def search(self, title, localtitle, year):
try:
import sys
reload(sys)
sys.setdefaultencoding('utf8')
simply_name = cleantitle.get(localtitle)
simply_name2 = cleantitle.get(title)
simply_name = cleantitle.query(localtitle).split(' ')
simply_name2 = cleantitle.query(title).split(' ')
query = self.search_link % urllib.quote_plus(
cleantitle.query(localtitle))
url = urlparse.urljoin(self.base_link, query)
result = client.request(url)
result = client.parseDOM(result,
'div',
attrs={'class': 'row search-results'})
results = client.parseDOM(
result,
'div',
attrs={'class': 'item-detail-bigblock title title-bigblock'})
for result in results:
movieneourl = client.parseDOM(result, 'a', ret='href')[0]
result = client.parseDOM(result, 'a')[0]
for word in simply_name:
if word in result and year in result:
return [
urlparse.urljoin(self.base_link, movieneourl),
result
]
continue
except Exception, e:
print str(e)
return
def search(self, title, localtitle, year, search_type):
try:
url = self.do_search(cleantitle.query(title), title, localtitle, year, search_type)
if not url:
url = self.do_search(cleantitle.query(localtitle), title, localtitle, year, search_type)
return url
except:
return
def __search(self, title, season):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(title)))
query = urlparse.urljoin(self.base_link, query)
t = cleantitle.get(title)
r = client.request(query)
r = client.parseDOM(r, 'div', attrs={'class': 'moviefilm'})
r = client.parseDOM(r, 'div', attrs={'class': 'movief'})
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a'))
for i in r]
r = [(i[0][0], i[1][0].lower()) for i in r
if len(i[0]) > 0 and len(i[1]) > 0]
r = [(i[0], i[1], re.findall('(.+?)\s+(?:saison)\s+(\d+)', i[1]))
for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1],
i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = [(i[0], i[1], re.findall('\((.+?)\)$', i[1]), i[2]) for i in r]
r = [(i[0], i[2][0] if len(i[2]) > 0 else i[1], i[3]) for i in r]
r = [
i[0] for i in r
if t == cleantitle.get(i[1]) and int(i[2]) == int(season)
][0]
url = re.findall('(?://.+?|)(/.+)', r)[0]
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
return url
except:
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)))
cookies = client.request(self.base_link, output='cookie')
cache.cache_insert('alltube_cookie', cookies)
for title in titles:
r = client.request(urljoin(self.base_link, self.search_link),
post={'search': cleantitle.query(title)}, headers={'Cookie': cookies})
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.encode('utf-8').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_words(name, words) and (not found_year or found_year == year):
return url
else:
continue
continue
except:
return
def __search(self, titles, year, content_type):
try:
query = self.search_link % (quote_plus(cleantitle.query(
titles[0])), content_type)
query = urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(query)
r = dom_parser.parse_dom(r, 'div', attrs={'id': 'search'})
r = dom_parser.parse_dom(r, 'table')
r = dom_parser.parse_dom(r,
'tr',
attrs={'class': re.compile('entry\d+')})
r = [(dom_parser.parse_dom(i, 'a'),
dom_parser.parse_dom(i,
'img',
attrs={
'class': 'flag',
'alt': 'de'
})) for i in r]
r = [i[0] for i in r if i[0] and i[1]]
r = [(i[0].attrs['href'], i[0].content) for i in r]
r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1],
i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0]
return source_utils.strip_domain(r)
except:
return
def __search(self, titles, year):
try:
n = cache.get(self.__get_nonce, 24)
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0])), n)
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(query)
r = json.loads(r)
r = [(r[i].get('url'), r[i].get('title'),
r[i].get('extra').get('date')) for i in r]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0]
return source_utils.strip_domain(r)
except:
return
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0] + ' ' + year)))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
r = dom_parser.parse_dom(r,
'figure',
attrs={'class': 'pretty-figure'})
r = dom_parser.parse_dom(r, 'figcaption')
for i in r:
title = client.replaceHTMLCodes(i[0]['title'])
title = cleantitle.get(title)
if title in t:
x = dom_parser.parse_dom(i, 'a', req='href')
return source_utils.strip_domain(x[0][0]['href'])
return
except:
return
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(query)
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'details'})
r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'title'}),
dom_parser.parse_dom(i, 'span', attrs={'class': 'year'}))
for i in r]
r = [(dom_parser.parse_dom(i[0][0], 'a',
req='href'), i[1][0].content) for i in r
if i[0] and i[1]]
r = [(i[0][0].attrs['href'],
client.replaceHTMLCodes(i[0][0].content), i[1]) for i in r
if i[0]]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0]
return source_utils.strip_domain(r)
except:
return
def search(self, localtitle, year, search_type):
try:
simply_name = cleantitle.get(localtitle)
query = self.search_link % urllib.quote_plus(
cleantitle.query(localtitle))
query = urlparse.urljoin(self.base_link, query)
result = client.request(query)
result = client.parseDOM(result, 'div', attrs={'id': search_type})
links = client.parseDOM(result, 'figcaption')
names = client.parseDOM(result, 'figcaption', ret='title')
urls = []
for i in range(len(names)):
name = cleantitle.get(names[i])
url = client.parseDOM(links[i], 'a', ret='href')[0]
if (name == simply_name):
urls.append(url)
if len(urls) == 1:
return urls[0]
else:
return self.findMatchByYear(year, urls)
except:
return
def search(self, title, localtitle, year):
try:
simply_name = cleantitle.get(localtitle)
simply_name2 = cleantitle.get(title)
query = self.search_link % urllib.quote_plus(cleantitle.query(localtitle))
url = urlparse.urljoin(self.base_link, query)
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0',
'Referer': 'https://segos.es/?page=login'}
data = {"login": self.user_name, 'password': self.user_pass, 'loguj': ''}
url = 'https://segos.es/?page=login'
s = requests.Session()
s.post('https://segos.es/?page=login', data=data, headers=headers)
url = urlparse.urljoin(self.base_link, query)
k = s.get(url)
result = k.text
results = client.parseDOM(result, 'div', attrs={'class': 'col-lg-12 col-md-12 col-xs-12'})
for result in results:
segosurl = client.parseDOM(result, 'a', ret='href')[0]
result = client.parseDOM(result, 'a')
segostitles = cleantitle.get(result[1]).split('/')
for segostitle in segostitles:
if simply_name == segostitle or simply_name2 == segostitle:
return urlparse.urljoin(self.base_link, segosurl)
continue
except Exception as e:
print(str(e))
return
def __search(self, titles, year, season='0'):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']
r = self.scraper.get(query).content
r = dom_parser.parse_dom(r, 'ul', attrs={'class': ['products', 'row']})
r = dom_parser.parse_dom(r, 'div', attrs={'class': ['box-product', 'clearfix']})
if int(season) > 0:
r = [i for i in r if dom_parser.parse_dom(i, 'div', attrs={'class': 'episode'})]
else:
r = [i for i in r if not dom_parser.parse_dom(i, 'div', attrs={'class': 'episode'})]
r = dom_parser.parse_dom(r, 'h3', attrs={'class': 'title-product'})
r = dom_parser.parse_dom(r, 'a', req='href')
r = [(i.attrs['href'], i.content.lower()) for i in r if i]
r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = [(i[0], i[1], i[2], re.findall('(.+?)\s+(?:staf+el|s)\s+(\d+)', i[1])) for i in r]
r = [(i[0], i[3][0][0] if len(i[3]) > 0 else i[1], i[2], i[3][0][1] if len(i[3]) > 0 else '0') for i in r]
r = [(i[0], i[1].replace(' hd', ''), i[2], '1' if int(season) > 0 and i[3] == '0' else i[3]) for i in r]
r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y and int(i[3]) == int(season)][0]
url = source_utils.strip_domain(r)
url = url.replace('-info', '-stream')
return url
except:
return
def __search(self, titles, year, season='0'):
try:
aj = cache.get(self.__get_ajax_object, 24)
t = [cleantitle.get(i) for i in set(titles) if i]
y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']
