fix

Merge into dev branch

.gitignore

@@ -6,3 +6,4 @@ dist/
 .python-version
 .DS_Store
 output/
+venv/

.travis.yml

@@ -3,7 +3,6 @@ os:
 
 language: python
 python:
-    - 2.7
     - 3.7
 
 install:
@@ -11,10 +10,9 @@ install:
 
 script:
     - echo 268642 > /tmp/test.txt
-    - nhentai --cookie "csrftoken=xIh7s9d4NB8qSLN7eJZG9064zsV84aHEYFoAU49Ib9anqmoT0pZRw6TIdayLzQuT; sessionid=un101zfgpglsyffdnsm72le4euuisp7t"
+    - nhentai --cookie "_ga=GA1.2.2000087053.1558179358; __cfduid=d8930f7b43d04e1b2117719e28386b2e31593148489; csrftoken=3914GQGSmmqQyfQTBswNgfXuhFiefu8sAgOnsfZWiiqS4PJpKivuTp34p2USV6xu; sessionid=be0w2lwlprlmld3ahg9i592ipsuaw840"
     - nhentai --search umaru
     - nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
-    - nhentai --tag lolicon --sorting popular
     - nhentai -F
     - nhentai --file /tmp/test.txt
     - nhentai --id=152503,146134 --gen-main --output=/tmp/

README.rst

@@ -19,15 +19,30 @@ nhentai
 
 nHentai is a CLI tool for downloading doujinshi from <http://nhentai.net>
 
-============
-Installation
-============
+===================
+Manual Installation
+===================
 .. code-block::
 
     git clone https://github.com/RicterZ/nhentai
     cd nhentai
     python setup.py install
-    
+
+==================
+Installation (pip)
+==================
+Alternatively, install from PyPI with pip:
+
+.. code-block::
+
+           pip install nhentai
+
+For a self-contained installation, use `Pipx <https://github.com/pipxproject/pipx/>`_:
+
+.. code-block::
+
+           pipx install nhentai
+
 =====================
 Installation (Gentoo)
 =====================
@@ -50,6 +65,8 @@ Set your nhentai cookie against captcha:
 
     nhentai --cookie "YOUR COOKIE FROM nhentai.net"
 
+**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+
 Download specified doujinshi:
 
 .. code-block:: bash
@@ -62,53 +79,20 @@ Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
     nhentai --file=doujinshi.txt
 
+Set search default language
+
+.. code-block:: bash
+
+    nhentai --language=english
+
 Search a keyword and download the first page:
 
 .. code-block:: bash
 
     nhentai --search="tomori" --page=1 --download
-
-Download by tag name:
-
-.. code-block:: bash
-
-    nhentai --tag lolicon --download --page=2
-
-Download by language:
-
-.. code-block:: bash
-
-    nhentai --language english --download --page=2
-
-Download by artist name:
-
-.. code-block:: bash
-
-    nhentai --artist henreader --download
-
-Download by character name:
-
-.. code-block:: bash
-
-    nhentai --character "kuro von einsbern" --download
-
-Download by parody name:
-
-.. code-block:: bash
-
-    nhentai --parody "the idolmaster" --download
-
-Download by group name:
-
-.. code-block:: bash
-
-    nhentai --group clesta --download
-
-Download using multiple tags (--tag, --character, --paordy and --group supported):
-
-.. code-block:: bash
-
-    nhentai --tag "lolicon, teasing" --artist "tamano kedama, atte nanakusa"
+    # you also can download by tags and multiple keywords
+    nhentai --search="tag:lolicon, artist:henreader, tag:full color"
+    nhentai --search="lolicon, henreader, full color"
 
 Download your favorites with delay:
 
@@ -170,8 +154,9 @@ Other options:
       --no-html             don't generate HTML after downloading
       --gen-main            generate a main viewer contain all the doujin in the folder
       -C, --cbz             generate Comic Book CBZ File
+      -P --pdf              generate PDF file
       --rm-origin-dir       remove downloaded doujinshi dir when generated CBZ
-                            file.
+                            or PDF file.
 
       # nHentai options
       --cookie=COOKIE       set cookie of nhentai to bypass Google recaptcha
@@ -183,7 +168,7 @@ nHentai Mirror
 If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`.
 For example:
 
-.. code-block:: 
+.. code-block::
 
     i.h.loli.club -> i.nhentai.net
     h.loli.club -> nhentai.net

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.8'
+__version__ = '0.4.1'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -38,7 +38,7 @@ def banner():
 def cmd_parser():
     parser = OptionParser('\n  nhentai --search [keyword] --download'
                           '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
-                          '\n  nhentai --file [filename]'    
+                          '\n  nhentai --file [filename]'
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
     # operation options
@@ -50,26 +50,17 @@ def cmd_parser():
     parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
-    parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
-    parser.add_option('--artist', type='string', dest='artist', action='store', help='download doujinshi by artist')
-    parser.add_option('--character', type='string', dest='character', action='store',
-                      help='download doujinshi by character')
-    parser.add_option('--parody', type='string', dest='parody', action='store', help='download doujinshi by parody')
-    parser.add_option('--group', type='string', dest='group', action='store', help='download doujinshi by group')
-    parser.add_option('--language', type='string', dest='language', action='store',
-                      help='download doujinshi by language')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
                       help='list or download your favorites.')
 
     # page options
     parser.add_option('--page', type='int', dest='page', action='store', default=1,
                       help='page number of search results')
-    parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1,
-                      help='The max page when recursive download tagged doujinshi')
     parser.add_option('--page-range', type='string', dest='page_range', action='store',
                       help='page range of favorites.  e.g. 1,2-5,14')
-    parser.add_option('--sorting', dest='sorting', action='store', default='date',
-                      help='sorting of doujinshi (date / popular)', choices=['date', 'popular'])
+    parser.add_option('--sorting', dest='sorting', action='store', default='recent',
+                      help='sorting of doujinshi (recent / popular / popular-[today|week])',
+                      choices=['recent', 'popular', 'popular-today', 'popular-week'])
 
     # download options
     parser.add_option('--output', '-o', type='string', dest='output_dir', action='store', default='',
@@ -95,12 +86,16 @@ 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('--pdf', '-P', dest='is_pdf', action='store_true',
+                      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 file.')
+                      help='remove downloaded doujinshi dir when generated CBZ or PDF file.')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
                       help='set cookie of nhentai to bypass Google recaptcha')
+    parser.add_option('--language', type='str', dest='language', action='store',
+                      help='set default language to parse doujinshis')
     parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
                       default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
     parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
@@ -120,9 +115,7 @@ def cmd_parser():
         generate_html()
         exit(0)
 
-    if args.main_viewer and not args.id and not args.keyword and \
-            not args.tag and not args.artist and not args.character and \
-            not args.parody and not args.group and not args.language and not args.favorites:
+    if args.main_viewer and not args.id and not args.keyword and not args.favorites:
         generate_main_html()
         exit(0)
 
@@ -151,6 +144,25 @@ def cmd_parser():
         logger.info('Cookie saved.')
         exit(0)
 
+    if os.path.exists(constant.NHENTAI_LANGUAGE) and not args.language:
+        with open(constant.NHENTAI_LANGUAGE, 'r') as f:
+            constant.LANGUAGE = f.read()
+            args.language = f.read()
+
+    if args.language:
+        try:
+            if not os.path.exists(constant.NHENTAI_HOME):
+                os.mkdir(constant.NHENTAI_HOME)
+
+            with open(constant.NHENTAI_LANGUAGE, 'w') as f:
+                f.write(args.language)
+        except Exception as e:
+            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+            exit(1)
+
+        logger.info('Default language now is {}.'.format(args.language))
+        exit(0)
+
     if os.path.exists(constant.NHENTAI_PROXY):
         with open(constant.NHENTAI_PROXY, 'r') as f:
             link = f.read()
@@ -189,15 +201,12 @@ def cmd_parser():
             _ = [i.strip() for i in f.readlines()]
             args.id = set(int(i) for i in _ if i.isdigit())
 
-    if (args.is_download or args.is_show) and not args.id and not args.keyword and \
-            not args.tag and not args.artist and not args.character and \
-            not args.parody and not args.group and not args.language and not args.favorites:
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.favorites:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
         exit(1)
 
