NussNougate/nhentai
4
0
Fork 0
mirror of https://github.com/RicterZ/nhentai.git synced 2025-11-04 02:50:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #28 from tbinavsl/master

Browse Source 
Max retries + misc. language fixes
This commit is contained in:
Ricter Zheng
2018-09-28 13:28:44 +08:00
committed by GitHub
parent b8ea917db2 6f20405f47
commit 86c31f9b5e
5 changed files with 103 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
nhentai/cmdline.py
View File

@@ -40,23 +40,23 @@ def cmd_parser():
'\n\nEnvironment Variable:\n'
' NHENTAI nhentai mirror url')
parser.add_option('--download', dest='is_download', action='store_true',
help='download doujinshi (for search result)')
help='download doujinshi (for search results)')
parser.add_option('--show-info', dest='is_show', action='store_true', help='just show the doujinshi information')
parser.add_option('--id', type='string', dest='id', action='store', help='doujinshi ids set, e.g. 1,2,3')
parser.add_option('--search', type='string', dest='keyword', action='store', help='search doujinshi by keyword')
parser.add_option('--page', type='int', dest='page', action='store', default=1,
help='page number of search result')
help='page number of search results')
parser.add_option('--tag', type='string', dest='tag', action='store', help='download doujinshi by tag')
parser.add_option('--max-page', type='int', dest='max_page', action='store', default=1,
help='The max page when recursive download tagged doujinshi')
parser.add_option('--output', type='string', dest='output_dir', action='store', default='',
help='output dir')
parser.add_option('--threads', '-t', type='int', dest='threads', action='store', default=5,
help='thread count of download doujinshi')
help='thread count for downloading doujinshi')
parser.add_option('--timeout', type='int', dest='timeout', action='store', default=30,
help='timeout of download doujinshi')
help='timeout for downloading doujinshi')
parser.add_option('--proxy', type='string', dest='proxy', action='store', default='',
help='use proxy, example: http://127.0.0.1:1080')
help='uses a proxy, for example: http://127.0.0.1:1080')
parser.add_option('--html', dest='html_viewer', action='store_true',
help='generate a html viewer at current directory')

4
nhentai/command.py
View File

@@ -23,7 +23,7 @@ def main():
if options.login:
username, password = options.login.split(':', 1)
logger.info('Login to nhentai use credential \'%s:%s\'' % (username, '*' * len(password)))
logger.info('Logging in to nhentai using credential pair \'%s:%s\'' % (username, '*' * len(password)))
for doujinshi_info in login_parser(username=username, password=password):
doujinshi_list.append(Doujinshi(**doujinshi_info))
@@ -68,7 +68,7 @@ def main():
def signal_handler(signal, frame):
logger.error('Ctrl-C signal received. Quit.')
logger.error('Ctrl-C signal received. Stopping...')
exit(1)

5
nhentai/doujinshi.py
View File

@@ -11,6 +11,7 @@ from nhentai.utils import format_filename
EXT_MAP = {
'j': 'jpg',
'p': 'png',
'g': 'gif',
}
@@ -53,7 +54,7 @@ class Doujinshi(object):
logger.info(u'Print doujinshi information of {0}\n{1}'.format(self.id, tabulate(table)))
def download(self):
logger.info('Start download doujinshi: %s' % self.name)
logger.info('Starting to download doujinshi: %s' % self.name)
if self.downloader:
download_queue = []
for i in range(len(self.ext)):
@@ -61,7 +62,7 @@ class Doujinshi(object):
self.downloader.download(download_queue, format_filename('%s-%s' % (self.id, self.name[:200])))
else:
logger.critical('Downloader has not be loaded')
logger.critical('Downloader has not been loaded')
if __name__ == '__main__':

20
nhentai/downloader.py
View File

@@ -32,17 +32,27 @@ class Downloader(Singleton):
self.timeout = timeout
def _download(self, url, folder='', filename='', retried=0):
logger.info('Start downloading: {0} ...'.format(url))
logger.info('Starting to download {0} ...'.format(url))
filename = filename if filename else os.path.basename(urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
try:
if os.path.exists(os.path.join(folder, base_filename.zfill(3) + extension)):
logger.warning('File: {0} existed, ignore.'.format(os.path.join(folder, base_filename.zfill(3) +
logger.warning('File: {0} exists, ignoring'.format(os.path.join(folder, base_filename.zfill(3) +
extension)))
return 1, url
with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
response = request('get', url, stream=True, timeout=self.timeout)
i=0
while i<10:
try:
response = request('get', url, stream=True, timeout=self.timeout)
except Exception as e:
i+=1
if not i<10:
logger.critical(str(e))
return 0, None
continue
break
if response.status_code != 200:
raise NhentaiImageNotExistException
length = response.headers.get('content-length')
@@ -77,7 +87,7 @@ class Downloader(Singleton):
elif result == -1:
logger.warning('url {} return status code 404'.format(data))
else:
logger.log(15, '{0} download successfully'.format(data))
logger.log(15, '{0} downloaded successfully'.format(data))
def download(self, queue, folder=''):
if not isinstance(folder, text):
@@ -87,7 +97,7 @@ class Downloader(Singleton):
folder = os.path.join(self.path, folder)
if not os.path.exists(folder):
logger.warn('Path \'{0}\' not exist.'.format(folder))
logger.warn('Path \'{0}\' does not exist, creating.'.format(folder))
try:
os.makedirs(folder)
except EnvironmentError as e:

113
nhentai/parser.py
View File

@@ -5,6 +5,7 @@ import os
import re
import threadpool
import requests
import time
from bs4 import BeautifulSoup
from tabulate import tabulate
@@ -40,14 +41,14 @@ def login_parser(username, password):
'password': password,
}
resp = s.post(constant.LOGIN_URL, data=login_dict)
if 'Invalid username (or email) or password' in resp.text:
if 'Invalid username/email or password' in resp.text:
logger.error('Login failed, please check your username and password')
exit(1)
html = BeautifulSoup(s.get(constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error('Cannot get count of your favorites, maybe login failed.')
logger.error("Can't get your number of favorited doujins. Did the login failed?")
count = int(count.text.strip('(').strip(')'))
if count == 0:
@@ -60,7 +61,7 @@ def login_parser(username, password):
else:
pages = 1
logger.info('Your have %d favorites in %d pages.' % (count, pages))
logger.info('You have %d favorites in %d pages.' % (count, pages))
if os.getenv('DEBUG'):
pages = 1
@@ -75,7 +76,7 @@ def login_parser(username, password):
for page in range(1, pages+1):
try:
logger.info('Getting doujinshi id of page %d' % page)
logger.info('Getting doujinshi ids of page %d' % page)
resp = s.get(constant.FAV_URL + '?page=%d' % page).text
ids = doujinshi_id.findall(resp)
requests_ = threadpool.makeRequests(doujinshi_parser, ids, _callback)
@@ -92,16 +93,21 @@ def doujinshi_parser(id_):
raise Exception('Doujinshi id({0}) is not valid'.format(id_))
id_ = int(id_)
logger.log(15, 'Fetching doujinshi information of id {0}'.format(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_)
try:
response = request('get', url).json()
except Exception as e:
logger.critical(str(e))
exit(1)
i=0
while i<5:
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']
@@ -130,16 +136,23 @@ def doujinshi_parser(id_):
def search_parser(keyword, page):
logger.debug('Searching doujinshis of keyword {0}'.format(keyword))
logger.debug('Searching doujinshis using keywords {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)
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']
@@ -147,7 +160,7 @@ def search_parser(keyword, page):
result.append({'id': row['id'], 'title': title})
if not result:
logger.warn('Not found anything of keyword {}'.format(keyword))
logger.warn('No results for keywords {}'.format(keyword))
return result
@@ -157,30 +170,49 @@ def print_doujinshi(doujinshi_list):
return
doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
headers = ['id', 'doujinshi']
data = tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst')
logger.info('Search Result\n{}'.format(data))
logger.info('Search Result\n' +
tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
def tag_parser(tag_id, max_page=1):
logger.info('Get doujinshi of tag id: {0}'.format(tag_id))
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()
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('Get page {} ...'.format(i))
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})
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('Not found anything of tag id {}'.format(tag_id))
logger.warn('No results for tag id {}'.format(tag_id))
return result
@@ -188,7 +220,18 @@ def tag_guessing(tag_name):
tag_name = tag_name.lower()
tag_name = tag_name.replace(' ', '-')
logger.info('Trying to get tag_id of tag \'{0}\''.format(tag_name))
response = request('get', url='%s/%s' % (constant.TAG_URL, tag_name)).content
i=0
while i<5:
try:
response = request('get', url='%s/%s' % (constant.TAG_URL, tag_name)).content
except Exception as e:
i+=1
if not i<5:
logger.critical(str(e))
exit(1)
continue
break
html = BeautifulSoup(response, 'html.parser')
first_item = html.find('div', attrs={'class': 'gallery'})
if not first_item: