def EPISOADE(continut,sezon):
#link=get_url(url)
#<h3 align="center" style="color:#000;"> Supernatural 2005 online - sezonul 8</h3>
#match=re.compile('<h3.+?>(.+?)online - (sezonul [0-9]+).*?</h3>', re.IGNORECASE).findall(link)
match=re.compile('<td class="ep">(.+?)</td><td class="tf">(.+?)</td><td class="ad"><a href="(.+?)".+?target=', re.IGNORECASE).findall(continut)
#print match
for episod,nume,legatura in match:
legatura=legatura.replace(" ", "%20")
#print legatura
episod = htmlcleaner.clean(episod, strip=False)
nume = htmlcleaner.clean(nume, strip=False)
nume = nume.replace('<font color="#000">',"")
nume = nume.replace('</font>',"")
if 'Episodul ' in episod:
episod = episod.replace('Episodul ',"EP")
if 'Episod ' in episod:
episod = episod.replace('Episod ',"EP")
sezon=sezon.strip()
if 'Sezonul ' in sezon:
sezon = sezon.replace('Sezonul ',"S0")
titlu = sezon+' '+episod+' - '+nume
addDirSort(titlu,legatura,8,'')
def CLEANUP_FOR_META(name):
# cleaner for when using a name for a metadata lookup
# left these legacy functions in even thought they are not really needed
# thanks to htmlcleaner. might help with some meta lookups
name = re.sub("'", "'", name)
name = re.sub("&", "&", name)
name = re.sub("Æ", "AE", name)
name = re.sub("'", "'", name)
name = re.sub("í", "i", name)
name = re.sub("½", " 1/2", name)
name = re.sub("½", " 1/2", name)
name = re.sub("&", "&", name)
name = re.sub(""", "", name)
name = re.sub("ô", "o", name)
name = re.sub("é", "e", name)
name = re.sub("ë", "e", name)
name = re.sub("ø", "o", name)
name = re.sub("â", "a", name)
name = re.sub("û", "u", name)
name = re.sub("'", "'", name)
name = re.sub("á", "a", name)
name = re.sub("ü", "u", name)
# run the unicode cleaner, but strip unicode to ASCII
name = htmlcleaner.clean(name, strip=True)
return name
def nameCleaner(name):
name = name.replace('–','')
name = name.replace("’","")
name = name.replace("'s","'s")
name = unicode(name, errors='ignore')
name = htmlcleaner.clean(name,strip=True)
return(name)
def CLEANUP_FOR_META(name):
#cleaner for when using a name for a metadata lookup
# left these legacy functions in even thought they are not really needed
# thanks to htmlcleaner. might help with some meta lookups
name=re.sub(''',"'",name)
name=re.sub('&','&',name)
name=re.sub('Æ','AE',name)
name=re.sub(''',"'",name)
name=re.sub('í','i',name)
name=re.sub('½',' 1/2',name)
name=re.sub('½',' 1/2',name)
name=re.sub('&','&',name)
name=re.sub('"','',name)
name=re.sub('ô','o',name)
name=re.sub('é',"e",name)
name=re.sub('ë',"e",name)
name=re.sub('ø',"o",name)
name=re.sub('â',"a",name)
name=re.sub('û',"u",name)
name=re.sub(''',"'",name)
name=re.sub('á',"a",name)
name=re.sub('ü',"u",name)
#run the unicode cleaner, but strip unicode to ASCII
name = htmlcleaner.clean(name,strip=True)
return name
def Episodes(url, page):
page = int(page) + 1
DOTCOM, THEPAGE, API = GetLang()
headers = {
'Referer':
'http://www.nickjr.%s' % DOTCOM,
'User-Agent':
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.2.13) Gecko/20101203 Firefox/3.6.13 (.NET CLR 3.5.30729)'
}
link = net.http_GET(
'http://www.nickjr.%s/data/property%s.json?&urlKey=%s&apiKey=%s&page=%s'
% (DOTCOM, THEPAGE, url, API, page),
headers=headers).content
link = json.loads(link)
data = link['stream']
for k in data:
for w in k['items']:
try:
try:
URL = w['data']['id']
except:
URL = None
try:
duration = ' - [' + w['data']['duration'] + ']'
except:
duration = ''
try:
name = w['data']['title'] + duration
except:
try:
name = htmlcleaner.cleanUnicode(
w['data']['title']) + duration
except:
try:
name = htmlcleaner.clean(