-    if not args.keyword and not args.id and not args.tag and not args.artist and \
-            not args.character and not args.parody and not args.group and not args.language and not args.favorites:
+    if not args.keyword and not args.id and not  args.favorites:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -6,12 +6,12 @@ import platform
 import time
 
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser
 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, check_cookie, signal_handler, DB
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, check_cookie, signal_handler, DB
 
 
 def main():
@@ -21,7 +21,7 @@ def main():
 
     from nhentai.constant import PROXY
     # constant.PROXY will be changed after cmd_parser()
-    if PROXY != {}:
+    if PROXY:
         logger.info('Using proxy: {0}'.format(PROXY))
 
     # check your cookie
@@ -37,25 +37,11 @@ def main():
 
         doujinshis = favorites_parser(options.page_range)
 
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, sorting=options.sorting, max_page=options.max_page)
-
-    elif options.artist:
-        doujinshis = tag_parser(options.artist, max_page=options.max_page, index=1)
-
-    elif options.character:
-        doujinshis = tag_parser(options.character, max_page=options.max_page, index=2)
-
-    elif options.parody:
-        doujinshis = tag_parser(options.parody, max_page=options.max_page, index=3)
-
-    elif options.group:
-        doujinshis = tag_parser(options.group, max_page=options.max_page, index=4)
-
-    elif options.language:
-        doujinshis = tag_parser(options.language, max_page=options.max_page, index=5)
-
     elif options.keyword:
+        from nhentai.constant import LANGUAGE
+        if LANGUAGE:
+            logger.info('Using deafult language: {0}'.format(LANGUAGE))
+            options.keyword += ', language:{}'.format(LANGUAGE)
         doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
 
     elif not doujinshi_ids:
@@ -96,10 +82,12 @@ def main():
                 with DB() as db:
                     db.add_one(doujinshi.id)
 
-            if not options.is_nohtml and not options.is_cbz:
+            if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
                 generate_html(options.output_dir, doujinshi)
             elif options.is_cbz:
                 generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
+            elif options.is_pdf:
+                generate_pdf(options.output_dir, doujinshi, options.rm_origin_dir)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)
@@ -115,6 +103,5 @@ def main():
 
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

@@ -12,17 +12,10 @@ except ImportError:
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
 __api_suspended_DETAIL_URL = '%s/api/gallery' % BASE_URL
-__api_suspended_SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
 DETAIL_URL = '%s/g' % BASE_URL
-SEARCH_URL = '%s/search/' % BASE_URL
+SEARCH_URL = '%s/api/galleries/search' % BASE_URL
 
-TAG_URL = ['%s/tag' % BASE_URL,
-           '%s/artist' % BASE_URL,
-           '%s/character' % BASE_URL,
-           '%s/parody' % BASE_URL,
-           '%s/group' % BASE_URL,
-           '%s/language' % BASE_URL]
 
 TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
 LOGIN_URL = '%s/login/' % BASE_URL
@@ -35,8 +28,10 @@ IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
 NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
 NHENTAI_PROXY = os.path.join(NHENTAI_HOME, 'proxy')
 NHENTAI_COOKIE = os.path.join(NHENTAI_HOME, 'cookie')
+NHENTAI_LANGUAGE = os.path.join(NHENTAI_HOME, 'language')
 NHENTAI_HISTORY = os.path.join(NHENTAI_HOME, 'history.sqlite3')
 
 PROXY = {}
 
 COOKIE = ''
+LANGUAGE = ''

nhentai/downloader.py

@@ -5,11 +5,10 @@ import multiprocessing
 import signal
 
 from future.builtins import str as text
+import sys
 import os
 import requests
-import threadpool
 import time
-import multiprocessing as mp
 
 try:
     from urllib.parse import urlparse
@@ -18,10 +17,10 @@ except ImportError:
 
 from nhentai.logger import logger
 from nhentai.parser import request
-from nhentai.utils import Singleton, signal_handler
+from nhentai.utils import Singleton
 
 requests.packages.urllib3.disable_warnings()
-semaphore = mp.Semaphore()
+semaphore = multiprocessing.Semaphore(1)
 
