2 from __future__ import unicode_literals, print_function
8 from bs4 import BeautifulSoup
9 from tabulate import tabulate
11 import nhentai.constant as constant
12 from nhentai.utils import request
13 from nhentai.logger import logger
16 def _get_csrf_token(content):
17 html = BeautifulSoup(content, 'html.parser')
18 csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
19 if not csrf_token_elem:
20 raise Exception('Cannot find csrf token to login')
21 return csrf_token_elem.attrs['value']
24 def login(username, password):
25 logger.warning('This feature is deprecated, please use --cookie to set your cookie.')
26 csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).text)
27 if os.getenv('DEBUG'):
28 logger.info('Getting CSRF token ...')
30 if os.getenv('DEBUG'):
31 logger.info('CSRF token is {}'.format(csrf_token))
34 'csrfmiddlewaretoken': csrf_token,
35 'username_or_email': username,
38 resp = request('post', url=constant.LOGIN_URL, data=login_dict)
40 if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
41 csrf_token = _get_csrf_token(resp.text)
42 resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
44 if 'Invalid username/email or password' in resp.text:
45 logger.error('Login failed, please check your username and password')
48 if 'You\'re loading pages way too quickly.' in resp.text or 'Really, slow down' in resp.text:
49 logger.error('Using nhentai --cookie \'YOUR_COOKIE_HERE\' to save your Cookie.')
53 def _get_title_and_id(response):
55 html = BeautifulSoup(response, 'html.parser')
56 doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
57 for doujinshi in doujinshi_search_result:
58 doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
59 title = doujinshi_container.text.strip()
60 title = title if len(title) < 85 else title[:82] + '...'
61 id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
62 result.append({'id': id_, 'title': title})
67 def favorites_parser(page=None):
69 html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
70 count = html.find('span', attrs={'class': 'count'})
72 logger.error("Can't get your number of favorited doujins. Did the login failed?")
75 count = int(count.text.strip('(').strip(')').replace(',', ''))
77 logger.warning('No favorites found')
79 pages = int(count / 25)
82 page_range_list = page
85 pages += 1 if count % (25 * pages) else 0
89 logger.info('You have %d favorites in %d pages.' % (count, pages))
91 if os.getenv('DEBUG'):
94 page_range_list = range(1, pages + 1)
96 for page in page_range_list:
98 logger.info('Getting doujinshi ids of page %d' % page)
99 resp = request('get', constant.FAV_URL + '?page=%d' % page).content
101 result.extend(_get_title_and_id(resp))
102 except Exception as e:
103 logger.error('Error: %s, continue', str(e))
108 def doujinshi_parser(id_):
109 if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
110 raise Exception('Doujinshi id({0}) is not valid'.format(id_))
113 logger.log(15, 'Fetching doujinshi information of id {0}'.format(id_))
115 doujinshi['id'] = id_
116 url = '{0}/{1}/'.format(constant.DETAIL_URL, id_)
119 response = request('get', url)
120 if response.status_code in (200,):
121 response = response.content
123 logger.debug('Slow down and retry ({}) ...'.format(id_))
125 return doujinshi_parser(str(id_))
127 except Exception as e:
128 logger.warn('Error: {}, ignored'.format(str(e)))
131 html = BeautifulSoup(response, 'html.parser')
132 doujinshi_info = html.find('div', attrs={'id': 'info'})
134 title = doujinshi_info.find('h1').text
135 subtitle = doujinshi_info.find('h2')
137 doujinshi['name'] = title
138 doujinshi['subtitle'] = subtitle.text if subtitle else ''
140 doujinshi_cover = html.find('div', attrs={'id': 'cover'})
141 img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
144 for i in html.find_all('div', attrs={'class': 'thumb-container'}):
145 _, ext_name = os.path.basename(i.img.attrs['data-src']).rsplit('.', 1)
149 logger.critical('Tried yo get image id failed')
152 doujinshi['img_id'] = img_id.group(1)
153 doujinshi['ext'] = ext
155 for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
156 if re.search('Pages:', _.text):
157 pages = _.find('span', class_='name').string
158 doujinshi['pages'] = int(pages)
160 # gain information of the doujinshi
161 information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
162 needed_fields = ['Characters', 'Artists', 'Languages', 'Tags', 'Parodies', 'Groups', 'Categories']
163 for field in information_fields:
164 field_name = field.contents[0].strip().strip(':')
165 if field_name in needed_fields:
166 data = [sub_field.find('span', attrs={'class': 'name'}).contents[0].strip() for sub_field in
167 field.find_all('a', attrs={'class': 'tag'})]
168 doujinshi[field_name.lower()] = ', '.join(data)
170 time_field = doujinshi_info.find('time')
171 if time_field.has_attr('datetime'):
172 doujinshi['date'] = time_field['datetime']
176 def old_search_parser(keyword, sorting='date', page=1):
177 logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
178 response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
180 result = _get_title_and_id(response)
182 logger.warn('Not found anything of keyword {}'.format(keyword))
187 def print_doujinshi(doujinshi_list):
188 if not doujinshi_list:
190 doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
191 headers = ['id', 'doujinshi']
192 logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
193 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
196 def search_parser(keyword, sorting, page):
197 # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
204 logger.info('Searching doujinshis using keywords "{0}" on page {1}'.format(keyword, p))
207 url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
208 'page': p, 'sort': sorting}).url
209 response = request('get', url.replace('%2B', '+')).json()
210 except Exception as e:
211 logger.critical(str(e))
215 if 'result' not in response:
216 logger.warn('No result in response in page {}'.format(p))
219 for row in response['result']:
220 title = row['title']['english']
221 title = title[:85] + '..' if len(title) > 85 else title
222 result.append({'id': row['id'], 'title': title})
225 logger.warn('No results for keywords {}'.format(keyword))
230 def search_parser_all(keyword):
231 logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
235 url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
236 init_response = request('get', url.replace('%2B', '+')).json()
238 for page in range(init_response['num_pages']):
240 url = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page+1}).url
241 response = request('get', url.replace('%2B', '+')).json()
243 print('Obtained %d / %d pages.' % (page+1, init_response['num_pages']), end='\r')
245 except Exception as e:
246 logger.critical(str(e))
248 if 'result' not in response:
249 raise Exception('No result in response')
251 for row in response['result']:
252 title = row['title']['english']
253 title = title[:85] + '..' if len(title) > 85 else title
254 result.append({'id': row['id'], 'title': title})
257 logger.warn('No results for keywords {}'.format(keyword))
262 def __api_suspended_doujinshi_parser(id_):
263 if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
264 raise Exception('Doujinshi id({0}) is not valid'.format(id_))
267 logger.log(15, 'Fetching information of doujinshi id {0}'.format(id_))
269 doujinshi['id'] = id_
270 url = '{0}/{1}'.format(constant.DETAIL_URL, id_)
274 response = request('get', url).json()
275 except Exception as e:
278 logger.critical(str(e))
283 doujinshi['name'] = response['title']['english']
284 doujinshi['subtitle'] = response['title']['japanese']
285 doujinshi['img_id'] = response['media_id']
286 doujinshi['ext'] = ''.join([i['t'] for i in response['images']['pages']])
287 doujinshi['pages'] = len(response['images']['pages'])
289 # gain information of the doujinshi
290 needed_fields = ['character', 'artist', 'language', 'tag', 'parody', 'group', 'category']
291 for tag in response['tags']:
292 tag_type = tag['type']
293 if tag_type in needed_fields:
294 if tag_type == 'tag':
295 if tag_type not in doujinshi:
296 doujinshi[tag_type] = {}
298 tag['name'] = tag['name'].replace(' ', '-')
299 tag['name'] = tag['name'].lower()
300 doujinshi[tag_type][tag['name']] = tag['id']
301 elif tag_type not in doujinshi:
302 doujinshi[tag_type] = tag['name']
304 doujinshi[tag_type] += ', ' + tag['name']
309 if __name__ == '__main__':
310 print(doujinshi_parser("32271"))