Merge pull request #21 from mentaterasmus/master

fixing issue 16 and adding functionalities

README.md

@@ -47,6 +47,8 @@ nhentai --login "username:password" --download
 `--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
 
 ### 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。  

nhentai/cmdline.py

@@ -56,6 +56,12 @@ def cmd_parser():
     parser.add_option('--login', '-l', type='str', dest='login', action='store',
                       help='username:password pair of nhentai account')
 
+    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')                      
+                      
     try:
         sys.argv = list(map(lambda x: unicode(x.decode(sys.stdin.encoding)), sys.argv))
     except (NameError, TypeError):

nhentai/command.py

@@ -10,7 +10,7 @@ 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
+from nhentai.utils import generate_html, generate_cbz
 
 
 def main():
@@ -47,10 +47,13 @@ def main():
         for doujinshi in doujinshi_list:
             doujinshi.downloader = downloader
             doujinshi.download()
+            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)
 
         if not platform.system() == 'Windows':
-            logger.log(15, '🍺 All done.')
+            logger.log(15, '? All done.')
         else:
             logger.log(15, 'All done.')
 

nhentai/parser.py

@@ -27,7 +27,7 @@ def login_parser(username, password):
 
     s.get(constant.LOGIN_URL)
     content = s.get(constant.LOGIN_URL).content
-    html = BeautifulSoup(content, 'html.parser')
+    html = BeautifulSoup(content, 'html.parser').encode("ascii")
     csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
 
     if not csrf_token_elem:
@@ -44,7 +44,7 @@ def login_parser(username, password):
         logger.error('Login failed, please check your username and password')
         exit(1)
 
-    html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')
+    html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser').encode("ascii")
     count = html.find('span', attrs={'class': 'count'})
     if not count:
         logger.error('Cannot get count of your favorites, maybe login failed.')
@@ -95,7 +95,7 @@ def doujinshi_parser(id_):
         logger.critical(str(e))
         exit(1)
 
-    doujinshi['name'] = response['title']['english']
+    doujinshi['name'] = str(response['title']['english'].encode('utf-8'))[2:]
     doujinshi['subtitle'] = response['title']['japanese']
     doujinshi['img_id'] = response['media_id']
     doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))

nhentai/utils.py

@@ -3,6 +3,8 @@ from __future__ import unicode_literals, print_function
 
 import os
 import string
+import zipfile
+import shutil
 from nhentai.logger import logger
 
 
@@ -35,7 +37,7 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
     if doujinshi_obj is not None:
         doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
-                                                                            doujinshi_obj.name[:200])))
+                                                                            str(doujinshi_obj.name[:200]))))
     else:
         doujinshi_dir = '.'
 
@@ -70,6 +72,33 @@ def generate_html(output_dir='.', doujinshi_obj=None):
     logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
 
 
+def generate_cbz(output_dir='.', doujinshi_obj=None):
+    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]))))
+    else:
+        cbz_filename = './doujinshi.cbz'
+        doujinshi_dir = '.'
+
+    file_list = os.listdir(doujinshi_dir)
+    file_list.sort()
+    
+    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)
+            
+    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