r = client.request(aj.get('ajax_url'), post={'action': aj.get('search'), 'nonce': aj.get('snonce'),
'query': cleantitle.query(titles[0])})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'search-result'})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'search-item-content'})
r = dom_parser.parse_dom(r, 'a', req='href')
r = [(i.attrs['href'], i.content.lower()) for i in r if i]
r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})', i[1])) for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = [(i[0], i[1], i[2], re.findall('(.+?)\s+(?:staf+el|s)\s+(\d+)', i[1])) for i in r]
r = [(i[0], i[3][0][0] if len(i[3]) > 0 else i[1], i[2], i[3][0][1] if len(i[3]) > 0 else '0') for i in r]
r = [(i[0], i[1].replace(' hd', ''), i[2], '1' if int(season) > 0 and i[3] == '0' else i[3]) for i in r]
r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y and int(i[3]) == int(season)][0]
return source_utils.strip_domain(r)
except:
return
def search(self, localtitle, year, search_type):
try:
simply_name = cleantitle.get(localtitle)
query = self.search_link % urllib.quote_plus(
cleantitle.query(localtitle))
query = urlparse.urljoin(self.base_link, query)
result = self.scraper.get(query).content
result = client.parseDOM(result,
'div',
attrs={'class': 'result-item'})
for x in result:
correct_type = client.parseDOM(x,
'span',
attrs={'class': search_type})
correct_year = client.parseDOM(x,
'span',
attrs={'class':
'year'})[0] == year
name = client.parseDOM(x, 'div', attrs={'class': 'title'})[0]
url = client.parseDOM(name, 'a', ret='href')[0]
name = cleantitle.get(client.parseDOM(name, 'a')[0])
if (correct_type and correct_year and name == simply_name):
return url
except:
return
def sezonlukdizi_tvcache(self):
try:
url = urlparse.urljoin(self.base_link, self.search_link)
result = client.request(url, redirect=False)
if not result:
r = client.request(self.base_link)
r = \
dom_parser.parse_dom(r, 'script', attrs={'type': 'text/javascript', 'src': re.compile('.*/js/dizi.*')},
req='src')[0]
url = urlparse.urljoin(self.base_link, r.attrs['src'])
result = client.request(url)
result = re.compile('{(.+?)}').findall(result)
result = [
(re.findall('u\s*:\s*(?:\'|\")(.+?)(?:\'|\")', i), re.findall('d\s*:\s*(?:\'|\")(.+?)(?:\',|\")', i))
for i in result]
result = [(i[0][0], i[1][0]) for i in result if len(i[0]) > 0 and len(i[1]) > 0]
result = [(re.compile('/diziler(/.+?)(?://|\.|$)').findall(i[0]), re.sub('&#\d*;', '', i[1])) for i in
result]
result = [(i[0][0] + '/', cleantitle.query(self.lat2asc(i[1]))) for i in result if len(i[0]) > 0]
return result
except BaseException:
return []
def search(self, localtitle, year, search_type):
try:
url = urlparse.urljoin(self.base_link, self.search_link)
r = client.request(url,
redirect=False,
post={
'q': cleantitle.query(localtitle),
'sb': ''
})
r = client.parseDOM(r, 'div', attrs={'class': 'small-item'})
local_simple = cleantitle.get(localtitle)
for row in r:
name_found = client.parseDOM(row, 'a')[1]
year_found = name_found[name_found.find("(") +
1:name_found.find(")")]
url = client.parseDOM(row, 'a', ret='href')[1]
if not search_type in url:
continue
if cleantitle.get(
name_found) == local_simple and year_found == year:
return url
except:
return
def __search(self, titles, year):
try:
query = self.search_link % urllib.quote_plus(
cleantitle.query(titles[0]))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(query, XHR=True)
if r and r.startswith('{'): r = '[%s]' % r
r = json.loads(r)
r = [(i['url'], i['name']) for i in r
if 'name' in i and 'url' in i]
r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})?\)*$', i[1]))
for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1],
i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0]
url = source_utils.strip_domain(r)
url = url.replace('serien/', '')
return url
except:
return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
query = self.search_link % urllib.quote_plus(
cleantitle.query(tvshowtitle))
for i in range(3):
result = self.scraper.get(query).content
if not result is None:
break
