def __init__(self, configfile, dbfile, device, logging, scraper, filename,
internal_name):
self._INTERNAL_NAME = internal_name
self.configfile = configfile
self.dbfile = dbfile
self.device = device
self.hostnames = RssConfig('Hostnames', self.configfile)
self.sf = self.hostnames.get('sf')
self.config = RssConfig(self._INTERNAL_NAME, self.configfile)
self.rsscrawler = RssConfig("RSScrawler", self.configfile)
self.hevc_retail = self.config.get("hevc_retail")
self.retail_only = self.config.get("retail_only")
self.hoster_fallback = self.config.get("hoster_fallback")
self.hosters = RssConfig("Hosters", configfile).get_section()
self.log_info = logging.info
self.log_error = logging.error
self.log_debug = logging.debug
self.scraper = scraper
self.filename = filename
self.db = RssDb(self.dbfile, 'rsscrawler')
self.quality = self.config.get("quality")
self.cdc = RssDb(self.dbfile, 'cdc')
self.last_set_sf = self.cdc.retrieve("SFSet-" + self.filename)
self.last_sha_sf = self.cdc.retrieve("SF-" + self.filename)
self.headers = {
'If-Modified-Since':
str(self.cdc.retrieve("SFHeaders-" + self.filename))
}
settings = [
"quality", "rejectlist", "regex", "hevc_retail", "retail_only",
"hoster_fallback"
]
self.settings = []
self.settings.append(self.rsscrawler.get("english"))
self.settings.append(self.rsscrawler.get("surround"))
self.settings.append(self.hosters)
for s in settings:
self.settings.append(self.config.get(s))
self.empty_list = False
if self.filename == 'SJ_Staffeln_Regex':
self.level = 3
elif self.filename == 'MB_Staffeln':
self.seasonssource = self.config.get('seasonssource').lower()
self.level = 2
elif self.filename == 'SJ_Serien_Regex':
self.level = 1
else:
self.level = 0
self.pattern = r'^(' + "|".join(
self.get_series_list(self.filename, self.level)).lower() + ')'
self.listtype = ""
self.day = 0
def __init__(self, configfile, dbfile, device, logging, scraper):
self.configfile = configfile
self.dbfile = dbfile
self.device = device
self.config = RssConfig(self._INTERNAL_NAME, self.configfile)
self.log_info = logging.info
self.log_error = logging.error
self.log_debug = logging.debug
self.scraper = scraper
self.db = RssDb(self.dbfile, 'rsscrawler')
def myjd_download(configfile, dbfile, device, title, subdir, links, password):
if device:
is_episode = re.findall(r'[\w.\s]*S\d{1,2}(E\d{1,2})[\w.\s]*', title)
if is_episode:
exists = check_failed_link_exists(links, configfile, device)
if exists:
broken_title = False
device = exists[0]
old_title = exists[3]
old_path = exists[4]
try:
new_episode = is_episode.pop()
except:
broken_title = True
try:
old_episode = re.findall(
r'[\w.\s]*(?!S\d{1,2})((?:E\d{1,2}-E\d{1,2})|(?:E\d{1,2}E\d{1,2})|(?:E\d{1,2}-\d{1,2})|(?:E\d{1,2}))[\w.\s]*',
old_title).pop()
combined_episodes = new_episode + '-' + old_episode
except:
broken_title = True
if not broken_title:
linkids = exists[1]
package_id = [exists[2]]
new_title = title.replace(new_episode, combined_episodes)
new_path = old_path.replace(old_title, new_title)
device = move_to_new_package(configfile, device, linkids,
package_id, new_title,
new_path)
RssDb(dbfile, 'crawldog').store(new_title, 'added')
RssDb(dbfile, 'crawldog').delete(old_title)
return device
device = download(configfile, dbfile, device, title, subdir, links,
password)
if device:
return device
return False
def get_to_decrypt(dbfile):
try:
to_decrypt = RssDb(dbfile, 'to_decrypt').retrieve_all_titles()
if to_decrypt:
packages = []
for package in to_decrypt:
title = package[0]
details = package[1].split('|')
url = details[0]
password = details[1]
packages.append({
'name': title,
'url': url,
'password': password
})
return packages
else:
return False
except:
return False
def crawler(configfile, dbfile, device, rsscrawler, log_level, log_file,
log_format):
sys.stdout = Unbuffered(sys.stdout)
logger = logging.getLogger('rsscrawler')
logger.setLevel(log_level)
console = logging.StreamHandler(stream=sys.stdout)
formatter = logging.Formatter(log_format)
console.setLevel(log_level)
logfile = logging.handlers.RotatingFileHandler(log_file)
logfile.setFormatter(formatter)
logfile.setLevel(logging.INFO)
logger.addHandler(logfile)
logger.addHandler(console)
if log_level == 10:
logfile_debug = logging.handlers.RotatingFileHandler(
log_file.replace("RSScrawler.log", "RSScrawler_DEBUG.log"))
logfile_debug.setFormatter(formatter)
logfile_debug.setLevel(10)
logger.addHandler(logfile_debug)
disable_request_warnings(InsecureRequestWarning)
log_debug = logger.debug
crawltimes = RssDb(dbfile, "crawltimes")
arguments = docopt(__doc__, version='RSScrawler')
if not arguments['--testlauf']:
while True:
try:
if not device or not is_device(device):
device = get_device(configfile)
scraper = check_url(configfile, dbfile)
start_time = time.time()
crawltimes.update_store("active", "True")
crawltimes.update_store("start_time", start_time * 1000)
log_debug("--------Alle Suchfunktion gestartet.--------")
if device:
device = ombi(configfile, dbfile, device, log_debug)
for task in search_pool(configfile, dbfile, device, logger,
scraper):
name = task._INTERNAL_NAME
try:
file = " - Liste: " + task.filename
except AttributeError:
file = ""
log_debug("-----------Suchfunktion (" + name + file +
") gestartet!-----------")
device = task.periodical_task()
log_debug("-----------Suchfunktion (" + name + file +
") ausgeführt!-----------")
end_time = time.time()
total_time = end_time - start_time
interval = int(rsscrawler.get('interval')) * 60
random_range = random.randrange(0, interval // 4)
wait = interval + random_range
next_start = end_time + wait
log_debug("-----Alle Suchfunktion ausgeführt (Dauer: " +
readable_time(total_time) +
")! Wartezeit bis zum nächsten Suchlauf: " +
readable_time(wait))
print(
time.strftime("%Y-%m-%d %H:%M:%S") +
u" - Alle Suchfunktion ausgeführt (Dauer: " +
readable_time(total_time) +
u")! Wartezeit bis zum nächsten Suchlauf: " +
readable_time(wait))
crawltimes.update_store("end_time", end_time * 1000)
crawltimes.update_store("total_time",
readable_time(total_time))
crawltimes.update_store("next_start", next_start * 1000)
crawltimes.update_store("active", "False")
time.sleep(wait)
log_debug("-------------Wartezeit verstrichen-------------")
except Exception:
traceback.print_exc()
time.sleep(10)
else:
try:
if not device or not is_device(device):
device = get_device(configfile)
scraper = check_url(configfile, dbfile)
start_time = time.time()
log_debug("--------Testlauf gestartet.--------")
if device:
device = ombi(configfile, dbfile, device, log_debug)
for task in search_pool(configfile, dbfile, device, logger,
scraper):
name = task._INTERNAL_NAME
try:
file = " - Liste: " + task.filename
except AttributeError:
file = ""
log_debug("-----------Suchfunktion (" + name + file +
") gestartet!-----------")
task.periodical_task()
log_debug("-----------Suchfunktion (" + name + file +
") ausgeführt!-----------")
end_time = time.time()
total_time = end_time - start_time
log_debug("---Testlauf ausgeführt (Dauer: " +
readable_time(total_time) + ")!---")
print(
time.strftime("%Y-%m-%d %H:%M:%S") +
u" - Testlauf ausgeführt (Dauer: " +
readable_time(total_time) + ")!")
except Exception:
traceback.print_exc()
time.sleep(10)
def main():
arguments = docopt(__doc__, version='RSScrawler')
print(u"┌──────────────────────────────────────────────┐")
print(u" RSScrawler " + version + " von RiX")
print(u" https://github.com/rix1337/RSScrawler")
print(u"└──────────────────────────────────────────────┘")
if arguments['--docker']:
configpath = "/config"
else:
configpath = files.config(arguments['--config'])
configfile = os.path.join(configpath, "RSScrawler.ini")
dbfile = os.path.join(configpath, "RSScrawler.db")
print(u"Nutze das Verzeichnis " + configpath + u" für Einstellungen/Logs")
log_level = logging.__dict__[arguments['--log-level']] if arguments[
'--log-level'] in logging.__dict__ else logging.INFO
log_file = os.path.join(configpath, 'RSScrawler.log')
log_format = '%(asctime)s - %(message)s'
hostnames = RssConfig('Hostnames', configfile)
def clean_up_hostname(host, string):
if '/' in string:
string = string.replace('https://', '').replace('http://', '')
string = re.findall(r'([a-z-.]*\.[a-z]*)', string)[0]
hostnames.save(host, string)
if re.match(r'.*[A-Z].*', string):
hostnames.save(host, string.lower())
if not string:
print(u'Kein Hostname gesetzt: ' + host.upper() +
' (Seite wird ignoriert!)')
return string
set_hostnames = {}
list_names = ['sj', 'dj', 'sf', 'mb', 'hw', 'hs', 'fx', 'nk', 'fc']
for name in list_names:
hostname = clean_up_hostname(name, hostnames.get(name))
if hostname:
set_hostnames[name] = hostname
if not arguments['--testlauf'] and not set_hostnames:
print(
u'Keine Hostnamen in der RSScrawler.ini gefunden! Beende RSScrawler!'
