modify tests #54

Add viewer arrow support, add README license badge.

.gitignore

@@ -5,3 +5,4 @@ dist/
 *.egg-info
 .python-version
 .DS_Store
+output/

.travis.yml

@@ -4,14 +4,18 @@ os:
 language: python
 python:
     - 2.7
-    - 2.6
-    - 3.3
+    - 3.6
+    - 3.5
     - 3.4
-    - 3.5.2
 
 install:
     - python setup.py install
 
 script:
+    - echo 268642 > /tmp/test.txt
+    - NHENTAI=https://nhentai.net nhentai --cookie '__cfduid=da09f237ceb0f51c75980b0b3fda3ce571558179357; _ga=GA1.2.2000087053.1558179358; _gid=GA1.2.717818542.1558179358; csrftoken=iSxrTFOjrujJqauhAqWvTTI9dl3sfWnxdEFoMuqgmlBrbMin5Gj9wJW4r61cmH1X; sessionid=ewuaayfewbzpiukrarx9d52oxwlz2esd'
     - NHENTAI=https://nhentai.net nhentai --search umaru
-    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/
+    - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/ --cbz
+    - NHENTAI=https://nhentai.net nhentai --tag lolicon
+    - NHENTAI=https://nhentai.net nhentai -F
+    - NHENTAI=https://nhentai.net nhentai --file /tmp/test.txt

MANIFEST.in

@@ -1,3 +1,5 @@
 include README.md
 include requirements.txt
-include nhentai/doujinshi.html
+include nhentai/viewer/index.html
+include nhentai/viewer/styles.css
+include nhentai/viewer/scripts.js

README.md

@@ -7,11 +7,10 @@ nhentai
     |_| |_|_| |_|\___|_| |_|\__\__,_|_|
 
 あなたも変態。 いいね?  
-[![Build Status](https://travis-ci.org/RicterZ/nhentai.svg?branch=master)](https://travis-ci.org/RicterZ/nhentai)  
+[![Build Status](https://travis-ci.org/RicterZ/nhentai.svg?branch=master)](https://travis-ci.org/RicterZ/nhentai) ![nhentai PyPI Downloads](https://img.shields.io/pypi/dm/nhentai.svg) [![license](https://img.shields.io/cocoapods/l/AFNetworking.svg)](https://github.com/RicterZ/nhentai/blob/master/LICENSE)
 
-🎉🎉 nhentai 现在支持 Windows 啦！
 
-由于 [http://nhentai.net](http://nhentai.net) 下载下来的种子速度很慢，而且官方也提供在线观看本子的功能，所以可以利用本脚本下载本子。
+nHentai is a CLI tool for downloading doujinshi from [nhentai.net](http://nhentai.net).
 
 ### Installation
 
@@ -19,40 +18,60 @@ nhentai
     cd nhentai
     python setup.py install
     
-### Gentoo
+### Installation (Gentoo)
 
     layman -fa glicOne
     sudo emerge net-misc/nhentai
 
 ### Usage
-下载指定 id 列表的本子：
+**IMPORTANT**: To bypass the nhentai frequency limit, you should use `--login` option to log into nhentai.net.
+
+*The default download folder will be the path where you run the command (CLI path).*
+
+Download specified doujinshi:
 ```bash
 nhentai --id=123855,123866
 ```
 
-下载某关键词第一页的本子：
+Download doujinshi with ids specified in a file:
+```bash
+nhentai --file=doujinshi.txt
+```
+
+Search a keyword and download the first page:
 ```bash
 nhentai --search="tomori" --page=1 --download
 ```
 
-下载用户 favorites 内容：
+Download your favourite doujinshi (login required):
 ```bash
 nhentai --login "username:password" --download
 ```
 
+Download by tag name:
+```bash
+nhentai --tag lolicon --download
+```
+
 ### Options
 
-`-t, --thread`：指定下载的线程数，最多为 10 线程。  
-`--path`：指定下载文件的输出路径，默认为当前目录。  
-`--timeout`：指定下载图片的超时时间，默认为 30 秒。  
-`--proxy`：指定下载的代理，例如: http://127.0.0.1:8080/
-`--login`：nhentai 账号的“用户名:密码”组合
++ `-t, --thread`: Download threads, max: 10  
++ `--output`:Output dir of saving doujinshi  
++ `--tag`:Download by tag name  
++ `--timeout`: Timeout of downloading each image   
++ `--proxy`: Use proxy, example: http://127.0.0.1:8080/  
++ `--login`: username:password pair of your nhentai account  
++ `--nohtml`: Do not generate HTML  
++ `--cbz`: Generate Comic Book CBZ File  
 
 ### nHentai Mirror
-如果想用自建镜像下载 nhentai 的本子，需要搭建 nhentai.net 和 i.nhentai.net 的反向代理。  
-例如用 h.loli.club 来做反向代理的话，需要 h.loli.club 反代 nhentai.net，i.h.loli.club 反带 i.nhentai.net。  
-然后利用环境变量来下载：  
+If you want to use a mirror, you should set up a reverse proxy of `nhentai.net` and `i.nhentai.net`.
+For example:
 
+    i.h.loli.club -> i.nhentai.net
+    h.loli.club -> nhentai.net
+
+Set `NHENTAI` env var to your nhentai mirror.
 ```bash
 NHENTAI=http://h.loli.club nhentai --id 123456
 ```
@@ -61,8 +80,5 @@ NHENTAI=http://h.loli.club nhentai --id 123456
 ![](./images/download.png)  
 ![](./images/viewer.png)  
 
-### License  
-MIT
-
 ### あなたも変態
 ![](./images/image.jpg)

doujinshi.txt

@@ -0,0 +1,5 @@
+184212
+204944
+222460
+244502
+261909

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.2.12'
-__author__ = 'Ricter'
+__version__ = '0.3.1'
+__author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -1,5 +1,6 @@
 # coding: utf-8
 from __future__ import print_function
+import os
 import sys
 from optparse import OptionParser
 try:
@@ -8,53 +9,80 @@ except ImportError:
     pass
 
 import nhentai.constant as constant
+from nhentai import __version__
 from nhentai.utils import urlparse, generate_html
 from nhentai.logger import logger
 
 try:
-    reload(sys)
-    sys.setdefaultencoding(sys.stdin.encoding)
+    if sys.version_info < (3, 0, 0):
+        import codecs
+        import locale
+        sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout)
+        sys.stderr = codecs.getwriter(locale.getpreferredencoding())(sys.stderr)
+
 except NameError:
     # python3
     pass
 
 
 def banner():
-    logger.info(u'''nHentai: あなたも変態。 いいね?
+    logger.info(u'''nHentai ver %s: あなたも変態。 いいね?
        _   _            _        _
  _ __ | | | | ___ _ __ | |_ __ _(_)
 | '_ \| |_| |/ _ \ '_ \| __/ _` | |
 | | | |  _  |  __/ | | | || (_| | |
 |_| |_|_| |_|\___|_| |_|\__\__,_|_|
-''')
+''' % __version__)
 
 
 def cmd_parser():
     parser = OptionParser('\n  nhentai --search [keyword] --download'
                           '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n  nhentai --file [filename]'    
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
+    # operation options
     parser.add_option('--download', dest='is_download', action='store_true',
-                      help='download doujinshi (for search result)')
-    parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
+                      help='download doujinshi (for search results)')
+    parser.add_option('--show', dest='is_show', action='store_true', help='just show the doujinshi information')
+
+    # doujinshi options
     parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
     parser.add_option('--search', 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('--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 result')
-    parser.add_option('--tags', type='string', dest='tags', action='store', help='download doujinshi by tags')
+                      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')
+
+    # download options
     parser.add_option('--output', type='string', dest='output_dir', action='store', default='',
                       help='output dir')
     parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
-                      help='thread count of download doujinshi')
+                      help='thread count for downloading doujinshi')
     parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
-                      help='timeout of download doujinshi')
+                      help='timeout for downloading doujinshi')
     parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
-                      help='use proxy, example: http://127.0.0.1:1080')
+                      help='uses a proxy, for example: http://127.0.0.1:1080')
+    parser.add_option('--file',  '-f', type='string', dest='file', action='store', help='read gallery IDs from file.')
+
+    # generate options
     parser.add_option('--html', dest='html_viewer', action='store_true',
                       help='generate a html viewer at current directory')
+    parser.add_option('--nohtml', dest='is_nohtml', action='store_true',
+                      help='don\'t generate HTML')
+    parser.add_option('--cbz', dest='is_cbz', action='store_true',
+                      help='generate Comic Book CBZ 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.')
 
-    parser.add_option('--login', '-l', type='str', dest='login', action='store',
-                      help='username:password pair of nhentai account')
+    # nhentai options
+    parser.add_option('--cookie', type='str', dest='cookie', action='store',
+                      help='set cookie of nhentai to bypass Google recaptcha')
 
     try:
         sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
@@ -69,6 +97,25 @@ def cmd_parser():
         generate_html()
         exit(0)
 
