def get_url_headers(url, configfile, dbfile, headers):
config = RssConfig('RSScrawler', configfile)
proxy = config.get('proxy')
scraper = cfscrape.create_scraper(delay=10)
agent = fake_user_agent()
headers.update({'User-Agent': agent})
if proxy:
sj = decode_base64("c2VyaWVuanVua2llcy5vcmc=")
mb = decode_base64("bW92aWUtYmxvZy50bw==")
db = RssDb(dbfile, 'proxystatus')
if sj in url:
if db.retrieve("SJ") and config.get("fallback"):
return scraper.get(url, headers=headers, timeout=30)
elif mb in url:
if db.retrieve("MB") and config.get("fallback"):
return scraper.get(url, headers=headers, timeout=30)
proxies = {'http': proxy, 'https': proxy}
try:
response = scraper.get(url, headers=headers, proxies=proxies, timeout=30)
return response
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ""
else:
try:
response = scraper.get(url, headers=headers, timeout=30)
return response
except Exception as e:
print(u"Fehler beim Abruf von: " + url + " " + str(e))
return ""
def send_package(self, title, links, englisch_info, genre):
if genre == "Doku":
genre = ""
else:
genre = "/" + genre
englisch = ""
if englisch_info:
englisch = "Englisch - "
if self.filename == 'DJ_Dokus_Regex':
link_placeholder = '[Doku' + genre + '/RegEx] - ' + englisch
else:
link_placeholder = '[Doku' + genre + '] - ' + englisch
try:
storage = self.db.retrieve(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s" % (e, title))
return
if storage == 'added':
self.log_debug(title + " - Release ignoriert (bereits gefunden)")
else:
self.device = myjd_download(self.configfile, self.device, title, "RSScrawler", links,
decode_base64("ZG9rdWp1bmtpZXMub3Jn"))
if self.device:
self.db.store(title, 'added')
log_entry = link_placeholder + title
self.log_info(log_entry)
notify([log_entry], self.configfile)
return log_entry
def check_url(configfile, dbfile):
sj_url = decode_base64("aHR0cDovL3Nlcmllbmp1bmtpZXMub3Jn")
mb_url = decode_base64("aHR0cDovL21vdmllLWJsb2cudG8v")
proxy = RssConfig('RSScrawler', configfile).get('proxy')
scraper = cfscrape.create_scraper(delay=10)
agent = fake_user_agent()
sj_blocked_proxy = False
mb_blocked_proxy = False
if proxy:
db = RssDb(dbfile, 'proxystatus')
proxies = {'http': proxy, 'https': proxy}
if "block." in str(
scraper.get(sj_url, headers={'User-Agent': agent}, proxies=proxies, timeout=30,
allow_redirects=False).headers.get("location")):
print(u"Der Zugriff auf SJ ist mit der aktuellen Proxy-IP nicht möglich!")
if RssConfig('RSScrawler', configfile).get("fallback"):
db.store("SJ", "Blocked")
sj_blocked_proxy = True
else:
db.delete("SJ")
if "<Response [403]>" in str(
scraper.get(mb_url, headers={'User-Agent': agent}, proxies=proxies, timeout=30, allow_redirects=False)):
print(u"Der Zugriff auf MB ist mit der aktuellen Proxy-IP nicht möglich!")
if RssConfig('RSScrawler', configfile).get("fallback"):
db.store("MB", "Blocked")
mb_blocked_proxy = True
else:
db.delete("MB")
# TODO check if HA is working!
if not proxy or sj_blocked_proxy == True or mb_blocked_proxy == True:
if "block." in str(
scraper.get(sj_url, headers={'User-Agent': agent}, timeout=30, allow_redirects=False).headers.get(
"location")):
print(u"Der Zugriff auf SJ ist mit der aktuellen IP nicht möglich!")
if "<Response [403]>" in str(
scraper.get(mb_url, headers={'User-Agent': agent}, timeout=30, allow_redirects=False)):
print(u"Der Zugriff auf MB ist mit der aktuellen IP nicht möglich!")
return
def download_sj(sj_id, special, device, configfile, dbfile):
url = get_url(decode_base64("aHR0cDovL3Nlcmllbmp1bmtpZXMub3JnLz9jYXQ9") + str(sj_id), configfile, dbfile)
season_pool = re.findall(r'<h2>Staffeln:(.*?)<h2>Feeds', url).pop()
season_links = re.findall(
r'href="(.{1,125})">.{1,90}(Staffel|Season).*?(\d{1,2}-?\d{1,2}|\d{1,2})', season_pool)
title = html_to_str(re.findall(r'>(.{1,85}?) &#', season_pool).pop())
rsscrawler = RssConfig('RSScrawler', configfile)
listen = ["SJ_Serien", "MB_Staffeln"]
for liste in listen:
cont = ListDb(dbfile, liste).retrieve()
list_title = sanitize(title)
if not cont:
cont = ""
if not list_title in cont:
ListDb(dbfile, liste).store(list_title)
staffeln = []
staffel_nr = []
seasons = []
for s in season_links:
if "staffel" in s[1].lower():
staffeln.append([s[2], s[0]])
if "-" in s[2]:
split = s[2].split("-")
split = range(int(split[0]), int(split[1]) + 1)
for nr in split:
staffel_nr.append(str(nr))
else:
staffel_nr.append(s[2])
else:
seasons.append([s[2], s[0]])
if rsscrawler.get("english"):
for se in seasons:
if not se[0] in staffel_nr:
staffeln.append(se)
to_dl = []
for s in staffeln:
if "-" in s[0]:
split = s[0].split("-")
split = range(int(split[0]), int(split[1]) + 1)
for i in split:
to_dl.append([str(i), s[1]])
else:
to_dl.append([s[0], s[1]])
found_seasons = {}
for dl in to_dl:
if len(dl[0]) is 1:
sxx = "S0" + str(dl[0])
else:
sxx = "S" + str(dl[0])
link = dl[1]
if sxx not in found_seasons:
found_seasons[sxx] = link
something_found = False
for sxx, link in found_seasons.items():
config = RssConfig('SJ', configfile)
quality = config.get('quality')
url = get_url(link, configfile, dbfile)
pakete = re.findall(re.compile(r'<p><strong>(.*?\.' + sxx + r'\..*?' + quality +
r'.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
folgen = re.findall(re.compile(r'<p><strong>(.*?\.' + sxx +
r'E\d{1,3}.*?' + quality + r'.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
lq_pakete = re.findall(re.compile(
r'<p><strong>(.*?\.' + sxx + r'\..*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
lq_folgen = re.findall(re.compile(
r'<p><strong>(.*?\.' + sxx + r'E\d{1,3}.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
if not pakete and not folgen and not lq_pakete and not lq_folgen:
sxx = sxx.replace("S0", "S")
pakete = re.findall(re.compile(r'<p><strong>(.*?\.' + sxx + r'\..*?' + quality +
r'.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
folgen = re.findall(re.compile(
r'<p><strong>(.*?\.' + sxx + r'E\d{1,3}.*?' + quality + r'.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
lq_pakete = re.findall(re.compile(
r'<p><strong>(.*?\.' + sxx + r'\..*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
lq_folgen = re.findall(re.compile(
r'<p><strong>(.*?\.' + sxx + r'E\d{1,3}.*?)<.*?\n.*?href="(.*?)".*? \| (.*)<(?:.*?\n.*?href="(.*?)".*? \| (.*)<|)'),
url)
if special and "e" in special.lower():
pakete = []
lq_pakete = []
best_matching_links = []
if pakete:
links = []
for x in pakete:
title = x[0]
score = rate(title, configfile)
hoster = [[x[2], x[1]], [x[4], x[3]]]
if special:
if special.lower() in title.lower():
links.append([score, title, hoster])
else:
links.append([score, title, hoster])
if links:
highest_score = sorted(links, reverse=True)[0][0]
for l in links:
if l[0] == highest_score:
for hoster in l[2]:
best_matching_links.append(
[l[1], hoster[0], hoster[1]])
elif folgen:
links = []
for x in folgen:
title = x[0]
score = rate(title, configfile)
hoster = [[x[2], x[1]], [x[4], x[3]]]
if special:
if special.lower() in title.lower():
links.append([score, title, hoster])
else:
links.append([score, title, hoster])
if links:
highest_score = sorted(links, reverse=True)[0][0]
for l in links:
if l[0] == highest_score:
for hoster in l[2]:
best_matching_links.append(
[l[1], hoster[0], hoster[1]])
elif lq_pakete:
links = []
for x in lq_pakete:
title = x[0]
score = rate(title, configfile)
hoster = [[x[2], x[1]], [x[4], x[3]]]
if special:
if special.lower() in title.lower():
links.append([score, title, hoster])
else:
links.append([score, title, hoster])
