Merge pull request #123 from Alocks/dev

--search fix, removed --tag commands

README.rst

@@ -79,53 +79,20 @@ Download doujinshi with ids specified in a file (doujinshi ids split by line):
 
     nhentai --file=doujinshi.txt
 
+Set search default language
+
+.. code-block:: bash
+
+    nhentai --language=english
+
 Search a keyword and download the first page:
 
 .. code-block:: bash
 
     nhentai --search="tomori" --page=1 --download
-
+    # you also can download by tags and multiple keywords
-Download by tag name:
+    nhentai --search="tag:lolicon, artist:henreader, tag:full color"
-
+    nhentai --search="lolicon, henreader, full color"
-.. code-block:: bash
-
-    nhentai --tag lolicon --download --page=2
-
-Download by language:
-
-.. code-block:: bash
-
-    nhentai --language english --download --page=2
-
-Download by artist name:
-
-.. code-block:: bash
-
-    nhentai --artist henreader --download
-
-Download by character name:
-
-.. code-block:: bash
-
-    nhentai --character "kuro von einsbern" --download
-
-Download by parody name:
-
-.. code-block:: bash
-
-    nhentai --parody "the idolmaster" --download
-
-Download by group name:
-
-.. code-block:: bash
-
-    nhentai --group clesta --download
-
-Download using multiple tags (--tag, --character, --paordy and --group supported):
-
-.. code-block:: bash
-
-    nhentai --tag "lolicon, teasing" --artist "tamano kedama, atte nanakusa"
 
 Download your favorites with delay:
 

nhentai/cmdline.py

@@ -50,14 +50,6 @@ def cmd_parser():
     parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
     parser.add_option('--search', '-s', type='string', dest='keyword', action='store',
                       help='search doujinshi by keyword')
-    parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
-    parser.add_option('--artist', type='string', dest='artist', action='store', help='download doujinshi by artist')
-    parser.add_option('--character', type='string', dest='character', action='store',
-                      help='download doujinshi by character')
-    parser.add_option('--parody', type='string', dest='parody', action='store', help='download doujinshi by parody')
-    parser.add_option('--group', type='string', dest='group', action='store', help='download doujinshi by group')
-    parser.add_option('--language', type='string', dest='language', action='store',
-                      help='download doujinshi by language')
     parser.add_option('--favorites', '-F', action='store_true', dest='favorites',
                       help='list or download your favorites.')
 
@@ -95,14 +87,14 @@ def cmd_parser():
                       help='generate a main viewer contain all the doujin in the folder')
     parser.add_option('--cbz', '-C', dest='is_cbz', action='store_true',
                       help='generate Comic Book CBZ File')
-    parser.add_option('--comic-info', dest='write_comic_info', action='store_true',
-                      help='when generating Comic Book CBZ File, also write ComicInfo.xml')
     parser.add_option('--rm-origin-dir', dest='rm_origin_dir', action='store_true', default=False,
                       help='remove downloaded doujinshi dir when generated CBZ file.')
 
     # nhentai options
     parser.add_option('--cookie', type='str', dest='cookie', action='store',
                       help='set cookie of nhentai to bypass Google recaptcha')
+    parser.add_option('--language', type='str', dest='language', action='store',
+                      help='set default language to parse doujinshis')
     parser.add_option('--save-download-history', dest='is_save_download_history', action='store_true',
                       default=False, help='save downloaded doujinshis, whose will be skipped if you re-download them')
     parser.add_option('--clean-download-history', action='store_true', default=False, dest='clean_download_history',
@@ -123,8 +115,7 @@ def cmd_parser():
         exit(0)
 
     if args.main_viewer and not args.id and not args.keyword and \
-            not args.tag and not args.artist and not args.character and \
+            not args.tag and not args.favorites:
-            not args.parody and not args.group and not args.language and not args.favorites:
         generate_main_html()
         exit(0)
 
