NussNougate/nhentai
4
0
Fork 0
mirror of https://github.com/RicterZ/nhentai.git synced 2025-11-03 18:50:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

bypass the challenge

Browse Source
This commit is contained in:
RicterZ
2019-04-11 22:39:20 +08:00
parent f74be0c665
commit 9160b38c3f
2 changed files with 28 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
nhentai/constant.py
View File

@@ -14,6 +14,7 @@ SEARCH_URL = '%s/search/' % BASE_URL
TAG_URL = '%s/tag' % BASE_URL
TAG_API_URL = '%s/api/galleries/tagged' % BASE_URL
LOGIN_URL = '%s/login/' % BASE_URL
CHALLENGE_URL = '%s/challenge' % BASE_URL
FAV_URL = '%s/favorites/' % BASE_URL
u = urlparse(BASE_URL)

35
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
@@ -13,6 +14,10 @@ from nhentai.logger import logger
session = requests.Session()
session.headers.update({
'Referer': constant.LOGIN_URL,
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
})
def request(method, url, **kwargs):
@@ -23,17 +28,21 @@ def request(method, url, **kwargs):
return getattr(session, method)(url, proxies=constant.PROXY, verify=False, **kwargs)
def login(username, password):
global session
request('get', url=constant.LOGIN_URL)
session.headers.update({'Referer': constant.LOGIN_URL})
content = request('get', url=constant.LOGIN_URL).content
def _get_csrf_token(content):
html = BeautifulSoup(content, 'html.parser')
csrf_token_elem = html.find('input', attrs={'name': 'csrfmiddlewaretoken'})
if not csrf_token_elem:
raise Exception('Cannot find csrf token to login')
csrf_token = csrf_token_elem.attrs['value']
return csrf_token_elem.attrs['value']
def login(username, password):
csrf_token = _get_csrf_token(request('get', url=constant.LOGIN_URL).content)
if os.getenv('DEBUG'):
logger.info('Getting CSRF token ...')
if os.getenv('DEBUG'):
logger.info('CSRF token is {}'.format(csrf_token))
login_dict = {
'csrfmiddlewaretoken': csrf_token,
@@ -41,16 +50,26 @@ def login(username, password):
'password': password,
}
resp = request('post', url=constant.LOGIN_URL, data=login_dict)
if 'Invalid username/email or password' in resp.text:
if 'You\'re loading pages way too quickly.' in resp.content:
csrf_token = _get_csrf_token(resp.content)
resp = request('post', url=resp.url, data={'csrfmiddlewaretoken': csrf_token, 'next': '/'})
if 'Invalid username/email or password' in resp.content:
logger.error('Login failed, please check your username and password')
exit(1)
if 'You\'re loading pages way too quickly.' in resp.content:
logger.error('You meet challenge again, please submit a issue at https://github.com/RicterZ/nhentai/issues')
exit(2)
def login_parser():
html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
if not count:
logger.error("Can't get your number of favorited doujins. Did the login failed?")
return
count = int(count.text.strip('(').strip(')').replace(',', ''))
if count == 0: