tag page download #40

requirement.txt missing new line

.travis.yml

@@ -4,9 +4,9 @@ os:
 language: python
 python:
     - 2.7
-    - 2.6
     - 3.6
-    - 3.7
+    - 3.5
+    - 3.4
 
 install:
     - python setup.py install
@@ -14,4 +14,6 @@ install:
 script:
     - NHENTAI=https://nhentai.net nhentai --search umaru
     - NHENTAI=https://nhentai.net nhentai --id=152503,146134 -t 10 --output=/tmp/
-    - NHENTAI=https://nhentai.net nhentai -l nhentai_test:nhentai --output=/tmp/
+    - NHENTAI=https://nhentai.net nhentai -l nhentai_test:nhentai --download --output=/tmp/
+    - NHENTAI=https://nhentai.net nhentai --tag lolicon
+    - NHENTAI=https://nhentai.net nhentai --id 92066 --output=/tmp/ --cbz

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://pypistats.com/badge/nhentai.svg)  
 
-🎉🎉 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
 
@@ -25,36 +24,45 @@ nhentai
     sudo emerge net-misc/nhentai
 
 ### Usage
-下载指定 id 列表的本子：
+Download specified doujinshi:
 ```bash
 nhentai --id=123855,123866
 ```
 
-下载某关键词第一页的本子：
+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
-`--nohtml`：nhentai Don't generate HTML
-`--cbz`：nhentai Generate Comic Book CBZ file
++ `-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
 ```

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.2.14'
+__version__ = '0.2.19'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -13,8 +13,12 @@ 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
@@ -36,21 +40,23 @@ def cmd_parser():
                           '\n\nEnvironment Variable:\n'
                           '  NHENTAI                 nhentai mirror url')
     parser.add_option('--download', dest='is_download', action='store_true',
-                      help='download doujinshi (for search result)')
+                      help='download doujinshi (for search results)')
     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,
-                      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('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
+    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('--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('--html', dest='html_viewer', action='store_true',
                       help='generate a html viewer at current directory')
 
@@ -62,6 +68,8 @@ def cmd_parser():
 
     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.')
                       
     try:
         sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
@@ -86,20 +94,17 @@ 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.id:
         _ = 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.is_download or args.is_show) and not args.id and not args.keyword and \
+            not args.login and not args.tag:
         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.login and not args.tag:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -5,7 +5,7 @@ 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, login_parser, tag_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
@@ -23,16 +23,23 @@ def main():
 
     if options.login:
         username, password = options.login.split(':', 1)
-        logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
+        logger.info('Logging in to nhentai using credential pair \'%s:%s\'' % (username, '*' * len(password)))
         for doujinshi_info in login_parser(username=username, password=password):
             doujinshi_list.append(Doujinshi(**doujinshi_info))
 
+    if options.tag:
+        doujinshis = tag_parser(options.tag, max_page=options.max_page)
+        print_doujinshi(doujinshis)
+        if options.is_download:
+            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:
@@ -50,7 +57,7 @@ def main():
             if not options.is_nohtml and not options.is_cbz:
                 generate_html(options.output_dir, doujinshi)
             elif options.is_cbz:
-                generate_cbz(options.output_dir, doujinshi)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
 
         if not platform.system() == 'Windows':
             logger.log(15, '🍻 All done.')
@@ -62,7 +69,7 @@ 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

@@ -5,8 +5,14 @@ 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
 FAV_URL = '%s/favorites/' % BASE_URL
 

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)
@@ -43,25 +45,32 @@ 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],
+            ["Tags", ', '.join(self.info.tag.keys())],
             ["URL", self.url],
             ["Pages", self.pages],
         ]
         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 = []
+
+            for i in range(1, self.pages + 1):
+                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext))
+
+            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:
+                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

@@ -104,6 +104,9 @@ class ColorizingStreamHandler(logging.StreamHandler):
                 text = parts.pop(0)
 
                 if text:
+                    if sys.version_info < (3, 0, 0):
+                        write(text.encode('utf-8'))
+                    else:
                         write(text)
 
                 if parts:

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
 
@@ -40,16 +41,16 @@ def login_parser(username, password):
         'password': password,
     }
     resp = s.post(constant.LOGIN_URL, data=login_dict)
-    if 'Invalid username (or email) or password' in resp.text:
+    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')
     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?")
 
-    count = int(count.text.strip('(').strip(')'))
+    count = int(count.text.strip('(').strip(')').replace(',', ''))
     if count == 0:
         logger.warning('No favorites found')
         return []
@@ -60,7 +61,7 @@ def login_parser(username, password):
     else:
         pages = 1
 
-    logger.info('Your have %d favorites in %d pages.' % (count, pages))
+    logger.info('You have %d favorites in %d pages.' % (count, pages))
 
     if os.getenv('DEBUG'):
         pages = 1
@@ -73,9 +74,9 @@ def login_parser(username, password):
 
     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)
+            logger.info('Getting doujinshi ids of page %d' % page)
             resp = s.get(constant.FAV_URL + '?page=%d' % page).text
             ids = doujinshi_id.findall(resp)
             requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
@@ -95,29 +96,49 @@ 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).content
     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'])
+    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'] = img_id.group(2)
+
+    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
 
@@ -126,13 +147,91 @@ 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.')
+        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']
@@ -140,7 +239,7 @@ 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
 
@@ -154,5 +253,55 @@ 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

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 
+import sys
 import os
 import string
 import zipfile
@@ -30,18 +31,19 @@ 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 = ''
 
     if doujinshi_obj is not None:
-        doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
-                                                                            str(doujinshi_obj.name[:200]))))
+        doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
     else:
         doujinshi_dir = '.'
 
@@ -61,22 +63,29 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
     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, 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')))
+    except Exception as e:
+        logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
 
 
-def generate_cbz(output_dir='.', doujinshi_obj=None):
+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, format_filename('%s-%s' % (doujinshi_obj.id,
-                                                                            str(doujinshi_obj.name[:200]))))    
-        cbz_filename = os.path.join(output_dir, format_filename('%s-%s.cbz' % (doujinshi_obj.id,
-                                                                            str(doujinshi_obj.name[:200]))))
+        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 = '.'
@@ -84,20 +93,18 @@ def generate_cbz(output_dir='.', doujinshi_obj=None):
     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):
     """Take a string and return a valid filename constructed from the string.
 Uses a whitelist approach: any characters not present in valid_chars are
@@ -109,7 +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

requirements.txt

@@ -2,4 +2,4 @@ requests>=2.5.0
 BeautifulSoup4>=4.0.0
 threadpool>=1.2.7
 tabulate>=0.7.5
-future>=0.15.2threadpool==1.3.2
+future>=0.15.2