@@ -153,6 +144,25 @@ def cmd_parser():
         logger.info('Cookie saved.')
         exit(0)
 
+    if os.path.exists(constant.NHENTAI_LANGUAGE) and not args.language:
+        with open(constant.NHENTAI_LANGUAGE, 'r') as f:
+            constant.LANGUAGE = f.read()
+            args.language = f.read()
+
+    if args.language:
+        try:
+            if not os.path.exists(constant.NHENTAI_HOME):
+                os.mkdir(constant.NHENTAI_HOME)
+
+            with open(constant.NHENTAI_LANGUAGE, 'w') as f:
+                f.write(args.language)
+        except Exception as e:
+            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
+            exit(1)
+
+        logger.info('Default language now is {}.'.format(args.language))
+        exit(0)
+
     if os.path.exists(constant.NHENTAI_PROXY):
         with open(constant.NHENTAI_PROXY, 'r') as f:
             link = f.read()
@@ -192,14 +202,12 @@ def cmd_parser():
             args.id = set(int(i) for i in _ if i.isdigit())
 
     if (args.is_download or args.is_show) and not args.id and not args.keyword and \
-            not args.tag and not args.artist and not args.character and \
+            not args.tag and not args.favorites:
-            not args.parody and not args.group and not args.language and not args.favorites:
         logger.critical('Doujinshi id(s) are required for downloading')
         parser.print_help()
         exit(1)
 
-    if not args.keyword and not args.id and not args.tag and not args.artist and \
+    if not args.keyword and not args.id and not  args.favorites:
-            not args.character and not args.parody and not args.group and not args.language and not args.favorites:
         parser.print_help()
         exit(1)
 

nhentai/command.py

@@ -6,7 +6,7 @@ import platform
 import time
 
 from nhentai.cmdline import cmd_parser, banner
-from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser, tag_parser
+from nhentai.parser import doujinshi_parser, search_parser, print_doujinshi, favorites_parser
 from nhentai.doujinshi import Doujinshi
 from nhentai.downloader import Downloader
 from nhentai.logger import logger
@@ -21,14 +21,12 @@ def main():
 
     from nhentai.constant import PROXY
     # constant.PROXY will be changed after cmd_parser()
-    if PROXY != {}:
+    if PROXY:
         logger.info('Using proxy: {0}'.format(PROXY))
 
     # check your cookie
     check_cookie()
 
-    index = 0
-    index_value = None
     doujinshis = []
     doujinshi_ids = []
     doujinshi_list = []
@@ -39,38 +37,16 @@ def main():
 
         doujinshis = favorites_parser(options.page_range)
 
-    elif options.tag:
-        doujinshis = tag_parser(options.tag, sorting=options.sorting, max_page=options.max_page)
-
-    elif options.artist:
-        index = 1
-        index_value = options.artist
-
-    elif options.character:
-        index = 2
-        index_value = options.character
-
-    elif options.parody:
-        index = 3
-        index_value = options.parody
-
-    elif options.group:
-        index = 4
-        index_value = options.group
-
-    elif options.language:
-        index = 5
-        index_value = options.language
-
     elif options.keyword:
+        from nhentai.constant import LANGUAGE
+        if LANGUAGE:
+            logger.info('Using deafult language: {0}'.format(LANGUAGE))
+            options.keyword += ', language:{}'.format(LANGUAGE)
         doujinshis = search_parser(options.keyword, sorting=options.sorting, page=options.page)
 
     elif not doujinshi_ids:
         doujinshi_ids = options.id
 
-    if index:
-        doujinshis = tag_parser(index_value, max_page=options.max_page, index=index)
-
     print_doujinshi(doujinshis)
     if options.is_download and doujinshis:
         doujinshi_ids = [i['id'] for i in doujinshis]
@@ -109,7 +85,7 @@ 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, options.rm_origin_dir, options.write_comic_info)
+                generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
 
         if options.main_viewer:
             generate_main_html(options.output_dir)
@@ -125,6 +101,5 @@ def main():
 
 signal.signal(signal.SIGINT, signal_handler)
 