if links:
highest_score = sorted(links, reverse=True)[0][0]
for l in links:
if l[0] == highest_score:
for hoster in l[2]:
best_matching_links.append(
[l[1], hoster[0], hoster[1]])
elif lq_folgen:
links = []
for x in lq_folgen:
title = x[0]
score = rate(title, configfile)
hoster = [[x[2], x[1]], [x[4], x[3]]]
if special:
if special.lower() in title.lower():
links.append([score, title, hoster])
else:
links.append([score, title, hoster])
if links:
highest_score = sorted(links, reverse=True)[0][0]
for l in links:
if l[0] == highest_score:
for hoster in l[2]:
best_matching_links.append(
[l[1], hoster[0], hoster[1]])
notify_array = []
for best_link in best_matching_links:
dl_title = best_link[0].replace(
"Staffelpack ", "").replace("Staffelpack.", "")
dl_hoster = best_link[1]
dl_link = best_link[2]
config = RssConfig('SJ', configfile)
hoster = re.compile(config.get('hoster'))
db = RssDb(dbfile, 'rsscrawler')
if re.match(hoster, dl_hoster.lower()):
if myjd_download(configfile, device, dl_title, "RSScrawler", dl_link,
decode_base64("c2VyaWVuanVua2llcy5vcmc=")):
db.store(dl_title, 'added')
log_entry = '[Suche/Serie] - ' + dl_title
logging.info(log_entry)
notify_array.append(log_entry)
else:
return False
if len(best_matching_links) > 0:
something_found = True
notify(notify_array, configfile)
if not something_found:
return False
return True
def download_bl(payload, device, configfile, dbfile):
payload = decode_base64(payload).split(";")
link = payload[0]
password = payload[1]
url = get_url(link, configfile, dbfile)
config = RssConfig('MB', configfile)
hoster = re.compile(config.get('hoster'))
db = RssDb(dbfile, 'rsscrawler')
soup = BeautifulSoup(url, 'lxml')
download = soup.find("div", {"id": "content"})
try:
key = re.findall(r'Permanent Link: (.*?)"', str(download)).pop()
url_hosters = re.findall(r'href="([^"\'>]*)".+?(.+?)<', str(download))
except:
items_head = soup.find("div", {"class": "topbox"})
key = items_head.contents[1].a["title"]
items_download = soup.find("div", {"class": "download"})
url_hosters = []
download = items_download.find_all("span", {"style": "display:inline;"}, text=True)
for link in download:
link = link.a
text = link.text.strip()
if text:
url_hosters.append([str(link["href"]), str(text)])
links = {}
for url_hoster in reversed(url_hosters):
if not decode_base64("bW92aWUtYmxvZy50by8=") in url_hoster[0] and "https://goo.gl/" not in url_hoster[0]:
link_hoster = url_hoster[1].lower().replace('target="_blank">', '').replace(" ", "-")
if re.match(hoster, link_hoster):
links[link_hoster] = url_hoster[0]
download_links = links.values() if six.PY2 else list(links.values())
englisch = False
if "*englisch*" in key.lower():
key = key.replace('*ENGLISCH*', '').replace("*Englisch*", "")
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:
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)
if staffel:
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:
logging.debug(
"%s - Keine passende Film-IMDB-Seite gefunden" % key)
if staffel:
filename = 'MB_Staffeln'
else:
filename = 'MB_Filme'
bl = BL(configfile, dbfile, device, logging, filename=filename)
if not imdb_id:
if not bl.dual_download(key, password):
logging.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:
logging.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":
logging.debug(
"%s - Originalsprache ist Deutsch. Breche Suche nach zweisprachigem Release ab!" % key)
else:
if not bl.dual_download(key, password) and not englisch:
logging.debug(
"%s - Kein zweisprachiges Release gefunden! Breche ab." % key)
if download_links:
if staffel:
if myjd_download(configfile, 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 = '[Staffel] - ' + key.replace(".COMPLETE", "").replace(".Complete", "")
logging.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 cutoff(key, '2', dbfile):
retail = True
if myjd_download(configfile, 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
logging.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 cutoff(key, '1', dbfile):
retail = True
else:
if cutoff(key, '0', dbfile):
retail = True
if myjd_download(configfile, 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
logging.info(log_entry)
notify([log_entry], configfile)
return True
else:
return False
def get(title, configfile, dbfile):
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
query = title.replace(".", " ").replace(" ", "+")
if special:
bl_query = query + "+" + special
else:
bl_query = query
unrated = []
config = RssConfig('MB', configfile)
quality = config.get('quality')
if "480p" not in quality:
search_quality = "+" + quality
else:
search_quality = ""
mb_search = get_url(
decode_base64('aHR0cDovL21vdmllLWJsb2cudG8=') + '/search/' + bl_query + "+" + search_quality + '/feed/rss2/',
configfile, dbfile)
mb_results = re.findall(r'<title>(.*?)<\/title>\n.*?<link>(.*?)<\/link>', mb_search)
password = decode_base64("bW92aWUtYmxvZy5vcmc=")
for result in mb_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 not result[0].endswith("-MB") and not result[0].endswith(".MB"):
unrated.append(
[rate(result[0], configfile), encode_base64(result[1] + ";" + password), result[0] + " (MB)"])
hw_search = get_url(
decode_base64('aHR0cDovL2hkLXdvcmxkLm9yZw==') + '/search/' + bl_query + "+" + search_quality + '/feed/rss2/',
configfile, dbfile)
hw_results = re.findall(r'<title>(.*?)<\/title>\n.*?<link>(.*?)<\/link>', hw_search)
password = decode_base64("aGQtd29ybGQub3Jn")
for result in hw_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], configfile), encode_base64(result[1] + ";" + password), result[0] + " (HW)"])
ha_search = decode_base64('aHR0cDovL3d3dy5oZC1hcmVhLm9yZy8/cz1zZWFyY2gmcT0=') + bl_query + "&c=" + search_quality
ha_results = ha_search_results(ha_search, configfile, dbfile)
password = decode_base64("aGQtYXJlYS5vcmc=")
for result in ha_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], configfile), encode_base64(result[1] + ";" + password), result[0] + " (HA)"])
if config.get("crawl3d"):
mb_search = get_url(
decode_base64('aHR0cDovL21vdmllLWJsb2cudG8=') + '/search/' + bl_query + "+3D+1080p" + '/feed/rss2/',
configfile, dbfile)
mb_results = re.findall(r'<title>(.*?)<\/title>\n.*?<link>(.*?)<\/link>', mb_search)
for result in mb_results:
if not result[1].endswith("-MB") and not result[1].endswith(".MB"):
unrated.append(
[rate(result[0], configfile), encode_base64(result[1] + ";" + password), result[0] + " (3D-MB)"])
hw_search = get_url(
decode_base64('aHR0cDovL2hkLXdvcmxkLm9yZw==') + '/search/' + bl_query + "+3D+1080p" + '/feed/rss2/',
configfile, dbfile)
hw_results = re.findall(r'<title>(.*?)<\/title>\n.*?<link>(.*?)<\/link>', hw_search)
password = decode_base64("aGQtd29ybGQub3Jn")
for result in hw_results:
unrated.append(
[rate(result[0], configfile), encode_base64(result[1] + ";" + password), result[0] + " (3D-HW)"])
ha_search = decode_base64('aHR0cDovL3d3dy5oZC1hcmVhLm9yZy8/cz1zZWFyY2gmcT0=') + bl_query + "&c=1080p"
ha_results = ha_search_results(ha_search, configfile, dbfile)
password = decode_base64("aGQtYXJlYS5vcmc=")
for result in ha_results:
if "3d" in result[0].lower():
unrated.append(
[rate(result[0], configfile), encode_base64(result[1] + ";" + password), result[0] + " (3D-HA)"])
rated = sorted(unrated, reverse=True)
results = {}
i = 0
for result in rated:
res = {"link": result[1], "title": result[2]}
results["result" + str(i)] = res
i += 1
mb_final = results
sj_search = post_url(decode_base64("aHR0cDovL3Nlcmllbmp1bmtpZXMub3JnL21lZGlhL2FqYXgvc2VhcmNoL3NlYXJjaC5waHA="),
configfile,
dbfile,
data={'string': "'" + query + "'"})
try:
sj_results = json.loads(sj_search)
except:
sj_results = []
if special:
append = " (" + special + ")"
else:
append = ""
i = 0
results = {}
for result in sj_results:
r_title = html_to_str(result[1])
r_rating = fuzz.ratio(title.lower(), r_title)
if r_rating > 65:
res = {"id": result[0], "title": r_title + append, "special": special}
results["result" + str(i)] = res
i += 1
sj_final = results
return mb_final, sj_final
def periodical_task(self):
if self.filename == 'DJ_Dokus_Regex':
if not self.config.get('regex'):
self.log_debug("Suche für DJ-Regex deaktiviert!")
return self.device
if self.empty_list:
self.log_debug(
"Liste ist leer. Stoppe Suche für Dokus!" + 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_dj = self.settings_hash(False)
header = False
if self.last_set_dj == set_dj:
try:
response = get_url_headers(
decode_base64('aHR0cDovL2Rva3VqdW5raWVzLm9yZy8='),
self.configfile,
self.dbfile,
self.headers)
feed = dj_content_to_soup(response.content)
except:
response = False
feed = False
if response:
if response.status_code == 304:
self.log_debug(
"DJ-Feed seit letztem Aufruf nicht aktualisiert - breche Suche ab!")
return self.device
header = True
else:
feed = dj_content_to_soup(
get_url(decode_base64('aHR0cDovL2Rva3VqdW5raWVzLm9yZy8='), self.configfile, self.dbfile))
response = False
if feed and feed.entries:
first_post_dj = feed.entries[0]
concat_dj = first_post_dj.title + first_post_dj.published + str(self.settings) + str(self.pattern)
sha_dj = hashlib.sha256(concat_dj.encode(
'ascii', 'ignore')).hexdigest()
else:
self.log_debug(
"Feed ist leer - breche Suche ab!")
return False
for post in feed.entries:
if not post.link:
continue
concat = post.title + post.published + str(self.settings) + str(self.pattern)
sha = hashlib.sha256(concat.encode(
'ascii', 'ignore')).hexdigest()
if sha == self.last_sha_dj:
self.log_debug(
"Feed ab hier bereits gecrawlt (" + post.title + ") - breche Suche ab!")
break
link = post.link
title = post.title
genre = post.genre
if self.filename == 'DJ_Dokus_Regex':
if self.config.get("regex"):
if '[DEUTSCH]' in title or '[TV-FILM]' in title:
language_ok = 1
elif self.rsscrawler.get('english'):
language_ok = 2
else:
language_ok = 0
if language_ok:
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 not re.match(self.genres, genre.lower()):
self.log_debug(
title + " - Release aufgrund unerwünschten Genres ignoriert (" + genre + ")")
continue
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.range_checkr(link, title, language_ok, genre)
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 not re.match(self.genres, genre.lower()):
self.log_debug(title + " - Release aufgrund unerwünschten Genres ignoriert (" + genre + ")")
continue
if 'german' in title.lower():
language_ok = 1
elif self.rsscrawler.get('english'):
language_ok = 2
else:
language_ok = 0
if language_ok:
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
title = re.sub(r'\[.*\] ', '', post.title)
try:
storage = self.db.retrieve(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s" % (e, title))
return self.device
if storage == 'added':
self.log_debug(
title + " - Release ignoriert (bereits gefunden)")
continue
self.range_checkr(link, title, language_ok, genre)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
else:
m = re.search(self.pattern, title.lower())
if m:
if '[DEUTSCH]' in title:
language_ok = 1
elif self.rsscrawler.get('english'):
language_ok = 2
else:
language_ok = 0
if language_ok:
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(title)
except Exception as e:
self.log_debug(
"Fehler bei Datenbankzugriff: %s, Grund: %s" % (e, title))
return self.device
if storage == 'added':
self.log_debug(
title + " - Release ignoriert (bereits gefunden)")
continue
self.range_checkr(link, title, language_ok, genre)
else:
self.log_debug(
"%s - Englische Releases deaktiviert" % title)
if set_dj:
new_set_dj = self.settings_hash(True)
if set_dj == new_set_dj:
self.cdc.delete("DJSet-" + self.filename)
self.cdc.store("DJSet-" + self.filename, set_dj)
self.cdc.delete("DJ-" + self.filename)
self.cdc.store("DJ-" + self.filename, sha_dj)
if header and response:
self.cdc.delete("DJHeaders-" + self.filename)
self.cdc.store("DJHeaders-" + self.filename, response.headers['Last-Modified'])
return self.device
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 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