t = [tvshowtitle] + source_utils.aliases_to_array(aliases)
t = [cleantitle.get(i) for i in set(t) if i]
items = dom_parser.parse_dom(result,
'div',
attrs={'class': 'result'})
url = None
for i in items:
result = re.findall(r'href="([^"]+)">(.*)<', i.content)
if re.sub('<[^<]+?>', '', cleantitle.get(cleantitle.normalize(result[0][1]))) in t and year in \
result[0][1]:
url = result[0][0]
if not url is None:
break
url = url.encode('utf-8')
return url
except:
return
def __search(self, search_link, imdb, titles):
try:
query = search_link % (urllib.quote_plus(
cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'big-list'})
r = dom_parser.parse_dom(r, 'table', attrs={'class': 'row'})
r = dom_parser.parse_dom(r, 'td', attrs={'class': 'list-name'})
r = dom_parser.parse_dom(r, 'a', req='href')
r = [
i.attrs['href'] for i in r
if i and cleantitle.get(i.content) in t
][0]
url = source_utils.strip_domain(r)
r = client.request(urlparse.urljoin(self.base_link, url))
r = dom_parser.parse_dom(r,
'a',
attrs={'href': re.compile('.*/tt\d+.*')},
req='href')
r = [re.findall('.+?(tt\d+).*?', i.attrs['href']) for i in r]
r = [i[0] for i in r if i]
return url if imdb in r else None
except:
return
def __search(self, titles, year):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(urljoin(self.base_link, self.search_link),
post={'query': cleantitle.query(titles[0])})
r = dom_parser.parse_dom(r, 'li', attrs={'class': 'entTd'})
r = dom_parser.parse_dom(r,
'div',
attrs={'class': 've-screen'},
req='title')
r = [(dom_parser.parse_dom(i, 'a', req='href'),
i.attrs['title'].split(' - ')[0]) for i in r]
r = [(i[0][0].attrs['href'], i[1],
re.findall('(.+?) \(*(\d{4})', i[1])) for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1],
i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0]
return source_utils.strip_domain(r)
except:
return
def do_search(self, title, local_title, year, video_type):
try:
url = urlparse.urljoin(self.base_link, self.search_link)
url = url % urllib.quote_plus(cleantitle.query(title))
result = client.request(url)
result = client.parseDOM(result, 'div', attrs={'class': 'item'})
for row in result:
row_type = client.parseDOM(row,
'div',
attrs={'class': 'typepost'})[0]
if row_type != video_type:
continue
names = client.parseDOM(row, 'span', attrs={'class': 'tt'})[0]
names = names.split('/')
year_found = client.parseDOM(row,
'span',
attrs={'class': 'year'})
titles = [cleantitle.get(i) for i in [title, local_title]]
if self.name_matches(names, titles,
year) and (len(year_found) == 0
or year_found[0] == year):
url = client.parseDOM(row, 'a', ret='href')[0]
return urlparse.urljoin(self.base_link, url)
except:
return
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0]) + ' ' + year))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i][0]
r = client.request(query)
r = client.parseDOM(r, 'div', attrs={'class': 'karatula'})
for i in r:
title = client.parseDOM(i, 'a', ret='title')[0]
y = re.findall('(\d{4})', title)[0]
title = cleantitle.get_simple(title)
if t in title and y == year:
x = dom_parser.parse_dom(i, 'a', req='href')
return source_utils.strip_domain(x[0][0]['href'])
return
except:
return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
query = self.tvsearch_link % urllib.quote_plus(
cleantitle.query(tvshowtitle))
query = urlparse.urljoin(self.base_link, query.lower())
result = client.request(query, referer=self.base_link)
result = client.parseDOM(result,
'div',
attrs={'class': 'index_item.+?'})
result = [(dom.parse_dom(i, 'a', req=['href', 'title'])[0])
for i in result if i]
result = [(
i.attrs['href']
) for i in result if cleantitle.get(tvshowtitle) == cleantitle.get(
re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+|3D)(\.|\)|\]|\s|)(.+|)',
'',
i.attrs['title'],
flags=re.I))][0]
url = client.replaceHTMLCodes(result)
url = url.encode('utf-8')
return url
except Exception:
return
def __search(self, titles, imdb, year):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(query, XHR=True)
r = json.loads(r)
r = [(i.get('title'), i.get('custom_fields', {}))
