0.4.4

Added --page-all option to download all search results

nhentai/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.4.2'
+__version__ = '0.4.4'
 __author__ = 'RicterZ'
 __email__ = 'ricterzheng@gmail.com'

nhentai/cmdline.py

@@ -2,7 +2,9 @@
 from __future__ import print_function
 import os
 import sys
+import json
 from optparse import OptionParser
+
 try:
     from itertools import ifilter as filter
 except ImportError:
@@ -35,7 +37,29 @@ def banner():
 ''' % __version__)
 
 
+def load_config():
+    if not os.path.exists(constant.NHENTAI_CONFIG_FILE):
+        return
+
+    try:
+        with open(constant.NHENTAI_CONFIG_FILE, 'r') as f:
+            constant.CONFIG = json.load(f)
+    except json.JSONDecodeError:
+        logger.error('Failed to load config file.')
+        write_config()
+
+
+def write_config():
+    if not os.path.exists(constant.NHENTAI_HOME):
+        os.mkdir(constant.NHENTAI_HOME)
+
+    with open(constant.NHENTAI_CONFIG_FILE, 'w') as f:
+        f.write(json.dumps(constant.CONFIG))
+
+
 def cmd_parser():
+    load_config()
+
     parser = OptionParser('\n  nhentai --search [keyword] --download'
                           '\n  NHENTAI=http://h.loli.club nhentai --id [ID ...]'
                           '\n  nhentai --file [filename]'
@@ -54,10 +78,10 @@ def cmd_parser():
                       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 results')
-    parser.add_option('--page-range', type='string', dest='page_range', action='store',
-                      help='page range of favorites.  e.g. 1,2-5,14')
+    parser.add_option('--page-all', dest='page_all', action='store_true', default=False,
+                      help='all search results')
+    parser.add_option('--page', '--page-range', type='string', dest='page', action='store', default='',
+                      help='page number of search results. e.g. 1,2-5,14')
     parser.add_option('--sorting', dest='sorting', action='store', default='recent',
                       help='sorting of doujinshi (recent / popular / popular-[today|week])',
                       choices=['recent', 'popular', 'popular-today', 'popular-week'])
@@ -96,6 +120,8 @@ def cmd_parser():
                       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('--clean-language', dest='clean_language', action='store_true', default=False,
+                      help='set DEFAULT as 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',
@@ -126,69 +152,35 @@ def cmd_parser():
         logger.info('Download history cleaned.')
         exit(0)
 
-    if os.path.exists(constant.NHENTAI_COOKIE):
-        with open(constant.NHENTAI_COOKIE, 'r') as f:
-            constant.COOKIE = f.read()
-
+    # --- set config ---
     if args.cookie:
-        try:
-            if not os.path.exists(constant.NHENTAI_HOME):
-                os.mkdir(constant.NHENTAI_HOME)
-
-            with open(constant.NHENTAI_COOKIE, 'w') as f:
-                f.write(args.cookie)
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
+        constant.CONFIG['cookie'] = args.cookie
         logger.info('Cookie saved.')
+        write_config()
         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))
+        constant.CONFIG['language'] = args.language
+        logger.info('LANGUAGE now set to \'{0}\''.format(args.language))
+        write_config()
         exit(0)
-
-    if os.path.exists(constant.NHENTAI_PROXY):
-        with open(constant.NHENTAI_PROXY, 'r') as f:
-            link = f.read()
-            constant.PROXY = {'http': link, 'https': link}
+        # TODO: search without language
 
     if args.proxy:
-        try:
-            if not os.path.exists(constant.NHENTAI_HOME):
-                os.mkdir(constant.NHENTAI_HOME)
-
         proxy_url = urlparse(args.proxy)
         if proxy_url.scheme not in ('http', 'https'):
             logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
-            else:
-                with open(constant.NHENTAI_PROXY, 'w') as f:
-                    f.write(args.proxy)
-
-        except Exception as e:
-            logger.error('Cannot create NHENTAI_HOME: {}'.format(str(e)))
-            exit(1)
-
+        constant.CONFIG['proxy'] = {
+            'http': args.proxy,
+            'https': args.proxy,
+        }
         logger.info('Proxy \'{0}\' saved.'.format(args.proxy))
+        write_config()
         exit(0)
+    # --- end set config ---
 
     if args.favorites:
-        if not constant.COOKIE:
+        if not constant.CONFIG['cookie']:
             logger.warning('Cookie has not been set, please use `nhentai --cookie \'COOKIE\'` to set it.')
             exit(1)
 

nhentai/command.py

@@ -1,17 +1,21 @@
 #!/usr/bin/env python2.7
 # coding: utf-8
 from __future__ import unicode_literals, print_function
+import json
+import os
 import signal
 import platform
 import time
 
+from nhentai import constant
 from nhentai.cmdline import cmd_parser, banner
 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
-from nhentai.constant import BASE_URL
-from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, check_cookie, signal_handler, DB
+from nhentai.constant import NHENTAI_CONFIG_FILE, BASE_URL
+from nhentai.utils import generate_html, generate_cbz, generate_main_html, generate_pdf, \
+    paging, check_cookie, signal_handler, DB
 
 
 def main():
@@ -19,10 +23,9 @@ def main():
     options = cmd_parser()
     logger.info('Using mirror: {0}'.format(BASE_URL))
 
-    from nhentai.constant import PROXY
-    # constant.PROXY will be changed after cmd_parser()
-    if PROXY:
-        logger.info('Using proxy: {0}'.format(PROXY))
+    # CONFIG['proxy'] will be changed after cmd_parser()
+    if constant.CONFIG['proxy']:
+        logger.info('Using proxy: {0}'.format(constant.CONFIG['proxy']))
 