 
 class NHentaiImageNotExistException(Exception):
@@ -133,16 +132,14 @@ class Downloader(Singleton):
         queue = [(self, url, folder) for url in queue]
 
         pool = multiprocessing.Pool(self.size, init_worker)
-
-        for item in queue:
-            pool.apply_async(download_wrapper, args=item, callback=self._download_callback)
+        [pool.apply_async(download_wrapper, args=item) for item in queue]
 
         pool.close()
         pool.join()
 
 
 def download_wrapper(obj, url, folder=''):
-    if semaphore.get_value():
+    if sys.platform == 'darwin' or semaphore.get_value():
         return Downloader.download_(obj, url=url, folder=folder)
     else:
         return -3, None

nhentai/parser.py

@@ -120,15 +120,15 @@ def page_range_parser(page_range, max_page_num):
         else:
             try:
                 left = int(range_str[:idx])
-                right = int(range_str[idx+1:])
+                right = int(range_str[idx + 1:])
                 if right > max_page_num:
                     right = max_page_num
-                for page in range(left, right+1):
+                for page in range(left, right + 1):
                     pages.add(page)
             except ValueError:
                 logger.error('page range({0}) is not valid'.format(page_range))
-    
-    return list(pages)    
+
+    return list(pages)
 
 
 def doujinshi_parser(id_):
@@ -143,7 +143,7 @@ def doujinshi_parser(id_):
 
     try:
         response = request('get', url)
-        if response.status_code in (200, ):
+        if response.status_code in (200,):
             response = response.content
         else:
             logger.debug('Slow down and retry ({}) ...'.format(id_))
@@ -178,12 +178,9 @@ def doujinshi_parser(id_):
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = ext
 
-    pages = 0
-    for _ in doujinshi_info.find_all('div', class_=''):
-        pages = re.search('([\d]+) pages', _.text)
-        if pages:
-            pages = pages.group(1)
-            break
+    for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
+        if re.search('Pages:', _.text):
+            pages = _.find('span', class_='name').string
     doujinshi['pages'] = int(pages)
 
     # gain information of the doujinshi
@@ -192,7 +189,7 @@ def doujinshi_parser(id_):
     for field in information_fields:
         field_name = field.contents[0].strip().strip(':')
         if field_name in needed_fields:
-            data = [sub_field.contents[0].strip() for sub_field in
+            data = [sub_field.find('span', attrs={'class': 'name'}).contents[0].strip() for sub_field in
                     field.find_all('a', attrs={'class': 'tag'})]
             doujinshi[field_name.lower()] = ', '.join(data)
 
@@ -202,7 +199,7 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def search_parser(keyword, sorting='date', page=1):
+def old_search_parser(keyword, sorting='date', page=1):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
 
@@ -222,50 +219,15 @@ def print_doujinshi(doujinshi_list):
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def tag_parser(tag_name, sorting='date', max_page=1, index=0):
-    result = []
-    tag_name = tag_name.lower()
-    if ',' in tag_name:
-        tag_name = [i.strip().replace(' ', '-') for i in tag_name.split(',')]
-    else:
-        tag_name = tag_name.strip().replace(' ', '-')
-    if sorting == 'date':
-        sorting = ''
-
-    for p in range(1, max_page + 1):
-        if sys.version_info >= (3, 0, 0):
-            unicode_ = str
-        else:
-            unicode_ = unicode
-
-        if isinstance(tag_name, (str, unicode_)):
-            logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
-            response = request('get', url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], tag_name, sorting, p)).content
-            result += _get_title_and_id(response)
-        else:
-            for i in tag_name:
-                logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, i))
-                response = request('get',
-                                   url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], i, sorting, p)).content
-                result += _get_title_and_id(response)
-
-        if not result:
-            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
-            return
-
-    if not result:
-        logger.warn('No results for tag \'{}\''.format(tag_name))
-
-    return result
-
-
-def __api_suspended_search_parser(keyword, sorting, page):
+def search_parser(keyword, sorting, page):
     logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
+    keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
     i = 0
     while i < 5:
         try:
-            response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).json()
+            url = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).url
+            response = request('get', url.replace('%2B', '+')).json()
         except Exception as e:
             i += 1
             if not i < 5:
@@ -289,29 +251,6 @@ def __api_suspended_search_parser(keyword, sorting, page):
     return result
 