)
time.sleep(10)
sys.exit(1)
disable_request_warnings(InsecureRequestWarning)
if arguments['--testlauf']:
device = False
else:
if not os.path.exists(configfile):
if arguments['--docker']:
if arguments['--jd-user'] and arguments['--jd-pass']:
device = files.myjd_input(configfile, arguments['--port'],
arguments['--jd-user'],
arguments['--jd-pass'],
arguments['--jd-device'])
else:
device = False
else:
device = files.myjd_input(configfile, arguments['--port'],
arguments['--jd-user'],
arguments['--jd-pass'],
arguments['--jd-device'])
else:
rsscrawler = RssConfig('RSScrawler', configfile)
user = rsscrawler.get('myjd_user')
password = rsscrawler.get('myjd_pass')
if user and password:
device = get_device(configfile)
if not device:
device = get_if_one_device(user, password)
if device:
print(u"Gerätename " + device +
" automatisch ermittelt.")
rsscrawler.save('myjd_device', device)
device = get_device(configfile)
else:
device = files.myjd_input(configfile, arguments['--port'],
arguments['--jd-user'],
arguments['--jd-pass'],
arguments['--jd-device'])
if not device and not arguments['--testlauf']:
print(
u'My JDownloader Zugangsdaten fehlerhaft! Beende RSScrawler!')
time.sleep(10)
sys.exit(1)
else:
print(u"Erfolgreich mit My JDownloader verbunden. Gerätename: " +
device.name)
rsscrawler = RssConfig('RSScrawler', configfile)
port = int(rsscrawler.get("port"))
docker = False
if arguments['--docker']:
port = int('9090')
docker = True
elif arguments['--port']:
port = int(arguments['--port'])
if rsscrawler.get("prefix"):
prefix = '/' + rsscrawler.get("prefix")
else:
prefix = ''
local_address = 'http://' + common.check_ip() + ':' + str(port) + prefix
if not arguments['--docker']:
print(u'Der Webserver ist erreichbar unter ' + local_address)
if arguments['--keep-cdc']:
print(u"CDC-Tabelle nicht geleert!")
else:
RssDb(dbfile, 'cdc').reset()
p = multiprocessing.Process(target=web_server,
args=(port, docker, configfile, dbfile,
log_level, log_file, log_format, device))
p.start()
if not arguments['--testlauf']:
c = multiprocessing.Process(target=crawler,
args=(configfile, dbfile, device,
rsscrawler, log_level, log_file,
log_format))
c.start()
w = multiprocessing.Process(target=crawldog, args=(configfile, dbfile))
w.start()
print(u'Drücke [Strg] + [C] zum Beenden')
def signal_handler():
print(u'Beende RSScrawler...')
p.terminate()
c.terminate()
w.terminate()
sys.exit(0)
signal.signal(signal.SIGINT, signal_handler)
try:
while True:
signal.pause()
except AttributeError:
while True:
time.sleep(1)
else:
crawler(configfile, dbfile, device, rsscrawler, log_level, log_file,
log_format)
p.terminate()
sys.exit(0)
def crawldog(configfile, dbfile):
disable_request_warnings(InsecureRequestWarning)
crawljobs = RssConfig('Crawljobs', configfile)
autostart = crawljobs.get("autostart")
db = RssDb(dbfile, 'crawldog')
grabber_was_collecting = False
device = False
while True:
try:
if not device or not is_device(device):
device = get_device(configfile)
myjd_packages = get_info(configfile, device)
grabber_collecting = myjd_packages[2]
if grabber_was_collecting or grabber_collecting:
grabber_was_collecting = grabber_collecting
time.sleep(5)
else:
packages_in_downloader_decrypted = myjd_packages[4][0]
packages_in_linkgrabber_decrypted = myjd_packages[4][1]
offline_packages = myjd_packages[4][2]
encrypted_packages = myjd_packages[4][3]
try:
watched_titles = db.retrieve_all_titles()
except:
watched_titles = False
notify_list = []
if packages_in_downloader_decrypted or packages_in_linkgrabber_decrypted or offline_packages or encrypted_packages:
if watched_titles:
for title in watched_titles:
if packages_in_downloader_decrypted:
for package in packages_in_downloader_decrypted:
if title[0] in package[
'name'] or title[0].replace(
".", " ") in package['name']:
check = hoster_check(
configfile, device, [package],
title[0], [0])
device = check[0]
if device:
db.delete(title[0])
if packages_in_linkgrabber_decrypted:
for package in packages_in_linkgrabber_decrypted:
if title[0] in package[
'name'] or title[0].replace(
".", " ") in package['name']:
check = hoster_check(
configfile, device, [package],
title[0], [0])
device = check[0]
episode = RssDb(
dbfile,
'episode_remover').retrieve(
title[0])
if episode:
filenames = package['filenames']
if len(filenames) > 1:
fname_episodes = []
for fname in filenames:
try:
if re.match(
r'.*S\d{1,3}E\d{1,3}.*',
fname,
flags=re.
IGNORECASE):
fname = re.findall(
r'S\d{1,3}E(\d{1,3})',
fname,
flags=re.
IGNORECASE
).pop()
else:
fname = fname.replace(
"hddl8",
"").replace(
"dd51", ""
).replace(
"264", ""
).replace(
"265", "")
except:
fname = fname.replace(
"hddl8",
"").replace(
"dd51",
"").replace(
"264", ""
).replace(
"265", "")
fname_episode = "".join(
re.findall(
r'\d+',
fname.split(
".part")[0]))
try:
fname_episodes.append(
str(
int(fname_episode
)))
except:
pass
replacer = longest_substr(
fname_episodes)
new_fname_episodes = []
for new_ep_fname in fname_episodes:
try:
new_fname_episodes.append(
str(
int(
new_ep_fname
.replace(
replacer,
""))))
except:
pass
replacer = longest_substr(
new_fname_episodes)
newer_fname_episodes = []
for new_ep_fname in new_fname_episodes:
try:
newer_fname_episodes.append(
str(
int(
re.sub(
replacer,
"",
new_ep_fname,
1))))
except:
pass
replacer = longest_substr(
newer_fname_episodes)
even_newer_fname_episodes = []
for newer_ep_fname in newer_fname_episodes:
try:
even_newer_fname_episodes.append(
str(
int(
re.sub(
replacer,
"",
newer_ep_fname,
1))))
except:
pass
if even_newer_fname_episodes:
fname_episodes = even_newer_fname_episodes
elif newer_fname_episodes:
fname_episodes = newer_fname_episodes
elif new_fname_episodes:
fname_episodes = new_fname_episodes
delete_linkids = []
pos = 0
for delete_id in package[
'linkids']:
if str(episode) != str(
fname_episodes[pos]
):
delete_linkids.append(
delete_id)
pos += 1
if delete_linkids:
delete_uuids = [
package['uuid']
]
RssDb(
dbfile,
'episode_remover'
).delete(title[0])
device = remove_from_linkgrabber(
configfile, device,
delete_linkids,
delete_uuids)
if autostart:
device = move_to_downloads(
configfile, device,
package['linkids'],
[package['uuid']])
if device:
db.delete(title[0])
if offline_packages:
for package in offline_packages:
if title[0] in package[
'name'] or title[0].replace(
".", " ") in package['name']:
notify_list.append("[Offline] - " +
title[0])
print((u"[Offline] - " + title[0]))
db.delete(title[0])
if encrypted_packages:
for package in encrypted_packages:
if title[0] in package[
'name'] or title[0].replace(
".", " ") in package['name']:
if title[1] == 'added':
if retry_decrypt(
configfile, dbfile, device,
package['linkids'],
[package['uuid']],
package['urls']):
db.delete(title[0])
db.store(title[0], 'retried')
else:
add_decrypt(
package['name'],
package['url'], "", dbfile)
device = remove_from_linkgrabber(
configfile, device,
package['linkids'],
[package['uuid']])
notify_list.append(
"[Click'n'Load notwendig] - " +
title[0])
print(
u"[Click'n'Load notwendig] - "
+ title[0])
db.delete(title[0])
else:
if not grabber_collecting:
db.reset()
if notify_list:
notify(notify_list, configfile)
time.sleep(30)
except Exception:
traceback.print_exc()
time.sleep(30)
def ombi(configfile, dbfile, device, log_debug):
db = RssDb(dbfile, 'Ombi')
config = RssConfig('Ombi', configfile)
url = config.get('url')
api = config.get('api')
if not url or not api:
return device
english = RssConfig('RSScrawler', configfile).get('english')
try:
requested_movies = requests.get(url + '/api/v1/Request/movie',
headers={'ApiKey': api})
requested_movies = json.loads(requested_movies.text)
requested_shows = requests.get(url + '/api/v1/Request/tv',
headers={'ApiKey': api})
requested_shows = json.loads(requested_shows.text)
except:
log_debug("Ombi ist nicht erreichbar!")
return False
scraper = False
for r in requested_movies:
if bool(r.get("approved")):
if not bool(r.get("available")):
imdb_id = r.get("imdbId")
if not db.retrieve('movie_' + str(imdb_id)) == 'added':
response = imdb_movie(imdb_id, configfile, dbfile, scraper)
title = response[0]
if title:
scraper = response[1]
best_result = search.best_result_bl(
title, configfile, dbfile)
print(u"Film: " + title + u" durch Ombi hinzugefügt.")
if best_result:
search.download_bl(best_result, device, configfile,
dbfile)
if english:
title = r.get('title')
best_result = search.best_result_bl(
title, configfile, dbfile)
print(u"Film: " + title +
u"durch Ombi hinzugefügt.")
if best_result:
search.download_bl(best_result, device,
configfile, dbfile)
db.store('movie_' + str(imdb_id), 'added')
else:
log_debug("Titel für IMDB-ID nicht abrufbar: " +
imdb_id)
for r in requested_shows:
imdb_id = r.get("imdbId")
infos = None
child_requests = r.get("childRequests")
for cr in child_requests:
if bool(cr.get("approved")):
if not bool(cr.get("available")):
details = cr.get("seasonRequests")
for season in details:
sn = season.get("seasonNumber")
eps = []
episodes = season.get("episodes")
for episode in episodes:
if not bool(episode.get("available")):
enr = episode.get("episodeNumber")
s = str(sn)
if len(s) == 1:
s = "0" + s
s = "S" + s
e = str(enr)
if len(e) == 1:
e = "0" + e
se = s + "E" + e
if not db.retrieve('show_' + str(imdb_id) +
'_' + se) == 'added':
eps.append(enr)
if eps:
if not infos:
infos = imdb_show(imdb_id, configfile, dbfile,
scraper)
if infos:
title = infos[0]
all_eps = infos[1]
scraper = infos[2]
check_sn = False
if all_eps:
check_sn = all_eps.get(sn)
if check_sn:
sn_length = len(eps)
check_sn_length = len(check_sn)
if check_sn_length > sn_length:
for ep in eps:
e = str(ep)
if len(e) == 1:
e = "0" + e
se = s + "E" + e
payload = search.best_result_sj(
title, configfile, dbfile)
if payload:
payload = decode_base64(
payload).split("|")
payload = encode_base64(
payload[0] + "|" +
payload[1] + "|" + se)
added_episode = search.download_sj(
payload, configfile,
dbfile)
if not added_episode:
payload = decode_base64(
payload).split("|")
payload = encode_base64(
payload[0] + "|" +
payload[1] + "|" + s)
add_season = search.download_sj(
payload, configfile,
dbfile)
for e in eps:
e = str(e)
if len(e) == 1:
e = "0" + e
se = s + "E" + e
db.store(
'show_' +
str(imdb_id) +
'_' + se, 'added')
if not add_season:
log_debug(
u"Konnte kein Release für "
+ title + " " +
se + "finden.")
break
db.store(
'show_' + str(imdb_id) + '_' +
se, 'added')
else:
payload = search.best_result_sj(
title, configfile, dbfile)
if payload:
payload = decode_base64(
payload).split("|")
payload = encode_base64(
payload[0] + "|" + payload[1] +
"|" + s)
search.download_sj(
payload, configfile, dbfile)
for ep in eps:
e = str(ep)
if len(e) == 1:
e = "0" + e
se = s + "E" + e
db.store(
'show_' + str(imdb_id) + '_' +
se, 'added')
print(u"Serie/Staffel/Episode: " + title +
u" durch Ombi hinzugefügt.")
return device
def check_url(configfile, dbfile, scraper=False):
hostnames = RssConfig('Hostnames', configfile)
sj = hostnames.get('sj')
dj = hostnames.get('dj')
sf = hostnames.get('sf')
mb = hostnames.get('mb')
hw = hostnames.get('hw')
hs = hostnames.get('hs')
fx = hostnames.get('fx')
nk = hostnames.get('nk')
dd = hostnames.get('dd')
fc = hostnames.get('fc')
if not scraper:
scraper = cloudscraper.create_scraper()
sj_url = 'https://' + sj
dj_url = 'https://' + sj
sf_url = 'https://' + sf
mb_url = 'https://' + mb
hw_url = 'https://' + hw
fx_url = 'https://' + fx
hs_url = 'https://' + hs + '/collection/neuerscheinungen/'
nk_url = 'https://' + nk
dd_url = 'https://' + dd
fc_url = 'https://' + fc
sj_blocked_proxy = False
dj_blocked_proxy = False
sf_blocked_proxy = False
mb_blocked_proxy = False
hw_blocked_proxy = False
fx_blocked_proxy = False
hs_blocked_proxy = False
nk_blocked_proxy = False
dd_blocked_proxy = False
fc_blocked_proxy = False
sj_blocked = False
dj_blocked = False
sf_blocked = False
mb_blocked = False
hw_blocked = False
fx_blocked = False
hs_blocked = False
nk_blocked = False
dd_blocked = False
fc_blocked = False
db = RssDb(dbfile, 'proxystatus')
db.delete("SJ")
db.delete("DJ")
db.delete("SF")
db.delete("MB")
db.delete("HW")
db.delete("FX")
db.delete("HS")
db.delete("NK")
db.delete("DD")
db.delete("FC")
db_normal = RssDb(dbfile, 'normalstatus')
db_normal.delete("SJ")
db_normal.delete("DJ")
db_normal.delete("SF")
db_normal.delete("MB")
db_normal.delete("HW")
db_normal.delete("FX")
db_normal.delete("HS")
db_normal.delete("NK")
db_normal.delete("DD")
db_normal.delete("FC")
proxy = RssConfig('RSScrawler', configfile).get('proxy')
fallback = RssConfig('RSScrawler', configfile).get('fallback')
if proxy:
proxies = {'http': proxy, 'https': proxy}
if not sj:
db.store("SJ", "Blocked")
else:
try:
if "block." in str(
scraper.get(
sj_url,
proxies=proxies,
timeout=30,
allow_redirects=False).headers.get("location")):
sj_blocked_proxy = True
else:
db.delete("SJ")
except:
sj_blocked_proxy = True
if sj_blocked_proxy:
print(
u"Der Zugriff auf SJ ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("SJ", "Blocked")
scraper = cloudscraper.create_scraper()
if not dj:
db.store("DJ", "Blocked")
else:
try:
if "block." in str(
scraper.get(
dj_url,
proxies=proxies,
timeout=30,
allow_redirects=False).headers.get("location")):
dj_blocked_proxy = True
else:
db.delete("DJ")
except:
dj_blocked_proxy = True
if dj_blocked_proxy:
print(
u"Der Zugriff auf DJ ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("DJ", "Blocked")
scraper = cloudscraper.create_scraper()
if not sf:
db.store("SF", "Blocked")
else:
try:
if "block." in str(
scraper.get(
sf_url,
proxies=proxies,
timeout=30,
allow_redirects=False).headers.get("location")):
sf_blocked_proxy = True
else:
db.delete("SF")
except:
sf_blocked_proxy = True
if sf_blocked_proxy:
print(
u"Der Zugriff auf SF ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("SF", "Blocked")
scraper = cloudscraper.create_scraper()
if not mb:
db.store("MB", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(mb_url,
proxies=proxies,
timeout=30,
allow_redirects=False)):
mb_blocked_proxy = True
else:
db.delete("MB")
except:
mb_blocked_proxy = True
if mb_blocked_proxy:
print(
u"Der Zugriff auf MB ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("MB", "Blocked")
scraper = cloudscraper.create_scraper()
if not hw:
db.store("HW", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(hw_url,
proxies=proxies,
timeout=30,
allow_redirects=False)):
hw_blocked_proxy = True
else:
db.delete("HW")
except:
hw_blocked_proxy = True
if hw_blocked_proxy:
print(
u"Der Zugriff auf HW ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("HW", "Blocked")
scraper = cloudscraper.create_scraper()
if not fx:
db.store("FX", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(fx_url,
proxies=proxies,
timeout=30,
allow_redirects=False)):
fx_blocked_proxy = True
else:
db.delete("FX")
except:
fx_blocked_proxy = True
session = requests.session()
session.headers = scraper.headers
session.cookies = scraper.cookies
session.verify = False
if "<Response [200]>" in str(
session.get(fx_url,
proxies=proxies,
timeout=30,
allow_redirects=False)):
fx_blocked_proxy = False
if fx_blocked_proxy:
print(
u"Der Zugriff auf FX ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("FX", "Blocked")
scraper = cloudscraper.create_scraper()
if not hs:
db.store("HS", "Blocked")
else:
try:
if "200" not in str(
scraper.get(hs_url, timeout=30,
allow_redirects=False).status_code):
hs_blocked_proxy = True
else:
db.delete("HS")
except:
hs_blocked_proxy = True
if hs_blocked_proxy:
print(
u"Der Zugriff auf HS ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("HS", "Blocked")
scraper = cloudscraper.create_scraper()
if not nk:
db.store("NK", "Blocked")
else:
try:
if "200" not in str(
scraper.get(nk_url, timeout=30,
allow_redirects=False).status_code):
nk_blocked_proxy = True
else:
db.delete("NK")
except:
nk_blocked_proxy = True
if nk_blocked_proxy:
print(
u"Der Zugriff auf NK ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("NK", "Blocked")
scraper = cloudscraper.create_scraper()
if not dd:
db.store("DD", "Blocked")
else:
try:
if "200" not in str(
scraper.get(dd_url, timeout=30,
allow_redirects=False).status_code):
dd_blocked_proxy = True
else:
db.delete("DD")
except:
dd_blocked_proxy = True
if dd_blocked_proxy:
print(
u"Der Zugriff auf DD ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("DD", "Blocked")
scraper = cloudscraper.create_scraper()
if not fc:
db.store("FC", "Blocked")
else:
try:
if "200" not in str(
scraper.get(fc_url, timeout=30).status_code):
fc_blocked_proxy = True
else:
db.delete("FC")
except:
fc_blocked_proxy = True
if fc_blocked_proxy:
print(
u"Der Zugriff auf FC ist mit der aktuellen Proxy-IP nicht möglich!"
)
db.store("FC", "Blocked")
scraper = cloudscraper.create_scraper()
if not proxy or (proxy and sj_blocked_proxy and fallback):
if not sj:
db.store("SJ", "Blocked")
else:
try:
if "block." in str(
scraper.get(
sj_url, timeout=30,
allow_redirects=False).headers.get("location")):
sj_blocked = True
except:
sj_blocked = True
if sj_blocked:
db_normal.store("SJ", "Blocked")
print(
u"Der Zugriff auf SJ ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and dj_blocked_proxy and fallback):
if not dj:
db.store("DJ", "Blocked")
else:
try:
if "block." in str(
scraper.get(
dj_url, timeout=30,
allow_redirects=False).headers.get("location")):
dj_blocked = True
except:
dj_blocked = True
if dj_blocked:
db_normal.store("DJ", "Blocked")
print(
u"Der Zugriff auf DJ ist mit der aktuellen IP nicht möglich!"
)
if not sf:
db.store("SF", "Blocked")
else:
try:
if "block." in str(
scraper.get(
sf_url, timeout=30,
allow_redirects=False).headers.get("location")):
sf_blocked = True
except:
sf_blocked = True
if sf_blocked:
db_normal.store("SF", "Blocked")
print(
u"Der Zugriff auf SF ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and mb_blocked_proxy and fallback):
if not mb:
db.store("MB", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(mb_url, timeout=30,
allow_redirects=False)):
mb_blocked = True
except:
mb_blocked = True
if mb_blocked:
db_normal.store("MB", "Blocked")
print(
u"Der Zugriff auf MB ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and hw_blocked_proxy and fallback):
if not hw:
db.store("HW", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(hw_url, timeout=30,
allow_redirects=False)):
hw_blocked = True
except:
hw_blocked = True
if hw_blocked:
db_normal.store("HW", "Blocked")
print(
u"Der Zugriff auf HW ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and fx_blocked_proxy and fallback):
if not fx:
db.store("FX", "Blocked")
else:
try:
if "<Response [403]>" in str(
scraper.get(fx_url, timeout=30,
allow_redirects=False)):
fx_blocked = True
except:
fx_blocked = True
session = requests.session()
session.headers = scraper.headers
session.cookies = scraper.cookies
session.verify = False
if "<Response [200]>" in str(
session.get(fx_url, timeout=30,
allow_redirects=False)):
fx_blocked = False
if fx_blocked:
db_normal.store("FX", "Blocked")
print(
u"Der Zugriff auf FX ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and hs_blocked_proxy and fallback):
if not hs:
db.store("HS", "Blocked")
else:
try:
if "200" not in str(
scraper.get(hs_url, timeout=30,
allow_redirects=False).status_code):
hs_blocked = True
except:
hs_blocked = True
if hs_blocked:
db_normal.store("HS", "Blocked")
print(
u"Der Zugriff auf HS ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and nk_blocked_proxy and fallback):
if not nk:
db.store("NK", "Blocked")
else:
try:
if "200" not in str(
scraper.get(nk_url, timeout=30,
allow_redirects=False).status_code):
nk_blocked = True
except:
nk_blocked = True
if nk_blocked:
db_normal.store("NK", "Blocked")
print(
u"Der Zugriff auf NK ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and dd_blocked_proxy and fallback):
if not dd:
db.store("DD", "Blocked")
else:
try:
if "200" not in str(
scraper.get(dd_url, timeout=30,
allow_redirects=False).status_code):
dd_blocked = True
except:
dd_blocked = True
if dd_blocked:
db_normal.store("DD", "Blocked")
print(
u"Der Zugriff auf DD ist mit der aktuellen IP nicht möglich!"
)
if not proxy or (proxy and fc_blocked_proxy and fallback):
if not fc:
db.store("FC", "Blocked")
else:
try:
if "200" not in str(
scraper.get(fc_url, timeout=30).status_code):
fc_blocked = True
except:
fc_blocked = True
if fc_blocked:
db_normal.store("FC", "Blocked")
print(
u"Der Zugriff auf FC ist mit der aktuellen IP nicht möglich!"
)
return scraper
def get_url_headers(url, configfile, dbfile, headers, scraper=False):
config = RssConfig('RSScrawler', configfile)
proxy = config.get('proxy')
if not scraper:
scraper = cloudscraper.create_scraper()
db = RssDb(dbfile, 'proxystatus')
db_normal = RssDb(dbfile, 'normalstatus')
site = check_is_site(url, configfile)
if proxy:
try:
if site and "SJ" in site:
if db.retrieve("SJ"):
if config.get("fallback") and not db_normal.retrieve("SJ"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "DJ" in site:
if db.retrieve("DJ"):
if config.get("fallback") and not db_normal.retrieve("DJ"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "SF" in site:
if db.retrieve("SF"):
if config.get("fallback") and not db_normal.retrieve("SF"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "MB" in site:
if db.retrieve("MB"):
if config.get("fallback") and not db_normal.retrieve("MB"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "HW" in site:
if db.retrieve("HW"):
if config.get("fallback") and not db_normal.retrieve("HW"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "FX" in site:
if db.retrieve("FX"):
if config.get("fallback") and not db_normal.retrieve("FX"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "HS" in site:
if db.retrieve("HS"):
if config.get("fallback") and not db_normal.retrieve("HS"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "NK" in site:
if db.retrieve("NK"):
if config.get("fallback") and not db_normal.retrieve("NK"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "DD" in site:
if db.retrieve("DD"):
if config.get("fallback") and not db_normal.retrieve("DD"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
elif site and "FC" in site:
if db.retrieve("FC"):
if config.get("fallback") and not db_normal.retrieve("FC"):
return [
scraper.get(url, headers=headers, timeout=30),
scraper
]
else:
return ["", scraper]
proxies = {'http': proxy, 'https': proxy}
response = scraper.get(url,
headers=headers,
proxies=proxies,
timeout=30)
return [response, scraper]
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ["", scraper]
else:
try:
if site and "SJ" in site and db_normal.retrieve("SJ"):
return ["", scraper]
elif site and "DJ" in site and db_normal.retrieve("DJ"):
return ["", scraper]
elif site and "SF" in site and db_normal.retrieve("SF"):
return ["", scraper]
elif site and "MB" in site and db_normal.retrieve("MB"):
return ["", scraper]
elif site and "HW" in site and db_normal.retrieve("HW"):
return ["", scraper]
elif site and "FX" in site and db_normal.retrieve("FX"):
return ["", scraper]
elif site and "HS" in site and db_normal.retrieve("HS"):
return ["", scraper]
elif site and "NK" in site and db_normal.retrieve("NK"):
return ["", scraper]
elif site and "DD" in site and db_normal.retrieve("DD"):
return ["", scraper]
elif site and "FC" in site and db_normal.retrieve("FC"):
return ["", scraper]
response = scraper.get(url, headers=headers, timeout=30)
return [response, scraper]
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ["", scraper]
class DD:
_INTERNAL_NAME = 'DD'
def __init__(self, configfile, dbfile, device, logging, scraper):
self.configfile = configfile
self.dbfile = dbfile
self.device = device
self.config = RssConfig(self._INTERNAL_NAME, self.configfile)
self.log_info = logging.info
self.log_error = logging.error
self.log_debug = logging.debug
self.scraper = scraper
self.db = RssDb(self.dbfile, 'rsscrawler')
def periodical_task(self):
feeds = self.config.get("feeds")
if feeds:
added_items = []
feeds = feeds.replace(" ", "").split(',')
for feed in feeds:
feed = feedparser.parse(
get_url(feed, self.configfile, self.dbfile, self.scraper))
for post in feed.entries:
key = post.title.replace(" ", ".")
epoch = datetime(1970, 1, 1)
current_epoch = int(time())
published_format = "%Y-%m-%d %H:%M:%S+00:00"
published_timestamp = str(parser.parse(post.published))
published_epoch = int((datetime.strptime(
published_timestamp, published_format) -
epoch).total_seconds())
if (current_epoch - 1800) > published_epoch:
link_pool = post.summary
unicode_links = re.findall(r'(http.*)', link_pool)
links = []
for link in unicode_links:
if check_hoster(link, self.configfile):
links.append(str(link))
if self.config.get("hoster_fallback") and not links:
for link in unicode_links:
links.append(str(link))
storage = self.db.retrieve_all(key)
if not links:
if 'added' not in storage and 'notdl' not in storage:
wrong_hoster = '[DD/Hoster fehlt] - ' + key
if 'wrong_hoster' not in storage:
self.log_info(wrong_hoster)
self.db.store(key, 'wrong_hoster')
notify([wrong_hoster], self.configfile)
else:
self.log_debug(wrong_hoster)
elif 'added' in storage:
self.log_debug(
"%s - Release ignoriert (bereits gefunden)" %
key)
else:
self.device = myjd_download(
self.configfile, self.dbfile, self.device, key,
"RSScrawler", links, "")
if self.device:
self.db.store(key, 'added')
log_entry = '[Englisch] - ' + key + ' - [DD]'
self.log_info(log_entry)
notify([log_entry], self.configfile)
added_items.append(log_entry)
else:
self.log_debug(
"%s - Releasezeitpunkt weniger als 30 Minuten in der Vergangenheit - wird ignoriert."
% key)
else:
self.log_debug("Liste ist leer. Stoppe Suche für DD!")
return self.device
def download_sj(payload, configfile, dbfile):
hostnames = RssConfig('Hostnames', configfile)
sj = hostnames.get('sj')
payload = decode_base64(payload).split("|")
href = payload[0]
title = payload[1]
special = payload[2].strip().replace("None", "")
series_url = 'https://' + sj + href
series_info = get_url(series_url, configfile, dbfile)
series_id = re.findall(r'data-mediaid="(.*?)"', series_info)[0]
api_url = 'https://' + sj + '/api/media/' + series_id + '/releases'
releases = get_url(api_url, configfile, dbfile)
seasons = json.loads(releases)
listen = ["SJ_Serien", "MB_Staffeln"]
for liste in listen:
cont = ListDb(dbfile, liste).retrieve()
list_title = sanitize(title)
if not cont:
cont = ""
if list_title not in cont:
ListDb(dbfile, liste).store(list_title)
config = RssConfig('SJ', configfile)
english_ok = RssConfig('RSScrawler', configfile).get("english")
quality = config.get('quality')
ignore = config.get('rejectlist')
result_seasons = {}
result_episodes = {}
for season in seasons:
releases = seasons[season]
for release in releases['items']:
name = release['name'].encode('ascii',
errors='ignore').decode('utf-8')
hosters = release['hoster']
try:
valid = bool(release['resolution'] == quality)
except:
valid = re.match(re.compile(r'.*' + quality + r'.*'), name)
if valid and special:
valid = bool("." + special.lower() + "." in name.lower())
if valid and not english_ok:
valid = bool(".german." in name.lower())
if valid:
valid = False
for hoster in hosters:
if hoster and check_hoster(
hoster,
configfile) or config.get("hoster_fallback"):
valid = True
if valid:
try:
ep = release['episode']
if ep:
existing = result_episodes.get(season)
if existing:
for e in existing:
if e == ep:
if rate(name, ignore) > rate(
existing[e], ignore):
existing.update({ep: name})
else:
existing = {ep: name}
result_episodes.update({season: existing})
continue
except:
pass
existing = result_seasons.get(season)
dont = False
if existing:
if rate(name, ignore) < rate(existing, ignore):
dont = True
if not dont:
result_seasons.update({season: name})
try:
if result_seasons[season] and result_episodes[season]:
del result_episodes[season]
except:
pass
success = False
try:
if result_seasons[season]:
success = True
except:
try:
if result_episodes[season]:
success = True
except:
pass
if success:
logger.debug(u"Websuche erfolgreich für " + title + " - " + season)
else:
for release in releases['items']:
name = release['name'].encode('ascii',
errors='ignore').decode('utf-8')
hosters = release['hoster']
valid = True
if valid and special:
valid = bool("." + special.lower() + "." in name.lower())
if valid and not english_ok:
valid = bool(".german." in name.lower())
if valid:
valid = False
for hoster in hosters:
if hoster and check_hoster(
hoster,
configfile) or config.get("hoster_fallback"):
valid = True
if valid:
try:
ep = release['episode']
if ep:
existing = result_episodes.get(season)
if existing:
for e in existing:
if e == ep:
if rate(name, ignore) > rate(
existing[e], ignore):
existing.update({ep: name})
else:
existing = {ep: name}
result_episodes.update({season: existing})
continue
except:
pass
existing = result_seasons.get(season)
dont = False
if existing:
if rate(name, ignore) < rate(existing, ignore):
dont = True
if not dont:
result_seasons.update({season: name})
try:
if result_seasons[season] and result_episodes[season]:
del result_episodes[season]
except:
pass
logger.debug(u"Websuche erfolgreich für " + title + " - " + season)
matches = []
for season in result_seasons:
matches.append(result_seasons[season])
for season in result_episodes:
for episode in result_episodes[season]:
matches.append(result_episodes[season][episode])
notify_array = []
for title in matches:
db = RssDb(dbfile, 'rsscrawler')
if add_decrypt(title, series_url, sj, dbfile):
db.store(title, 'added')
log_entry = u'[Suche/Serie] - ' + title + ' - [SJ]'
logger.info(log_entry)
notify_array.append(log_entry)
notify(notify_array, configfile)
if not matches:
return False
return matches
def download_bl(payload, device, configfile, dbfile):
hostnames = RssConfig('Hostnames', configfile)
mb = hostnames.get('mb')
nk = hostnames.get('nk')
fc = hostnames.get('fc').replace('www.', '').split('.')[0]
payload = decode_base64(payload).split("|")
link = payload[0]
password = payload[1]
url = get_url(link, configfile, dbfile)
if not url or "NinjaFirewall 429" in url:
return False
config = RssConfig('MB', configfile)
db = RssDb(dbfile, 'rsscrawler')
soup = BeautifulSoup(url, 'lxml')
site = check_is_site(link, configfile)
if not site:
return False
else:
if "MB" in site:
if not fc:
print(
u"FC Hostname nicht gesetzt. MB kann keine Links finden!")
return False
key = soup.find("span", {"class": "fn"}).text
hosters = soup.find_all("a", href=re.compile(fc))
url_hosters = []
for hoster in hosters:
dl = hoster["href"]
hoster = hoster.text
url_hosters.append([dl, hoster])
elif "HW" in site:
if not fc:
print(
u"FC Hostname nicht gesetzt. MB kann keine Links finden!")
