fix bug and add --html

0.2.8
sort #10
2025-07-01 07:59:29 +02:00 · 2018-01-01 17:44:55 +08:00 · 2017-08-19 00:50:38 +08:00 · 2017-08-19 00:48:53 +08:00 · 2017-07-06 15:41:33 +08:00 · 2017-06-18 16:48:54 +08:00
13 changed files with 227 additions and 25 deletions
--- a/.gitignore
+++ b/.gitignore
@ -4,4 +4,4 @@ build
 dist/
 *.egg-info
 .python-version
-
+.DS_Store
--- a/MANIFEST.in
+++ b/MANIFEST.in
@ -1,2 +1,3 @@
 include README.md
 include requirements.txt
+include nhentai/doujinshi.html
--- a/README.md
+++ b/README.md
@ -47,6 +47,7 @@ nhentai

 ![](./images/search.png)  
 ![](./images/download.png)  
+![](./images/viewer.png)  

 ### License  
 MIT
--- a/images/image.jpg
+++ b/images/image.jpg
--- a/images/viewer.png
+++ b/images/viewer.png
--- a/nhentai/init.py
+++ b/nhentai/init.py
@ -1,3 +1,3 @@
-__version__ = '0.2.2'
+__version__ = '0.2.9'
 __author__ = 'Ricter'
 __email__ = 'ricterzheng@gmail.com'
--- a/nhentai/cmdline.py
+++ b/nhentai/cmdline.py
@ -8,7 +8,7 @@ except ImportError:
    pass

 import nhentai.constant as constant
-from nhentai.utils import urlparse
+from nhentai.utils import urlparse, generate_html
 from nhentai.logger import logger

 try:
@ -30,9 +30,12 @@ def banner():


 def cmd_parser():
-    parser = OptionParser()
-    parser.add_option('--download', dest='is_download', action='store_true', help='download doujinshi or not')
-    parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information.')
+    parser = OptionParser('\n  nhentai --search [keyword] --download'
+                          '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
+                          '\n\nEnvironment Variable:\n'
+                          '  NHENTAI                 nhentai mirror url')
+    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')
    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('--page', type='int', dest='page', action='store', default=1,
@ -46,6 +49,7 @@ def cmd_parser():
                      help='timeout of download doujinshi')
    parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
                      help='use proxy, example: http://127.0.0.1:1080')
+    parser.add_option('--html', dest='html_viewer', action='store_true', help='generate a html viewer at current directory')

    try:
        sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
@ -56,6 +60,10 @@ def cmd_parser():

    args, _ = parser.parse_args(sys.argv[1:])

+    if args.html_viewer:
+        generate_html()
+        exit(0)
+
    if args.tags:
        logger.warning('`--tags` is under construction')
        exit(0)
@ -76,8 +84,8 @@ def cmd_parser():
    if args.threads <= 0:
        args.threads = 1

-    elif args.threads > 10:
-        logger.critical('Maximum number of used threads is 10')
+    elif args.threads > 15:
+        logger.critical('Maximum number of used threads is 15')
        exit(0)

    if args.proxy:
--- a/nhentai/command.py
+++ b/nhentai/command.py
@ -1,6 +1,7 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
 from __future__ import unicode_literals, print_function
+import os
 import signal
 import platform

@ -10,6 +11,7 @@ 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


 def main():
@ -42,6 +44,7 @@ def main():
        for doujinshi in doujinshi_list:
            doujinshi.downloader = downloader
            doujinshi.download()
+            generate_html(doujinshi, output_dir)

        if not platform.system() == 'Windows':
            logger.log(15, '🍺 All done.')
--- a/nhentai/doujinshi.html
+++ b/nhentai/doujinshi.html
@ -0,0 +1,126 @@
+<!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>
--- a/nhentai/downloader.py
+++ b/nhentai/downloader.py
@ -14,45 +14,65 @@ from nhentai.parser import request
 from nhentai.utils import Singleton


+requests.packages.urllib3.disable_warnings()
+
+
+class NhentaiImageNotExistException(Exception):
+    pass
+
+
 class Downloader(Singleton):

    def __init__(self, path='', thread=1, timeout=30):
-        if not isinstance(thread, (int, )) or thread < 1 or thread > 10:
+        if not isinstance(thread, (int, )) or thread < 1 or thread > 15:
            raise ValueError('Invalid threads count')
        self.path = str(path)
        self.thread_count = thread
        self.threads = []
        self.timeout = timeout