+    if os.path.exists(os.path.join(constant.NHENTAI_HOME, 'cookie')):
+        with open(os.path.join(constant.NHENTAI_HOME, 'cookie'), 'r') as f:
+            constant.COOKIE = f.read()
+
+    if args.cookie:
+        try:
+            if not os.path.exists(constant.NHENTAI_HOME):
+                os.mkdir(constant.NHENTAI_HOME)
+
+            with open(os.path.join(constant.NHENTAI_HOME, 'cookie'), 'w') as f:
+                f.write(args.cookie)
+        except Exception as e:
+            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+            exit(1)
+
+        logger.info('Cookie saved.')
+        exit(0)
+
+    '''
     if args.login:
         try:
             _, _ = args.login.split(':', 1)
@@ -78,21 +125,29 @@ def cmd_parser():
 
         if not args.is_download:
             logger.warning('YOU DO NOT SPECIFY `--download` OPTION !!!')
+    '''
 
-    if args.tags:
-        logger.warning('`--tags` is under construction')
-        exit(1)
+    if args.favorites:
+        if not constant.COOKIE:
+            logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
+            exit(1)
 
     if args.id:
-        _ = map(lambda id: id.strip(), args.id.split(','))
+        _ = map(lambda id_: id_.strip(), args.id.split(','))
         args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
 
-    if (args.is_download or args.is_show) and not args.id and not args.keyword and not args.login:
+    if args.file:
+        with open(args.file, 'r') as f:
+            _ = map(lambda id: id.strip(), f.readlines())
+            args.id = set(map(int, filter(lambda id_: id_.isdigit(), _)))
+
+    if (args.is_download or args.is_show) and not args.id and not args.keyword and \
+            not args.tag 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.login:
+    if not args.keyword and not args.id and not args.tag and not args.favorites:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -5,12 +5,12 @@ import signal
 import platform
 
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, login_parser
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser, login
 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
+from nhentai.utils import generate_html, generate_cbz
 
 
 def main():
@@ -21,18 +21,30 @@ def main():
     doujinshi_ids = []
     doujinshi_list = []
 
-    if options.login:
-        username, password = options.login.split(':', 1)
-        logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
-        for doujinshi_info in login_parser(username=username, password=password):
+    if options.favorites:
+        if not options.is_download:
+            logger.warning('You do not specify --download option')
+
+        for doujinshi_info in favorites_parser():
             doujinshi_list.append(Doujinshi(**doujinshi_info))
 
+        if not options.is_download:
+            print_doujinshi([{'id': i.id, 'title': i.name} for i in doujinshi_list])
+            exit(0)
+
+    if options.tag:
+        doujinshis = tag_parser(options.tag, max_page=options.max_page)
+        print_doujinshi(doujinshis)
+        if options.is_download and doujinshis:
+            doujinshi_ids = map(lambda d: d['id'], doujinshis)
+
     if options.keyword:
         doujinshis = search_parser(options.keyword, options.page)
         print_doujinshi(doujinshis)
         if options.is_download:
             doujinshi_ids = map(lambda d: d['id'], doujinshis)
-    else:
+
+    if not doujinshi_ids:
         doujinshi_ids = options.id
 
     if doujinshi_ids:
@@ -47,10 +59,13 @@ def main():
         for doujinshi in doujinshi_list:
             doujinshi.downloader = downloader
             doujinshi.download()
-            generate_html(options.output_dir, doujinshi)
+            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)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍺 All done.')
+            logger.log(15, '🍻 All done.')
         else:
             logger.log(15, 'All done.')
 
@@ -59,7 +74,7 @@ def main():
 
 
 def signal_handler(signal, frame):
-    logger.error('Ctrl-C signal received. Quit.')
+    logger.error('Ctrl-C signal received. Stopping...')
     exit(1)
 
 

nhentai/constant.py

@@ -1,16 +1,28 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 import os
+import tempfile
 from nhentai.utils import urlparse
 
 BASE_URL = os.getenv('NHENTAI', 'https://nhentai.net')
 
-DETAIL_URL = '%s/api/gallery' % BASE_URL
-SEARCH_URL = '%s/api/galleries/search' % BASE_URL
+__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
+
+TAG_URL = '%s/tag' % BASE_URL
+TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
 LOGIN_URL = '%s/login/' % BASE_URL
+CHALLENGE_URL = '%s/challenge' % BASE_URL
 FAV_URL = '%s/favorites/' % BASE_URL
 
 u = urlparse(BASE_URL)
 IMAGE_URL = '%s://i.%s/galleries' % (u.scheme, u.hostname)
 
+NHENTAI_HOME = os.path.join(os.getenv('HOME', tempfile.gettempdir()), '.nhentai')
+
 PROXY = {}
+
+COOKIE = ''

nhentai/doujinshi.html

@@ -1,126 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <title>{TITLE}</title>
-    <style>
-        html, body {{
-            background-color: #e8e6e6;
-            height: 100%;
-            padding: 0;
-            margin: 0;
-            overflow: hidden;
-        }}
-
-        .container img {{
-            display: block;
-            width: 100%;
-            margin: 30px 0;
-            padding:  10px;
-            cursor: pointer;
-        }}
-
-        .container {{
-            height: 100%;
-            overflow: scroll;
-            background: #e8e6e6;
-            width: 200px;
-            padding: 30px;
-            float: left;
-        }}
-
-        .image {{
-            margin-left: 260px;
-            height: 100%;
-            background: #222;
-            text-align: center;
-        }}
-
-        .image img {{
-            height: 100%;
-        }}
-
-        .i a {{
-            display: block;
-            position: absolute;
-            top: 0;
-            width: 50%;
-            height: 100%;
-        }}
-
-        .i {{
-            position: relative;
-            height: 100%;
-        }}
-
-        .current {{
-            background: #BBB;
-            border-radius: 10px;
-        }}
-    </style>
-
-    <script>
-        function cursorfocus(elem) {{
-            var container = document.getElementsByClassName('container')[0];
-            container.scrollTop = elem.offsetTop - 500;
-        }}
-
-        function getImage(type) {{
-            var current = document.getElementsByClassName("current")[0];
-            current.className = "image-item";
-            var img_src = type == 1 ? current.getAttribute('attr-next') : current.getAttribute('attr-prev');
-            if (img_src === "") {{
-                img_src = current.src;
-            }}
-
-            var img_list = document.getElementsByClassName("image-item");
-            for (i=0; i<img_list.length; i++) {{
-                if (img_list[i].src.endsWith(img_src)) {{
-                    img_list[i].className = "image-item current";
-                    cursorfocus(img_list[i]);
-                    break;
-                }}
-            }}
-            var display = document.getElementById("dest");
-            display.src = img_src;
-            display.focus();
-        }}
-    </script>
-</head>
-<body>
-
-<div class="container">
-{IMAGES}</div>
-<div class="image">
-    <div class="i">
-        <img src="" id="dest">
-        <a href="javascript:getImage(-1)" style="left: 0;"></a>
-        <a href="javascript:getImage(1)" style="left: 50%;"></a>
-    </div>
-</div>
-</body>
-
-<script>
-    var img_list = document.getElementsByClassName("image-item");
-
-    var display = document.getElementById("dest");
-    display.src = img_list[0].src;
-
-    for (var i = 0; i < img_list.length; i++) {{
-        img_list[i].addEventListener('click', function() {{
-            var current = document.getElementsByClassName("current")[0];
-            current.className = "image-item";
-            this.className = "image-item current";
-            var display = document.getElementById("dest");
-            display.src = this.src;
-            display.focus();
-        }}, false);
-    }}
-
-    document.onkeypress = function(e) {{
-        if (e.keyCode == 32) {{
-            getImage(1);
-        }}
-    }}
-</script>
-</html>

nhentai/doujinshi.py

@@ -11,6 +11,7 @@ from nhentai.utils import format_filename
 EXT_MAP = {
     'j': 'jpg',
     'p': 'png',
+    'g': 'gif',
 }
 
 
@@ -35,6 +36,7 @@ class Doujinshi(object):
         self.downloader = None
         self.url = '%s/%d' % (DETAIL_URL, self.id)
         self.info = DoujinshiInfo(**kwargs)
+        self.filename = format_filename('[%s][%s][%s]' % (self.id, self.info.artist, self.name))
 
     def __repr__(self):
         return '<Doujinshi: {0}>'.format(self.name)
@@ -43,8 +45,8 @@ class Doujinshi(object):
         table = [
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
-            ["Characters", self.info.characters],
-            ["Authors", self.info.artists],
+            ["Characters", self.info.character],
+            ["Authors", self.info.artist],
             ["Language", self.info.language],
             ["Tags", self.info.tags],
             ["URL", self.url],
@@ -53,15 +55,25 @@ class Doujinshi(object):
         logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
 
     def download(self):
-        logger.info('Start download doujinshi: %s' % self.name)
+        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')
+
+            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]))
+
+            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]]))
+            '''
 
-            self.downloader.download(download_queue, format_filename('%s-%s' % (self.id, self.name[:200])))
         else:
-            logger.critical('Downloader has not be loaded')
+            logger.critical('Downloader has not been loaded')
 
 
 if __name__ == '__main__':

nhentai/downloader.py

@@ -29,22 +29,40 @@ class Downloader(Singleton):
         self.path = str(path)
         self.thread_count = thread
         self.threads = []
+        self.thread_pool = None
         self.timeout = timeout
 
     def _download(self, url, folder='', filename='', retried=0):
-        logger.info('Start downloading: {0} ...'.format(url))
+        logger.info('Starting to download {0} ...'.format(url))
         filename = filename if filename else os.path.basename(urlparse(url).path)
         base_filename, extension = os.path.splitext(filename)
         try:
             if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
-                logger.warning('File: {0} existed, ignore.'.format(os.path.join(folder, base_filename.zfill(3) +
+                logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
                                                                                 extension)))
                 return 1, url
 
+            response = None
             with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
-                response = request('get', url, stream=True, timeout=self.timeout)
-                if response.status_code != 200:
-                    raise NhentaiImageNotExistException
+                i = 0
+                while i < 10:
+                    try:
+                        response = request('get', url, stream=True, timeout=self.timeout)
+                        if response.status_code != 200:
+                            raise NhentaiImageNotExistException
+
+                    except NhentaiImageNotExistException as e:
+                        raise e
+
+                    except Exception as e:
+                        i += 1
+                        if not i < 10:
+                            logger.critical(str(e))
+                            return 0, None
+                        continue
+
+                    break
+
                 length = response.headers.get('content-length')
                 if length is None:
                     f.write(response.content)
@@ -77,7 +95,7 @@ class Downloader(Singleton):
         elif result == -1:
             logger.warning('url {} return status code 404'.format(data))
         else:
-            logger.log(15, '{0} download successfully'.format(data))
+            logger.log(15, '{0} downloaded successfully'.format(data))
 
     def download(self, queue, folder=''):
         if not isinstance(folder, text):
@@ -87,7 +105,7 @@ class Downloader(Singleton):
             folder = os.path.join(self.path, folder)
 
         if not os.path.exists(folder):
-            logger.warn('Path \'{0}\' not exist.'.format(folder))
+            logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
             try:
                 os.makedirs(folder)
             except EnvironmentError as e:

nhentai/logger.py

@@ -104,7 +104,10 @@ class ColorizingStreamHandler(logging.StreamHandler):
                 text = parts.pop(0)
 
                 if text:
-                    write(text)
+                    if sys.version_info < (3, 0, 0):
+                        write(text.encode('utf-8'))
+                    else:
+                        write(text)
 
                 if parts:
                     params = parts.pop(0)

nhentai/parser.py

@@ -5,6 +5,7 @@ import os
 import re
 import threadpool
 import requests
+import time
 from bs4 import BeautifulSoup
 from tabulate import tabulate
 
@@ -12,47 +13,78 @@ import nhentai.constant as constant
 from nhentai.logger import logger
 
 
+session = requests.Session()
+session.headers.update({
+    'Referer': constant.LOGIN_URL,
+    'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+})
+
+
 def request(method, url, **kwargs):
-    if not hasattr(requests, method):
-        raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
+    global session
+    if not hasattr(session, method):
+        raise AttributeError('\'requests.Session\' object has no attribute \'{0}\''.format(method))
 
-    return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
+    session.headers.update({'Cookie': constant.COOKIE})
+    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
 
 
-def login_parser(username, password):
-    s = requests.Session()
-    s.proxies = constant.PROXY
-    s.verify = False
-    s.headers.update({'Referer': constant.LOGIN_URL})
-
-    s.get(constant.LOGIN_URL)
-    content = s.get(constant.LOGIN_URL).content
+def _get_csrf_token(content):
     html = BeautifulSoup(content, 'html.parser')
     csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
-
     if not csrf_token_elem:
         raise Exception('Cannot find csrf token to login')
-    csrf_token = csrf_token_elem.attrs['value']
+    return csrf_token_elem.attrs['value']
+
+
+def login(username, password):
+    logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
+    csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
+    if os.getenv('DEBUG'):
+        logger.info('Getting CSRF token ...')
+
+    if os.getenv('DEBUG'):
+        logger.info('CSRF token is {}'.format(csrf_token))
 
     login_dict = {
         'csrfmiddlewaretoken': csrf_token,
         'username_or_email': username,
         'password': password,
     }
-    resp = s.post(constant.LOGIN_URL, data=login_dict)
-    if 'Invalid username (or email) or password' in resp.text:
+    resp = request('post', url=constant.LOGIN_URL, data=login_dict)
+
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        csrf_token = _get_csrf_token(resp.text)
+        resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
+
+    if 'Invalid username/email or password' in resp.text:
         logger.error('Login failed, please check your username and password')
         exit(1)
 
-    html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')
+    if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+        logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
+        exit(2)
+
+
+def favorites_parser():
+    html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
     if not count:
-        logger.error('Cannot get count of your favorites, maybe login failed.')
+        logger.error("Can't get your number of favorited doujins. Did the login failed?")
+        return []
 
