source: main/trunk/model-sites-dev/atea/collect/digital-nz/prepare/dnz-search-language-mi--python3.py@ 34460

#!/usr/bin/env python3

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from builtins import str

import os
import sys
import re
import json
#import pprint

import dnz.api


output_dir = "downloads"

# DNZ key
with open('dnzkey.txt','r') as file:
    dnzkey_str = file.read().strip()
    
# print("dnzkey_str = '" + dnzkey_str + "'")
DNZ = dnz.api.Dnz(dnzkey_str) 


#result = dnz.search('kiwi tui')
#result = dnz.search('kiwi tui', per_page=50, page=10, fields=['id', 'title', 'collection', 'content_partner'])
#result = dnz.search(_or={'category':['Videos', 'Images']}, _and={'content_partner':['Ministry for Culture and Heritage']})

query_term={'language':['mi']}

results = DNZ.search(_and=query_term, per_page=50)
num_results=results.result_count
print("Number of matching records: " + str(results.result_count))


for i in range(0,num_results,50):
    page = i / 50
    results = DNZ.search(_and=query_term, page=page, per_page=50)

    for rec in results.records:
        #    pprint.pprint(rec)
        landing_url = rec["landing_url"]
        print("Landing URL: " + rec["landing_url"])

        ### !!! landing_url = unicode(landing_url).encode('utf8')
        ##landing_url = str(landing_url).encode('utf8')
        #json_landing_filename = re.sub('[:/.]', '-', landing_url) + ".json"

        json_landing_filename1 = re.sub('[:]', '~COLON~', landing_url)
        json_landing_filename2 = re.sub('[/]', '~SLASH~', json_landing_filename1)
        json_landing_filename  = re.sub('[.]', '~DOT~', json_landing_filename2) + ".json"
                
        full_json_landing_filename = os.path.join(output_dir,json_landing_filename)
        print("json_landing_filename:\t" + json_landing_filename)
        
        dc_identifiers = rec["dc_identifier"]

        #json.dump(rec, sys.stdout)

        if (len(dc_identifiers)>0):
                        
            ### !!! full_id = unicode(dc_identifiers[0]).encode('utf8')
            full_id = dc_identifiers[0]
            
            print("  ID: " + full_id)

            # tail_id = full_id.replace('http://hdl.handle.net/','')
        
            # json_filename = re.sub('[:/.]', '-', tail_id) + ".json"
            # print json_filename
        else:
            print("**** No ID specified")


        with open(full_json_landing_filename, 'w') as outfile:
            json.dump(rec, outfile)
            
        print("")

#pprint.pprint(result.records)