def get_movie(self, imdb, title, year):
mytitle = title
try:
t = 'http://www.imdb.com/title/%s' % imdb
t = client.source(t, headers={'Accept-Language': 'es-ES'})
t = client.parseDOM(t, 'title')[0]
t = re.sub('(?:\(|\s)\d{4}.+', '', t).strip()
mytitle = t
except:
pass
try:
t = cleantitle.get(mytitle)
query = self.search3_link % urllib.quote_plus(cleantitle.query2(mytitle))
query = urlparse.urljoin(self.base_link, query)
result = client2.http_get(query)
result = re.sub(r'[^\x00-\x7F]+','', result)
r = result.split('<li class=')
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'i'), re.findall('\((\d{4})\)', i)) for i in r]
r = [(i[0][0], re.sub('\(|\)','', i[1][0]), i[2][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0 and len(i[2]) > 0]
r = [i[0] for i in r if year == i[2]][0]
try: url = re.findall('//.+?(/.+)', r)[0]
except: url = r
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
return url
except:
pass
def get_show(self, imdb, tvdb, tvshowtitle, year):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.query2(tvshowtitle)))
query = urlparse.urljoin(self.base_link, query)
result = client.request(query)
result = result.decode('utf-8-sig')
result = client.parseDOM(result, 'ul', attrs={'id': 'resultList2'})[0]
result = client.parseDOM(result, 'li')
result = [(client.parseDOM(i,'div', attrs={'class':'title'}),
client.parseDOM(i, 'div', attrs={'class': 'info'}),
client.parseDOM(i, 'a', ret='href')[0]) for i in result]
result = [(i[0][0], re.findall(r"(\d{4})", i[1][0])[0], i[2]) for i in result]
years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]
result = [i for i in result if cleantitle.movie(tvshowtitle) in cleantitle.movie(i[0])]
result = [i[2] for i in result if any(x in i[1] for x in years)][0]
try: url = re.compile('//.+?(/.+)').findall(result)[0]
except: url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
print url
return url
except:
return
def get_movie(self, imdb, title, year):
try:
t = cleantitle.query2(title)
hash = hashlib.md5(title).hexdigest()
query = urllib.urlencode({'keyword': title, 'hash':hash})
url = urlparse.urljoin(self.base_link, self.search_link)
r = client.request(url, post=query, headers=self.headers)
r = json.loads(r)['content']
r = zip(client.parseDOM(r, 'a', ret='href', attrs = {'class': 'ss-title'}), client.parseDOM(r, 'a', attrs = {'class': 'ss-title'}))
r = [i[0] for i in r if cleantitle.get(t) == cleantitle.get(i[1])][:2]
r = [(i, re.findall('(\d+)', i)[-1]) for i in r]
url = None
print r
for i in r:
try:
print i[1]
#y, q = cache.get(self.myesmovies_info(), 9000, i[1])
y, q = self.myesmovies_info(i[0])
print("yQ",y,q,year)
if not y == year:
print "NOT",type(y),type(year)
raise Exception()
return urlparse.urlparse(i[0]).path
except:
pass
print(url)
return url
except Exception as e:
control.log('Error %s' % e)
return
def get_movie(self, imdb, title, year):
print("ALLtube originaltitle:%s" % title)
print cleantitle.query(title)
try:
query = self.moviesearch_link % urllib.quote_plus(cleantitle.query2(title))
query = urlparse.urljoin(self.base_link, query)
control.log('ALLTUBE T URL %s' % query)
result = client.source(query)
result = json.loads(result)
result = [i for i in result['suggestions'] if len(i) > 0]
years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]
result = [(i['data'].encode('utf8'),i['value'].encode('utf8')) for i in result]
result = [i for i in result if cleantitle.movie(title) in cleantitle.movie(i[1])]
result = [i[0] for i in result if any(x in i[1] for x in years)][0]
print("ALLtube result :", result)
try: url = re.compile('//.+?(/.+)').findall(result)[0]
except: url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
control.log('ALLTUBE URL %s' % url)
return url
except:
try:
query = self.moviesearch_link % cleantitle.query_quote(originaltitle)
query = urlparse.urljoin(self.base_link, query)
control.log('ALLTUBE T URL %s' % query)
result = client.source(query)
result = json.loads(result)
result = [i for i in result['suggestions'] if len(i) > 0]
years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]
result = [(i['data'].encode('utf8'),i['value'].encode('utf8')) for i in result]
print result
result = [i for i in result if cleantitle.movie(originaltitle) in cleantitle.movie(i[1])]
result = [i[0] for i in result if any(x in i[1] for x in years)][0]
print("ALLtube result :", result)
try: url = re.compile('//.+?(/.+)').findall(result)[0]
except: url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
control.log('ALLTUBE URL %s' % url)
return url
except:
return
def get_movie(self, imdb, title, year):
try:
r = client.request(self.base_link, limit='0', output='extended')
cookie2 = r[4]
headers = r[3]
r1 = r[0]
t = cleantitle.query2(title)
hash = hashlib.md5(title).hexdigest()
query = urllib.urlencode({'keyword': title, 'hash': hash})
url = urlparse.urljoin(self.base_link, self.search_link)
headers['X-Requested-With'] = 'XMLHttpRequest'
r = client.request(url, post=query, headers=headers)
print "res", r
r = json.loads(r)['content']
r = zip(
client.parseDOM(r,
'a',
ret='href',
attrs={'class': 'ss-title'}),
client.parseDOM(r, 'a', attrs={'class': 'ss-title'}))
r = [i[0] for i in r
if cleantitle.get(t) == cleantitle.get(i[1])][:2]
r = [(i, re.findall('(\d+)', i)[-1]) for i in r]
url = None
print r
for i in r:
try:
print i[1]
#y, q = cache.get(self.myesmovies_info(), 9000, i[1])
y, q = self.myesmovies_info(i[0])
print("yQ", y, q, year)
if not y == year:
print "NOT", type(y), type(year)
raise Exception()
print("URL", urlparse.urlparse(i[0]).path, i[0])
return urlparse.urlparse(i[0]).path
except:
pass
return url
except Exception as e:
control.log('Error %s' % e)
return
def get_movie(self, imdb, title, year):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.query2(title)))
query = urlparse.urljoin(self.base_link, query)
result = client.request(query)
title = cleantitle.movie(title)
result = client.parseDOM(result, 'div', attrs={'class':'well_2'})
result = [(client.parseDOM(i, 'a', ret='href')[0], client.parseDOM(i, 'a')[0],str(re.findall(r"(\d{4})", client.parseDOM(i, 'a')[0])[0])) for i in result]
years = ['%s' % str(year), '%s' % str(int(year)+1), '%s' % str(int(year)-1)]
result = [i for i in result if title in cleantitle.movie(i[1])]
result = [i[0] for i in result if any(x in i[2] for x in years)][0]
try: url = re.compile('//.+?(/.+)').findall(result)[0]
except: url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
control.log('Segos URL %s' % url)
return url
except:
return
def get_show(self, imdb, tvdb, tvshowtitle, year):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query2(tvshowtitle)))
query = urlparse.urljoin(self.base_link, query)
result = client.request(query)
result = result.decode('utf-8-sig')
result = client.parseDOM(result, 'ul', attrs={'id':
'resultList2'})[0]
result = client.parseDOM(result, 'li')
result = [(client.parseDOM(i, 'div', attrs={'class': 'title'}),
client.parseDOM(i, 'div', attrs={'class': 'info'}),
client.parseDOM(i, 'a', ret='href')[0]) for i in result]
result = [(i[0][0], re.findall(r"(\d{4})", i[1][0])[0], i[2])
for i in result]
years = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1)
]
result = [
i for i in result
if cleantitle.movie(tvshowtitle) in cleantitle.movie(i[0])
]
result = [i[2] for i in result if any(x in i[1] for x in years)][0]
try:
url = re.compile('//.+?(/.+)').findall(result)[0]
except:
url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
print url
return url
except:
return
def get_movie(self, imdb, title, year):
try:
query = self.moviesearch_link % urllib.quote_plus(
cleantitle.query2(title))
query = urlparse.urljoin(self.base_link, query)
result = client.source(query)
result = json.loads(result)
result = [i for i in result['suggestions'] if len(i) > 0]
years = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1)
]
result = [(i['data'].encode('utf8'), i['value'].encode('utf8'))
for i in result]
result = [
i for i in result
if cleantitle.movie(title) in cleantitle.movie(i[1])
]
result = [i[0] for i in result if any(x in i[1] for x in years)][0]
try:
url = re.compile('//.+?(/.+)').findall(result)[0]
except:
url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
return url
except:
try:
query = self.moviesearch_link % cleantitle.query_quote(
originaltitle)
query = urlparse.urljoin(self.base_link, query)
result = client.source(query)
result = json.loads(result)
result = [i for i in result['suggestions'] if len(i) > 0]
years = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1)
]
result = [(i['data'].encode('utf8'), i['value'].encode('utf8'))
for i in result]
result = [
i for i in result if cleantitle.movie(originaltitle) in
cleantitle.movie(i[1])
]
result = [
i[0] for i in result if any(x in i[1] for x in years)
][0]
try:
url = re.compile('//.+?(/.+)').findall(result)[0]
except:
url = result
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
return url
except:
return
