def get_original_language(key, imdb_details, imdb_url, configfile, dbfile,
scraper, log_debug):
original_language = False
if imdb_details and len(imdb_details) > 0:
soup = BeautifulSoup(imdb_details, 'lxml')
try:
original_language = soup.find(
'h4', text=re.compile(r'Language:')).parent.find("a").text
except:
pass
elif imdb_url and len(imdb_url) > 0:
imdb_details = get_url(imdb_url, configfile, dbfile, scraper)
if imdb_details:
soup = BeautifulSoup(imdb_details, 'lxml')
try:
original_language = soup.find(
'h4', text=re.compile(r'Language:')).parent.find("a").text
except:
pass
if not original_language:
if imdb_details and len(imdb_details) > 0:
soup = BeautifulSoup(imdb_details, 'lxml')
try:
original_language = \
soup.find('h3', text=re.compile(r'Language')).next.next.next.text.strip().replace("\n", "").split(
",")[
0]
except:
pass
elif imdb_url and len(imdb_url) > 0:
imdb_details = get_url(imdb_url, configfile, dbfile, scraper)
if imdb_details:
soup = BeautifulSoup(imdb_details, 'lxml')
try:
original_language = \
soup.find('h3', text=re.compile(r'Language')).next.next.next.text.strip().replace("\n",
"").split(
",")[0]
except:
pass
if not original_language:
log_debug("%s - Originalsprache nicht ermittelbar" % key)
if original_language and original_language == "German":
log_debug(
"%s - Originalsprache ist Deutsch. Breche Suche nach zweisprachigem Release ab!"
% key)
return False
else:
return original_language
def j_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 False
if self.filename == 'List_ContentAll_Seasons':
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 False
if not re.search(self.seasonssource, title.lower()):
self.log_debug(title + " - Release hat falsche Quelle")
return False
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.url + '/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)
return False
else:
return [title, series_url, language_id, False, False]
except:
print(self._INTERNAL_NAME +
u" hat die Serien-API angepasst. Breche Download-Prüfung ab!")
return False
def ww_get_download_links(self, content, title):
base_url = "https://" + CrawlerConfig('Hostnames',
self.configfile).get('ww')
content = content.replace("mkv|", "")
download_links = []
try:
response = get_url(content, self.configfile, self.dbfile, self.scraper)
if not response or "NinjaFirewall 429" in response:
print(
u"WW hat den Link-Abruf für " + title +
" blockiert. Eine spätere Anfrage hat möglicherweise Erfolg!")
return False
links = BeautifulSoup(response,
'lxml').findAll("div", {"id": "download-links"})
for link in links:
hoster = link.text
if 'Direct Download 100 MBit/s' not in hoster:
url = base_url + link.find("a")["href"]
download_links.append('href="' + url + '" ' + hoster + '<')
download_links = "".join(download_links)
download_links = get_download_links(self, download_links, title)
return download_links
except:
return False
def fx_search_results(content, configfile, dbfile, scraper):
articles = content.find("main").find_all("article")
result_urls = []
for article in articles:
url = article.find("a")["href"]
if url:
result_urls.append(url)
items = []
if result_urls:
results = []
for url in result_urls:
results.append(get_url(url, configfile, dbfile, scraper))
for result in results:
article = BeautifulSoup(str(result), 'lxml')
titles = article.find_all("a", href=re.compile("filecrypt"))
for title in titles:
link = article.find("link", rel="canonical")["href"]
title = title.text.encode("ascii",
errors="ignore").decode().replace(
"/", "")
if title:
if "download" in title.lower():
try:
title = str(
content.find("strong",
text=re.compile(
r".*Release.*")).nextSibling)
except:
continue
items.append([title, link + "|" + title])
return items
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 = '[' + self._SITE + '/Hoster fehlt] - ' + key
if 'wrong_hoster' not in storage:
print(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,
"FeedCrawler", links, "")
if self.device:
self.db.store(key, 'added')
log_entry = '[Englisch] - ' + key + ' - [' + self._SITE + ']'
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 " + self._SITE +
"!")
return self.device
def nk_page_download_link(self, download_link, key):
unused_get_feed_parameter(key)
nk = self.hostnames.get('nk')
download_link = get_url(download_link, self.configfile, self.dbfile)
soup = BeautifulSoup(download_link, 'lxml')
url_hosters = []
hosters = soup.find_all("a", href=re.compile("/go/"))
for hoster in hosters:
url_hosters.append(['https://' + nk + hoster["href"], hoster.text])
return check_download_links(self, url_hosters)
def dw_parse_download(self, release_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 False
if self.filename == 'List_ContentAll_Seasons':
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 False
if not re.search(self.seasonssource, title.lower()):
self.log_debug(title + " - Release hat falsche Quelle")
return False
try:
release_info = get_url(release_url, self.configfile, self.dbfile)
post_hosters = BeautifulSoup(release_info, 'lxml').find(
"div", {
"id": "download"
}).findAll("img", src=re.compile(r"images/hosterimg"))
hosters = []
valid = False
for hoster in post_hosters:
hoster = hoster["title"].replace("Premium-Account bei ",
"").replace("ddownload", "ddl")
if hoster not in hosters:
hosters.append(hoster)
for hoster in hosters:
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)
return False
else:
return [title, release_url, language_id, False, False]
except:
print(self._INTERNAL_NAME +
u" hat die Serien-API angepasst. Breche Download-Prüfung ab!")
return False
def dw_mirror(self, title):
hostnames = CrawlerConfig('Hostnames', self.configfile)
dw = hostnames.get('dw')
if dw:
dw_search = 'https://' + dw + '/?search=' + title
dw_results = get_url(dw_search, self.configfile, self.dbfile,
self.scraper)
dw_results = dw_search_results(dw_results, dw)
for result in dw_results:
release_url = result[1].split("|")[0]
release_info = get_url(release_url, self.configfile, self.dbfile)
post_hosters = BeautifulSoup(release_info, 'lxml').find(
"div", {
"id": "download"
}).findAll("img", src=re.compile(r"images/hosterimg"))
hosters = []
valid = False
for hoster in post_hosters:
hoster = hoster["title"].replace("Premium-Account bei ",
"").replace(
"ddownload", "ddl")
if hoster not in hosters:
hosters.append(hoster)
for hoster in hosters:
if hoster:
if check_hoster(hoster, self.configfile):
valid = True
if not valid and not self.hoster_fallback:
return False
else:
return [release_url]
return False
def get_imdb_id(key, content, filename, configfile, dbfile, scraper,
log_debug):
try:
imdb_id = re.findall(
r'.*?(?:href=.?http(?:|s):\/\/(?:|www\.)imdb\.com\/title\/(tt[0-9]{7,9}).*?).*?(\d(?:\.|\,)\d)(?:.|.*?)<\/a>.*?',
content)
except:
imdb_id = False
if imdb_id:
imdb_id = imdb_id[0][0]
else:
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, scraper)
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)
except:
return False
total_results = len(search_results)
if filename == 'List_ContentAll_Seasons':
imdb_id = search_results[0][0]
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:
log_debug("%s - Keine passende Film-IMDB-Seite gefunden" % key)
if not imdb_id:
return False
return imdb_id
def by_page_download_link(self, download_link, key):
unused_get_feed_parameter(key)
by = self.hostnames.get('by')
download_link = get_url(download_link, self.configfile, self.dbfile)
soup = BeautifulSoup(download_link, 'lxml')
links = soup.find_all("iframe")
async_link_results = []
for link in links:
link = link["src"]
if 'https://' + by in link:
async_link_results.append(link)
async_link_results = get_urls_async(async_link_results, self.configfile,
self.dbfile)
links = async_link_results[0]
url_hosters = []
for link in links:
if link:
link = BeautifulSoup(link,
'lxml').find("a",
href=re.compile("/go\.php\?"))
if link:
url_hosters.append([link["href"], link.text.replace(" ", "")])
return check_download_links(self, url_hosters)
def get(title, configfile, dbfile, bl_only=False, sj_only=False):
hostnames = CrawlerConfig('Hostnames', configfile)
by = hostnames.get('by')
dw = hostnames.get('dw')
fx = hostnames.get('fx')
nk = hostnames.get('nk')
sj = hostnames.get('sj')
specific_season = re.match(r'^(.*),(s\d{1,3})$', title.lower())
specific_episode = re.match(r'^(.*),(s\d{1,3}e\d{1,3})$', title.lower())
if specific_season:
split = title.split(",")
title = split[0]
special = split[1].upper()
elif specific_episode:
split = title.split(",")
title = split[0]
special = split[1].upper()
else:
special = None
bl_final = {}
sj_final = {}
scraper = cloudscraper.create_scraper()
if not sj_only:
mb_query = sanitize(title).replace(" ", "+")
if special:
bl_query = mb_query + "+" + special
else:
bl_query = mb_query
unrated = []
config = CrawlerConfig('ContentAll', configfile)
quality = config.get('quality')
ignore = config.get('ignore')
if "480p" not in quality:
search_quality = "+" + quality
else:
search_quality = ""
if by:
by_search = 'https://' + by + '/?q=' + bl_query + search_quality
else:
by_search = None
if dw:
dw_search = 'https://' + dw + '/?kategorie=Movies&search=' + bl_query + search_quality
else:
dw_search = None
if fx:
fx_search = 'https://' + fx + '/?s=' + bl_query
else:
fx_search = None
async_results = get_urls_async([by_search, dw_search, fx_search],
configfile, dbfile, scraper)
scraper = async_results[1]
async_results = async_results[0]
by_results = []
dw_results = []
fx_results = []
for res in async_results:
if check_is_site(res, configfile) == 'BY':
by_results = by_search_results(res, by)
elif check_is_site(res, configfile) == 'DW':
dw_results = dw_search_results(res, dw)
elif check_is_site(res, configfile) == 'FX':
fx_results = fx_search_results(fx_content_to_soup(res),
configfile, dbfile, scraper)
if nk:
nk_search = post_url(
'https://' + nk + "/search",
configfile,
dbfile,
data={'search': bl_query.replace("+", " ") + " " + quality})
nk_results = nk_search_results(nk_search, 'https://' + nk + '/')
else:
nk_results = []
password = by
for result in by_results:
if "480p" in quality:
if "720p" in result[0].lower() or "1080p" in result[0].lower() or "1080i" in result[
0].lower() or "2160p" in \
result[0].lower() or "complete.bluray" in result[0].lower() or "complete.mbluray" in result[
0].lower() or "complete.uhd.bluray" in result[0].lower():
continue
if "xxx" not in result[0].lower():
unrated.append([
rate(result[0], ignore),
encode_base64(result[1] + "|" + password),
result[0] + " (BY)"
])
password = dw
for result in dw_results:
if "480p" in quality:
if "720p" in result[0].lower() or "1080p" in result[0].lower() or "1080i" in result[
0].lower() or "2160p" in \
result[0].lower() or "complete.bluray" in result[0].lower() or "complete.mbluray" in result[
0].lower() or "complete.uhd.bluray" in result[0].lower():
continue
unrated.append([
rate(result[0], ignore),
encode_base64(result[1] + "|" + password), result[0] + " (DW)"
])
password = fx.split('.')[0]
for result in fx_results:
if "480p" in quality:
if "720p" in result[0].lower() or "1080p" in result[0].lower() or "1080i" in result[
0].lower() or "2160p" in \
result[0].lower() or "complete.bluray" in result[0].lower() or "complete.mbluray" in result[
0].lower() or "complete.uhd.bluray" in result[0].lower():
continue
if "-low" not in result[0].lower():
unrated.append([
rate(result[0], ignore),
encode_base64(result[1] + "|" + password),
result[0] + " (FX)"
])
password = nk.split('.')[0].capitalize()
for result in nk_results:
if "480p" in quality:
if "720p" in result[0].lower() or "1080p" in result[0].lower() or "1080i" in result[
0].lower() or "2160p" in \
result[0].lower() or "complete.bluray" in result[0].lower() or "complete.mbluray" in result[
0].lower() or "complete.uhd.bluray" in result[0].lower():
continue
unrated.append([
rate(result[0], ignore),
encode_base64(result[1] + "|" + password), result[0] + " (NK)"
])
rated = sorted(unrated, reverse=True)
results = {}
i = 0
for result in rated:
res = {"payload": result[1], "title": result[2]}
results["result" + str(i + 1000)] = res
i += 1
bl_final = results
if not bl_only:
if sj:
sj_query = sanitize(title).replace(" ", "+")
sj_search = get_url(
'https://' + sj + '/serie/search?q=' + sj_query, configfile,
dbfile, scraper)
try:
sj_results = BeautifulSoup(sj_search, 'lxml').findAll(
"a", href=re.compile("/serie"))
except:
sj_results = []
else:
sj_results = []
if special:
append = " (" + special + ")"
else:
append = ""
i = 0
results = {}
for result in sj_results:
r_title = result.text
r_rating = fuzz.ratio(title.lower(), r_title)
if r_rating > 40:
res = {
"payload":
encode_base64(result['href'] + "|" + r_title + "|" +
str(special)),
"title":
r_title + append
}
results["result" + str(i + 1000)] = res
i += 1
sj_final = results
return bl_final, sj_final
def download(payload, configfile, dbfile):
hostnames = CrawlerConfig('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)
unsorted_seasons = json.loads(releases)
listen = ["List_ContentShows_Shows", "List_ContentAll_Seasons"]
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 = CrawlerConfig('ContentShows', configfile)
english_ok = CrawlerConfig('FeedCrawler', configfile).get("english")
quality = config.get('quality')
ignore = config.get('rejectlist')
result_seasons = {}
result_episodes = {}
seasons = {}
for season in unsorted_seasons:
if "sp" in season.lower():
seasons[season] = unsorted_seasons[season]
for season in unsorted_seasons:
if "sp" not in season.lower():
seasons[season] = unsorted_seasons[season]
for season in seasons:
releases = seasons[season]
for release in releases['items']:
name = release['name'].encode('ascii',
errors='ignore').decode('utf-8')
try:
season = re.findall(r'.*\.(s\d{1,3}).*', name,
re.IGNORECASE)[0]
except:
pass
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:
valid = False
for e in existing:
if e == ep:
if rate(name, ignore) > rate(
existing[e], ignore):
valid = True
else:
valid = True
if valid:
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 = FeedDb(dbfile, 'FeedCrawler')
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(payload, device, configfile, dbfile):
config = CrawlerConfig('ContentAll', configfile)
db = FeedDb(dbfile, 'FeedCrawler')
hostnames = CrawlerConfig('Hostnames', configfile)
by = hostnames.get('by')
nk = hostnames.get('nk')
payload = decode_base64(payload).split("|")
link = payload[0]
password = payload[1]
site = check_is_site(link, configfile)
if not site:
return False
elif "DW" in site:
download_method = add_decrypt_instead_of_download
download_links = [link]
key = payload[1]
password = payload[2]
else:
url = get_url(link, configfile, dbfile)
if not url or "NinjaFirewall 429" in url:
return False
download_method = myjd_download
soup = BeautifulSoup(url, 'lxml')
if "BY" in site:
key = soup.find("small").text
links = soup.find_all("iframe")
async_link_results = []
for link in links:
link = link["src"]
if 'https://' + by in link:
async_link_results.append(link)
async_link_results = get_urls_async(async_link_results, configfile,
dbfile)
links = async_link_results[0]
url_hosters = []
for link in links:
if link:
link = BeautifulSoup(link, 'lxml').find(
"a", href=re.compile("/go\.php\?"))
if link:
url_hosters.append(
[link["href"],
link.text.replace(" ", "")])
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 "FX" in site:
class FX:
configfile = ""
FX.configfile = configfile
download_links = fx_get_download_links(FX, url, key)
else:
for url_hoster in reversed(url_hosters):
try:
link_hoster = url_hoster[1].lower().replace(
'target="_blank">',
'').replace(" ", "-").replace("ddownload", "ddl")
if check_hoster(link_hoster, configfile):
link = url_hoster[0]
if by in link:
demasked_link = get_redirected_url(
link, configfile, dbfile, False)
if demasked_link:
link = demasked_link
links[link_hoster] = link
except:
pass
if config.get("hoster_fallback") and not links:
for url_hoster in reversed(url_hosters):
link_hoster = url_hoster[1].lower().replace(
'target="_blank">',
'').replace(" ", "-").replace("ddownload", "ddl")
link = url_hoster[0]
if by in link:
demasked_link = get_redirected_url(
link, configfile, dbfile, False)
if demasked_link:
link = demasked_link
links[link_hoster] = link
download_links = list(links.values())
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 download_links:
if staffel:
if download_method(configfile, dbfile, device, key, "FeedCrawler",
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
else:
retail = False
if config.get('cutoff') and '.COMPLETE.' not in key.lower():
if is_retail(key, dbfile):
retail = True
if download_method(configfile, dbfile, device, key, "FeedCrawler",
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 sf_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 False
if self.filename == 'List_ContentAll_Seasons':
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 False
if not re.search(self.seasonssource, title.lower()):
self.log_debug(title + " - Release hat falsche Quelle")
return False
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().replace(".repack", "")
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')
download_link = False
for link in links:
if check_hoster(link.text.replace('\n', ''), self.configfile):
download_link = get_redirected_url(
"https://" + self.url + link['href'], self.configfile,
self.dbfile, self.scraper)
break
if not download_link 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:
print(wrong_hoster)
self.db.store(title, 'wrong_hoster')
notify([wrong_hoster], self.configfile)
else:
self.log_debug(wrong_hoster)
return False
else:
return [title, download_link, language_id, season, episode]
except:
print(u"SF hat die Serien-API angepasst. Breche Download-Prüfung ab!")
return False
def periodical_task(self):
if not self.url:
return self.device
if self.filename == 'List_ContentShows_Shows_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für " + self._SITE + "-Regex deaktiviert!")
return self.device
elif self.filename == 'List_ContentShows_Seasons_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für " + self._SITE + "-Regex deaktiviert!")
return self.device
elif self.filename == 'List_ContentAll_Seasons':
if not self.config.get('crawlseasons'):
self.log_debug("Suche für " + self._SITE +
"-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$"
except TypeError:
reject = r"^unmatchable$"
current_set = settings_hash(self, False)
sha = False
header = False
response = False
while self.day < 8:
if self.last_set == current_set:
try:
url = feed_url(self)
if url:
response = get_url_headers(url, self.configfile,
self.dbfile, self.headers,
self.scraper)
self.scraper = response[1]
response = response[0]
if self.filename == "List_ContentAll_Seasons" or self.filename == "List_ContentShows_Seasons_Regex":
feed = self.get_feed_method(response.text, "seasons",
'https://' + self.url,
True)
else:
feed = self.get_feed_method(response.text, "episodes",
'https://' + self.url,
True)
else:
feed = False
except:
print(self._SITE +
u" hat die Feed-API angepasst. Breche Suche ab!")
feed = False
if response:
if response.status_code == 304:
self.log_debug(
self._SITE +
"-Feed seit letztem Aufruf nicht aktualisiert - breche Suche ab!"