-    count = int(count.text.strip('(').strip(')'))
-    pages = count / 25
-    pages += 1 if count % (25 * pages) else 0
-    logger.info('Your have %d favorites in %d pages.' % (count, pages))
+    count = int(count.text.strip('(').strip(')').replace(',', ''))
+    if count == 0:
+        logger.warning('No favorites found')
+        return []
+    pages = int(count / 25)
+
+    if pages:
+        pages += 1 if count % (25 * pages) else 0
+    else:
+        pages = 1
+
+    logger.info('You have %d favorites in %d pages.' % (count, pages))
 
     if os.getenv('DEBUG'):
         pages = 1
@@ -60,19 +92,15 @@ def login_parser(username, password):
     ret = []
     doujinshi_id = re.compile('data-id="([\d]+)"')
 
-    def _callback(request, result):
-        ret.append(result)
-
-    thread_pool = threadpool.ThreadPool(5)
-
-    for page in range(1, pages+1):
+    for page in range(1, pages + 1):
         try:
-            logger.info('Getting doujinshi id of page %d' % page)
-            resp = s.get(constant.FAV_URL + '?page=%d' % page).content
+            logger.info('Getting doujinshi ids of page %d' % page)
+            resp = request('get', constant.FAV_URL + '?page=%d' % page).text
             ids = doujinshi_id.findall(resp)
-            requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
-            [thread_pool.putRequest(req) for req in requests_]
-            thread_pool.wait()
+
+            for i in ids:
+                ret.append(doujinshi_parser(i))
+
         except Exception as e:
             logger.error('Error: %s, continue', str(e))
 
@@ -87,29 +115,62 @@ def doujinshi_parser(id_):
     logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
     doujinshi = dict()
     doujinshi['id'] = id_
-    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
 
     try:
-        response = request('get', url).json()
+        response = request('get', url)
+        if response.status_code in (200, ):
+            response = response.content
+        else:
+            logger.debug('Slow down and retry ({}) ...'.format(id_))
+            time.sleep(1)
+            return doujinshi_parser(str(id_))
+
     except Exception as e:
         logger.critical(str(e))
+        raise SystemExit
+
+    html = BeautifulSoup(response, 'html.parser')
+    doujinshi_info = html.find('div', attrs={'id': 'info'})
+
+    title = doujinshi_info.find('h1').text
+    subtitle = doujinshi_info.find('h2')
+
+    doujinshi['name'] = title
+    doujinshi['subtitle'] = subtitle.text if subtitle else ''
+
+    doujinshi_cover = html.find('div', attrs={'id': 'cover'})
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
+
+    ext = []
+    for i in html.find_all('div', attrs={'class': 'thumb-container'}):
+        _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
+        ext.append(ext_name)
+
+    if not img_id:
+        logger.critical('Tried yo get image id failed')
         exit(1)
 
-    doujinshi['name'] = response['title']['english']
-    doujinshi['subtitle'] = response['title']['japanese']
-    doujinshi['img_id'] = response['media_id']
-    doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))
-    doujinshi['pages'] = len(response['images']['pages'])
+    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
+    doujinshi['pages'] = int(pages)
 
     # gain information of the doujinshi
-    needed_fields = ['character', 'artist', 'language']
-    for tag in response['tags']:
-        tag_type = tag['type']
-        if tag_type in needed_fields:
-            if tag_type not in doujinshi:
-                doujinshi[tag_type] = tag['name']
-            else:
-                doujinshi[tag_type] += tag['name']
+    information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
+    needed_fields = ['Characters', 'Artists', 'Language', 'Tags']
+    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
+                    field.find_all('a', attrs={'class': 'tag'})]
+            doujinshi[field_name.lower()] = ', '.join(data)
 
     return doujinshi
 
@@ -118,13 +179,91 @@ def search_parser(keyword, page):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     result = []
     try:
-        response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()
-        if 'result' not in response:
-            raise Exception('No result in response')
+        response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page}).content
     except requests.ConnectionError as e:
         logger.critical(e)
         logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
-        exit(1)
+        raise SystemExit
+
+    html = BeautifulSoup(response, 'html.parser')
+    doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
+    for doujinshi in doujinshi_search_result:
+        doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
+        title = doujinshi_container.text.strip()
+        title = title if len(title) < 85 else title[:82] + '...'
+        id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
+        result.append({'id': id_, 'title': title})
+    if not result:
+        logger.warn('Not found anything of keyword {}'.format(keyword))
+
+    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_))
+
+    id_ = int(id_)
+    logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
+    doujinshi = dict()
+    doujinshi['id'] = id_
+    url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
+    i = 0
+    while 5 > i:
+        try:
+            response = request('get', url).json()
+        except Exception as e:
+            i += 1
+            if not i < 5:
+                logger.critical(str(e))
+                exit(1)
+            continue
+        break
+
+    doujinshi['name'] = response['title']['english']
+    doujinshi['subtitle'] = response['title']['japanese']
+    doujinshi['img_id'] = response['media_id']
+    doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))
+    doujinshi['pages'] = len(response['images']['pages'])
+
+    # gain information of the doujinshi
+    needed_fields = ['character', 'artist', 'language', 'tag']
+    for tag in response['tags']:
+        tag_type = tag['type']
+        if tag_type in needed_fields:
+            if tag_type == 'tag':
+                if tag_type not in doujinshi:
+                    doujinshi[tag_type] = {}
+
+                tag['name'] = tag['name'].replace(' ', '-')
+                tag['name'] = tag['name'].lower()
+                doujinshi[tag_type][tag['name']] = tag['id']
+            elif tag_type not in doujinshi:
+                doujinshi[tag_type] = tag['name']
+            else:
+                doujinshi[tag_type] += ', ' + tag['name']
+
+    return doujinshi
+
+
+def __api_suspended_search_parser(keyword, page):
+    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
+    result = []
+    i = 0
+    while i < 5:
+        try:
+            response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()
+        except Exception as e:
+            i += 1
+            if not i < 5:
+                logger.critical(str(e))
+                logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
+                exit(1)
+            continue
+        break
+
+    if 'result' not in response:
+        raise Exception('No result in response')
 
