID == "no":
						o.write(term + ' not found' + '\n')
						print(term + ' not found')
					else:
						#if a collection ID is provided and a title is not found to be selected, this triggers the script to pull the full KBART
						#and then search to see if the title is not in the collection at all or simply not selected
						if completeKbartCheck == 0:
							collectionURL = 'http://worldcat.org/webservices/kb/rest/collections/'+collectionID+'?wskey='+key
							print(collectionURL)
							collectionResponse = requests.get(collectionURL.strip()).text
							collectionResults = collectionResponse.encode('utf-8')
							collectionResultsRoot = ET.fromstring(collectionResults)
							#Xpath may need to be fixed. Likely may need to do xpath just with attribute and value...?
							getLink = collectionResultsRoot.find('./atom:link[@title="kbart file"]', ns)
							link = getLink.get('href')
							kbartTitle = collectionID+'kbart.txt'
							fullLink = link + '?wskey='+key
							print(fullLink)
							print("downloading: " + kbartTitle)
							kbartRequest = requests.get(fullLink.strip()).text
							kbartTitle = collectionID+'kbart.txt'
							kbartWriter = open(kbartTitle, 'w+')
							kbartWriter.write(kbartRequest)
							kbartWriter.close()
						completeKbartCheck += 1
						kbartData = open(kbartTitle, 'r')
						#after writing KBART data to a file, the script then reads the KBART and tries to find a match based on the kind of query, ISSN, OCN, etc
						tsvreader = csv.DictReader(kbartData, delimiter='\t')
						matchFound = 'no'
						for row in tsvreader:
							if queryType == 'ISSN':
								if term == row['online_identifier']:
									matchFound = 'yes'
								elif term == row['print_identifier']:
									matchFound = 'yes'
							elif queryType == 'ISBN':
								if term == row['online_identifier']:
									matchFound = 'yes'
								elif term == row['print_identifier']:
									matchFound = 'yes'
							elif queryType == 'Title':
								if term == row['publication_title']:
									matchFound = 'yes'
							elif queryType == 'OCN':
								if term == row["oclc_number"]:
									matchFound = 'yes'
							else:
								matchFound = 'no'
						numb = str(termCount)
						if matchFound == 'yes':
							o.write(numb+'\t'+'not selected but available in global KB'+'\t\t\t\t\t\t\t'+term+'\n')
							print(term + ' not selected')
						elif matchFound == 'no':
							o.write(numb+'\t'+'not available'+'\t\t\t\t\t\t\t'+term+'\n')
							print(term + ' not available')
				
				else:						
					entryLoopNumber = 0
					for entry in root.findall('atom:entry', ns):
						entryLoopNumber +=1
						numb =str(termCount)+'.'+str(entryLoopNumber)
						titleText = entry.find('atom:title', ns)
						status = 'selected'
						if titleText is None:
							title = "No title"
						else:
							title = titleText.text
						ocnText = entry.find('kb:oclcnum', ns)
						if ocnText is None:
							ocn = "no OCN"
						else:
							ocn = ocnText.text
						covText = entry.find('kb:coverage', ns)
						if covText is None:
							cov = "no coverage"
						else:
							cov = covText.text
						coll = entry.find('kb:collection_name', ns).text
						issnCheck = entry.find('kb:issn', ns)
						if issnCheck is None:
							isbnCheck = entry.find('kb:isbn', ns)
							if isbnCheck is None:
								sn = "No Standard number found"
							else:
								sn = isbnCheck.text
						else:
							sn = issnCheck.text
						uidText = entry.find('kb:entry_uid', ns)
						if uidText is None:
							uid = "no KB ID"
						else:
							uid = uidText.text
						data = numb+'	'+status+'	'+title+'	'+sn+'	'+ocn+'	'+coll+'	'+uid+'	'+cov+'	'+term+'	'+'\n'
						print(data)
						o.write(data)