 
-def __api_suspended_tag_parser(tag_id, sorting, max_page=1):
-    logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
-    result = []
-    response = request('get', url=constant.TAG_API_URL, params={'sort': sorting, 'tag_id': tag_id}).json()
-    page = max_page if max_page <= response['num_pages'] else int(response['num_pages'])
-
-    for i in range(1, page + 1):
-        logger.info('Getting page {} ...'.format(i))
-
-        if page != 1:
-            response = request('get', url=constant.TAG_API_URL,
-                               params={'sort': sorting, 'tag_id': tag_id}).json()
-    for row in response['result']:
-        title = row['title']['english']
-        title = title[:85] + '..' if len(title) > 85 else title
-        result.append({'id': row['id'], 'title': title})
-
-    if not result:
-        logger.warn('No results for tag id {}'.format(tag_id))
-
-    return result
-
-
 def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
         raise Exception('Doujinshi id({0}) is not valid'.format(id_))

nhentai/serializer.py

@@ -1,9 +1,10 @@
 # coding: utf-8
 import json
 import os
+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 +29,51 @@ def serialize(doujinshi, dir):
         json.dump(metadata, f, separators=','':')
 
 
+def serialize_comicxml(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')
+        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('{}<{}>{}</{}>\n'.format(' ' * indent, name, escape(str(val)), name))
+
+
 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 +190,40 @@ 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 generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+    try:
+        import img2pdf
+    except ImportError:
+        logger.error("Please install img2pdf package by using pip.")
+
+    """Write images to a PDF file using img2pdf."""
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        pdf_filename = os.path.join(
+            os.path.join(doujinshi_dir, '..'),
+            '{}.pdf'.format(doujinshi_obj.filename)
+        )
+    else:
+        pdf_filename = './doujinshi.pdf'
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    logger.info('Writing PDF file to path: {}'.format(pdf_filename))
+    with open(pdf_filename, 'wb') as pdf_f:
+        full_path_list = (
+            [os.path.join(doujinshi_dir, image) for image in file_list]
+        )
+        pdf_f.write(img2pdf.convert(full_path_list))
+
+    if rm_origin_dir:
+        shutil.rmtree(doujinshi_dir, ignore_errors=True)
+
+    logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
 
 
 def format_filename(s):
@@ -202,6 +237,7 @@ and append a file extension like '.txt', so I avoid the potential of using
 an invalid filename.
 
 """
+    # maybe you can use `--format` to select a suitable filename
     valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
     filename = ''.join(c for c in s if c in valid_chars)
     if len(filename) > 100:

nhentai/viewer/main.css

@@ -148,7 +148,7 @@ blockquote {
   -webkit-user-select: none; /* Safari */
   -khtml-user-select: none; /* Konqueror HTML */
   -moz-user-select: none; /* Old versions of Firefox */
-  ms-user-select: none; /* Internet Explorer/Edge */
+  -ms-user-select: none; /* Internet Explorer/Edge */
   user-select: none;
 }
 
@@ -157,7 +157,7 @@ blockquote {
   padding: 5px 0px 5px 15px;
   text-decoration: none;
   font-size: 15px;
-  color: #0d0d0d9;
+  color: #0d0d0d;
   display: block;
   text-align: left;
 }
@@ -329,4 +329,4 @@ html.theme-black .gallery:hover .caption {
 html.theme-black .caption {
     background-color: #404040;
     color: #d9d9d9
-}
+}

requirements.txt

@@ -1,5 +1,7 @@
 requests>=2.5.0
+soupsieve<2.0
 BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
 future>=0.15.2
+iso8601 >= 0.1

setup.py

@@ -23,7 +23,7 @@ setup(
 
     author=__author__,
     author_email=__email__,
-    keywords='nhentai, doujinshi',
+    keywords=['nhentai', 'doujinshi', 'downloader'],
     description='nhentai.net doujinshis downloader',
     long_description=long_description(),
     url='https://github.com/RicterZ/nhentai',