     for row in response['result']:
         title = row['title']['english']
@@ -132,7 +271,7 @@ def search_parser(keyword, page):
         result.append({'id': row['id'], 'title': title})
 
     if not result:
-        logger.warn('Not found anything of keyword {}'.format(keyword))
+        logger.warn('No results for keywords {}'.format(keyword))
 
     return result
 
@@ -146,5 +285,55 @@ def print_doujinshi(doujinshi_list):
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
+def __api_suspended_tag_parser(tag_id, 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': 'popular', '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': 'popular', '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 tag_parser(tag_name, max_page=1):
+    result = []
+    tag_name = tag_name.lower()
+    tag_name = tag_name.replace(' ', '-')
+
+    for p in range(1, max_page + 1):
+        logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
+        response = request('get', url='%s/%s?page=%d' % (constant.TAG_URL, tag_name, p)).content
+
+        html = BeautifulSoup(response, 'html.parser')
+        doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
+        if not doujinshi_items:
+            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
+            return
+
+        for i in doujinshi_items:
+            doujinshi_id = i.a.attrs['href'].strip('/g')
+            doujinshi_title = i.a.text.strip()
+            doujinshi_title = doujinshi_title if len(doujinshi_title) < 85 else doujinshi_title[:82] + '...'
+            result.append({'title': doujinshi_title, 'id': doujinshi_id})
+
+    if not result:
+        logger.warn('No results for tag \'{}\''.format(tag_name))
+
+    return result
+
+
 if __name__ == '__main__':
     print(doujinshi_parser("32271"))

nhentai/utils.py

@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 
+import sys
 import os
 import string
+import zipfile
+import shutil
 from nhentai.logger import logger
 
 
@@ -29,45 +32,77 @@ def urlparse(url):
     return urlparse(url)
 
 
+def readfile(path):
+    loc = os.path.dirname(__file__)
+
+    with open(os.path.join(loc, path), 'r') as file:
+        return file.read()
+
+
 def generate_html(output_dir='.', doujinshi_obj=None):
     image_html = ''
-    previous = ''
 
     if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
-                                                                            doujinshi_obj.name[:200])))
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
     else:
         doujinshi_dir = '.'
 
     file_list = os.listdir(doujinshi_dir)
     file_list.sort()
 
-    for index, image in enumerate(file_list):
+    for image in file_list:
         if not os.path.splitext(image)[1] in ('.jpg', '.png'):
             continue
 
-        try:
-            next_ = file_list[file_list.index(image) + 1]
-        except IndexError:
-            next_ = ''
+        image_html += '<img src="{0}" class="image-item"/>\n'\
+            .format(image)
 
-        image_html += '<img src="{0}" class="image-item {1}" attr-prev="{2}" attr-next="{3}">\n'\
-            .format(image, 'current' if index == 0 else '', previous, next_)
-        previous = image
-
-    with open(os.path.join(os.path.dirname(__file__), 'doujinshi.html'), 'r') as template:
-        html = template.read()
+    html = readfile('viewer/index.html')
+    css = readfile('viewer/styles.css')
+    js = readfile('viewer/scripts.js')
 
     if doujinshi_obj is not None:
         title = doujinshi_obj.name
+        if sys.version_info < (3, 0):
+            title = title.encode('utf-8')
     else:
         title = 'nHentai HTML Viewer'
 
-    data = html.format(TITLE=title, IMAGES=image_html)
-    with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
-        f.write(data)
+    data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
+    try:
+        if sys.version_info < (3, 0):
+            with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
+                f.write(data)
+        else:
+            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 write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
+    except Exception as e:
+        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
+
+
+def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
+        cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '%s.cbz' % doujinshi_obj.id)
+    else:
+        cbz_filename = './doujinshi.cbz'
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
+    with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
+        for image in file_list:
+            image_path = os.path.join(doujinshi_dir, image)
+            cbz_pf.write(image_path, image)
+
+    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))
 
 
 def format_filename(s):
@@ -81,7 +116,12 @@ and append a file extension like '.txt', so I avoid the potential of using
 an invalid filename.
 
