def generate_html(output_dir='.', doujinshi_obj=None):
image_html = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, format_filename('%s-%s' % (doujinshi_obj.id,
str(doujinshi_obj.name[:200]))))
else:
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image)
html = readfile('viewer/index.html')
css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js')
if doujinshi_obj is not None:
title = doujinshi_obj.name
else:
title = 'nHentai HTML Viewer'
data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
def generate_cbz(output_dir='.', doujinshi_obj=None):
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(
output_dir,
format_filename('%s-%s' %
(doujinshi_obj.id, str(doujinshi_obj.name[:200]))))
cbz_filename = os.path.join(
output_dir,
format_filename('%s-%s.cbz' %
(doujinshi_obj.id, str(doujinshi_obj.name[:200]))))
else:
cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
for image in file_list:
image_path = os.path.join(doujinshi_dir, image)
cbz_pf.write(image_path, image)
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(
15,
'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
"""Write images to a PDF file using img2pdf."""
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
pdf_filename = os.path.join(os.path.join(doujinshi_dir, '..'),
'{}.pdf'.format(doujinshi_obj.filename))
else:
pdf_filename = './doujinshi.pdf'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info('Writing PDF file to path: {}'.format(pdf_filename))
with open(pdf_filename, 'wb') as pdf_f:
full_path_list = ([
os.path.join(doujinshi_dir, image) for image in file_list
])
pdf_f.write(img2pdf.convert(full_path_list))
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(15,
'PDF file has been written to \'{0}\''.format(doujinshi_dir))
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).json()
except Exception as e:
logger.critical(str(e))
exit(1)
doujinshi['name'] = str(response['title']['english'].encode('utf-8'))[2:]
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'])
# 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']
return doujinshi
def main():
banner()
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
else:
doujinshi_ids = options.ids
if doujinshi_ids:
for id in doujinshi_ids:
doujinshi_info = doujinshi_parser(id)
doujinshi_list.append(Doujinshi(**doujinshi_info))
else:
exit(0)
if options.is_download:
downloader = Downloader(path=options.saved_path,
thread=options.threads,
timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
else:
map(lambda doujinshi: doujinshi.show(), doujinshi_list)
logger.log(15, u'🍺 All done.')
def generate_cbz(output_dir='.',
doujinshi_obj=None,
rm_origin_dir=False,
write_comic_info=False):
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
if write_comic_info:
serialize_comicxml(doujinshi_obj, doujinshi_dir)
cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'),
'{}.cbz'.format(doujinshi_obj.filename))
else:
cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
for image in file_list:
image_path = os.path.join(doujinshi_dir, image)
cbz_pf.write(image_path, image)
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(
15, 'Comic Book CBZ file has been written to \'{0}\''.format(
doujinshi_dir))
def generate_main_html(output_dir='./'):
"""
Generate a main html to show all the contain doujinshi.
With a link to their `index.html`.
Default output folder will be the CLI path.
"""
image_html = ''
main = readfile('viewer/main.html')
css = readfile('viewer/main.css')
js = readfile('viewer/main.js')
element = '\n\
<div class="gallery-favorite">\n\
<div class="gallery">\n\
<a href="./{FOLDER}/index.html" class="cover" style="padding:0 0 141.6% 0"><img\n\
src="./{FOLDER}/{IMAGE}" />\n\
<div class="caption">{TITLE}</div>\n\
</a>\n\
</div>\n\
</div>\n'
os.chdir(output_dir)
doujinshi_dirs = next(os.walk('.'))[1]
for folder in doujinshi_dirs:
files = os.listdir(folder)
files.sort()
if 'index.html' in files:
logger.info('Add doujinshi \'{}\''.format(folder))
else:
continue
image = files[0] # 001.jpg or 001.png
if folder is not None:
title = folder.replace('_', ' ')
else:
title = 'nHentai HTML Viewer'
image_html += element.format(FOLDER=folder, IMAGE=image, TITLE=title)
if image_html == '':
logger.warning('No index.html found, --gen-main paused.')
