-# coding: utf-8\r
-from __future__ import unicode_literals, print_function\r
-\r
-import os\r
-import re\r
-import threadpool\r
-import requests\r
-from bs4 import BeautifulSoup\r
-from tabulate import tabulate\r
-\r
-import nhentai.constant as constant\r
-from nhentai.logger import logger\r
-\r
-\r
-def request(method, url, **kwargs):\r
- if not hasattr(requests, method):\r
- raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))\r
-\r
- return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)\r
-\r
-\r
-def login_parser(username, password):\r
- s = requests.Session()\r
- s.proxies = constant.PROXY\r
- s.verify = False\r
- s.headers.update({'Referer': constant.LOGIN_URL})\r
-\r
- s.get(constant.LOGIN_URL)\r
- content = s.get(constant.LOGIN_URL).content\r
- html = BeautifulSoup(content, 'html.parser')\r
- csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})\r
-\r
- if not csrf_token_elem:\r
- raise Exception('Cannot find csrf token to login')\r
- csrf_token = csrf_token_elem.attrs['value']\r
-\r
- login_dict = {\r
- 'csrfmiddlewaretoken': csrf_token,\r
- 'username_or_email': username,\r
- 'password': password,\r
- }\r
- resp = s.post(constant.LOGIN_URL, data=login_dict)\r
- if 'Invalid username (or email) or password' in resp.text:\r
- logger.error('Login failed, please check your username and password')\r
- exit(1)\r
-\r
- html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')\r
- count = html.find('span', attrs={'class': 'count'})\r
- if not count:\r
- logger.error('Cannot get count of your favorites, maybe login failed.')\r
-\r
- count = int(count.text.strip('(').strip(')'))\r
- if count == 0:\r
- logger.warning('No favorites found')\r
- return []\r
- pages = int(count / 25)\r
-\r
- if pages:\r
- pages += 1 if count % (25 * pages) else 0\r
- else:\r
- pages = 1\r
-\r
- logger.info('Your have %d favorites in %d pages.' % (count, pages))\r
-\r
- if os.getenv('DEBUG'):\r
- pages = 1\r
-\r
- ret = []\r
- doujinshi_id = re.compile('data-id="([\d]+)"')\r
-\r
- def _callback(request, result):\r
- ret.append(result)\r
-\r
- thread_pool = threadpool.ThreadPool(5)\r
-\r
- for page in range(1, pages+1):\r
- try:\r
- logger.info('Getting doujinshi id of page %d' % page)\r
- resp = s.get(constant.FAV_URL + '?page=%d' % page).text\r
- ids = doujinshi_id.findall(resp)\r
- requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)\r
- [thread_pool.putRequest(req) for req in requests_]\r
- thread_pool.wait()\r
- except Exception as e:\r
- logger.error('Error: %s, continue', str(e))\r
-\r
- return ret\r
-\r
-\r
-def doujinshi_parser(id_):\r
- if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):\r
- raise Exception('Doujinshi id({0}) is not valid'.format(id_))\r
-\r
- id_ = int(id_)\r
- logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))\r
- doujinshi = dict()\r
- doujinshi['id'] = id_\r
- url = '{0}/{1}'.format(constant.DETAIL_URL, id_)\r
-\r
- try:\r
- response = request('get', url).json()\r
- except Exception as e:\r
- logger.critical(str(e))\r
- exit(1)\r
-\r
- doujinshi['name'] = response['title']['english']\r
- doujinshi['subtitle'] = response['title']['japanese']\r
- doujinshi['img_id'] = response['media_id']\r
- doujinshi['ext'] = ''.join(map(lambda s: s['t'], response['images']['pages']))\r
- doujinshi['pages'] = len(response['images']['pages'])\r
-\r
- # gain information of the doujinshi\r
- needed_fields = ['character', 'artist', 'language']\r
- for tag in response['tags']:\r
- tag_type = tag['type']\r
- if tag_type in needed_fields:\r
- if tag_type not in doujinshi:\r
- doujinshi[tag_type] = tag['name']\r
- else:\r
- doujinshi[tag_type] += tag['name']\r
-\r
- return doujinshi\r
-\r
-\r
-def search_parser(keyword, page):\r
- logger.debug('Searching doujinshis of keyword {0}'.format(keyword))\r
- result = []\r
- try:\r
- response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page}).json()\r
- if 'result' not in response:\r
- raise Exception('No result in response')\r
- except requests.ConnectionError as e:\r
- logger.critical(e)\r
- logger.warn('If you are in China, please configure the proxy to fu*k GFW.')\r
- exit(1)\r
-\r
- for row in response['result']:\r
- title = row['title']['english']\r
- title = title[:85] + '..' if len(title) > 85 else title\r
- result.append({'id': row['id'], 'title': title})\r
-\r
- if not result:\r
- logger.warn('Not found anything of keyword {}'.format(keyword))\r
-\r
- return result\r
-\r
-\r
-def print_doujinshi(doujinshi_list):\r
- if not doujinshi_list:\r
- return\r
- doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]\r
- headers = ['id', 'doujinshi']\r
- logger.info('Search Result\n' +\r
- tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))\r
-\r
-\r
-if __name__ == '__main__':\r
- print(doujinshi_parser("32271"))\r
+# coding: utf-8
+from __future__ import unicode_literals, print_function
+
+import os
+import re
+import threadpool
+import requests
+import time
+from bs4 import BeautifulSoup
+from tabulate import tabulate
+
+import nhentai.constant as constant
+from nhentai.utils import request
+from nhentai.logger import logger
+
+
+def _get_csrf_token(content):
+ html = BeautifulSoup(content, 'html.parser')
+ csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
+ if not csrf_token_elem:
+ raise Exception('Cannot find csrf token to login')
+ return csrf_token_elem.attrs['value']
+
+
+def login(username, password):
+ logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
+ csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
+ if os.getenv('DEBUG'):
+ logger.info('Getting CSRF token ...')
