nhentai/serializer.py

   1 # coding: utf-8
   2 import json
   3 import os
   4 from xml.sax.saxutils import escape
   5 from nhentai.constant import LANGUAGEISO
   6
   7 def serialize_json(doujinshi, dir):
   8     metadata = {'title': doujinshi.name,
   9                 'subtitle': doujinshi.info.subtitle}
  10     if doujinshi.info.date:
  11         metadata['upload_date'] = doujinshi.info.date
  12     if doujinshi.info.parodies:
  13         metadata['parody'] = [i.strip() for i in doujinshi.info.parodies.split(',')]
  14     if doujinshi.info.characters:
  15         metadata['character'] = [i.strip() for i in doujinshi.info.characters.split(',')]
  16     if doujinshi.info.tags:
  17         metadata['tag'] = [i.strip() for i in doujinshi.info.tags.split(',')]
  18     if doujinshi.info.artists:
  19         metadata['artist'] = [i.strip() for i in doujinshi.info.artists.split(',')]
  20     if doujinshi.info.groups:
  21         metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
  22     if doujinshi.info.languages:
  23         metadata['language'] = [i.strip() for i in doujinshi.info.languages.split(',')]
  24     metadata['category'] = doujinshi.info.categories
  25     metadata['URL'] = doujinshi.url
  26     metadata['Pages'] = doujinshi.pages
  27
  28     with open(os.path.join(dir, 'metadata.json'), 'w') as f:
  29         json.dump(metadata, f, separators=','':')
  30
  31
  32 def serialize_comicxml(doujinshi, dir):
  33     from iso8601 import parse_date
  34     with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
  35         f.write('<?xml version="1.0" encoding="utf-8"?>\n')
  36         f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" '
  37                 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
  38
  39         xml_write_simple_tag(f, 'Manga', 'Yes')
  40
  41         xml_write_simple_tag(f, 'Title', doujinshi.name)
  42         xml_write_simple_tag(f, 'Summary', doujinshi.info.subtitle)
  43         xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
  44         xml_write_simple_tag(f, 'URL', doujinshi.url)
  45         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
  46         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
  47
  48         xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and 'full color' in doujinshi.info.tags else 'Yes')
  49
  50         if doujinshi.info.date:
  51             dt = parse_date(doujinshi.info.date)
  52             xml_write_simple_tag(f, 'Year', dt.year)
  53             xml_write_simple_tag(f, 'Month', dt.month)
  54             xml_write_simple_tag(f, 'Day', dt.day)
  55         if doujinshi.info.parodies:
  56             xml_write_simple_tag(f, 'Series', doujinshi.info.parodies)
  57         if doujinshi.info.characters:
  58             xml_write_simple_tag(f, 'Characters', doujinshi.info.characters)
  59         if doujinshi.info.tags:
  60             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
  61         if doujinshi.info.artists:
  62             xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
  63         # if doujinshi.info.groups:
  64         #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
  65         if doujinshi.info.languages:
  66             languages = [i.strip() for i in doujinshi.info.languages.split(',')]
  67             xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
  68             [xml_write_simple_tag(f, 'LanguageISO', LANGUAGEISO[i]) for i in languages \
  69                 if (i != 'translated' and i in LANGUAGEISO)]
  70
  71         f.write('</ComicInfo>')
  72
  73
  74 def xml_write_simple_tag(f, name, val, indent=1):
  75     f.write('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
  76
  77
  78 def merge_json():
  79     lst = []
  80     output_dir = "./"
  81     os.chdir(output_dir)
  82     doujinshi_dirs = next(os.walk('.'))[1]
  83     for folder in doujinshi_dirs:
  84         files = os.listdir(folder)
  85         if 'metadata.json' not in files:
  86             continue
  87         data_folder = output_dir + folder + '/' + 'metadata.json'
  88         json_file = open(data_folder, 'r')
  89         json_dict = json.load(json_file)
  90         json_dict['Folder'] = folder
  91         lst.append(json_dict)
  92     return lst
  93
  94
  95 def serialize_unique(lst):
  96     dictionary = {}
  97     parody = []
  98     character = []
  99     tag = []
 100     artist = []
 101     group = []
 102     for dic in lst:
 103         if 'parody' in dic:
 104             parody.extend([i for i in dic['parody']])
 105         if 'character' in dic:
 106             character.extend([i for i in dic['character']])
 107         if 'tag' in dic:
 108             tag.extend([i for i in dic['tag']])
 109         if 'artist' in dic:
 110             artist.extend([i for i in dic['artist']])
 111         if 'group' in dic:
 112             group.extend([i for i in dic['group']])
 113     dictionary['parody'] = list(set(parody))
 114     dictionary['character'] = list(set(character))
 115     dictionary['tag'] = list(set(tag))
 116     dictionary['artist'] = list(set(artist))
 117     dictionary['group'] = list(set(group))
 118     return dictionary
 119
 120
 121 def set_js_database():
 122     with open('data.js', 'w') as f:
 123         indexed_json = merge_json()
 124         unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
 125         indexed_json = json.dumps(indexed_json, separators=','':')
 126         f.write('var data = ' + indexed_json)
 127         f.write(';\nvar tags = ' + unique_json)