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