fix #220 add pretty name of doujinshi format

nhentai/doujinshi.py

@@ -26,8 +26,10 @@ class DoujinshiInfo(dict):
 
 
 class Doujinshi(object):
-    def __init__(self, name=None, id=None, img_id=None, ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
+    def __init__(self, name=None, pretty_name=None, id=None, img_id=None,
+                 ext='', pages=0, name_format='[%i][%a][%t]', **kwargs):
         self.name = name
+        self.pretty_name = pretty_name
         self.id = id
         self.img_id = img_id
         self.ext = ext
@@ -39,6 +41,7 @@ class Doujinshi(object):
         name_format = name_format.replace('%i', str(self.id))
         name_format = name_format.replace('%a', self.info.artists)
         name_format = name_format.replace('%t', self.name)
+        name_format = name_format.replace('%p', self.pretty_name)
         name_format = name_format.replace('%s', self.info.subtitle)
         self.filename = format_filename(name_format)
 
@@ -63,7 +66,6 @@ class Doujinshi(object):
         logger.info('Starting to download doujinshi: %s' % self.name)
         if self.downloader:
             download_queue = []
-
             if len(self.ext) != self.pages:
                 logger.warning('Page count and ext count do not equal')
 
@@ -71,12 +73,6 @@ class Doujinshi(object):
                 download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
 
             self.downloader.download(download_queue, self.filename)
-
-            '''
-            for i in range(len(self.ext)):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
-            '''
-
         else:
             logger.critical('Downloader has not been loaded')
 

nhentai/parser.py

@@ -133,13 +133,16 @@ def doujinshi_parser(id_):
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
+    pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
     subtitle = doujinshi_info.find('h2')
 
     doujinshi['name'] = title
+    doujinshi['pretty_name'] = pretty_name
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+    img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+                       doujinshi_cover.a.img.attrs['data-src'])
 
     ext = []
     for i in html.find_all('div', attrs={'class': 'thumb-container'}):

nhentai/serializer.py

@@ -4,6 +4,7 @@ import os
 from xml.sax.saxutils import escape
 from nhentai.constant import LANGUAGEISO
 
+
 def serialize_json(doujinshi, dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
@@ -26,10 +27,10 @@ def serialize_json(doujinshi, dir):
     metadata['Pages'] = doujinshi.pages
 
     with open(os.path.join(dir, 'metadata.json'), 'w') as f:
-        json.dump(metadata, f, separators=','':')
+        json.dump(metadata, f, separators=(',', ':'))
 
 
-def serialize_comicxml(doujinshi, dir):
+def serialize_comic_xml(doujinshi, dir):
     from iso8601 import parse_date
     with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
         f.write('<?xml version="1.0" encoding="utf-8"?>\n')
@@ -45,7 +46,8 @@ def serialize_comicxml(doujinshi, dir):
         xml_write_simple_tag(f, 'NhentaiId', doujinshi.id)
         xml_write_simple_tag(f, 'Genre', doujinshi.info.categories)
 
-        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and 'full color' in doujinshi.info.tags else 'Yes')
+        xml_write_simple_tag(f, 'BlackAndWhite', 'No' if doujinshi.info.tags and
+                             'full color' in doujinshi.info.tags else 'Yes')
 
         if doujinshi.info.date:
             dt = parse_date(doujinshi.info.date)
@@ -59,13 +61,13 @@ def serialize_comicxml(doujinshi, dir):
         if doujinshi.info.tags:
             xml_write_simple_tag(f, 'Tags', doujinshi.info.tags)
         if doujinshi.info.artists:
-            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in doujinshi.info.artists.split(',')]))
-        # if doujinshi.info.groups:
-        #     metadata['group'] = [i.strip() for i in doujinshi.info.groups.split(',')]
+            xml_write_simple_tag(f, 'Writer', ' & '.join([i.strip() for i in
+                                                          doujinshi.info.artists.split(',')]))
+
         if doujinshi.info.languages:
             languages = [i.strip() for i in doujinshi.info.languages.split(',')]
             xml_write_simple_tag(f, 'Translated', 'Yes' if 'translated' in languages else 'No')
-            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGEISO[i]) for i in languages \
+            [xml_write_simple_tag(f, 'LanguageISO', LANGUAGEISO[i]) for i in languages
                 if (i != 'translated' and i in LANGUAGEISO)]
 
         f.write('</ComicInfo>')
@@ -121,7 +123,7 @@ def serialize_unique(lst):
 def set_js_database():
     with open('data.js', 'w') as f:
         indexed_json = merge_json()
-        unique_json = json.dumps(serialize_unique(indexed_json), separators=','':')
-        indexed_json = json.dumps(indexed_json, separators=','':')
+        unique_json = json.dumps(serialize_unique(indexed_json), separators=(',', ':'))
+        indexed_json = json.dumps(indexed_json, separators=(',', ':'))
         f.write('var data = ' + indexed_json)
         f.write(';\nvar tags = ' + unique_json)

nhentai/utils.py

@@ -10,7 +10,7 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
+from nhentai.serializer import serialize_json, serialize_comic_xml, set_js_database
 
 
 def request(method, url, **kwargs):
@@ -174,7 +174,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
         if write_comic_info:
-            serialize_comicxml(doujinshi_obj, doujinshi_dir)
+            serialize_comic_xml(doujinshi_obj, doujinshi_dir)
         cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
     else:
         cbz_filename = './doujinshi.cbz'
@@ -246,7 +246,6 @@ def format_filename(s):
     ban_chars = '\\\'/:,;*?"<>|\t'
     filename = s.translate(str.maketrans(ban_chars, ' '*len(ban_chars))).strip()
     filename = ' '.join(filename.split())
-    print(repr(filename))
 
     while filename.endswith('.'):
         filename = filename[:-1]