)
return self.device
header = True
else:
try:
url = feed_url(self)
if url:
response = get_url(url, self.configfile, self.dbfile,
self.scraper)
if self.filename == "List_ContentAll_Seasons" or self.filename == "List_ContentShows_Seasons_Regex":
feed = self.get_feed_method(response, "seasons",
'https://' + self.url,
True)
else:
feed = self.get_feed_method(response, "episodes",
'https://' + self.url,
True)
else:
feed = False
except:
print(self._SITE +
u" hat die Feed-API angepasst. Breche Suche ab!")
feed = False
self.day += 1
if feed and feed.entries:
first_post = feed.entries[0]
concat = first_post.title + first_post.published + str(
self.settings) + str(self.pattern)
sha = hashlib.sha256(concat.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:
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 == 'List_ContentShows_Shows_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.feedcrawler.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)
package = self.parse_download_method(
self, series_url, title, language_id)
if package:
title = package[0]
site = self._SITE
download_link = False
if self.prefer_dw_mirror and "DW" not in site:
download_links = dw_mirror(self, title)
if download_links:
download_link = download_links[0]
site = "DW/" + site
if not download_link:
download_link = package[1]
language_id = package[2]
season = package[3]
episode = package[4]
send_package(self, title, download_link,
language_id, season, episode,
site)
else:
self.log_debug("%s - Englische Releases deaktiviert" %
title)
else:
continue
elif self.filename == 'List_ContentShows_Seasons_Regex':
if self.config.get("regex"):
if '.german.' in title.lower():
language_id = 1
elif self.feedcrawler.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)
package = self.parse_download_method(
self, series_url, title, language_id)
if package:
title = package[0]
site = self._SITE
download_link = False
if self.prefer_dw_mirror and "DW" not in site:
download_links = dw_mirror(self, title)
if download_links:
download_link = download_links[0]
site = "DW/" + site
if not download_link:
download_link = package[1]
language_id = package[2]
season = package[3]
episode = package[4]
send_package(self, title, download_link,
language_id, season, episode,
site)
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.feedcrawler.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.feedcrawler.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
package = self.parse_download_method(
self, series_url, title, language_id)
if package:
title = package[0]
site = self._SITE
download_link = False
if self.prefer_dw_mirror and "DW" not in site:
download_links = dw_mirror(self, title)
if download_links:
download_link = download_links[0]
site = "DW/" + site
if not download_link:
download_link = package[1]
language_id = package[2]
season = package[3]
episode = package[4]
send_package(self, title, download_link,
language_id, season, episode,
site)
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.feedcrawler.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.feedcrawler.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
package = self.parse_download_method(
self, series_url, title, language_id)
if package:
title = package[0]
site = self._SITE
download_link = False
if self.prefer_dw_mirror and "DW" not in site:
download_links = dw_mirror(self, title)
if download_links:
download_link = download_links[0]
site = "DW/" + site
if not download_link:
download_link = package[1]
language_id = package[2]
season = package[3]
episode = package[4]
send_package(self, title, download_link,
language_id, season, episode,
site)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" %
title)
if current_set and sha:
new_set = settings_hash(self, True)
if current_set == new_set:
self.cdc.delete(self._INTERNAL_NAME + "Set-" + self.filename)
self.cdc.store(self._INTERNAL_NAME + "Set-" + self.filename,
current_set)
self.cdc.delete(self._INTERNAL_NAME + "-" + self.filename)
self.cdc.store(self._INTERNAL_NAME + "-" + self.filename, sha)
if header and response:
self.cdc.delete(self._INTERNAL_NAME + "Headers-" + self.filename)
self.cdc.store(self._INTERNAL_NAME + "Headers-" + self.filename,
response.headers['date'])
return self.device