return False
key = re.findall(r'Permanent Link: (.*?)"', str(soup)).pop()
hosters = soup.find_all("a", href=re.compile(fc))
url_hosters = []
for hoster in hosters:
dl = hoster["href"]
hoster = hoster.text
url_hosters.append([dl, hoster])
elif "HS" in site:
download = soup.find("div", {"class": "entry-content"})
key = soup.find("h2", {"class": "entry-title"}).text
url_hosters = re.findall(r'href="([^"\'>]*)".+?(.+?)<',
str(download))
elif "NK" in site:
key = soup.find("span", {"class": "subtitle"}).text
url_hosters = []
hosters = soup.find_all("a", href=re.compile("/go/"))
for hoster in hosters:
url_hosters.append(
['https://' + nk + hoster["href"], hoster.text])
elif "FX" in site:
key = payload[1]
password = payload[2]
else:
return False
links = {}
if "MB" in site or "HW" in site or "HS" in site or "NK" in site:
for url_hoster in reversed(url_hosters):
try:
if mb.split('.')[0] not in url_hoster[
0] and "https://goo.gl/" not in url_hoster[0]:
link_hoster = url_hoster[1].lower().replace(
'target="_blank">', '').replace(" ", "-")
if check_hoster(link_hoster, configfile):
links[link_hoster] = url_hoster[0]
except:
pass
if config.get("hoster_fallback") and not links:
for url_hoster in reversed(url_hosters):
if mb.split('.')[0] not in url_hoster[
0] and "https://goo.gl/" not in url_hoster[0]:
link_hoster = url_hoster[1].lower().replace(
'target="_blank">', '').replace(" ", "-")
links[link_hoster] = url_hoster[0]
download_links = list(links.values())
elif "FX" in site:
download_links = fx_download_links(url, key, configfile)
englisch = False
if "*englisch" in key.lower() or "*english" in key.lower():
key = key.replace('*ENGLISCH',
'').replace("*Englisch", "").replace(
"*ENGLISH", "").replace("*English",
"").replace("*", "")
englisch = True
staffel = re.search(r"s\d{1,2}(-s\d{1,2}|-\d{1,2}|\.)", key.lower())
if config.get('enforcedl') and '.dl.' not in key.lower():
fail = False
get_imdb_url = url
key_regex = r'<title>' + \
re.escape(
key) + r'.*?<\/title>\n.*?<link>(?:(?:.*?\n){1,25}).*?[mM][kK][vV].*?(?:|href=.?http(?:|s):\/\/(?:|www\.)imdb\.com\/title\/(tt[0-9]{7,9}).*?)[iI][mM][dD][bB].*?(?!\d(?:\.|\,)\d)(?:.|.*?)<\/a>'
imdb_id = re.findall(key_regex, get_imdb_url)
if len(imdb_id) > 0:
if not imdb_id[0]:
fail = True
else:
imdb_id = imdb_id[0]
else:
fail = True
if fail:
try:
search_title = re.findall(
r"(.*?)(?:\.(?:(?:19|20)\d{2})|\.German|\.\d{3,4}p|\.S(?:\d{1,3})\.)",
key)[0].replace(".", "+")
search_url = "http://www.imdb.com/find?q=" + search_title
search_page = get_url(search_url, configfile, dbfile)
search_results = re.findall(
r'<td class="result_text"> <a href="\/title\/(tt[0-9]{7,9})\/\?ref_=fn_al_tt_\d" >(.*?)<\/a>.*? \((\d{4})\)..(.{9})',
search_page)
total_results = len(search_results)
except:
return False
if staffel:
try:
imdb_id = search_results[0][0]
except:
imdb_id = False
else:
no_series = False
while total_results > 0:
attempt = 0
for result in search_results:
if result[3] == "TV Series":
no_series = False
total_results -= 1
attempt += 1
else:
no_series = True
imdb_id = search_results[attempt][0]
total_results = 0
break
if no_series is False:
logger.debug(
"%s - Keine passende Film-IMDB-Seite gefunden" %
key)
if staffel:
filename = 'MB_Staffeln'
else:
filename = 'MB_Filme'
scraper = cloudscraper.create_scraper()
blog = BL(configfile,
dbfile,
device,
logging,
scraper,
filename=filename)
if not imdb_id:
if not blog.dual_download(key, password):
logger.debug("%s - Kein zweisprachiges Release gefunden." %
key)
else:
if isinstance(imdb_id, list):
imdb_id = imdb_id.pop()
imdb_url = "http://www.imdb.com/title/" + imdb_id
details = get_url(imdb_url, configfile, dbfile)
if not details:
logger.debug("%s - Originalsprache nicht ermittelbar" %
key)
original_language = re.findall(
r"Language:<\/h4>\n.*?\n.*?url'>(.*?)<\/a>", details)
if original_language:
original_language = original_language[0]
if original_language == "German":
logger.debug(
"%s - Originalsprache ist Deutsch. Breche Suche nach zweisprachigem Release ab!"
% key)
else:
if not blog.dual_download(key, password) and not englisch:
logger.debug(
"%s - Kein zweisprachiges Release gefunden!" % key)
if download_links:
if staffel:
if myjd_download(configfile, dbfile, device, key, "RSScrawler",
download_links, password):
db.store(
key.replace(".COMPLETE", "").replace(".Complete", ""),
'notdl' if config.get('enforcedl')
and '.dl.' not in key.lower() else 'added')
log_entry = '[Suche/Staffel] - ' + key.replace(
".COMPLETE", "").replace(".Complete",
"") + ' - [' + site + ']'
logger.info(log_entry)
notify([log_entry], configfile)
return True
elif '.3d.' in key.lower():
retail = False
if config.get('cutoff') and '.COMPLETE.' not in key.lower():
if config.get('enforcedl'):
if is_retail(key, '2', dbfile):
retail = True
if myjd_download(configfile, dbfile, device, key,
"RSScrawler/3Dcrawler", download_links,
password):
db.store(
key, 'notdl' if config.get('enforcedl')
and '.dl.' not in key.lower() else 'added')
log_entry = '[Suche/Film' + (
'/Retail' if retail else
"") + '/3D] - ' + key + ' - [' + site + ']'
logger.info(log_entry)
notify([log_entry], configfile)
return True
else:
retail = False
if config.get('cutoff') and '.COMPLETE.' not in key.lower():
if config.get('enforcedl'):
if is_retail(key, '1', dbfile):
retail = True
else:
if is_retail(key, '0', dbfile):
retail = True
if myjd_download(configfile, dbfile, device, key, "RSScrawler",
download_links, password):
db.store(
key, 'notdl' if config.get('enforcedl')
and '.dl.' not in key.lower() else 'added')
log_entry = '[Suche/Film' + (
'/Englisch' if englisch and not retail else
'') + ('/Englisch/Retail' if englisch and retail else
'') + ('/Retail' if not englisch and retail else
'') + '] - ' + key + ' - [' + site + ']'
logger.info(log_entry)
notify([log_entry], configfile)
return [key]
else:
return False
def add_decrypt(title, link, password, dbfile):
try:
RssDb(dbfile, 'to_decrypt').store(title, link + '|' + password)
return True
except:
return False
def remove_decrypt(title, dbfile):
try:
RssDb(dbfile, 'to_decrypt').delete(title)
return True
except:
return False
class SF:
def __init__(self, configfile, dbfile, device, logging, scraper, filename,
internal_name):
self._INTERNAL_NAME = internal_name
self.configfile = configfile
self.dbfile = dbfile
self.device = device
self.hostnames = RssConfig('Hostnames', self.configfile)
self.sf = self.hostnames.get('sf')
self.config = RssConfig(self._INTERNAL_NAME, self.configfile)
self.rsscrawler = RssConfig("RSScrawler", self.configfile)
self.hevc_retail = self.config.get("hevc_retail")
self.retail_only = self.config.get("retail_only")
self.hoster_fallback = self.config.get("hoster_fallback")
self.hosters = RssConfig("Hosters", configfile).get_section()
self.log_info = logging.info
self.log_error = logging.error
self.log_debug = logging.debug
self.scraper = scraper
self.filename = filename
self.db = RssDb(self.dbfile, 'rsscrawler')
self.quality = self.config.get("quality")
self.cdc = RssDb(self.dbfile, 'cdc')
self.last_set_sf = self.cdc.retrieve("SFSet-" + self.filename)
self.last_sha_sf = self.cdc.retrieve("SF-" + self.filename)
self.headers = {
'If-Modified-Since':
str(self.cdc.retrieve("SFHeaders-" + self.filename))
}
settings = [
"quality", "rejectlist", "regex", "hevc_retail", "retail_only",
"hoster_fallback"
]
self.settings = []
self.settings.append(self.rsscrawler.get("english"))
self.settings.append(self.rsscrawler.get("surround"))
self.settings.append(self.hosters)
for s in settings:
self.settings.append(self.config.get(s))
self.empty_list = False
if self.filename == 'SJ_Staffeln_Regex':
self.level = 3
elif self.filename == 'MB_Staffeln':
self.seasonssource = self.config.get('seasonssource').lower()
self.level = 2
elif self.filename == 'SJ_Serien_Regex':
self.level = 1
else:
self.level = 0
self.pattern = r'^(' + "|".join(
self.get_series_list(self.filename, self.level)).lower() + ')'
self.listtype = ""
self.day = 0
def settings_hash(self, refresh):
if refresh:
settings = [
"quality", "rejectlist", "regex", "hevc_retail", "retail_only",
"hoster_fallback"
]
self.settings = []
self.settings.append(self.rsscrawler.get("english"))
self.settings.append(self.rsscrawler.get("surround"))
self.settings.append(self.hosters)
for s in settings:
self.settings.append(self.config.get(s))
self.pattern = r'^(' + "|".join(
self.get_series_list(self.filename, self.level)).lower() + ')'
set_sf = str(self.settings) + str(self.pattern)
return hashlib.sha256(set_sf.encode('ascii', 'ignore')).hexdigest()
def get_series_list(self, liste, series_type):
if series_type == 1:
self.listtype = " (RegEx)"
elif series_type == 2:
self.listtype = " (Staffeln)"
elif series_type == 3:
self.listtype = " (Staffeln/RegEx)"
cont = ListDb(self.dbfile, liste).retrieve()
titles = []
if cont:
for title in cont:
if title:
title = title.replace(" ", ".")
titles.append(title)
if not titles:
self.empty_list = True
return titles
def parse_download(self, series_url, title, language_id):
if not check_valid_release(title, self.retail_only, self.hevc_retail,
self.dbfile):
self.log_debug(
title +
u" - Release ignoriert (Gleiche oder bessere Quelle bereits vorhanden)"
)
return
if self.filename == 'MB_Staffeln':
if not self.config.get("seasonpacks"):
staffelpack = re.search(r"s\d.*(-|\.).*s\d", title.lower())
if staffelpack:
self.log_debug("%s - Release ignoriert (Staffelpaket)" %
title)
return
if not re.search(self.seasonssource, title.lower()):
self.log_debug(title + " - Release hat falsche Quelle")
return
try:
if language_id == 2:
lang = 'EN'
else:
lang = 'DE'
epoch = str(datetime.datetime.now().timestamp()).replace('.',
'')[:-3]
api_url = series_url + '?lang=' + lang + '&_=' + epoch
response = get_url(api_url, self.configfile, self.dbfile,
self.scraper)
info = json.loads(response)
is_episode = re.findall(r'.*\.(s\d{1,3}e\d{1,3})\..*', title,
re.IGNORECASE)
if is_episode:
episode_string = re.findall(r'.*S\d{1,3}(E\d{1,3}).*',
is_episode[0])[0].lower()
season_string = re.findall(r'.*(S\d{1,3})E\d{1,3}.*',
is_episode[0])[0].lower()
season_title = rreplace(
title.lower().replace(episode_string, ''), "-", ".*",
1).lower()
season_title = season_title.replace(".untouched",
".*").replace(
".dd+51", ".dd.51")
episode = str(int(episode_string.replace("e", "")))
season = str(int(season_string.replace("s", "")))
episode_name = re.findall(r'.*\.s\d{1,3}(\..*).german',
season_title, re.IGNORECASE)
if episode_name:
season_title = season_title.replace(episode_name[0], '')
codec_tags = [".h264", ".x264"]
for tag in codec_tags:
season_title = season_title.replace(tag, ".*264")
web_tags = [".web-rip", ".webrip", ".webdl", ".web-dl"]
for tag in web_tags:
season_title = season_title.replace(tag, ".web.*")
else:
season = False
episode = False
season_title = title
multiple_episodes = re.findall(r'(e\d{1,3}-e*\d{1,3}\.)',
season_title, re.IGNORECASE)
if multiple_episodes:
season_title = season_title.replace(
multiple_episodes[0], '.*')
content = BeautifulSoup(info['html'], 'lxml')
releases = content.find(
"small", text=re.compile(season_title,
re.IGNORECASE)).parent.parent.parent
links = releases.findAll("div", {'class': 'row'})[1].findAll('a')
valid = False
for link in links:
download_link = link['href']
if check_hoster(link.text.replace('\n', ''), self.configfile):
valid = True
break
if not valid and not self.hoster_fallback:
storage = self.db.retrieve_all(title)
if 'added' not in storage and 'notdl' not in storage:
wrong_hoster = '[SF/Hoster fehlt] - ' + title
if 'wrong_hoster' not in storage:
self.log_info(wrong_hoster)
self.db.store(title, 'wrong_hoster')
notify([wrong_hoster], self.configfile)
else:
self.log_debug(wrong_hoster)
else:
return self.send_package(title, download_link, language_id,
season, episode)
except:
print(
u"SF hat die Serien-API angepasst. Breche Download-Prüfung ab!"
)
def send_package(self, title, download_link, language_id, season, episode):
englisch = ""
if language_id == 2:
englisch = "/Englisch"
if self.filename == 'SJ_Serien_Regex':
link_placeholder = '[Episode/RegEx' + englisch + '] - '
elif self.filename == 'SJ_Serien':
link_placeholder = '[Episode' + englisch + '] - '
elif self.filename == 'SJ_Staffeln_Regex]':
link_placeholder = '[Staffel/RegEx' + englisch + '] - '
else:
link_placeholder = '[Staffel' + englisch + '] - '
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug("Fehler bei Datenbankzugriff: %s, Grund: %s" %
(e, title))
return
if 'added' in storage or 'notdl' in storage:
self.log_debug(title + " - Release ignoriert (bereits gefunden)")
else:
download_link = 'https://' + self.sf + download_link
if season and episode:
download_link = download_link.replace(
'&_=', '&season=' + str(season) + '&episode=' +
str(episode) + '&_=')
download = add_decrypt(title, download_link, self.sf, self.dbfile)
if download:
self.db.store(title, 'added')
log_entry = link_placeholder + title + ' - [SF]'
self.log_info(log_entry)
notify(["[Click'n'Load notwendig] - " + log_entry],
self.configfile)
return log_entry
def periodical_task(self):
if not self.sf:
return self.device
if self.filename == 'SJ_Serien_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für SF-Regex deaktiviert!")
return self.device
elif self.filename == 'SJ_Staffeln_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für SF-Regex deaktiviert!")
return self.device
elif self.filename == 'MB_Staffeln':
if not self.config.get('crawlseasons'):
self.log_debug("Suche für SF-Staffeln deaktiviert!")
return self.device
if self.empty_list:
self.log_debug("Liste ist leer. Stoppe Suche für Serien!" +
self.listtype)
return self.device
try:
reject = self.config.get("rejectlist").replace(
",", "|").lower() if len(
self.config.get("rejectlist")) > 0 else r"^unmatchable$"
except TypeError:
reject = r"^unmatchable$"
set_sf = self.settings_hash(False)
header = False
response = False
while self.day < 8:
if self.last_set_sf == set_sf:
try:
delta = (
datetime.datetime.now() -
datetime.timedelta(days=self.day)).strftime("%Y-%m-%d")
response = get_url_headers(
'https://' + self.sf + '/updates/' + delta,
self.configfile, self.dbfile, self.headers,
self.scraper)
self.scraper = response[1]
response = response[0]
if self.filename == "MB_Staffeln" or self.filename == "SJ_Staffeln_Regex":
feed = sf_releases_to_feedparser_dict(
response.text, "seasons", 'https://' + self.sf,
True)
else:
feed = sf_releases_to_feedparser_dict(
response.text, "episodes", 'https://' + self.sf,
True)
except:
print(u"SF hat die Feed-API angepasst. Breche Suche ab!")
feed = False
if response:
if response.status_code == 304:
self.log_debug(
"SF-Feed seit letztem Aufruf nicht aktualisiert - breche Suche ab!"
)
return self.device
header = True
else:
try:
delta = (
datetime.datetime.now() -
datetime.timedelta(days=self.day)).strftime("%Y-%m-%d")
response = get_url(
'https://' + self.sf + '/updates/' + delta,
self.configfile, self.dbfile, self.scraper)
if self.filename == "MB_Staffeln" or self.filename == "SJ_Staffeln_Regex":
feed = sf_releases_to_feedparser_dict(
response, "seasons", 'https://' + self.sf, True)
else:
feed = sf_releases_to_feedparser_dict(
response, "episodes", 'https://' + self.sf, True)
except:
print(u"SF hat die Feed-API angepasst. Breche Suche ab!")
feed = False
self.day += 1
if feed and feed.entries:
first_post_sf = feed.entries[0]
concat_sf = first_post_sf.title + first_post_sf.published + str(
self.settings) + str(self.pattern)
sha_sf = hashlib.sha256(concat_sf.encode(
'ascii', 'ignore')).hexdigest()
else:
self.log_debug("Feed ist leer - breche Suche ab!")
return False
for post in feed.entries:
concat = post.title + post.published + \
str(self.settings) + str(self.pattern)
sha = hashlib.sha256(concat.encode('ascii',
'ignore')).hexdigest()
if sha == self.last_sha_sf:
self.log_debug("Feed ab hier bereits gecrawlt (" +
post.title + ") - breche Suche ab!")
break
series_url = post.series_url
title = post.title.replace("-", "-")
if self.filename == 'SJ_Serien_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
m = re.search(self.pattern, title.lower())
if not m and "720p" not in title and "1080p" not in title and "2160p" not in title:
m = re.search(
self.pattern.replace("480p", "."),
title.lower())
self.quality = "480p"
if m:
if "720p" in title.lower():
self.quality = "720p"
if "1080p" in title.lower():
self.quality = "1080p"
if "2160p" in title.lower():
self.quality = "2160p"
m = re.search(reject, title.lower())
if m:
self.log_debug(
title +
" - Release durch Regex gefunden (trotz rejectlist-Einstellung)"
)
title = re.sub(r'\[.*\] ', '', post.title)
self.parse_download(series_url, title,
language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
else:
continue
elif self.filename == 'SJ_Staffeln_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
m = re.search(self.pattern, title.lower())
if not m and "720p" not in title and "1080p" not in title and "2160p" not in title:
m = re.search(
self.pattern.replace("480p", "."),
title.lower())
self.quality = "480p"
if m:
if "720p" in title.lower():
self.quality = "720p"
if "1080p" in title.lower():
self.quality = "1080p"
if "2160p" in title.lower():
self.quality = "2160p"
m = re.search(reject, title.lower())
if m:
self.log_debug(
title +
" - Release durch Regex gefunden (trotz rejectlist-Einstellung)"
)
title = re.sub(r'\[.*\] ', '', post.title)
self.parse_download(series_url, title,
language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
else:
continue
else:
if self.config.get("quality") != '480p':
m = re.search(self.pattern, title.lower())
if m:
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
mm = re.search(self.quality, title.lower())
if mm:
mmm = re.search(reject, title.lower())
if mmm:
self.log_debug(
title +
" - Release ignoriert (basierend auf rejectlist-Einstellung)"
)
continue
if self.rsscrawler.get("surround"):
if not re.match(
r'.*\.(DTS|DD\+*51|DD\+*71|AC3\.5\.*1)\..*',
title):
self.log_debug(
title +
" - Release ignoriert (kein Mehrkanalton)"
)
continue
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s"
% (e, title))
return self.device
if 'added' in storage:
self.log_debug(
title +
" - Release ignoriert (bereits gefunden)"
)
continue
self.parse_download(
series_url, title, language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" %
title)
else:
m = re.search(self.pattern, title.lower())
if m:
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
if "720p" in title.lower(
) or "1080p" in title.lower(
) or "2160p" in title.lower():
continue
mm = re.search(reject, title.lower())
if mm:
self.log_debug(
title +
" Release ignoriert (basierend auf rejectlist-Einstellung)"
)
continue
if self.rsscrawler.get("surround"):
if not re.match(
r'.*\.(DTS|DD\+*51|DD\+*71|AC3\.5\.*1)\..*',
title):
self.log_debug(
title +
" - Release ignoriert (kein Mehrkanalton)"
)
continue
title = re.sub(r'\[.*\] ', '', post.title)
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s"
% (e, title))
return self.device
if 'added' in storage:
self.log_debug(
title +
" - Release ignoriert (bereits gefunden)"
)
continue
self.parse_download(
series_url, title, language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" %
title)
if set_sf:
new_set_sf = self.settings_hash(True)
if set_sf == new_set_sf:
self.cdc.delete("SFSet-" + self.filename)
self.cdc.store("SFSet-" + self.filename, set_sf)
self.cdc.delete("SF-" + self.filename)
self.cdc.store("SF-" + self.filename, sha_sf)
if header and response:
self.cdc.delete("SFHeaders-" + self.filename)
self.cdc.store("SFHeaders-" + self.filename,
response.headers['date'])
return self.device
class SJ:
def __init__(self, configfile, dbfile, device, logging, scraper, filename,
internal_name):
self._INTERNAL_NAME = internal_name
self.configfile = configfile
self.dbfile = dbfile
self.device = device
self.hostnames = RssConfig('Hostnames', self.configfile)
self.sj = self.hostnames.get('sj')
self.config = RssConfig(self._INTERNAL_NAME, self.configfile)
self.rsscrawler = RssConfig("RSScrawler", self.configfile)
self.hevc_retail = self.config.get("hevc_retail")
self.retail_only = self.config.get("retail_only")
self.hoster_fallback = self.config.get("hoster_fallback")
self.hosters = RssConfig("Hosters", configfile).get_section()
self.log_info = logging.info
self.log_error = logging.error
self.log_debug = logging.debug
self.scraper = scraper
self.filename = filename
self.db = RssDb(self.dbfile, 'rsscrawler')
self.quality = self.config.get("quality")
self.cdc = RssDb(self.dbfile, 'cdc')
self.last_set_sj = self.cdc.retrieve("SJSet-" + self.filename)
self.last_sha_sj = self.cdc.retrieve("SJ-" + self.filename)
self.headers = {
'If-Modified-Since':
str(self.cdc.retrieve("SJHeaders-" + self.filename))
}
settings = [
"quality", "rejectlist", "regex", "hevc_retail", "retail_only",
"hoster_fallback"
]
self.settings = []
self.settings.append(self.rsscrawler.get("english"))
self.settings.append(self.rsscrawler.get("surround"))
self.settings.append(self.hosters)
for s in settings:
self.settings.append(self.config.get(s))
self.empty_list = False
if self.filename == 'SJ_Staffeln_Regex':
self.level = 3
elif self.filename == 'MB_Staffeln':
self.seasonssource = self.config.get('seasonssource').lower()
self.level = 2
elif self.filename == 'SJ_Serien_Regex':
self.level = 1
else:
self.level = 0
self.pattern = r'^(' + "|".join(
self.get_series_list(self.filename, self.level)).lower() + ')'
self.listtype = ""
self.day = 0
def settings_hash(self, refresh):
if refresh:
settings = [
"quality", "rejectlist", "regex", "hevc_retail", "retail_only",
"hoster_fallback"
]
self.settings = []
self.settings.append(self.rsscrawler.get("english"))
self.settings.append(self.rsscrawler.get("surround"))
self.settings.append(self.hosters)
for s in settings:
self.settings.append(self.config.get(s))
self.pattern = r'^(' + "|".join(
self.get_series_list(self.filename, self.level)).lower() + ')'
set_sj = str(self.settings) + str(self.pattern)
return hashlib.sha256(set_sj.encode('ascii', 'ignore')).hexdigest()
def get_series_list(self, liste, series_type):
if series_type == 1:
self.listtype = " (RegEx)"
elif series_type == 2:
self.listtype = " (Staffeln)"
elif series_type == 3:
self.listtype = " (Staffeln/RegEx)"
cont = ListDb(self.dbfile, liste).retrieve()
titles = []
if cont:
for title in cont:
if title:
title = title.replace(" ", ".")
