def download(self, queue, folder=''):
if not isinstance(folder, text):
folder = str(folder)
if self.path:
folder = os.path.join(self.path, folder)
if not os.path.exists(folder):
logger.warn(
'Path \'{0}\' does not exist, creating.'.format(folder))
try:
os.makedirs(folder)
except EnvironmentError as e:
logger.critical('{0}'.format(str(e)))
else:
logger.warn('Path \'{0}\' already exist.'.format(folder))
queue = [(self, url, folder) for url in queue]
pool = multiprocessing.Pool(self.size, init_worker)
[pool.apply_async(download_wrapper, args=item) for item in queue]
pool.close()
pool.join()
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_search_parser(keyword, 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()
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 search_parser(keyword, page):
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
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})
if not result:
logger.warn('Not found anything of keyword {}'.format(keyword))
return result
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
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
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
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})
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
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
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
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})
if not result:
logger.warn('No results for tag \'{}\''.format(tag_name))
return result
def __api_suspended_search_parser(keyword, 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()
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 download(self, queue, folder=''):
if not isinstance(folder, text):
folder = str(folder)
if self.path:
folder = os.path.join(self.path, folder)
if not os.path.exists(folder):
logger.warn(
'Path \'{0}\' does not exist, creating.'.format(folder))
try:
os.makedirs(folder)
except EnvironmentError as e:
logger.critical('{0}'.format(str(e)))
exit(1)
else:
logger.warn('Path \'{0}\' already exist.'.format(folder))
queue = [([url], {'folder': folder}) for url in queue]
self.thread_pool = threadpool.ThreadPool(self.thread_count)
requests_ = threadpool.makeRequests(self._download, queue,
self._download_callback)
[self.thread_pool.putRequest(req) for req in requests_]
self.thread_pool.wait()
def tag_parser(tag_id, max_page=1):
logger.info('Searching for doujinshi with tag id {0}'.format(tag_id))
result = []
i = 0
while i < 5:
try:
response = request('get',
url=constant.TAG_API_URL,
params={
'sort': 'popular',
'tag_id': tag_id
}).json()
except Exception as e:
i += 1
if not i < 5:
logger.critical(str(e))
exit(1)
continue
break
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:
i = 0
while i < 5:
try:
response = request('get',
url=constant.TAG_API_URL,
params={
'sort': 'popular',
'tag_id': tag_id
}).json()
except Exception as e:
i += 1
if not i < 5:
logger.critical(str(e))
exit(1)
continue
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 tag id {}'.format(tag_id))
return result
def tag_parser(tag_id):
logger.info('Get doujinshi of tag id: {0}'.format(tag_id))
result = []
response = request('get', url=constant.TAG_API_URL, params={'sort': 'popular', '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('Not found anything of tag id {}'.format(tag_id))
return result
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 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 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 sys.version_info >= (3, 0, 0):
unicode_ = str
else:
unicode_ = unicode
if isinstance(tag_name, (str, unicode_)):
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 search_parser(keyword, page):
logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
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
result = _get_title_and_id(response)
if not result:
logger.warn('Not found anything of keyword {}'.format(keyword))
return result
def __api_suspended_tag_parser(tag_id, 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()
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': 'popular', '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 search_parser(keyword, page):
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})
if not result:
logger.warn('Not found anything of keyword {}'.format(keyword))
return result
def tag_parser(tag_name, max_page=1):
result = []
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
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
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 search_parser(keyword, page):
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.')
exit(1)
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[:85] + '..') if len(title) > 85 else title
id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
result.append({'id': id_, 'title': title})
if not result:
logger.warn('Not found anything of keyword {}'.format(keyword))
return result
def search_parser(keyword, sorting, page):
logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
keyword = '+'.join(
[i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
result = []
i = 0
while i < 5:
try:
url = request('get',
url=constant.SEARCH_URL,
params={
'query': keyword,
'page': page,
'sort': sorting
}).url
response = request('get', url.replace('%2B', '+')).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 download(self, queue, folder=''):
if not isinstance(folder, (text)):
folder = str(folder)
if self.path:
folder = os.path.join(self.path, folder)
if not os.path.exists(folder):
logger.warn('Path \'{0}\' not exist.'.format(folder))
try:
os.makedirs(folder)
except EnvironmentError as e:
logger.critical('{0}'.format(str(e)))
exit(1)
else:
logger.warn('Path \'{0}\' already exist.'.format(folder))
queue = [([url], {'folder': folder}) for url in queue]
self.thread_pool = threadpool.ThreadPool(self.thread_count)
requests_ = threadpool.makeRequests(self._download, queue, self._download_callback)
[self.thread_pool.putRequest(req) for req in requests_]
self.thread_pool.wait()
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)$',
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']
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)
return doujinshi