-
 if __name__ == '__main__':
     main()

nhentai/constant.py

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

nhentai/parser.py

@@ -120,10 +120,10 @@ def page_range_parser(page_range, max_page_num):
         else:
             try:
                 left = int(range_str[:idx])
-                right = int(range_str[idx+1:])
+                right = int(range_str[idx + 1:])
                 if right > max_page_num:
                     right = max_page_num
-                for page in range(left, right+1):
+                for page in range(left, right + 1):
                     pages.add(page)
             except ValueError:
                 logger.error('page range({0}) is not valid'.format(page_range))
@@ -143,7 +143,7 @@ def doujinshi_parser(id_):
 
     try:
         response = request('get', url)
-        if response.status_code in (200, ):
+        if response.status_code in (200,):
             response = response.content
         else:
             logger.debug('Slow down and retry ({}) ...'.format(id_))
@@ -202,7 +202,7 @@ def doujinshi_parser(id_):
     return doujinshi
 
 
-def search_parser(keyword, sorting='date', page=1):
+def old_search_parser(keyword, sorting='date', page=1):
     logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
     response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
 
@@ -222,50 +222,15 @@ def print_doujinshi(doujinshi_list):
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def tag_parser(tag_name, sorting='date', max_page=1, index=0):
+def search_parser(keyword, sorting, page):
-    result = []
-    tag_name = tag_name.lower()
-    if ',' in tag_name:
-        tag_name = [i.strip().replace(' ', '-') for i in tag_name.split(',')]
-    else:
-        tag_name = tag_name.strip().replace(' ', '-')
-    if sorting == 'date':
-        sorting = ''
-
-    for p in range(1, max_page + 1):
-        if sys.version_info >= (3, 0, 0):
-            unicode_ = str
-        else:
-            unicode_ = unicode
-
-        if isinstance(tag_name, (str, unicode_)):
-            logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
-            response = request('get', url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], tag_name, sorting, p)).content
-            result += _get_title_and_id(response)
-        else:
-            for i in tag_name:
-                logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, i))
-                response = request('get',
-                                   url='%s/%s/%s?page=%d' % (constant.TAG_URL[index], i, sorting, p)).content
-                result += _get_title_and_id(response)
-
-        if not result:
-            logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
-            return
-
-    if not result:
-        logger.warn('No results for tag \'{}\''.format(tag_name))
-
-    return result
-
-
-def __api_suspended_search_parser(keyword, sorting, page):
     logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
+    keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
     i = 0
     while i < 5:
         try:
-            response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).json()
+            url = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).url
+            response = request('get', url.replace('%2B', '+')).json()
         except Exception as e:
             i += 1
             if not i < 5:
@@ -289,29 +254,6 @@ def __api_suspended_search_parser(keyword, sorting, page):
     return result
 
 
-def __api_suspended_tag_parser(tag_id, sorting, max_page=1):
-    logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
-    result = []
-    response = request('get', url=constant.TAG_API_URL, params={'sort': sorting, 'tag_id': tag_id}).json()
-    page = max_page if max_page <= response['num_pages'] else int(response['num_pages'])
-
-    for i in range(1, page + 1):
-        logger.info('Getting page {} ...'.format(i))
-
-        if page != 1:
-            response = request('get', url=constant.TAG_API_URL,
-                               params={'sort': sorting, 'tag_id': tag_id}).json()
-    for row in response['result']:
-        title = row['title']['english']
-        title = title[:85] + '..' if len(title) > 85 else title
-        result.append({'id': row['id'], 'title': title})
-
-    if not result:
-        logger.warn('No results for tag id {}'.format(tag_id))
-
-    return result
-
-
 def __api_suspended_doujinshi_parser(id_):
     if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
         raise Exception('Doujinshi id({0}) is not valid'.format(id_))