from tabulate import tabulate
import nhentai.constant as constant
+from nhentai.utils import request
from nhentai.logger import logger
-session = requests.Session()
-session.headers.update({
- 'Referer': constant.LOGIN_URL,
- 'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
-})
-
-
-def request(method, url, **kwargs):
- global session
- if not hasattr(session, method):
- raise AttributeError('\'requests.Session\' object has no attribute \'{0}\''.format(method))
-
- return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
-
-
def _get_csrf_token(content):
html = BeautifulSoup(content, 'html.parser')
csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
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 ...')
}
resp = request('post', url=constant.LOGIN_URL, data=login_dict)
- if 'You\'re loading pages way too quickly.' in resp.text:
+ 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': '/'})
logger.error('Login failed, please check your username and password')
exit(1)
- if 'You\'re loading pages way too quickly.' in resp.text:
- logger.error('You meet challenge insistently, please submit a issue'
- ' at https://github.com/RicterZ/nhentai/issues')
+ 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 login_parser():
+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:
if os.getenv('DEBUG'):
pages = 1
- ret = []
- doujinshi_id = re.compile('data-id="([\d]+)"')
-
- def _callback(request, result):
- ret.append(result)
-
- # TODO: reduce threads number ...
- thread_pool = threadpool.ThreadPool(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).text
- ids = doujinshi_id.findall(resp)
- requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
- [thread_pool.putRequest(req) for req in requests_]
- thread_pool.wait()
+ 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_):
return doujinshi_parser(str(id_))
except Exception as e:
- logger.critical(str(e))
- raise SystemExit
+ logger.warn('Error: {}, ignored'.format(str(e)))
+ return None
html = BeautifulSoup(response, 'html.parser')
doujinshi_info = html.find('div', attrs={'id': 'info'})
doujinshi['subtitle'] = subtitle.text if subtitle else ''
doujinshi_cover = html.find('div', attrs={'id': 'cover'})
- img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
+ img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
ext = []
for i in html.find_all('div', attrs={'class': 'thumb-container'}):
# gain information of the doujinshi
information_fields = doujinshi_info.find_all('div', attrs={'class': 'field-name'})
- needed_fields = ['Characters', 'Artists', 'Language', 'Tags']
+ 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:
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 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={'q': keyword, 'page': page}).content
- except requests.ConnectionError as e:
- logger.critical(e)
- logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
- raise SystemExit
+ response = request('get', url=constant.SEARCH_URL, params={'q': keyword, 'page': page, 'sort': sorting}).content
- 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})
+ result = _get_title_and_id(response)
if not result:
logger.warn('Not found anything of keyword {}'.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_))
+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'))
- 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(map(lambda s: s['t'], response['images']['pages']))
- doujinshi['pages'] = len(response['images']['pages'])
+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 = ''
- # gain information of the doujinshi
- needed_fields = ['character', 'artist', 'language', 'tag']
- 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] = {}
+ 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)
- 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']
+ if not result:
+ logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
+ return
- return doujinshi
+ if not result:
+ logger.warn('No results for tag \'{}\''.format(tag_name))
+
+ return result
-def __api_suspended_search_parser(keyword, page):
+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}).json()
+ 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:
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 __api_suspended_tag_parser(tag_id, max_page=1):
+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': 'popular', 'tag_id': tag_id}).json()
+ 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):
if page != 1:
response = request('get', url=constant.TAG_API_URL,
- params={'sort': 'popular', 'tag_id': tag_id}).json()
+ 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
return result
-def tag_parser(tag_name, max_page=1):
- result = []
- tag_name = tag_name.lower()
- tag_name = tag_name.replace(' ', '-')
+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_))
- for p in range(1, max_page + 1):
- logger.debug('Fetching page {0} for doujinshi with tag \'{1}\''.format(p, tag_name))
- response = request('get', url='%s/%s?page=%d' % (constant.TAG_URL, tag_name, p)).content
+ 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
- html = BeautifulSoup(response, 'html.parser')
- doujinshi_items = html.find_all('div', attrs={'class': 'gallery'})
- if not doujinshi_items:
- logger.error('Cannot find doujinshi id of tag \'{0}\''.format(tag_name))
- return
+ 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'])
- for i in doujinshi_items:
- doujinshi_id = i.a.attrs['href'].strip('/g')
- doujinshi_title = i.a.text.strip()
- doujinshi_title = doujinshi_title if len(doujinshi_title) < 85 else doujinshi_title[:82] + '...'
- result.append({'title': doujinshi_title, 'id': doujinshi_id})
+ # 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] = {}
- if not result:
- logger.warn('No results for tag \'{}\''.format(tag_name))
+ 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 result
+ return doujinshi
if __name__ == '__main__':
projects / nhentai.git / blobdiff