titles.append(title)
if not titles:
self.empty_list = True
return titles
def parse_download(self, series_url, title, language_id):
if not check_valid_release(title, self.retail_only, self.hevc_retail,
self.dbfile):
self.log_debug(
title +
u" - Release ignoriert (Gleiche oder bessere Quelle bereits vorhanden)"
)
return
if self.filename == 'MB_Staffeln':
if not self.config.get("seasonpacks"):
staffelpack = re.search(r"s\d.*(-|\.).*s\d", title.lower())
if staffelpack:
self.log_debug("%s - Release ignoriert (Staffelpaket)" %
title)
return
if not re.search(self.seasonssource, title.lower()):
self.log_debug(title + " - Release hat falsche Quelle")
return
try:
series_info = get_url(series_url, self.configfile, self.dbfile)
series_id = re.findall(r'data-mediaid="(.*?)"', series_info)[0]
api_url = 'https://' + self.sj + '/api/media/' + series_id + '/releases'
response = get_url(api_url, self.configfile, self.dbfile,
self.scraper)
seasons = json.loads(response)
for season in seasons:
season = seasons[season]
for item in season['items']:
if item['name'] == title:
valid = False
for hoster in item['hoster']:
if hoster:
if check_hoster(hoster, self.configfile):
valid = True
if not valid and not self.hoster_fallback:
storage = self.db.retrieve_all(title)
if 'added' not in storage and 'notdl' not in storage:
wrong_hoster = '[SJ/Hoster fehlt] - ' + title
if 'wrong_hoster' not in storage:
print(wrong_hoster)
self.db.store(title, 'wrong_hoster')
notify([wrong_hoster], self.configfile)
else:
self.log_debug(wrong_hoster)
else:
return self.send_package(title, series_url,
language_id)
except:
print(
u"SJ hat die Serien-API angepasst. Breche Download-Prüfung ab!"
)
def send_package(self, title, series_url, language_id):
englisch = ""
if language_id == 2:
englisch = "/Englisch"
if self.filename == 'SJ_Serien_Regex':
link_placeholder = '[Episode/RegEx' + englisch + '] - '
elif self.filename == 'SJ_Serien':
link_placeholder = '[Episode' + englisch + '] - '
elif self.filename == 'SJ_Staffeln_Regex]':
link_placeholder = '[Staffel/RegEx' + englisch + '] - '
else:
link_placeholder = '[Staffel' + englisch + '] - '
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug("Fehler bei Datenbankzugriff: %s, Grund: %s" %
(e, title))
return
if 'added' in storage or 'notdl' in storage:
self.log_debug(title + " - Release ignoriert (bereits gefunden)")
else:
download = add_decrypt(title, series_url, self.sj, self.dbfile)
if download:
self.db.store(title, 'added')
log_entry = link_placeholder + title + ' - [SJ]'
self.log_info(log_entry)
notify(["[Click'n'Load notwendig] - " + log_entry],
self.configfile)
return log_entry
def periodical_task(self):
if not self.sj:
return self.device
if self.filename == 'SJ_Serien_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für SJ-Regex deaktiviert!")
return self.device
elif self.filename == 'SJ_Staffeln_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für SJ-Regex deaktiviert!")
return self.device
elif self.filename == 'MB_Staffeln':
if not self.config.get('crawlseasons'):
self.log_debug("Suche für SJ-Staffeln deaktiviert!")
return self.device
if self.empty_list:
self.log_debug("Liste ist leer. Stoppe Suche für Serien!" +
self.listtype)
return self.device
try:
reject = self.config.get("rejectlist").replace(
",", "|").lower() if len(
self.config.get("rejectlist")) > 0 else r"^unmatchable$"
except TypeError:
reject = r"^unmatchable$"
set_sj = self.settings_hash(False)
header = False
response = False
while self.day < 8:
if self.last_set_sj == set_sj:
try:
response = get_url_headers(
'https://' + self.sj + '/api/releases/latest/' +
str(self.day), self.configfile, self.dbfile,
self.headers, self.scraper)
self.scraper = response[1]
response = response[0]
if self.filename == "MB_Staffeln" or self.filename == "SJ_Staffeln_Regex":
feed = j_releases_to_feedparser_dict(
response.text, "seasons", 'https://' + self.sj,
True)
else:
feed = j_releases_to_feedparser_dict(
response.text, "episodes", 'https://' + self.sj,
True)
except:
print(u"SJ hat die Feed-API angepasst. Breche Suche ab!")
feed = False
if response:
if response.status_code == 304:
self.log_debug(
"SJ-Feed seit letztem Aufruf nicht aktualisiert - breche Suche ab!"
)
return self.device
header = True
else:
try:
response = get_url(
'https://' + self.sj + '/api/releases/latest/' +
str(self.day), self.configfile, self.dbfile,
self.scraper)
if self.filename == "MB_Staffeln" or self.filename == "SJ_Staffeln_Regex":
feed = j_releases_to_feedparser_dict(
response, "seasons", 'https://' + self.sj, True)
else:
feed = j_releases_to_feedparser_dict(
response, "episodes", 'https://' + self.sj, True)
except:
print(u"SJ hat die Feed-API angepasst. Breche Suche ab!")
feed = False
self.day += 1
if feed and feed.entries:
first_post_sj = feed.entries[0]
concat_sj = first_post_sj.title + first_post_sj.published + str(
self.settings) + str(self.pattern)
sha_sj = hashlib.sha256(concat_sj.encode(
'ascii', 'ignore')).hexdigest()
else:
self.log_debug("Feed ist leer - breche Suche ab!")
return False
for post in feed.entries:
concat = post.title + post.published + \
str(self.settings) + str(self.pattern)
sha = hashlib.sha256(concat.encode('ascii',
'ignore')).hexdigest()
if sha == self.last_sha_sj:
self.log_debug("Feed ab hier bereits gecrawlt (" +
post.title + ") - breche Suche ab!")
