def get_source(self, url, title, year, season, episode, start_time):
try:
self.items = []
count = 0
if url is None:
return self.sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
self.title = data[
'tvshowtitle'] if 'tvshowtitle' in data else data['title']
self.hdlr = 'S%02dE%02d' % (
int(data['season']), int(data['episode'])
) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
urls = []
if 'tvshowtitle' in data:
urls.append(self.tvsearch.format(urllib.quote(query), '1'))
urls.append(self.tvsearch.format(urllib.quote(query), '2'))
urls.append(self.tvsearch.format(urllib.quote(query), '3'))
else:
urls.append(self.moviesearch.format(urllib.quote(query), '1'))
urls.append(self.moviesearch.format(urllib.quote(query), '2'))
urls.append(self.moviesearch.format(urllib.quote(query), '3'))
threads = []
for url in urls:
threads.append(workers.Thread(self._get_items, url))
[i.start() for i in threads]
[i.join() for i in threads]
threads2 = []
for i in self.items:
count += 1
threads2.append(workers.Thread(self._get_sources, i))
[i.start() for i in threads2]
[i.join() for i in threads2]
if dev_log == 'true':
end_time = time.time() - float(start_time)
send_log(self.name,
end_time,
count,
title,
year,
season=season,
episode=episode)
# xbmc.log('@#@SOURCES:%s' % self._sources, xbmc.LOGNOTICE)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_episode(self,
title,
show_year,
year,
season,
episode,
imdb,
tvdb,
debrid=False):
try:
start_time = time.time()
hdlr = 'S%02dE%02d' % (int(season), int(episode))
query = clean_search(title)
self.query = urllib.quote_plus(query + ' ' + hdlr).replace(
'+', '%20')
threads = []
for link in self.search_links:
threads.append(
workers.Thread(self._get_sources, link, title, year,
'show', season, episode, str(start_time)))
[i.start() for i in threads]
[i.join() for i in threads]
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = '%s %s' % (title, year)
movie_url = self.base_link + self.search_link % urllib.quote_plus(
search_id)
r = client.request(movie_url)
items = client.parseDOM(r, 'article', attrs={'id': 'post-\d+'})
#xbmc.log('@#@ITEMS:%s' % items, xbmc.LOGNOTICE)
links = []
for item in items:
name = client.parseDOM(item, 'a')[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+|3D)(\.|\)|\]|\s|)(.+|)',
'',
name,
flags=re.I)
if not clean_title(title) == clean_title(t):
continue
if not year in name:
continue
link = client.parseDOM(item, 'a', ret='href')[0]
link += '/2/'
links.append(link)
#xbmc.log('@#@LINKS:%s' % links, xbmc.LOGNOTICE)
threads = []
for i in links:
threads.append(
workers.Thread(self.get_source, i, title, year, '', '',
str(start_time)))
[i.start() for i in threads]
alive = [x for x in threads if x.is_alive() is True]
while alive:
alive = [x for x in threads if x.is_alive() is True]
time.sleep(0.1)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def get(self, netloc, ua, timeout):
try:
self.netloc = netloc
self.ua = ua
self.timeout = timeout
self.cookie = None
threads = []
# for i in range(0, 5): threads.append(workers.Thread(self._get_cookie))
threads.append(workers.Thread(self._get_cookie))
[i.start() for i in threads]
[i.join() for i in threads]
while [x for x in threads if x.is_alive() == True]: time.sleep(0.5)
if self.cookie == None:
xbmc.log('%s returned an error. Could not collect tokens.' % netloc, xbmc.LOGDEBUG)
return self.cookie
except Exception as e:
xbmc.log('%s returned an error. Could not collect tokens - Error: %s.' % (netloc, str(e)),
xbmc.LOGDEBUG)
return self.cookie
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
query = clean_search(title)
self.query = urllib.quote_plus(query + ' ' + year).replace(
'+', '%20')
threads = []
for link in self.search_links:
threads.append(
workers.Thread(self._get_sources, link, title, year,
'movie', '', '', str(start_time)))
[i.start() for i in threads]
[i.join() for i in threads]
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
if not debrid: return self.sources
query = '%s %s' % (title, year)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
query = urllib.quote_plus(query).replace('+', '%2B')
url = urlparse.urljoin(self.search_base_link,
self.search_link % query)
headers = {'User-Agent': client.agent(), 'Referer': self.base_link}
scraper = cfscrape.create_scraper()
r = scraper.get(url, headers=headers).content
posts = json.loads(r)['results']
posts = [(i['post_title'], i['post_name']) for i in posts]
posts = [(i[0], i[1]) for i in posts if clean_title(
i[0].lower().split(year)[0]) == clean_title(title)]
filter = [
'uhd', '4K', '2160', '1080', '720', 'hevc', 'bluray', 'web'
]
posts = [(urlparse.urljoin(self.base_link, i[1]), year)
for i in posts if any(x in i[1] for x in filter)]
threads = []
for i in posts:
threads.append(
workers.Thread(self.get_sources, i, title, year, '', '',
str(start_time)))
[i.start() for i in threads]
alive = [x for x in threads if x.is_alive() is True]
while alive:
alive = [x for x in threads if x.is_alive() is True]
time.sleep(0.1)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources