def initialize(self):
self.session = Session()
self.session.headers['User-Agent'] = 'Subliminal/%s' % subliminal.__short_version__
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
logger.debug("Addic7ed: using random user agents")
self.session.headers['User-Agent'] = AGENT_LIST[randint(0, len(AGENT_LIST) - 1)]
self.session.headers['Referer'] = self.server_url
# login
if self.username and self.password:
def check_verification(cache_region):
rr = self.session.get(self.server_url + 'panel.php', allow_redirects=False, timeout=10,
headers={"Referer": self.server_url})
if rr.status_code == 302:
logger.info('Addic7ed: Login expired')
cache_region.delete("addic7ed_data")
else:
logger.info('Addic7ed: Re-using old login')
self.logged_in = True
return True
if load_verification("addic7ed", self.session, callback=check_verification):
return
logger.info('Addic7ed: Logging in')
data = {'username': self.username, 'password': self.password, 'Submit': 'Log in', 'url': '',
'remember': 'true'}
tries = 0
while tries < 3:
r = self.session.get(self.server_url + 'login.php', timeout=10, headers={"Referer": self.server_url})
if "grecaptcha" in r.content:
logger.info('Addic7ed: Solving captcha. This might take a couple of minutes, but should only '
'happen once every so often')
site_key = re.search(r'grecaptcha.execute\(\'(.+?)\',', r.content).group(1)
if not site_key:
logger.error("Addic7ed: Captcha site-key not found!")
return
pitcher = pitchers.get_pitcher()("Addic7ed", self.server_url + 'login.php', site_key,
user_agent=self.session.headers["User-Agent"],
cookies=self.session.cookies.get_dict(),
is_invisible=True)
result = pitcher.throw()
if not result:
raise Exception("Addic7ed: Couldn't solve captcha!")
data["recaptcha_response"] = result
r = self.session.post(self.server_url + 'dologin.php', data, allow_redirects=False, timeout=10,
headers={"Referer": self.server_url + "login.php"})
if "relax, slow down" in r.content:
raise TooManyRequests(self.username)
if r.status_code != 302:
if "User <b></b> doesn't exist" in r.content and tries <= 2:
logger.info("Addic7ed: Error, trying again. (%s/%s)", tries+1, 3)
tries += 1
continue
raise AuthenticationError(self.username)
break
store_verification("addic7ed", self.session)
logger.debug('Addic7ed: Logged in')
self.logged_in = True
def initialize(self):
self.session = Session()
self.session.headers[
'User-Agent'] = 'Subliminal/%s' % subliminal.__short_version__
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
logger.debug("Addic7ed: using random user agents")
self.session.headers['User-Agent'] = AGENT_LIST[randint(
0,
len(AGENT_LIST) - 1)]
self.session.headers['Referer'] = self.server_url
# login
if self.username and self.password:
def check_verification(cache_region):
try:
rr = self.session.get(self.server_url + 'panel.php',
allow_redirects=False,
timeout=10,
headers={"Referer": self.server_url})
if rr.status_code == 302:
logger.info('Addic7ed: Login expired')
cache_region.delete("addic7ed_data")
else:
logger.info('Addic7ed: Re-using old login')
self.logged_in = True
return True
except ConnectionError as e:
logger.debug(
"Addic7ed: There was a problem reaching the server: %s."
% e)
raise IPAddressBlocked(
"Addic7ed: Your IP is temporarily blocked.")
if load_verification("addic7ed",
self.session,
callback=check_verification):
return
logger.info('Addic7ed: Logging in')
data = {
'username': self.username,
'password': self.password,
'Submit': 'Log in',
'url': '',
'remember': 'true'
}
tries = 0
while tries <= 3:
tries += 1
r = self.session.get(self.server_url + 'login.php',
timeout=10,
headers={"Referer": self.server_url})
if "g-recaptcha" in r.text or "grecaptcha" in r.text:
logger.info(
'Addic7ed: Solving captcha. This might take a couple of minutes, but should only '
'happen once every so often')
for g, s in (("g-recaptcha-response",
r'g-recaptcha.+?data-sitekey=\"(.+?)\"'),
("recaptcha_response",
r'grecaptcha.execute\(\'(.+?)\',')):
site_key = re.search(s, r.text).group(1)
if site_key:
break
if not site_key:
logger.error("Addic7ed: Captcha site-key not found!")
return
pitcher = pitchers.get_pitcher()(
"Addic7ed",
self.server_url + 'login.php',
site_key,
user_agent=self.session.headers["User-Agent"],
cookies=self.session.cookies.get_dict(),
is_invisible=True)
result = pitcher.throw()
if not result:
if tries >= 3:
raise Exception(
"Addic7ed: Couldn't solve captcha!")
logger.info(
"Addic7ed: Couldn't solve captcha! Retrying")
continue
data[g] = result
r = self.session.post(
self.server_url + 'dologin.php',
data,
allow_redirects=False,
timeout=10,
headers={"Referer": self.server_url + "login.php"})
if "relax, slow down" in r.text:
raise TooManyRequests(self.username)
if "Wrong password" in r.text or "doesn't exist" in r.text:
raise AuthenticationError(self.username)
if r.status_code != 302:
if tries >= 3:
logger.error(
"Addic7ed: Something went wrong when logging in")
raise AuthenticationError(self.username)
logger.info(
"Addic7ed: Something went wrong when logging in; retrying"
)
continue
break
store_verification("addic7ed", self.session)
logger.debug('Addic7ed: Logged in')
self.logged_in = True
def query(self,
languages,
title,
season=None,
episode=None,
year=None,
video=None):
items_per_page = 10
current_page = 1
used_languages = languages
lang_strings = [str(lang) for lang in used_languages]
# handle possible duplicate use of Serbian Latin
if "sr" in lang_strings and "sr-Latn" in lang_strings:
logger.info(
'Duplicate entries <Language [sr]> and <Language [sr-Latn]> found, filtering languages'
)
used_languages = filter(
lambda l: l != Language.fromietf('sr-Latn'), used_languages)
logger.info('Filtered language list %r', used_languages)
# convert list of languages into search string
langs = '|'.join(map(str, [l.titlovi for l in used_languages]))
# set query params
params = {'prijevod': title, 'jezik': langs}
is_episode = False
if season and episode:
is_episode = True
params['s'] = season
params['e'] = episode
if year:
params['g'] = year
# loop through paginated results
logger.info('Searching subtitles %r', params)
subtitles = []
while True:
# query the server
try:
r = self.session.get(self.search_url,
params=params,
timeout=10)
r.raise_for_status()
except RequestException as e:
captcha_passed = False
if e.response.status_code == 403 and "data-sitekey" in e.response.content:
logger.info(
'titlovi: Solving captcha. This might take a couple of minutes, but should only '
'happen once every so often')
site_key = re.search(r'data-sitekey="(.+?)"',
e.response.content).group(1)
challenge_s = re.search(
r'type="hidden" name="s" value="(.+?)"',
e.response.content).group(1)
challenge_ray = re.search(r'data-ray="(.+?)"',
e.response.content).group(1)
if not all([site_key, challenge_s, challenge_ray]):
raise Exception("titlovi: Captcha site-key not found!")
pitcher = pitchers.get_pitcher()(
"titlovi",
e.request.url,
site_key,
user_agent=self.session.headers["User-Agent"],
cookies=self.session.cookies.get_dict(),
is_invisible=True)
result = pitcher.throw()
if not result:
raise Exception("titlovi: Couldn't solve captcha!")
s_params = {
"s": challenge_s,
"id": challenge_ray,
"g-recaptcha-response": result,
}
r = self.session.get(self.server_url +
"/cdn-cgi/l/chk_captcha",
params=s_params,
timeout=10,
allow_redirects=False)
r.raise_for_status()
r = self.session.get(self.search_url,
params=params,
timeout=10)
r.raise_for_status()
store_verification("titlovi", self.session)
captcha_passed = True
if not captcha_passed:
logger.exception('RequestException %s', e)
break
else:
try:
soup = BeautifulSoup(r.content, 'lxml')
# number of results
result_count = int(
soup.select_one('.results_count b').string)
except:
result_count = None
# exit if no results
if not result_count:
if not subtitles:
logger.debug('No subtitles found')
else:
logger.debug("No more subtitles found")
break
# number of pages with results
pages = int(math.ceil(result_count / float(items_per_page)))
# get current page
if 'pg' in params:
current_page = int(params['pg'])
try:
sublist = soup.select(
'section.titlovi > ul.titlovi > li.subtitleContainer.canEdit'
)
for sub in sublist:
# subtitle id
sid = sub.find(attrs={
'data-id': True
}).attrs['data-id']
# get download link
download_link = self.download_url + sid
# title and alternate title
match = title_re.search(sub.a.string)
if match:
_title = match.group('title')
alt_title = match.group('altitle')
else:
continue
# page link
page_link = self.server_url + sub.a.attrs['href']
# subtitle language
match = lang_re.search(
sub.select_one('.lang').attrs['src'])
if match:
try:
# decode language
lang = Language.fromtitlovi(
match.group('lang') +
match.group('script'))
except ValueError:
continue
# relase year or series start year
match = year_re.search(
sub.find(attrs={
'data-id': True
}).parent.i.string)
if match:
r_year = int(match.group('year'))
# fps
match = fps_re.search(sub.select_one('.fps').string)
if match:
fps = match.group('fps')
# releases
releases = str(
sub.select_one('.fps').parent.contents[0].string)
# handle movies and series separately
if is_episode:
# season and episode info
sxe = sub.select_one('.s0xe0y').string
r_season = None
r_episode = None
if sxe:
match = season_re.search(sxe)
if match:
r_season = int(match.group('season'))
match = episode_re.search(sxe)
if match:
r_episode = int(match.group('episode'))
subtitle = self.subtitle_class(
lang,
page_link,
download_link,
sid,
releases,
_title,
alt_title=alt_title,
season=r_season,
episode=r_episode,
year=r_year,
fps=fps,
asked_for_release_group=video.release_group,
asked_for_episode=episode)
else:
subtitle = self.subtitle_class(
lang,
page_link,
download_link,
sid,
releases,
_title,
alt_title=alt_title,
year=r_year,
fps=fps,
asked_for_release_group=video.release_group)
logger.debug('Found subtitle %r', subtitle)
# prime our matches so we can use the values later
subtitle.get_matches(video)
# add found subtitles
subtitles.append(subtitle)
finally:
soup.decompose()
# stop on last page
if current_page >= pages:
break
# increment current page
params['pg'] = current_page + 1
logger.debug('Getting page %d', params['pg'])
return subtitles