2 from __future__ import unicode_literals, print_function
7 from bs4 import BeautifulSoup
8 from tabulate import tabulate
10 import nhentai.constant as constant
11 from nhentai.utils import request
12 from nhentai.logger import logger
15 def _get_csrf_token(content):
16 html = BeautifulSoup(content, 'html.parser')
17 csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
18 if not csrf_token_elem:
19 raise Exception('Cannot find csrf token to login')
20 return csrf_token_elem.attrs['value']
23 def login(username, password):
24 logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
25 csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
26 if os.getenv('DEBUG'):
27 logger.info('Getting CSRF token ...')
29 if os.getenv('DEBUG'):
30 logger.info('CSRF token is {}'.format(csrf_token))
33 'csrfmiddlewaretoken': csrf_token,
34 'username_or_email': username,
37 resp = request('post', url=constant.LOGIN_URL, data=login_dict)
39 if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
40 csrf_token = _get_csrf_token(resp.text)
41 resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
43 if 'Invalid username/email or password' in resp.text:
44 logger.error('Login failed, please check your username and password')
47 if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
48 logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
52 def _get_title_and_id(response):
54 html = BeautifulSoup(response, 'html.parser')
55 doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
56 for doujinshi in doujinshi_search_result:
57 doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
58 title = doujinshi_container.text.strip()
59 title = title if len(title) < 85 else title[:82] + '...'
60 id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
61 result.append({'id': id_, 'title': title})
66 def favorites_parser(page=None):
68 html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
69 count = html.find('span', attrs={'class': 'count'})
71 logger.error("Can't get your number of favorited doujins. Did the login failed?")
74 count = int(count.text.strip('(').strip(')').replace(',', ''))
76 logger.warning('No favorites found')
78 pages = int(count / 25)
81 page_range_list = page
84 pages += 1 if count % (25 * pages) else 0
88 logger.info('You have %d favorites in %d pages.' % (count, pages))
90 if os.getenv('DEBUG'):
93 page_range_list = range(1, pages + 1)
95 for page in page_range_list:
97 logger.info('Getting doujinshi ids of page %d' % page)
98 resp = request('get', constant.FAV_URL + '?page=%d' % page).content
100 result.extend(_get_title_and_id(resp))
101 except Exception as e:
102 logger.error('Error: %s, continue', str(e))
107 def doujinshi_parser(id_):
108 if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
109 raise Exception('Doujinshi id({0}) is not valid'.format(id_))
112 logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
114 doujinshi['id'] = id_
115 url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
118 response = request('get', url)
119 if response.status_code in (200, ):
120 response = response.content
121 elif response.status_code in (404,):
122 logger.error("Doujinshi with id {0} cannot be found".format(id_))
125 logger.debug('Slow down and retry ({}) ...'.format(id_))
127 return doujinshi_parser(str(id_))
129 except Exception as e:
130 logger.warn('Error: {}, ignored'.format(str(e)))
133 html = BeautifulSoup(response, 'html.parser')
134 doujinshi_info = html.find('div', attrs={'id': 'info'})
136 title = doujinshi_info.find('h1').text
137 subtitle = doujinshi_info.find('h2')
139 doujinshi['name'] = title
140 doujinshi['subtitle'] = subtitle.text if subtitle else ''
142 doujinshi_cover = html.find('div', attrs={'id': 'cover'})
143 img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
146 for i in html.find_all('div', attrs={'class': 'thumb-container'}):
147 _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
151 logger.critical('Tried yo get image id failed')
154 doujinshi['img_id'] = img_id.group(1)
155 doujinshi['ext'] = ext
157 for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
158 if re.search('Pages:', _.text):
159 pages = _.find('span', class_='name').string
160 doujinshi['pages'] = int(pages)
162 # gain information of the doujinshi
163 information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
164 needed_fields = ['Characters', 'Artists', 'Languages', 'Tags', 'Parodies', 'Groups', 'Categories']
165 for field in information_fields:
166 field_name = field.contents[0].strip().strip(':')
167 if field_name in needed_fields:
168 data = [sub_field.find('span', attrs={'class': 'name'}).contents[0].strip() for sub_field in
169 field.find_all('a', attrs={'class': 'tag'})]
170 doujinshi[field_name.lower()] = ', '.join(data)
172 time_field = doujinshi_info.find('time')
173 if time_field.has_attr('datetime'):
174 doujinshi['date'] = time_field['datetime']
178 def old_search_parser(keyword, sorting='date', page=1):
179 logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
180 response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
182 result = _get_title_and_id(response)
184 logger.warn('Not found anything of keyword {}'.format(keyword))
189 def print_doujinshi(doujinshi_list):
190 if not doujinshi_list:
192 doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
193 headers = ['id', 'doujinshi']
194 logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
195 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
198 def search_parser(keyword, sorting, page, is_page_all=False):
199 # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
205 url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
206 init_response = request('get', url.replace('%2B', '+')).json()
207 page = range(1, init_response['num_pages']+1)
209 total = '/{0}'.format(page[-1]) if is_page_all else ''
213 logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
216 url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
217 'page': p, 'sort': sorting}).url
218 response = request('get', url.replace('%2B', '+')).json()
219 except Exception as e:
220 logger.critical(str(e))
224 if 'result' not in response:
225 logger.warn('No result in response in page {}'.format(p))
228 for row in response['result']:
229 title = row['title']['english']
230 title = title[:85] + '..' if len(title) > 85 else title
231 result.append({'id': row['id'], 'title': title})
234 logger.warn('No results for keywords {}'.format(keyword))
239 def __api_suspended_doujinshi_parser(id_):
240 if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
241 raise Exception('Doujinshi id({0}) is not valid'.format(id_))
244 logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
246 doujinshi['id'] = id_
247 url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
251 response = request('get', url).json()
252 except Exception as e:
255 logger.critical(str(e))
260 doujinshi['name'] = response['title']['english']
261 doujinshi['subtitle'] = response['title']['japanese']
262 doujinshi['img_id'] = response['media_id']
263 doujinshi['ext'] = ''.join([i['t'] for i in response['images']['pages']])
264 doujinshi['pages'] = len(response['images']['pages'])
266 # gain information of the doujinshi
267 needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
268 for tag in response['tags']:
269 tag_type = tag['type']
270 if tag_type in needed_fields:
271 if tag_type == 'tag':
272 if tag_type not in doujinshi:
273 doujinshi[tag_type] = {}
275 tag['name'] = tag['name'].replace(' ', '-')
276 tag['name'] = tag['name'].lower()
277 doujinshi[tag_type][tag['name']] = tag['id']
278 elif tag_type not in doujinshi:
279 doujinshi[tag_type] = tag['name']
281 doujinshi[tag_type] += ', ' + tag['name']
286 if __name__ == '__main__':
287 print(doujinshi_parser("32271"))