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 request(method, url, **kwargs):
- if not hasattr(requests, method):
- raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
-
- return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
-
-
-def login_parser(username, password):
- s = requests.Session()
- s.proxies = constant.PROXY
- s.verify = False
- s.headers.update({'Referer': constant.LOGIN_URL})
-
- s.get(constant.LOGIN_URL)
- content = s.get(constant.LOGIN_URL).content
- html = BeautifulSoup(content, 'html.parser').encode("ascii")
+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')
- csrf_token = csrf_token_elem.attrs['value']
+ 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 = s.post(constant.LOGIN_URL, data=login_dict)
- if 'Invalid username (or email) or password' in resp.text:
+ 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)
- html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser').encode("ascii")
+ 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(page=None):
+ result = []
+ html = BeautifulSoup(request('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?")
+ return []
- count = int(count.text.strip('(').strip(')'))
- pages = count / 25
- pages += 1 if count % (25 * pages) else 0
- logger.info('Your have %d favorites in %d pages.' % (count, pages))
+ count = int(count.text.strip('(').strip(')').replace(',', ''))
+ if count == 0:
+ logger.warning('No favorites found')
+ return []
+ pages = int(count / 25)
- if os.getenv('DEBUG'):
- pages = 1
+ if page:
+ page_range_list = page
+ else:
+ if pages:
+ pages += 1 if count % (25 * pages) else 0
+ else:
+ pages = 1
- ret = []
- doujinshi_id = re.compile('data-id="([\d]+)"')
+ logger.info('You have %d favorites in %d pages.' % (count, pages))
- def _callback(request, result):
- ret.append(result)
+ if os.getenv('DEBUG'):
+ pages = 1
- thread_pool = threadpool.ThreadPool(5)
+ page_range_list = range(1, pages + 1)
- for page in range(1, pages+1):
+ for page in page_range_list:
try:
- logger.info('Getting doujinshi id of page %d' % page)
- resp = s.get(constant.FAV_URL + '?page=%d' % page).content
- ids = doujinshi_id.findall(resp)
- requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
- [thread_pool.putRequest(req) for req in requests_]
- thread_pool.wait()
+ 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 ret
+ return result
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)
+ if response.status_code in (200, ):
+ response = response.content
+ elif response.status_code in (404, ):
+ raise Exception('Seems doujinshi {} does not exist'.format(id_))
+ else:
+ logger.debug('Slow down and retry ({}) ...'.format(id_))
+ time.sleep(1)
+ return doujinshi_parser(str(id_))
+
except Exception as e:
- logger.critical(str(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['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'] = ext
- # 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']
+ for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
+ if re.search('Pages:', _.text):
+ pages = _.find('span', class_='name').string
+ 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.find('span', attrs={'class': 'name'}).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, page):
+def old_search_parser(keyword, sorting='date', page=1):
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')
- except requests.ConnectionError as e:
- logger.critical(e)
- logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
- exit(1)
-
- 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})
+ 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
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, 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
+
+ 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': p, 'sort': sorting}).url
+ response = request('get', url.replace('%2B', '+')).json()
+ except Exception as e:
+ logger.critical(str(e))
+
+ break
+
+ if 'result' not in response:
+ logger.warn('No result in response in page {}'.format(p))
+ break
+
+ 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_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