 """
-    valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
+    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
     filename = ''.join(c for c in s if c in valid_chars)
     filename = filename.replace(' ', '_')  # I don't like spaces in filenames.
+    if len(filename) > 100:
+        filename = filename[:100] + '...]'
+
+    # Remove [] from filename
+    filename = filename.replace('[]', '')
     return filename

nhentai/viewer/index.html

@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <title>{TITLE}</title>
+    <style>
+{STYLES}
+    </style>
+</head>
+<body>
+
+<nav id="list">
+{IMAGES}</nav>
+
+<div id="image-container">
+    <span id="page-num"></span>
+    <div id="dest"></div>
+</div>
+
+<script>
+{SCRIPTS}
+</script>
+</body>
+</html>

nhentai/viewer/scripts.js

@@ -0,0 +1,78 @@
+const pages = Array.from(document.querySelectorAll('img.image-item'));
+let currentPage = 0;
+
+function changePage(pageNum) {
+    const previous = pages[currentPage];
+    const current = pages[pageNum];
+
+    if (current == null) {
+        return;
+    }
+    
+    previous.classList.remove('current');
+    current.classList.add('current');
+
+    currentPage = pageNum;
+
+    const display = document.getElementById('dest');
+    display.style.backgroundImage = `url("${current.src}")`;
+
+    document.getElementById('page-num')
+        .innerText = [
+                (pageNum + 1).toLocaleString(),
+                pages.length.toLocaleString()
+            ].join('\u200a/\u200a');
+}
+
+changePage(0);
+
+document.getElementById('list').onclick = event => {
+    if (pages.includes(event.target)) {
+        changePage(pages.indexOf(event.target));
+    }
+};
+
+document.getElementById('image-container').onclick = event => {
+    const width = document.getElementById('image-container').clientWidth;
+    const clickPos = event.clientX / width;
+
+    if (clickPos < 0.5) {
+        changePage(currentPage - 1);
+    } else {
+        changePage(currentPage + 1);
+    }
+};
+
+document.onkeypress = event => {
+    switch (event.key.toLowerCase()) {
+        // Previous Image
+        case 'a':
+            changePage(currentPage - 1);
+            break;
+
+        // Next Image
+        case ' ':
+        case 'esc': // future close page function
+        case 'enter':
+        case 'd':
+            changePage(currentPage + 1);
+            break;
+    }// remove arrow cause it won't work
+};
+
+document.onkeydown = event =>{
+    switch (event.keyCode) {
+        case 37: //left
+            changePage(currentPage - 1);
+            break;
+        case 38: //up
+            changePage(currentPage - 1);
+            break;
+        case 39: //right
+            changePage(currentPage + 1);
+            break;
+        case 40: //down
+            changePage(currentPage + 1);
+            break;
+    }
+};

nhentai/viewer/styles.css

@@ -0,0 +1,69 @@
+*, *::after, *::before {
+    box-sizing: border-box;
+}
+
+img {
+    vertical-align: middle;
+}
+
+html, body {
+    display: flex;
+    background-color: #e8e6e6;
+    height: 100%;
+    width: 100%;
+    padding: 0;
+    margin: 0;
+    font-family: sans-serif;
+}
+
+#list {
+    height: 100%;
+    overflow: auto;
+    width: 260px;
+    text-align: center;
+}
+
+#list img {
+    width: 200px;
+    padding: 10px;
+    border-radius: 10px;
+    margin: 15px 0;
+    cursor: pointer;
+}
+
+#list img.current {
+    background: #0003;
+}
+
+#image-container {
+    flex: auto;
+    height: 100vh;
+    background: #222;
+    color: #fff;
+    text-align: center;
+    cursor: pointer;
+    -webkit-user-select: none;
+    user-select: none;
+    position: relative;
+}
+
+#image-container #dest {
+    height: 100%;
+    width: 100%;
+    background-size: contain;
+    background-repeat: no-repeat;
+    background-position: center;
+}
+
+#image-container #page-num {
+    position: absolute;
+    font-size: 18pt;
+    left: 10px;
+    bottom: 5px;
+    font-weight: bold;
+    opacity: 0.75;
+    text-shadow: /* Duplicate the same shadow to make it very strong */
+        0 0 2px #222,
+        0 0 2px #222,
+        0 0 2px #222;
+}