+
+ if os.getenv('DEBUG'):
+ logger.info('CSRF token is {}'.format(csrf_token))
+
+ login_dict = {
+ 'csrfmiddlewaretoken': csrf_token,
+ 'username_or_email': username,
+ 'password': password,
+ }
+ resp = request('post', url=constant.LOGIN_URL, data=login_dict)
+
+ if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+ csrf_token = _get_csrf_token(resp.text)
+ resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
+
+ if 'Invalid username/email or password' in resp.text:
+ logger.error('Login failed, please check your username and password')
+ exit(1)
+
+ if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
+ logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
+ exit(2)
+
+
+def _get_title_and_id(response):
+ result = []
+ 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})
+
+ return result
+
+
+def favorites_parser():
+ result = []
+ html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
+ count = html.find('span', attrs={'class': 'count'})
+ if not count:
+ logger.error("Can't get your number of favorited doujins. Did the login failed?")
+ return []
+
+ count = int(count.text.strip('(').strip(')').replace(',', ''))
+ if count == 0:
+ logger.warning('No favorites found')
+ return []
+ pages = int(count / 25)
+
+ if pages:
+ pages += 1 if count % (25 * pages) else 0
+ else:
+ pages = 1
+
+ logger.info('You have %d favorites in %d pages.' % (count, pages))
+
+ if os.getenv('DEBUG'):
+ pages = 1
+
+ for page in range(1, pages + 1):
+ try:
+ logger.info('Getting doujinshi ids of page %d' % page)
+ resp = request('get', constant.FAV_URL + '?page=%d' % page).content
+
+ result.extend(_get_title_and_id(resp))
+ except Exception as e:
+ logger.error('Error: %s, continue', str(e))
+
+ return result
+
+
+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_))
+
+ id_ = int(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_)
+
+ try:
+ response = request('get', url)
+ if response.status_code in (200, ):
+ response = response.content
+ else:
+ logger.debug('Slow down and retry ({}) ...'.format(id_))
+ time.sleep(1)
+ return doujinshi_parser(str(id_))
+
+ except Exception as e:
+ logger.warn('Error: {}, ignored'.format(str(e)))
+ return None
+
+ 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|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+
+ ext = []
+ for i in html.find_all('div', attrs={'class': 'thumb-container'}):
+ _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
+ ext.append(ext_name)
+
+ if not img_id:
+ logger.critical('Tried yo get image id failed')
+ exit(1)
+
+ doujinshi['img_id'] = img_id.group(1)
+ doujinshi['ext'] = ext
+
+ 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
+ information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
+ needed_fields = ['Characters', 'Artists', 'Languages', 'Tags', 'Parodies', 'Groups', 'Categories']
+ 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)
+
+ time_field = doujinshi_info.find('time')
+ if time_field.has_attr('datetime'):
+ doujinshi['date'] = time_field['datetime']
+ return doujinshi
+
+
+def 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
+
+ result = _get_title_and_id(response)
+ if not result:
+ logger.warn('Not found anything of keyword {}'.format(keyword))
+
+ return result
+
+
+def print_doujinshi(doujinshi_list):
+ if not doujinshi_list:
+ return
+ doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
+ headers = ['id', 'doujinshi']
+ logger.info('Search Result\n' +
+ tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
+
+
+def tag_parser(tag_name, sorting='date', max_page=1, index=0):
+ 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 isinstance(tag_name, str):
+ 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))
+ result = []
+ i = 0
+ while i < 5:
+ try:
+ response = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).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']
+ title = title[:85] + '..' if len(title) > 85 else title
+ result.append({'id': row['id'], 'title': title})
+
+ if not result:
+ logger.warn('No results for keywords {}'.format(keyword))
+
+ 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_))
+
+ 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([i['t'] for i in response['images']['pages']])
+ doujinshi['pages'] = len(response['images']['pages'])
+
+ # gain information of the doujinshi
+ needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
+ 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
+
+
+if __name__ == '__main__':
+ print(doujinshi_parser("32271"))
projects / nhentai.git / blobdiff