w['data']['title']) + duration
except:
name = ''
try:
iconimage = w['data']['images']['thumbnail']['r1-1']
except:
try:
iconimage = w['data']['images']['thumbnail']['r25-12']
except:
iconimage = ''
try:
plot = htmlcleaner.cleanUnicode(w['data']['description'])
except:
plot = ''
if URL:
addDir(name, URL, 200, iconimage, plot)
except:
pass
if data:
addDir('Next Page >>', url, 1, '', str(page))
setView('movies', 'episode-view')
def SERIALE(url):
link=get_url(url)
match=re.compile('<li><a.+?href="(.+?.php)" title=".+?">(.+?)</a></li>', re.IGNORECASE).findall(link)
leg=list(set(match))
for legatura,nume in leg:
nume = nume.strip()
nume = htmlcleaner.clean(nume, strip=False)
the_link = 'http://www.serial-online.ro/'+legatura
addDirSort(nume,the_link,6,'')#fost 7
def SEZOANE(url,name):
link=get_url(url)
match=re.compile('<h3 align="center" style="color:#000;">(.+?)<', re.IGNORECASE).findall(link)
#content = link.split(match[0])[1]
content = link.split('<h3 align="center" style="color:#000;">')#[2]
for x in range(1, len(content)):
sezon = match[x-1].replace(' online - s',' - S')
if " »" in sezon:
sezon = sezon.replace(' »','')
sezon = htmlcleaner.clean(sezon)
continut = content[x]
addDirSort(sezon,continut,7,'')
def FILME_INFO(url):
raw=get_url(url)
cpag = raw.split("<div id='numarpagini'>")[1]
cpag = cpag.split("</div>")[0]
match=re.compile('<a.+?href="(.+?)">([0-9]+)</a>.+?', re.IGNORECASE).findall(cpag)
match.reverse()
masterlink = re.compile('(.+?)[0-9]+.html', re.IGNORECASE).findall(match[0][0])[0]
maxpag = match[0][1]
print masterlink, maxpag
x = 1
while x <= int(maxpag):
urlpag='http://www.990.ro/'+masterlink+str(x)+'.html'
print urlpag
x=x+1
content = raw.split("<div align='center' id='coloana-stanga'>")[1]
content = content.split("<div align='center' id='coloana-dreapta'>")[0]
filme=re.compile('width:630px(.+?)<iframe', re.DOTALL).findall(content)
#print filme[0]
#<img src='../poze/filme/240/210278.jpg' alt='
#inf=re.compile("<div.+?><a href='(.+?)'><img src='..(.+?.jpg)'.+?'link'>(.+?)</a> \(([0-9]+)\).+?", re.DOTALL).findall(filme[0])
#print inf
for film in filme:
inf=re.compile("<div.+?><a href='(.+?)'><img src='..(.+?.jpg)'.+'link'>(.+?)</a> \(([0-9]+)\).+<div align='left'.+? font:14px Tahoma;'>(.+?)<.+?<img src='images/nota.png' alt='nota (.+?)'.+Gen:(.+?)</div>.+weight:bold;'>(.+?)</div>", re.DOTALL).findall(film)
for link, img, titlu, an, titlu_ro, nota, gen, descriere in inf:
link = 'http://www.990.ro/'+link
img = 'http://www.990.ro'+img
titlu = htmlcleaner.clean(titlu,True)
titlu_ro = htmlcleaner.clean(titlu_ro).replace("\n","").replace("\t","")
gen = htmlcleaner.clean(gen).replace("\n","").replace("\t","")
descriere = htmlcleaner.clean(descriere).replace("\n","").replace("\t","")
nota = float(nota)/2
print link, img, titlu, an,titlu_ro , nota, htmlcleaner.clean(gen), htmlcleaner.clean(descriere)
addDir2(titlu,link,4,img,descriere, img, nota, int(an))
#print link, img, titlu, an#name,url,mode,iconimage,description,fanart
# pagina urmatoare
match=re.compile('.+?-([0-9]+).html', re.IGNORECASE).findall(url)
nr_pagina = match[0]
#stop XBMC
if len(filme)==20:
addNext('Pagina '+str(int(nr_pagina)+1)+' din '+maxpag,'http://www.990.ro/'+masterlink+str(int(nr_pagina)+1)+'.html', 1, next_thumb)
def cleanName(self, s, remove_year=False):
if remove_year and re.search('\\(\\d\\d\\d\\d\\)$', s):
s = s[0:len(s)-7]
s = htmlcleaner.clean(s,strip=True)
s = s.strip()
return(s)
def AFnameCleaner(name):
name = name.replace('–','')
name = name.replace("’","")
name = name.replace("'s","'s")
name = htmlcleaner.clean(name,strip=True)
return(name)