-    def _download(self, url, folder='', filename='', retried=False):
+    def _download(self, url, folder='', filename='', retried=0):
        logger.info('Start downloading: {0} ...'.format(url))
        filename = filename if filename else os.path.basename(urlparse(url).path)
        base_filename, extension = os.path.splitext(filename)
        try:
            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
                length = response.headers.get('content-length')
                if length is None:
                    f.write(response.content)
                else:
                    for chunk in response.iter_content(2048):
                        f.write(chunk)
-        except requests.HTTPError as e:
-            if not retried:
-                logger.error('Error: {0}, retrying'.format(str(e)))
-                return self._download(url=url, folder=folder, filename=filename, retried=True)
+
+        except (requests.HTTPError, requests.Timeout) as e:
+            if retried < 3:
+                logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
+                return 0, self._download(url=url, folder=folder, filename=filename, retried=retried+1)
            else:
-                return None
+                return 0, None
+
+        except NhentaiImageNotExistException as e:
+            os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
+            return -1, url
+
        except Exception as e:
            logger.critical(str(e))
-            return None
-        return url
+            return 0, None
+
+        return 1, url

    def _download_callback(self, request, result):
-        if not result:
-            logger.critical('Too many errors occurred, quit.')
-            exit(1)
-        logger.log(15, '{0} download successfully'.format(result))
+        result, data = result
+        if result == 0:
+            logger.warning('fatal errors occurred, ignored')
+            # exit(1)
+        elif result == -1:
+            logger.warning('url {} return status code 404'.format(data))
+        else:
+            logger.log(15, '{0} download successfully'.format(data))

    def download(self, queue, folder=''):
        if not isinstance(folder, (text)):
@ -66,7 +86,7 @@ class Downloader(Singleton):
            try:
                os.makedirs(folder)
            except EnvironmentError as e:
-                logger.critical('Error: {0}'.format(str(e)))
+                logger.critical('{0}'.format(str(e)))
                exit(1)
        else:
            logger.warn('Path \'{0}\' already exist.'.format(folder))
--- a/nhentai/parser.py
+++ b/nhentai/parser.py
@ -14,7 +14,7 @@ def request(method, url, **kwargs):
    if not hasattr(requests, method):
        raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))

-    return requests.__dict__[method](url, proxies=constant.PROXY, **kwargs)
+    return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)


 def doujinshi_parser(id_):
@ -43,7 +43,7 @@ def doujinshi_parser(id_):
    doujinshi['subtitle'] = subtitle.text if subtitle else ''

    doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img['src'])
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
    if not img_id:
        logger.critical('Tried yo get image id failed')
        exit(1)
--- a/nhentai/utils.py
+++ b/nhentai/utils.py
@ -1,6 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function

+import os
+from nhentai.logger import logger
+

 class _Singleton(type):
    """ A metaclass that creates a Singleton base class when called. """
@ -23,3 +26,43 @@ def urlparse(url):
        from urllib.parse import urlparse

    return urlparse(url)
+
+
+def generate_html(output_dir='.', doujinshi_obj=None):
+    image_html = ''
+    previous = ''
+
+    if doujinshi_obj is not None:
+        doujinshi_dir = os.path.join(output_dir, str(doujinshi_obj.id))
+    else:
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+
+    for index, image in enumerate(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 {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()
+
+    if doujinshi_obj is not None:
+        title = doujinshi_obj.name
+    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)
+
+    logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
--- a/setup.py
+++ b/setup.py
@ -9,7 +9,7 @@ with open('requirements.txt') as f:


 def long_description():
-    with codecs.open('README.md', 'rb') as f:
+    with codecs.open('README.md', 'r') as f:
        return str(f.read())

 setup(
Author	SHA1	Message	Date
Ricter Z	45fb35b950	fix bug and add --html	2018-01-01 17:44:55 +08:00
Ricter Z	2271b83d93	0.2.8	2017-08-19 00:50:38 +08:00
Ricter Z	0ee000edeb	sort #10	2017-08-19 00:48:53 +08:00
Ricter Z	a47359f411	tiny bug	2017-07-06 15:41:33 +08:00
Ricter Z	48c6fadc98	add viewer image	2017-06-18 16:48:54 +08:00
Ricter Z	dbc834ea2e	0.2.7	2017-06-18 14:25:00 +08:00
Ricter Z	71177ff94e	0.2.6	2017-06-18 14:19:28 +08:00
Ricter Z	d1ed9b6980	add html doujinshi viewer	2017-06-18 14:19:07 +08:00
Ricter Z	42a09e2c1e	fix timeout	2017-03-17 20:19:40 +08:00
Ricter Z	e306d50b7e	fix bug	2017-03-17 20:14:42 +08:00
Ricter Z	043f391d04	fix https error	2016-11-23 22:45:03 +08:00
Ricter Z	9549c5f5a2	fix bug	2016-11-23 22:35:56 +08:00
Ricter Z	5592b30be4	do not download 404	2016-11-23 22:11:47 +08:00