     # check your cookie
     check_cookie()
@@ -31,18 +34,20 @@ def main():
     doujinshi_ids = []
     doujinshi_list = []
 
+    page_list = paging(options.page)
+
     if options.favorites:
         if not options.is_download:
             logger.warning('You do not specify --download option')
 
-        doujinshis = favorites_parser(options.page_range)
+        doujinshis = favorites_parser(page=page_list)
 
     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)
+        if constant.CONFIG['language']:
+            logger.info('Using default language: {0}'.format(constant.CONFIG['language']))
+            options.keyword += ' language:{}'.format(constant.CONFIG['language'])
+        doujinshis = search_parser(options.keyword, sorting=options.sorting, page=page_list,
+                                   is_page_all=options.page_all)
 
     elif not doujinshi_ids:
         doujinshi_ids = options.id

nhentai/constant.py

@@ -26,12 +26,12 @@ 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')
-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')
+NHENTAI_CONFIG_FILE = os.path.join(NHENTAI_HOME, 'config.json')
 
-PROXY = {}
+CONFIG = {
+    'proxy': {},
+    'cookie': '',
+    'language': '',
+}
 
-COOKIE = ''
-LANGUAGE = ''

nhentai/doujinshi.py

@@ -48,6 +48,7 @@ class Doujinshi(object):
 
     def show(self):
         table = [
+            ["Parodies", self.info.parodies],
             ["Doujinshi", self.name],
             ["Subtitle", self.info.subtitle],
             ["Characters", self.info.characters],

nhentai/parser.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals, print_function
 
-import sys
 import os
 import re
 import time
@@ -64,7 +63,7 @@ def _get_title_and_id(response):
     return result
 
 
-def favorites_parser(page_range=''):
+def favorites_parser(page=None):
     result = []
     html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
     count = html.find('span', attrs={'class': 'count'})
@@ -78,6 +77,9 @@ def favorites_parser(page_range=''):
         return []
     pages = int(count / 25)
 
+    if page:
+        page_range_list = page
+    else:
         if pages:
             pages += 1 if count % (25 * pages) else 0
         else:
@@ -89,9 +91,6 @@ def favorites_parser(page_range=''):
             pages = 1
 
         page_range_list = range(1, pages + 1)
-    if page_range:
-        logger.info('page range is {0}'.format(page_range))
-        page_range_list = page_range_parser(page_range, pages)
 
     for page in page_range_list:
         try:
@@ -105,32 +104,6 @@ def favorites_parser(page_range=''):
     return result
 
 
-def page_range_parser(page_range, max_page_num):
-    pages = set()
-    ranges = str.split(page_range, ',')
-    for range_str in ranges:
-        idx = range_str.find('-')
-        if idx == -1:
-            try:
-                page = int(range_str)
-                if page <= max_page_num:
-                    pages.add(page)
-            except ValueError:
-                logger.error('page range({0}) is not valid'.format(page_range))
-        else:
-            try:
-                left = int(range_str[:idx])
-                right = int(range_str[idx + 1:])
-                if right > max_page_num:
-                    right = max_page_num
-                for page in range(left, right + 1):
-                    pages.add(page)
-            except ValueError:
-                logger.error('page range({0}) is not valid'.format(page_range))
-
-    return list(pages)
-
-
 def 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_))
@@ -215,18 +188,30 @@ def print_doujinshi(doujinshi_list):
         return
     doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
-    logger.info('Search Result\n' +
+    logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
 
 
-def search_parser(keyword, sorting, page):
-    logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
+def search_parser(keyword, sorting, page, is_page_all=False):
     # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
     result = []
+    if not page:
+        page = [1]
+
+    if is_page_all:
+        url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
+        init_response = request('get', url.replace('%2B', '+')).json()
+        page = range(1, init_response['num_pages']+1)
+
+    total = '/{0}'.format(page[-1]) if is_page_all else ''
+    for p in page:
         i = 0
-    while i < 5:
+
+        logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
+        while i < 3:
             try:
-            url = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).url
+                url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+                                                                      'page': p, 'sort': sorting}).url
                 response = request('get', url.replace('%2B', '+')).json()
             except Exception as e:
                 logger.critical(str(e))
@@ -234,7 +219,8 @@ def search_parser(keyword, sorting, page):
             break
 
         if 'result' not in response:
-        raise Exception('No result in response')
+            logger.warn('No result in response in page {}'.format(p))
+            break
 
         for row in response['result']:
             title = row['title']['english']

nhentai/utils.py

@@ -20,9 +20,9 @@ def request(method, url, **kwargs):
     session.headers.update({
         'Referer': constant.LOGIN_URL,
         'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
-        'Cookie': constant.COOKIE
+        'Cookie': constant.CONFIG['cookie']
     })
-    return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
+    return getattr(session, method)(url, proxies=constant.CONFIG['proxy'], verify=False, **kwargs)
 
 
 def check_cookie():
@@ -253,6 +253,26 @@ def signal_handler(signal, frame):
     exit(1)
 
 
+def paging(page_string):
+    # 1,3-5,14 -> [1, 3, 4, 5, 14]
+    if not page_string:
+        return []
+
+    page_list = []
+    for i in page_string.split(','):
+        if '-' in i:
+            start, end = i.split('-')
+            if not (start.isdigit() and end.isdigit()):
+                raise Exception('Invalid page number')
+            page_list.extend(list(range(int(start), int(end)+1)))
+        else:
+            if not i.isdigit():
+                raise Exception('Invalid page number')
+            page_list.append(int(i))
+
+    return page_list
+
+
 class DB(object):
     conn = None
     cur = None