def search(self, title, localtitle, year, search_type):
try:
titles= []
titles.append(cleantitle.normalize(cleantitle.getsearch(title)))
titles.append(cleantitle.normalize(cleantitle.getsearch(localtitle)))
for title in titles:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3435.0 Safari/537.36',
'Origin': 'http://alltube.pl',
'Referer': 'http://alltube.pl/szukaj'
}
r = client.request(urlparse.urljoin(self.base_link, self.search_link), post={'search': cleantitle.query(title)}, headers=headers)
r = self.get_rows(r, search_type)
for row in r:
url = client.parseDOM(row, 'a', ret='href')[0]
names_found = client.parseDOM(row, 'h3')[0]
if names_found.startswith('Zwiastun') and not title.startswith('Zwiastun'):
continue
names_found = names_found.split('/')
names_found = [cleantitle.normalize(cleantitle.getsearch(i)) for i in names_found]
for name in names_found:
name = name.replace(" "," ")
title = title.replace(" "," ")
words = title.split(" ")
found_year = self.try_read_year(url)
if self.contains_all_wors(name, words) and (not found_year or found_year == year):
return url
else:
continue
continue
except Exception, e:
print e
return
def search(self, title, localtitle, year, search_type):
try:
titles= []
titles.append(cleantitle.normalize(cleantitle.getsearch(title)))
titles.append(cleantitle.normalize(cleantitle.getsearch(localtitle)))
for title in titles:
r = client.request(urlparse.urljoin(self.base_link, self.search_link), post={'search': cleantitle.query(title)})
r = self.get_rows(r, search_type)
for row in r:
url = client.parseDOM(row, 'a', ret='href')[0]
names_found = client.parseDOM(row, 'h3')[0]
if names_found.startswith('Zwiastun') and not title.startswith('Zwiastun'):
continue
names_found = names_found.split('/')
names_found = [cleantitle.normalize(cleantitle.getsearch(i)) for i in names_found]
for name in names_found:
name = name.replace(" "," ")
title = title.replace(" "," ")
words = title.split(" ")
found_year = self.try_read_year(url)
if self.contains_all_wors(name, words) and (not found_year or found_year == year):
return url
else:
continue
continue
except Exception, e:
print e
return
def search(self, title, localtitle, year, is_movie_search):
try:
titles = []
titles.append(cleantitle.normalize(cleantitle.getsearch(title)))
titles.append(
cleantitle.normalize(cleantitle.getsearch(localtitle)))
for title in titles:
url = urlparse.urljoin(self.base_link, self.search_link)
url = url % urllib.quote(str(title).replace(" ", "_"))
result = client.request(url)
result = result.decode('utf-8')
h = HTMLParser()
result = h.unescape(result)
result = client.parseDOM(result,
'div',
attrs={'class': 'video-clip-wrapper'})
for item in result:
link = str(client.parseDOM(item, 'a', ret='href')[0])
nazwa = str(
client.parseDOM(item,
'a',
attrs={'class':
'link-title-visit'})[0])
name = cleantitle.normalize(cleantitle.getsearch(nazwa))
name = name.replace(" ", " ")
title = title.replace(" ", " ")
words = title.split(" ")
if self.contains_all_wors(name,
words) and str(year) in name:
return link
except Exception as e:
log_exception()
return
def search(self, title, localtitle, year):
try:
searchtitles = (localtitle,title)
for searchtitle in searchtitles:
simply_name = cleantitle.normalize(cleantitle.getsearch(localtitle))
simply_name2 = cleantitle.normalize(cleantitle.getsearch(title))
data = {
's': str(cleantitle.getsearch(searchtitle)),
'search-form':'5'
}
response = requests.post(self.base_link, data = data)
result = response.text
result = client.parseDOM(result, 'ul', attrs={'class':'film-num-list'})
titles = client.parseDOM(result, 'a')
links = client.parseDOM(result, 'a', ret='href')
rok = client.parseDOM(result, 'li')
counter = 0
for item in zip(titles,links):
if not str(item[1]).startswith("http://filmdom.pl/films/"):
continue
rok_film = str(rok[counter][-4:])
counter +=1
t2 = item[0].split(" / ")
for tytul in t2:
tytul = tytul.split(" (")
words = cleantitle.normalize(cleantitle.getsearch(tytul[0])).split(" ")
if (self.contains_all_wors(simply_name, words) or self.contains_all_wors(simply_name2, words)) and year == rok_film:
return item[1]
return
except Exception, e:
print str(e)
return
def search_ep(self, titles, season, episode, year):
try:
searchtitles = titles
for searchtitle in searchtitles:
response = requests.get(self.base_link +
self.search_serial % searchtitle)
result = response.content
h = HTMLParser()
result = h.unescape(result)
result = client.parseDOM(result,
'ul',
attrs={'class': 'resultsList hits'})
items = client.parseDOM(result, 'li')
items = [x for x in items if not str(x).startswith("<a href")]
orgtitles = []
for content in items:
try:
orgtitle = str(
client.parseDOM(
content,
'div',
attrs={'class':
'filmPreview__originalTitle'})[0])
except:
orgtitle = "0"
pass
orgtitles.append(orgtitle)
ids = client.parseDOM(items, 'data', ret='data-id')
titles = client.parseDOM(result, 'data', ret='data-title')
years = client.parseDOM(result,
'span',
attrs={'class': 'filmPreview__year'})
for item in zip(titles, ids, years, orgtitles):
f_title = str(item[0])
f_id = str(item[1])
f_year = str(item[2])
f_orgtitle = str(item[3])
teststring = cleantitle.normalize(
cleantitle.getsearch(searchtitle))
words = cleantitle.normalize(
cleantitle.getsearch(f_title)).split(" ")
if self.contains_all_wors(teststring,
words) and year == f_year:
return (f_title, f_id, f_year, f_orgtitle, "SERIAL",
season, episode)
except Exception, e:
print str(e)
return
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.getsearch(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = cleantitle.get(titles[0])
scraper = cfscrape.create_scraper()
data = scraper.get(query).content
#data = client.request(query, referer=self.base_link)
data = client.parseDOM(data, 'div', attrs={'class': 'result-item'})
r = dom_parser.parse_dom(data, 'div', attrs={'class': 'title'})
r = zip(
dom_parser.parse_dom(r, 'a'),
dom_parser.parse_dom(data, 'span', attrs={'class': 'year'}))
url = []
for i in range(len(r)):
title = cleantitle.get(r[i][0][1])
title = re.sub('(\d+p|4k|3d|hd|season\d+)', '', title)
y = r[i][1][1]
link = r[i][0][0]['href']
if 'season' in title: continue
if t == title and y == year:
if 'season' in link:
url.append(source_utils.strip_domain(link))
print url[0]
return url[0]
else:
url.append(source_utils.strip_domain(link))
return url
except:
return
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
url = urlparse.urljoin(
self.base_link, self.search_link %
urllib.quote_plus(cleantitle.getsearch(title)))
r = client.request(url, headers=headers, timeout='15')
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'),
client.parseDOM(r, 'a', ret='title'))
results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r]
try:
r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0]
url = [
i[0] for i in r
if self.matchAlias(i[1], aliases) and (year == i[2])
][0]
except:
url = None
pass
if (url == None):
url = [
i[0] for i in results if self.matchAlias(i[1], aliases)
][0]
return url
except:
return
def search_ep(self, titles,season,episode,year):
try:
searchtitles = titles
for searchtitle in searchtitles:
simply_name = cleantitle.normalize(cleantitle.getsearch(searchtitle))
data = {
's':cleantitle.normalize(cleantitle.getsearch(searchtitle)),
'search-form':'5'
}
response = requests.post(self.base_link, data = data)
result = response.text
result = client.parseDOM(result, 'ul', attrs={'class':'film-num-list'})
if len(result) == 2:
result = result[1]
titles = client.parseDOM(result, 'a')
links = client.parseDOM(result, 'a', ret='href')
rok = client.parseDOM(result, 'li')
counter = 0
for item in zip(titles,links):
if not str(item[1]).startswith("http://filmdom.pl/serials/"):
continue
rok_film = str(rok[counter][-4:])
counter +=1
t2 = item[0].split(" / ")
for tytul in t2:
if searchtitle == "Gra o tron":
year = "2011"
tytul = tytul.split(" (")
words = cleantitle.normalize(cleantitle.getsearch(tytul[0])).split(" ")
if self.contains_all_wors(simply_name, words) and year == rok_film:
return item[1]+"?sezon=%s&odcinek=%s" % (season,episode)
return
except Exception, e:
print str(e)
return
def search(self, title, localtitle, year, is_movie_search):
try:
titles = []
titles.append(cleantitle.normalize(cleantitle.getsearch(title)))
titles.append(
cleantitle.normalize(cleantitle.getsearch(localtitle)))
for title in titles:
url = urlparse.urljoin(self.base_link, self.search_link)
url = url % urllib.quote(title)
cookies = client.request(self.base_link, output='cookie')
cache.cache_insert('naszekino_cookie', cookies)
result = client.request(url, cookie=cookies)
result = result.decode('utf-8')
result = client.parseDOM(result,
'div',
attrs={'class': 'col-sm-4'})
for item in result:
link = str(client.parseDOM(item, 'a', ret='href')[0])
nazwa = str(client.parseDOM(item, 'a', ret='title')[0])
#rok = str(client.parseDOM(result, 'div', attrs={'class': 'year'})[0])
names_found = nazwa.split('/')
names_found = [
cleantitle.normalize(cleantitle.getsearch(i))
for i in names_found
]
for name in names_found:
name = name.replace(" ", " ")
title = title.replace(" ", " ")
words = title.split(" ")
if self.contains_all_wors(name,
words) and str(year) in link:
return link
except Exception, e:
print e
return
def sources(self, url, hostDict, hostprDict):
try:
words = cleantitle.getsearch(url).split(' ')
search_url = urlparse.urljoin(
self.base_link, self.search_link) % urllib.quote_plus(url)
result = client.request(search_url)
sources = []
result = client.parseDOM(result,
'div',
attrs={'class': 'tile-container'})
for el in result:
main = client.parseDOM(el, 'h3')
link = client.parseDOM(main, 'a', ret='href')[0]
found_title = client.parseDOM(main, 'a')[0]
if not self.contains_all_wors(found_title, words):
continue
quality = client.parseDOM(el,
'a',
attrs={'class': 'qualityLink'})
q = 'SD'
if quality:
if (quality[0] == '720p'):
q = 'HD'
if (quality[0] == '1080p'):
q = '1080p'
lang, info = self.get_lang_by_type(found_title)
sources.append({
'source': 'trt',
'quality': q,
'language': lang,
'url': link,
'info': info,
'direct': False,
'debridonly': False
})
return sources
except:
return sources
def searchShow(self, title, season, aliases, headers):
try:
title = cleantitle.normalize(title)
search = '%s Season %s' % (title, season)
url = urlparse.urljoin(
self.base_link, self.search_link %
urllib.quote_plus(cleantitle.getsearch(search)))
r = client.request(url)
url = re.findall(
'<a href=\"(.+?\/movie\/%s-season-%s-.+?\.html)\"' %
(cleantitle.geturl(title), season), r)[0]
return url
except:
return
def searchShow(self, title, season, aliases, headers):
try:
title = cleantitle.normalize(title)
search = '%s Season %01d' % (title, int(season))
url = urlparse.urljoin(
self.base_link, self.search_link %
urllib.quote_plus(cleantitle.getsearch(search)))
log_utils.log('shit Returned: %s' % str(url), log_utils.LOGNOTICE)
r = client.request(url, headers=headers, timeout='15')
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'),
client.parseDOM(r, 'a', ret='title'))
r = [(i[0], i[1], re.findall('(.*?)\s+-\s+Season\s+(\d)', i[1]))
for i in r]
r = [(i[0], i[1], i[2][0]) for i in r if len(i[2]) > 0]
url = [
i[0] for i in r
if self.matchAlias(i[2][0], aliases) and i[2][1] == season
][0]
return url
except:
return
def sources(self, url, hostDict, hostprDict):
try:
#import pydevd
#pydevd.settrace(stdoutToServer=True, stderrToServer=True)
sources = []
titles = []
titles.append(url[0])
titles.append(url[1])
try:
year = url[2]
except:
year = ''
for url_single in titles:
url_single = cleantitle.normalize(
cleantitle.getsearch(url_single))
words = url_single.split(' ')
search_url = urlparse.urljoin(
self.base_link,
self.search_link) % (url_single + " " + year)
cookies = client.request(self.base_link, output='cookie')
verifyGet = client.request(self.verify, cookie=cookies)
cookies = cookies + ";tmvh=" + self.crazy_cookie_hash(
verifyGet)
cache.cache_insert('szukajka_cookie', cookies)
result = client.request(search_url, cookie=cookies)
result = client.parseDOM(result,
'div',
attrs={'class': 'element'})
for el in result:
found_title = str(
client.parseDOM(el, 'div',
attrs={'class': 'title'})[0]).lower()
if ("zwiastun" or "trailer") in str(found_title).lower():
continue
if len(words) >= 4:
regtest = re.findall("\d{3}[^1080p]", found_title)
if len(regtest) > 0:
if not self.contains_all_wors(
found_title,
words) and year not in found_title:
continue
else:
if not self.contains_all_wors(found_title, words):
continue
else:
if not self.contains_all_wors(
found_title,
words) and year not in found_title:
continue
q = 'SD'
if self.contains_word(found_title,
'1080p') or self.contains_word(
found_title, 'FHD'):
q = '1080p'
elif self.contains_word(found_title, '720p'):
q = 'HD'
link = client.parseDOM(el,
'a',
attrs={'class': 'link'},
ret='href')[0]
transl_type = client.parseDOM(el,
'span',
attrs={'class':
'version'})[0]
transl_type = transl_type.split(' ')
transl_type = transl_type[-1]
host = client.parseDOM(el, 'span', attrs={'class':
'host'})[0]
host = host.split(' ')
host = host[-1]
lang, info = self.get_lang_by_type(transl_type)
sources.append({
'source': host,
'quality': q,
'language': lang,
'url': link,
'info': info,
'direct': False,
'debridonly': False
})
continue
return sources
except Exception, e:
print e
return sources
def clean_serach(self, serach_str):
result = cleantitle.getsearch(serach_str)
result = re.sub(' +', ' ', result)
return result.strip()