Merge pull request #224 from RicterZ/pull/221

Pull/221

nhentai/cmdline.py

@@ -104,6 +104,8 @@ def cmd_parser():
                       help='generate PDF file')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
                       help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
+    parser.add_option('--meta', dest='generate_metadata', action='store_true',
+                      help='generate a metadata file in doujinshi format')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',

nhentai/command.py

@@ -13,7 +13,7 @@ from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
 from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, generate_metadata_file, \
     paging, check_cookie, signal_handler, DB
 
 
@@ -93,6 +93,13 @@ def main():
                 doujinshi.downloader = downloader
                 doujinshi.download()
 
+            doujinshi.downloader = downloader
+            doujinshi.download()
+
+            if options.generate_metadata:
+                table = doujinshi.table
+                generate_metadata_file(options.output_dir, table, doujinshi)
+
             if options.is_save_download_history:
                 with DB() as db:
                     db.add_one(doujinshi.id)
@@ -118,6 +125,5 @@ def main():
 
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/doujinshi.py

@@ -6,7 +6,6 @@ from nhentai.constant import DETAIL_URL, IMAGE_URL
 from nhentai.logger import logger
 from nhentai.utils import format_filename
 
-
 EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
@@ -45,11 +44,7 @@ class Doujinshi(object):
         name_format = name_format.replace('%s', self.info.subtitle)
         self.filename = format_filename(name_format)
 
-    def __repr__(self):
+        self.table = [
-        return '<Doujinshi: {0}>'.format(self.name)
-
-    def show(self):
-        table = [
             ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
@@ -60,7 +55,13 @@ class Doujinshi(object):
             ["URL", self.url],
             ["Pages", self.pages],
         ]
-        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
+
+    def __repr__(self):
+        return '<Doujinshi: {0}>'.format(self.name)
+
+    def show(self):
+
+        logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(self.table)))
 
     def download(self):
         logger.info('Starting to download doujinshi: %s' % self.name)
@@ -70,7 +71,7 @@ class Doujinshi(object):
                 logger.warning('Page count and ext count do not equal')
 
             for i in range(1, min(self.pages, len(self.ext)) + 1):
-                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))
+                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)
         else:

nhentai/utils.py

@@ -88,7 +88,7 @@ def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
 
-        image_html += '<img src="{0}" class="image-item"/>\n'\
+        image_html += '<img src="{0}" class="image-item"/>\n' \
             .format(image)
     html = readfile('viewer/{}/index.html'.format(template))
     css = readfile('viewer/{}/styles.css'.format(template))
@@ -169,7 +169,7 @@ def generate_main_html(output_dir='./'):
         else:
             with open('./main.html', 'wb') as f:
                 f.write(data.encode('utf-8'))
-        shutil.copy(os.path.dirname(__file__)+'/viewer/logo.png', './')
+        shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
         set_js_database()
         logger.log(
             15, 'Main Viewer has been written to \'{0}main.html\''.format(output_dir))
@@ -235,6 +235,7 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     except ImportError:
         logger.error("Please install img2pdf package by using pip.")
 
+
 def unicode_truncate(s, length, encoding='utf-8'):
     """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
     """
@@ -251,7 +252,7 @@ def format_filename(s):
     """
     # maybe you can use `--format` to select a suitable filename
     ban_chars = '\\\'/:,;*?"<>|\t'
-    filename = s.translate(str.maketrans(ban_chars, ' '*len(ban_chars))).strip()
+    filename = s.translate(str.maketrans(ban_chars, ' ' * len(ban_chars))).strip()
     filename = ' '.join(filename.split())
 
     while filename.endswith('.'):
@@ -281,7 +282,7 @@ def paging(page_string):
             start, end = i.split('-')
             if not (start.isdigit() and end.isdigit()):
                 raise Exception('Invalid page number')
-            page_list.extend(list(range(int(start), int(end)+1)))
+            page_list.extend(list(range(int(start), int(end) + 1)))
         else:
             if not i.isdigit():
                 raise Exception('Invalid page number')
@@ -290,6 +291,34 @@ def paging(page_string):
     return page_list
 
 
+def generate_metadata_file(output_dir, table, doujinshi_obj=None):
+    logger.info('Writing Metadata Info')
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+    else:
+        doujinshi_dir = '.'
+
+    logger.info(doujinshi_dir)
+
+    f = open(os.path.join(doujinshi_dir, 'info.txt'), 'w', encoding='utf-8')
+
+    fields = ['TITLE', 'ORIGINAL TITLE', 'AUTHOR', 'ARTIST', 'CIRCLE', 'SCANLATOR',
+              'TRANSLATOR', 'PUBLISHER', 'DESCRIPTION', 'STATUS', 'CHAPTERS', 'PAGES',
+              'TAGS', 'TYPE', 'LANGUAGE', 'RELEASED', 'READING DIRECTION', 'CHARACTERS',
+              'SERIES', 'PARODY', 'URL']
+    special_fields = ['PARODY', 'TITLE', 'ORIGINAL TITLE', 'CHARACTERS', 'AUTHOR',
+                      'LANGUAGE', 'TAGS', 'URL', 'PAGES']
+
+    for i in range(len(fields)):
+        f.write('{}: '.format(fields[i]))
+        if fields[i] in special_fields:
+            f.write(str(table[special_fields.index(fields[i])][1]))
+        f.write('\n')
+
+    f.close()
+
+
 class DB(object):
     conn = None
     cur = None