Merge pull request #116 from AnhNhan/master

write ComicInfo.xml for CBZ files

nhentai/cmdline.py

@@ -95,6 +95,8 @@ def cmd_parser():
                       help='generate a main viewer contain all the doujin in the folder')
     parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true',
                       help='generate Comic Book CBZ File')
+    parser.add_option('--comic-info', dest='write_comic_info', action='store_true',
+                      help='when generating Comic Book CBZ File, also write ComicInfo.xml')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
                       help='remove downloaded doujinshi dir when generated CBZ file.')
 

nhentai/command.py

@@ -28,6 +28,7 @@ def main():
     check_cookie()
 
     index = 0
+    index_value = None
     doujinshis = []
     doujinshi_ids = []
     doujinshi_list = []
@@ -43,18 +44,23 @@ def main():
 
     elif options.artist:
         index = 1
+        index_value = options.artist
 
     elif options.character:
         index = 2
+        index_value = options.character
 
     elif options.parody:
         index = 3
+        index_value = options.parody
 
     elif options.group:
         index = 4
+        index_value = options.group
 
     elif options.language:
         index = 5
+        index_value = options.language
 
     elif options.keyword:
         doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
@@ -63,7 +69,7 @@ def main():
         doujinshi_ids = options.id
 
     if index:
-        doujinshis = tag_parser(options.language, max_page=options.max_page, index=index)
+        doujinshis = tag_parser(index_value, max_page=options.max_page, index=index)
 
     print_doujinshi(doujinshis)
     if options.is_download and doujinshis:
@@ -103,7 +109,7 @@ def main():
             if not options.is_nohtml and not options.is_cbz:
                 generate_html(options.output_dir, doujinshi)
             elif options.is_cbz:
-                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir, options.write_comic_info)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)

nhentai/serializer.py

@@ -1,9 +1,11 @@
 # coding: utf-8
 import json
 import os
+from iso8601 import parse_date
+from xml.sax.saxutils import escape
 
 
-def serialize(doujinshi, dir):
+def serialize_json(doujinshi, dir):
     metadata = {'title': doujinshi.name,
                 'subtitle': doujinshi.info.subtitle}
     if doujinshi.info.date:
@@ -28,6 +30,48 @@ def serialize(doujinshi, dir):
         json.dump(metadata, f, separators=','':')
 
 
+def serialize_comicxml(doujinshi, dir):
+    with open(os.path.join(dir, 'ComicInfo.xml'), 'w') as f:
+        f.write('<?xml version="1.0" encoding="utf-8"?>\n')
+        f.write('<ComicInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">\n')
+
+        xml_write_simple_tag(f, 'Manga', 'Yes')
+
+        xml_write_simple_tag(f, 'Title', doujinshi.name)
+        xml_write_simple_tag(f, 'Summary', doujinshi.info.subtitle)
+        xml_write_simple_tag(f, 'PageCount', doujinshi.pages)
+        xml_write_simple_tag(f, 'URL', doujinshi.url)
+        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')
+
+        if doujinshi.info.date:
+            dt = parse_date(doujinshi.info.date)
+            xml_write_simple_tag(f, 'Year', dt.year)
+            xml_write_simple_tag(f, 'Month', dt.month)
+            xml_write_simple_tag(f, 'Day', dt.day)
+        if doujinshi.info.parodies:
+            xml_write_simple_tag(f, 'Series', doujinshi.info.parodies)
+        if doujinshi.info.characters:
+            xml_write_simple_tag(f, 'Characters', doujinshi.info.characters)
+        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(',')]
+        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, 'Language', i) for i in languages if i != 'translated']
+
+        f.write('</ComicInfo>')
+
+
+def xml_write_simple_tag(f, name, val, indent=1):
+    f.write(f'{"  " * indent}<{name}>{escape(str(val))}</{name}>\n')
+
 def merge_json():
     lst = []
     output_dir = "./"

nhentai/utils.py

@@ -12,7 +12,7 @@ import sqlite3
 
 from nhentai import constant
 from nhentai.logger import logger
-from nhentai.serializer import serialize, set_js_database
+from nhentai.serializer import serialize_json, serialize_comicxml, set_js_database
 
 
 def request(method, url, **kwargs):
@@ -86,7 +86,7 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     js = readfile('viewer/scripts.js')
 
     if doujinshi_obj is not None:
-        serialize(doujinshi_obj, doujinshi_dir)
+        serialize_json(doujinshi_obj, doujinshi_dir)
         name = doujinshi_obj.name
         if sys.version_info < (3, 0):
             name = doujinshi_obj.name.encode('utf-8')
@@ -102,9 +102,9 @@ def generate_html(output_dir='.', doujinshi_obj=None):
             with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
                 f.write(data.encode('utf-8'))
 
-        logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+        logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
     except Exception as e:
-        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
 
 
 def generate_main_html(output_dir='./'):
@@ -150,7 +150,7 @@ def generate_main_html(output_dir='./'):
 
         image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
     if image_html == '':
-        logger.warning('None index.html found, --gen-main paused.')
+        logger.warning('No index.html found, --gen-main paused.')
         return
     try:
         data = main.format(STYLES=css, SCRIPTS=js, PICTURE=image_html)
@@ -163,14 +163,16 @@ def generate_main_html(output_dir='./'):
         shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
         set_js_database()
         logger.log(
-            15, 'Main Viewer has been write to \'{0}main.html\''.format(output_dir))
+            15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
     except Exception as e:
-        logger.warning('Writen Main Viewer failed ({})'.format(str(e)))
+        logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False, write_comic_info=False):
     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)
         cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '{}.cbz'.format(doujinshi_obj.filename))
     else:
         cbz_filename = './doujinshi.cbz'
@@ -188,7 +190,7 @@ def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     if rm_origin_dir:
         shutil.rmtree(doujinshi_dir, ignore_errors=True)
 
-    logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
+    logger.log(15, 'Comic Book CBZ file has been written to \'{0}\''.format(doujinshi_dir))
 
 
 def format_filename(s):

requirements.txt

@@ -4,3 +4,4 @@ BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
 future>=0.15.2
+iso8601 >= 0.1