break
series_url = post.series_url
title = post.title.replace("-", "-")
if self.filename == 'SJ_Serien_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
m = re.search(self.pattern, title.lower())
if not m and "720p" not in title and "1080p" not in title and "2160p" not in title:
m = re.search(
self.pattern.replace("480p", "."),
title.lower())
self.quality = "480p"
if m:
if "720p" in title.lower():
self.quality = "720p"
if "1080p" in title.lower():
self.quality = "1080p"
if "2160p" in title.lower():
self.quality = "2160p"
m = re.search(reject, title.lower())
if m:
self.log_debug(
title +
" - Release durch Regex gefunden (trotz rejectlist-Einstellung)"
)
title = re.sub(r'\[.*\] ', '', post.title)
self.parse_download(series_url, title,
language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
else:
continue
elif self.filename == 'SJ_Staffeln_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
m = re.search(self.pattern, title.lower())
if not m and "720p" not in title and "1080p" not in title and "2160p" not in title:
m = re.search(
self.pattern.replace("480p", "."),
title.lower())
self.quality = "480p"
if m:
if "720p" in title.lower():
self.quality = "720p"
if "1080p" in title.lower():
self.quality = "1080p"
if "2160p" in title.lower():
self.quality = "2160p"
m = re.search(reject, title.lower())
if m:
self.log_debug(
title +
" - Release durch Regex gefunden (trotz rejectlist-Einstellung)"
)
title = re.sub(r'\[.*\] ', '', post.title)
self.parse_download(series_url, title,
language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
else:
continue
else:
if self.config.get("quality") != '480p':
m = re.search(self.pattern, title.lower())
if m:
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
mm = re.search(self.quality, title.lower())
if mm:
mmm = re.search(reject, title.lower())
if mmm:
self.log_debug(
title +
" - Release ignoriert (basierend auf rejectlist-Einstellung)"
)
continue
if self.rsscrawler.get("surround"):
if not re.match(
r'.*\.(DTS|DD\+*51|DD\+*71|AC3\.5\.*1)\..*',
title):
self.log_debug(
title +
" - Release ignoriert (kein Mehrkanalton)"
)
continue
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s"
% (e, title))
return self.device
if 'added' in storage:
self.log_debug(
title +
" - Release ignoriert (bereits gefunden)"
)
continue
self.parse_download(
series_url, title, language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" %
title)
else:
m = re.search(self.pattern, title.lower())
if m:
if '.german.' in title.lower():
language_id = 1
elif self.rsscrawler.get('english'):
language_id = 2
else:
language_id = 0
if language_id:
if "720p" in title.lower(
) or "1080p" in title.lower(
) or "2160p" in title.lower():
continue
mm = re.search(reject, title.lower())
if mm:
self.log_debug(
title +
" Release ignoriert (basierend auf rejectlist-Einstellung)"
)
continue
if self.rsscrawler.get("surround"):
if not re.match(
r'.*\.(DTS|DD\+*51|DD\+*71|AC3\.5\.*1)\..*',
title):
self.log_debug(
title +
" - Release ignoriert (kein Mehrkanalton)"
)
continue
title = re.sub(r'\[.*\] ', '', post.title)
try:
storage = self.db.retrieve_all(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s"
% (e, title))
return self.device
if 'added' in storage:
self.log_debug(
title +
" - Release ignoriert (bereits gefunden)"
)
continue
self.parse_download(
series_url, title, language_id)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" %
title)
if set_sj:
new_set_sj = self.settings_hash(True)
if set_sj == new_set_sj:
self.cdc.delete("SJSet-" + self.filename)
self.cdc.store("SJSet-" + self.filename, set_sj)
self.cdc.delete("SJ-" + self.filename)
self.cdc.store("SJ-" + self.filename, sha_sj)
if header and response:
self.cdc.delete("SJHeaders-" + self.filename)
self.cdc.store("SJHeaders-" + self.filename,
response.headers['date'])
return self.device
def download(configfile,
dbfile,
device,
title,
subdir,
old_links,
password,
full_path=None,
autostart=False):
try:
if not device or not is_device(device):
device = get_device(configfile)
if isinstance(old_links, list):
links = []
for link in old_links:
if link not in links:
links.append(link)
else:
links = [old_links]
links = str(links).replace(" ", "")
crawljobs = RssConfig('Crawljobs', configfile)
usesubdir = crawljobs.get("subdir")
priority = "DEFAULT"
if full_path:
path = full_path
else:
if usesubdir:
path = subdir + "/<jd:packagename>"
else:
path = "<jd:packagename>"
if "Remux" in path:
priority = "LOWER"
try:
device.linkgrabber.add_links(
params=[{
"autostart": autostart,
"links": links,
"packageName": title,
"extractPassword": password,
"priority": priority,
"downloadPassword": password,
"destinationFolder": path,
"comment": "RSScrawler by rix1337",
"overwritePackagizerRules": False
}])
except rsscrawler.myjdapi.TokenExpiredException:
device = get_device(configfile)
if not device or not is_device(device):
return False
device.linkgrabber.add_links(
params=[{
"autostart": autostart,
"links": links,
"packageName": title,
"extractPassword": password,
"priority": priority,
"downloadPassword": password,
"destinationFolder": path,
"comment": "RSScrawler by rix1337",
"overwritePackagizerRules": False
}])
db = RssDb(dbfile, 'crawldog')
if db.retrieve(title):
db.delete(title)
db.store(title, 'retried')
else:
db.store(title, 'added')
return device
except rsscrawler.myjdapi.MYJDException as e:
print(u"Fehler bei der Verbindung mit MyJDownloader: " + str(e))
return False
def post_url(url, configfile, dbfile, data, scraper=False):
config = RssConfig('RSScrawler', configfile)
proxy = config.get('proxy')
if not scraper:
scraper = cloudscraper.create_scraper()
db = RssDb(dbfile, 'proxystatus')
db_normal = RssDb(dbfile, 'normalstatus')
site = check_is_site(url, configfile)
# Temporary fix for FX
if site and "FX" in site:
scraper = requests.session()
scraper.headers = scraper.headers
scraper.cookies = scraper.cookies
scraper.verify = False
if proxy:
try:
if site and "SJ" in site:
if db.retrieve("SJ"):
if config.get("fallback") and not db_normal.retrieve("SJ"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "DJ" in site:
if db.retrieve("DJ"):
if config.get("fallback") and not db_normal.retrieve("DJ"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "SF" in site:
if db.retrieve("SF"):
if config.get("fallback") and not db_normal.retrieve("SF"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "MB" in site:
if db.retrieve("MB"):
if config.get("fallback") and not db_normal.retrieve("MB"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "HW" in site:
if db.retrieve("HW"):
if config.get("fallback") and not db_normal.retrieve("HW"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "FX" in site:
if db.retrieve("FX"):
if config.get("fallback") and not db_normal.retrieve("FX"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "HS" in site:
if db.retrieve("HS"):
if config.get("fallback") and not db_normal.retrieve("HS"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "NK" in site:
if db.retrieve("NK"):
if config.get("fallback") and not db_normal.retrieve("NK"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "DD" in site:
if db.retrieve("DD"):
if config.get("fallback") and not db_normal.retrieve("DD"):
return scraper.post(url, data, timeout=30).content
else:
return ""
elif site and "FC" in site:
if db.retrieve("FC"):
if config.get("fallback") and not db_normal.retrieve("FC"):
return scraper.post(url, data, timeout=30).content
else:
return ""
proxies = {'http': proxy, 'https': proxy}
response = scraper.post(url, data, proxies=proxies,
timeout=30).content
return response
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ""
else:
try:
if site and "SJ" in site and db_normal.retrieve("SJ"):
return ""
elif site and "DJ" in site and db_normal.retrieve("DJ"):
return ""
elif site and "SF" in site and db_normal.retrieve("SF"):
return ""
elif site and "MB" in site and db_normal.retrieve("MB"):
return ""
elif site and "HW" in site and db_normal.retrieve("HW"):
return ""
elif site and "FX" in site and db_normal.retrieve("FX"):
return ""
elif site and "HS" in site and db_normal.retrieve("HS"):
return ""
elif site and "NK" in site and db_normal.retrieve("NK"):
return ""
elif site and "DD" in site and db_normal.retrieve("DD"):
return ""
elif site and "FC" in site and db_normal.retrieve("FC"):
return ""
response = scraper.post(url, data, timeout=30).content
return response
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ""
def check_valid_release(title, retail_only, hevc_retail, dbfile):
if retail_only:
if not is_retail(title, False, False):
return False
if ".German" in title:
search_title = title.split(".German")[0]
elif ".GERMAN" in title:
search_title = title.split(".GERMAN")[0]
else:
try:
quality = re.findall(r"\d{3,4}p", title)[0]
search_title = title.split(quality)[0]
except:
return True
db = RssDb(dbfile, 'rsscrawler')
is_episode = re.findall(r'.*\.s\d{1,3}(e\d{1,3}|e\d{1,3}-.*\d{1,3})\..*',
title, re.IGNORECASE)
if is_episode:
episode_name = re.findall(r'.*\.s\d{1,3}e\d{1,3}(\..*)', search_title,
re.IGNORECASE)
if episode_name:
search_title = search_title.replace(episode_name[0], "")
season_search_title = search_title.replace(is_episode[0], "") + "."
season_results = db.retrieve_all_beginning_with(season_search_title)
results = db.retrieve_all_beginning_with(search_title) + season_results
else:
db = RssDb(dbfile, 'rsscrawler')
results = db.retrieve_all_beginning_with(search_title)
if not results:
return True
bluray_tags = [
".bd-rip.", ".br-rip.", ".bluray-rip.", ".bluray.", ".bd-disk.",
".bd.", ".bd5.", ".bd9.", ".bd25.", ".bd50."
]
web_tags = [
".web.", ".web-rip.", ".webrip.", ".vod-rip.", ".webdl.", ".web-dl.",
".ddc."
]
trash_tags = [
".cam.", ".cam-rip.", ".ts.", ".telesync.", ".wp.", ".workprint.",
".tc.", ".telecine.", ".vhs-rip.", ".tv-rip.", ".hdtv-rip.", ".hdtv.",
".tvrip.", ".hdtvrip.", ".sat-rip.", ".dvb-rip.", ".ds-rip.", ".scr.",
".screener.", ".dvdscr.", ".dvdscreener.", ".bdscr.", ".r5.",
".dvdrip.", ".dvd."
]
unknown = []
trash = []
web = []
bluray = []
retail = []
# Get all previously found Releases and categorize them by their tags
for r in results:
if any(s in r.lower() for s in bluray_tags):
if is_retail(r, False, False):
retail.append(r)
else:
bluray.append(r)
elif any(s in r.lower() for s in web_tags):
web.append(r)
elif any(s in r.lower() for s in trash_tags):
trash.append(r)
else:
unknown.append(r)
# Categorize the current Release by its tag to check if a release of the same or better category was already found
# If no release is in the higher category, propers are allowed anytime
# If no HEVC is available in the current category or higher and the current release is HEVC, it will be allowed
if any(s in title.lower() for s in bluray_tags):
if is_retail(r, False, False):
if len(retail) > 0:
if hevc_retail:
if is_hevc(title):
no_hevc = True
for r in retail:
if is_hevc(r):
no_hevc = False
if no_hevc:
return True
if ".proper" in title.lower():
return True
return False
else:
if len(retail) == 0 and len(bluray) > 0:
if ".proper" in title.lower():
return True
if len(retail) > 0 or len(bluray) > 0:
if hevc_retail:
if is_hevc(title):
no_hevc = True
for r in retail + bluray:
if is_hevc(r):
no_hevc = False
if no_hevc:
return True
return False
elif any(s in title.lower() for s in web_tags):
if len(retail) == 0 and len(bluray) == 0 and len(web) > 0:
if ".proper" in title.lower():
return True
if len(retail) > 0 or len(bluray) > 0 or len(web) > 0:
if hevc_retail:
if is_hevc(title):
no_hevc = True
for r in retail + bluray + web:
if is_hevc(r):
no_hevc = False
if no_hevc:
return True
return False
elif any(s in title.lower() for s in trash_tags):
if len(retail) == 0 and len(bluray) == 0 and len(
web) == 0 and len(trash) > 0:
if ".proper" in title.lower():
return True
if len(retail) > 0 or len(bluray) > 0 or len(web) > 0 or len(
trash) > 0:
return False
else:
if len(retail) == 0 and len(bluray) == 0 and len(web) == 0 and len(
trash) == 0 and len(unknown) > 0:
if ".proper" in title.lower():
return True
if len(retail) > 0 or len(bluray) > 0 or len(web) > 0 or len(
trash) > 0 or len(unknown) > 0:
return False
return True