return
try:
data = main.format(STYLES=css, SCRIPTS=js, PICTURE=image_html)
if sys.version_info < (3, 0):
with open('./main.html', 'w') as f:
f.write(data)
else:
with open('./main.html', 'wb') as f:
f.write(data.encode('utf-8'))
shutil.copy(os.path.dirname(__file__) + '/viewer/logo.png', './')
set_js_database()
logger.log(
15, 'Main Viewer has been written to \'{0}main.html\''.format(
output_dir))
except Exception as e:
logger.warning('Writing Main Viewer failed ({})'.format(str(e)))
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).content
except Exception as e:
logger.critical(str(e))
raise SystemExit
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', 'Language', '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
def main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.login:
username, password = options.login.split(':', 1)
logger.info('Logging in to nhentai using credential pair \'%s:%s\'' %
(username, '*' * len(password)))
login(username, password)
if options.is_download:
for doujinshi_info in login_parser():
doujinshi_list.append(Doujinshi(**doujinshi_info))
if options.tag:
doujinshis = tag_parser(options.tag, max_page=options.max_page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
if not doujinshi_ids:
doujinshi_ids = options.id
if doujinshi_ids:
for id_ in doujinshi_ids:
doujinshi_info = doujinshi_parser(id_)
doujinshi_list.append(Doujinshi(**doujinshi_info))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads,
timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi)
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi,
options.rm_origin_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
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).content
except Exception as e:
logger.critical(str(e))
raise SystemExit
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', 'Language', '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
def _download_callback(self, request, result):
result, data = result
if result == 0:
logger.warning('fatal errors occurred, ignored')
# exit(1)
elif result == -1:
logger.warning('url {} return status code 404'.format(data))
else:
logger.log(15, '{0} downloaded successfully'.format(data))
def _download_callback(self, request, result):
result, data = result
if result == 0:
logger.critical('fatal errors occurred, quit.')
exit(1)
elif result == -1:
logger.warning('url {} return status code 404'.format(data))
else:
logger.log(15, '{0} download successfully'.format(data))
def main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.login:
username, password = options.login.split(':', 1)
logger.info('Logging in to nhentai using credential pair \'%s:%s\'' % (username, '*' * len(password)))
login(username, password)
if options.is_download:
for doujinshi_info in login_parser():
doujinshi_list.append(Doujinshi(**doujinshi_info))
if options.tag:
doujinshis = tag_parser(options.tag, max_page=options.max_page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
if not doujinshi_ids:
doujinshi_ids = options.id
if doujinshi_ids:
for id_ in doujinshi_ids:
doujinshi_info = doujinshi_parser(id_)
doujinshi_list.append(Doujinshi(**doujinshi_info))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi)
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.favorites:
if not options.is_download:
logger.warning('You do not specify --download option')
doujinshi_ids = favorites_parser()
elif options.tag:
doujinshis = tag_parser(options.tag, max_page=options.max_page)
print_doujinshi(doujinshis)
if options.is_download and doujinshis:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
elif options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
elif not doujinshi_ids:
doujinshi_ids = options.id
if doujinshi_ids:
for id_ in doujinshi_ids:
if options.delay:
time.sleep(options.delay)
doujinshi_info = doujinshi_parser(id_)
doujinshi_list.append(Doujinshi(name_format=options.name_format, path=options.output_dir, **doujinshi_info))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout, delay=options.delay)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi)
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi, options.rm_origin_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
image_html = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
else:
doujinshi_dir = '.'
if not os.path.exists(doujinshi_dir):
logger.warning(
'Path \'{0}\' does not exist, creating.'.format(doujinshi_dir))
try:
os.makedirs(doujinshi_dir)
except EnvironmentError as e:
logger.critical('{0}'.format(str(e)))
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image)
html = readfile('viewer/{}/index.html'.format(template))
css = readfile('viewer/{}/styles.css'.format(template))
js = readfile('viewer/{}/scripts.js'.format(template))
if doujinshi_obj is not None:
serialize_json(doujinshi_obj, doujinshi_dir)
name = doujinshi_obj.name
if sys.version_info < (3, 0):
name = doujinshi_obj.name.encode('utf-8')
else:
name = {'title': 'nHentai HTML Viewer'}
data = html.format(TITLE=name, IMAGES=image_html, SCRIPTS=js, STYLES=css)
try:
if sys.version_info < (3, 0):
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
else:
with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
f.write(data.encode('utf-8'))
logger.log(
15, 'HTML Viewer has been written to \'{0}\''.format(
os.path.join(doujinshi_dir, 'index.html')))
except Exception as e:
logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
def _download_callback(self, result):
result, data = result
if result == 0:
logger.warning('fatal errors occurred, ignored')
# exit(1)
elif result == -1:
logger.warning('url {} return status code 404'.format(data))
elif result == -2:
logger.warning('Ctrl-C pressed, exiting sub processes ...')