for i in r.get('posts', [])]
r = [(i[0], i[1]) for i in r if i[0] and i[1]]
r = [(i[0], i[1].get('Streaming', ['']), i[1].get('Jahr', ['0']),
i[1].get('IMDb-Link', [''])) for i in r if i]
r = [(i[0], i[1][0], i[2][0], re.findall('.+?(tt\d+).*?', i[3][0]))
for i in r if i[0] and i[1] and i[2] and i[3]]
r = [
i[1] for i in r
if imdb in i[3] or (cleantitle.get(i[0]) in t and i[2] in y)
][0]
return source_utils.strip_domain(r)
except:
return
def __search(self, titles):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'nag'})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'item-video'})
r = dom_parser.parse_dom(r, 'h2', attrs={'class': 'entry-title'})
r = dom_parser.parse_dom(r, 'a', req='href')
for i in r:
title = i[1]
if re.search('\*(?:.*?)\*', title) is not None:
title = re.sub('\*(?:.*?)\*', '', title)
title = cleantitle.get(title)
if title in t:
return source_utils.strip_domain(i[0]['href'])
else:
return
except:
return
def __search(self, titles, year):
try:
query = self.search_link % (quote_plus(cleantitle.query(
titles[0])))
query = urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
r = dom_parser.parse_dom(r, 'div', attrs={'id': 'main'})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'panel-body'})
r = [
(dom_parser.parse_dom(i.content,
'h4',
attrs={'class': 'title-list'}),
dom_parser.parse_dom(i.content,
'a',
attrs={'href':
re.compile('.*/year/.*')}))
for i in r
]
r = [(dom_parser.parse_dom(i[0][0].content, 'a', req='href'),
i[1][0].content if i[1] else '0') for i in r if i[0]]
r = [(i[0][0].attrs['href'], i[0][0].content,
re.sub('<.+?>|</.+?>', '', i[1])) for i in r
if i[0] and i[1]]
r = [(i[0], i[1], i[2].strip()) for i in r if i[2]]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [
i[0] for i in r if cleantitle.get(i[1]) in t and i[2] == year
][0]
return source_utils.strip_domain(r)
except:
return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
query = self.search_link % urllib.quote_plus(
cleantitle.query(tvshowtitle))
# req page 3 times to workaround their BS random 404's
# responses (legit & BS 404s) are actually very fast: timeout prob not important
for i in range(4):
result = client.request(query, timeout=3)
if not result == None: break
t = [tvshowtitle] + source_utils.aliases_to_array(aliases)
t = [cleantitle.get(i) for i in set(t) if i]
result = re.compile(
'itemprop="url"\s+href="([^"]+).*?itemprop="name"\s+class="serie-title">([^<]+)',
re.DOTALL).findall(result)
for i in result:
if cleantitle.get(cleantitle.normalize(
i[1])) in t and year in i[1]:
url = i[0]
url = url.encode('utf-8')
#log_utils.log('\n\n~~~ outgoing tvshow() url')
#log_utils.log(url)
# returned 'url' format like: /serie/x_files
return url
except:
return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
url = urlparse.urljoin(
self.base_link, self.search_link %
urllib.quote_plus(cleantitle.query(tvshowtitle)))
self.tvshowtitle = tvshowtitle
return url
except:
return
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
q = cleantitle.query(tvshowtitle)
r = self.scraper.get(self.search_link % q, headers={'referer': self.base_link}).content
r = client.parseDOM(r, 'div', attrs={'valign': '.+?'})
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title'), client.parseDOM(i, 'a'))
for i in r]
r = [(i[0][0], i[1][0], i[2][0]) for i in r if i[0] and i[1] and i[2]]
return r[0][0]
except:
return
def __search(self, titles):
try:
query = self.search_link % quote_plus(cleantitle.query(titles[0]))
query = urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query, XHR=True)
r = json.loads(r)
r = [(i.get('url'), i.get('name')) for i in r]
r = [(i[0]) for i in r if cleantitle.get(i[1]) in t][0]
return source_utils.strip_domain(r)
except:
return
def __search(self, titles):
try:
query = self.search_link % quote_plus(cleantitle.query(titles[0]))
query = urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
r = json.loads(r)
r = [(i.get('id'), i.get('value')) for i in r]
r = [i[0] for i in r if cleantitle.get(i[1]) in t][0]
return r
except:
return