elif result == -3:
# workers wont be run, just pass
pass
else:
logger.log(15, '{0} downloaded successfully'.format(data))
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
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(map(lambda s: s['t'], response['images']['pages']))
doujinshi['pages'] = len(response['images']['pages'])
# 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] = {}
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
def generate_html(output_dir='.', doujinshi_obj=None):
image_html = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(
output_dir,
format_filename('%s-%s' % (doujinshi_obj.id, doujinshi_obj.name)))
else:
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image)
html = readfile('viewer/index.html')
css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js')
if doujinshi_obj is not None:
title = doujinshi_obj.name
if sys.version_info < (3, 0):
title = title.encode('utf-8')
else:
title = 'nHentai HTML Viewer'
data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
try:
if sys.version_info < (3, 0):
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
else:
with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
f.write(data.encode('utf-8'))
logger.log(
15, 'HTML Viewer has been write to \'{0}\''.format(
os.path.join(doujinshi_dir, 'index.html')))
except Exception as e:
logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
def generate_html(output_dir='.', doujinshi_obj=None):
image_html = ''
previous = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(
output_dir,
format_filename('%s-%s' %
(doujinshi_obj.id, doujinshi_obj.name[:200])))
else:
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for index, image in enumerate(file_list):
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
try:
next_ = file_list[file_list.index(image) + 1]
except IndexError:
next_ = ''
image_html += '<img src="{0}" class="image-item {1}" attr-prev="{2}" attr-next="{3}">\n'\
.format(image, 'current' if index == 0 else '', previous, next_)
previous = image
with open(os.path.join(os.path.dirname(__file__), 'doujinshi.html'),
'r') as template:
html = template.read()
if doujinshi_obj is not None:
title = doujinshi_obj.name
else:
title = 'nHentai HTML Viewer'
data = html.format(TITLE=title, IMAGES=image_html)
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
logger.log(
15, 'HTML Viewer has been write to \'{0}\''.format(
os.path.join(doujinshi_dir, 'index.html')))
def generate_html(output_dir='.', doujinshi_obj=None):
image_html = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
else:
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list = list(filter(lambda x:x.split('.')[0].isdigit(), file_list)) # remove non-digit file names
file_list.sort(key = lambda x: int(x.split('.')[0])) # sort by num
for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image)
html = readfile('viewer/index.html')
css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js')
if doujinshi_obj is not None:
serialize_json(doujinshi_obj, doujinshi_dir)
name = doujinshi_obj.name
if sys.version_info < (3, 0):
name = doujinshi_obj.name.encode('utf-8')
else:
name = {'title': 'nHentai HTML Viewer'}
data = html.format(TITLE=name, IMAGES=image_html, SCRIPTS=js, STYLES=css)
try:
if sys.version_info < (3, 0):
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
else:
with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
f.write(data.encode('utf-8'))
logger.log(15, 'HTML Viewer has been written to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
except Exception as e:
logger.warning('Writing HTML Viewer failed ({})'.format(str(e)))
def generate_html(output_dir='.', doujinshi_obj=None):
image_html = ''
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
else:
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for image in file_list:
if not os.path.splitext(image)[1] in ('.jpg', '.png'):
continue
image_html += '<img src="{0}" class="image-item"/>\n'\
.format(image)
html = readfile('viewer/index.html')
css = readfile('viewer/styles.css')
js = readfile('viewer/scripts.js')
if doujinshi_obj is not None:
title = doujinshi_obj.name
if sys.version_info < (3, 0):
title = title.encode('utf-8')
else:
title = 'nHentai HTML Viewer'
data = html.format(TITLE=title, IMAGES=image_html, SCRIPTS=js, STYLES=css)
try:
if sys.version_info < (3, 0):
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
else:
with open(os.path.join(doujinshi_dir, 'index.html'), 'wb') as f:
f.write(data.encode('utf-8'))
logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
except Exception as e:
logger.warning('Writen HTML Viewer failed ({})'.format(str(e)))
def generate_cbz(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
if doujinshi_obj is not None:
doujinshi_dir = os.path.join(output_dir, doujinshi_obj.filename)
cbz_filename = os.path.join(os.path.join(doujinshi_dir, '..'), '%s.cbz' % doujinshi_obj.id)
else:
cbz_filename = './doujinshi.cbz'
doujinshi_dir = '.'
file_list = os.listdir(doujinshi_dir)
file_list.sort()
logger.info('Writing CBZ file to path: {}'.format(cbz_filename))
with zipfile.ZipFile(cbz_filename, 'w') as cbz_pf:
for image in file_list:
image_path = os.path.join(doujinshi_dir, image)
cbz_pf.write(image_path, image)
if rm_origin_dir:
shutil.rmtree(doujinshi_dir, ignore_errors=True)
logger.log(15, 'Comic Book CBZ file has been write to \'{0}\''.format(doujinshi_dir))
def main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
else:
doujinshi_ids = options.id
if doujinshi_ids:
for id in doujinshi_ids:
doujinshi_info = doujinshi_parser(id)
doujinshi_list.append(Doujinshi(**doujinshi_info))
else:
exit(0)
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
generate_html(options.output_dir, doujinshi)
if not platform.system() == 'Windows':
logger.log(15, '🍺 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
else:
doujinshi_ids = options.id
if doujinshi_ids:
for id in doujinshi_ids:
doujinshi_info = doujinshi_parser(id)
doujinshi_list.append(Doujinshi(**doujinshi_info))
else:
exit(0)
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
if not platform.system() == 'Windows':
logger.log(15, '🍺 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
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
elif response.status_code in (404, ):
logger.error("Doujinshi with id {0} cannot be found".format(id_))
return []
else:
logger.debug('Slow down and retry ({}) ...'.format(id_))
time.sleep(1)
return doujinshi_parser(str(id_))
except Exception as e:
logger.warning('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
pretty_name = doujinshi_info.find('h1').find('span',
attrs={
'class': 'pretty'
}).text
subtitle = doujinshi_info.find('h2')
doujinshi['name'] = title
doujinshi['pretty_name'] = pretty_name
doujinshi['subtitle'] = subtitle.text if subtitle else ''
doujinshi_cover = html.find('div', attrs={'id': 'cover'})
img_id = re.search('/galleries/([0-9]+)/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['img_id'] = img_id.group(1)
doujinshi['ext'] = ext
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 main():
banner()
logger.info('Using mirror: {0}'.format(BASE_URL))
options = cmd_parser()
doujinshi_ids = []
doujinshi_list = []
if options.keyword:
doujinshis = search_parser(options.keyword, options.page)
print_doujinshi(doujinshis)
if options.is_download:
doujinshi_ids = map(lambda d: d['id'], doujinshis)
else:
doujinshi_ids = options.id
if doujinshi_ids:
for id in doujinshi_ids:
doujinshi_info = doujinshi_parser(id)
doujinshi_list.append(Doujinshi(**doujinshi_info))
else:
exit(0)
if not options.is_show:
downloader = Downloader(path=options.output_dir,
thread=options.threads, timeout=options.timeout)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
image_html = ''
previous = ''
doujinshi_dir = os.path.join(options.output_dir, str(doujinshi.id))
file_list = os.listdir(doujinshi_dir)
file_list.sort()
for index, image in enumerate(file_list):
try:
next_ = file_list[file_list.index(image) + 1]
except IndexError:
next_ = ''
image_html += '<img src="{0}" class="image-item {1}" attr-prev="{2}" attr-next="{3}">\n'\
.format(image, 'current' if index == 0 else '', previous, next_)
previous = image
with open(os.path.join(os.path.dirname(__file__), 'doujinshi.html'), 'r') as template:
html = template.read()
data = html.format(TITLE=doujinshi.name, IMAGES=image_html)
with open(os.path.join(doujinshi_dir, 'index.html'), 'w') as f:
f.write(data)
logger.log(15, 'HTML Viewer has been write to \'{0}\''.format(os.path.join(doujinshi_dir, 'index.html')))
if not platform.system() == 'Windows':
logger.log(15, '🍺 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def _download_callback(self, request, result):
if not result:
logger.critical('Too many errors occurred, quit.')
exit(1)
logger.log(15, '{0} download successfully'.format(result))
def main():
banner()
options = cmd_parser()
logger.info('Using mirror: {0}'.format(BASE_URL))
from nhentai.constant import PROXY
# constant.PROXY will be changed after cmd_parser()
if PROXY != {}:
logger.info('Using proxy: {0}'.format(PROXY))
# check your cookie
check_cookie()
index = 0
index_value = None
doujinshis = []
doujinshi_ids = []
doujinshi_list = []
if options.favorites:
if not options.is_download:
logger.warning('You do not specify --download option')
doujinshis = favorites_parser(options.page_range)
elif options.tag:
doujinshis = tag_parser(options.tag,
sorting=options.sorting,
max_page=options.max_page)
elif options.artist:
index = 1
index_value = options.artist
elif options.character:
index = 2
index_value = options.character
elif options.parody:
index = 3
index_value = options.parody
elif options.group:
index = 4
index_value = options.group
elif options.language:
index = 5
index_value = options.language
elif options.keyword:
doujinshis = search_parser(options.keyword,
sorting=options.sorting,
page=options.page)
elif not doujinshi_ids:
doujinshi_ids = options.id
if index:
doujinshis = tag_parser(index_value,
max_page=options.max_page,
index=index)
print_doujinshi(doujinshis)
if options.is_download and doujinshis:
doujinshi_ids = [i['id'] for i in doujinshis]
if options.is_save_download_history:
with DB() as db:
data = set(db.get_all())
doujinshi_ids = list(set(doujinshi_ids) - data)
if doujinshi_ids:
for i, id_ in enumerate(doujinshi_ids):
if options.delay:
time.sleep(options.delay)
doujinshi_info = doujinshi_parser(id_)
if doujinshi_info:
doujinshi_list.append(
Doujinshi(name_format=options.name_format,
**doujinshi_info))
if (i + 1) % 10 == 0:
logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
size=options.threads,
timeout=options.timeout,
delay=options.delay)
for doujinshi in doujinshi_list:
doujinshi.downloader = downloader
doujinshi.download()
if options.is_save_download_history:
with DB() as db:
db.add_one(doujinshi.id)
if not options.is_nohtml and not options.is_cbz:
generate_html(options.output_dir, doujinshi)
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi,
options.rm_origin_dir, options.write_comic_info)
if options.main_viewer:
generate_main_html(options.output_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]
def main():
banner()
if sys.version_info < (3, 0, 0):
logger.error('nhentai now only support Python 3.x')
exit(1)
options = cmd_parser()
logger.info('Using mirror: {0}'.format(BASE_URL))
# CONFIG['proxy'] will be changed after cmd_parser()
if constant.CONFIG['proxy']['http']:
logger.info('Using proxy: {0}'.format(
constant.CONFIG['proxy']['http']))
if not constant.CONFIG['template']:
constant.CONFIG['template'] = 'default'
logger.info('Using viewer template "{}"'.format(
constant.CONFIG['template']))
# check your cookie
check_cookie()
doujinshis = []
doujinshi_ids = []
doujinshi_list = []
page_list = paging(options.page)
if options.favorites:
if not options.is_download:
logger.warning('You do not specify --download option')
doujinshis = favorites_parser(page=page_list)
elif options.keyword:
if constant.CONFIG['language']:
logger.info('Using default language: {0}'.format(
constant.CONFIG['language']))
options.keyword += ' language:{}'.format(
constant.CONFIG['language'])
doujinshis = search_parser(options.keyword,
sorting=options.sorting,
page=page_list,
is_page_all=options.page_all)
elif not doujinshi_ids:
doujinshi_ids = options.id
print_doujinshi(doujinshis)
if options.is_download and doujinshis:
doujinshi_ids = [i['id'] for i in doujinshis]
if options.is_save_download_history:
with DB() as db:
data = map(int, db.get_all())
doujinshi_ids = list(set(map(int, doujinshi_ids)) - set(data))
if doujinshi_ids:
for i, id_ in enumerate(doujinshi_ids):
if options.delay:
time.sleep(options.delay)
doujinshi_info = doujinshi_parser(id_)
if doujinshi_info:
doujinshi_list.append(
Doujinshi(name_format=options.name_format,
**doujinshi_info))
if (i + 1) % 10 == 0:
logger.info('Progress: %d / %d' % (i + 1, len(doujinshi_ids)))
if not options.is_show:
downloader = Downloader(path=options.output_dir,
size=options.threads,
timeout=options.timeout,
delay=options.delay)
for doujinshi in doujinshi_list:
if not options.dryrun:
doujinshi.downloader = downloader
doujinshi.download()
doujinshi.downloader = downloader
doujinshi.download()
if options.generate_metadata:
table = doujinshi.table
generate_metadata_file(options.output_dir, table, doujinshi)
if options.is_save_download_history:
with DB() as db:
db.add_one(doujinshi.id)
if not options.is_nohtml and not options.is_cbz and not options.is_pdf:
generate_html(options.output_dir,
doujinshi,
template=constant.CONFIG['template'])
elif options.is_cbz:
generate_cbz(options.output_dir, doujinshi,
options.rm_origin_dir)
elif options.is_pdf:
generate_pdf(options.output_dir, doujinshi,
options.rm_origin_dir)
if options.main_viewer:
generate_main_html(options.output_dir)
if not platform.system() == 'Windows':
logger.log(15, '🍻 All done.')
else:
logger.log(15, 'All done.')
else:
[doujinshi.show() for doujinshi in doujinshi_list]