def item_list_11(self):
try:
result = client.request(self.tvshows_link)
filter = client.parseDOM(result,
'div',
attrs={'class': 'panel-row row-.+?'})[0]
filter = client.parseDOM(filter,
'div',
attrs={'class': 'views.+?limit-'})
filter = client.parseDOM(filter, 'a', ret='href')
filter = [x for y, x in enumerate(filter) if x not in filter[:y]]
threads = []
for i in range(0, 7):
threads.append(
workers.Thread(self.thread, i, self.tvshows_link_2,
self.tvshows_link_3 % str(i)))
self.data.append('')
[i.start() for i in threads]
[i.join() for i in threads]
items = ''
for i in self.data:
items += json.loads(i)[1]['data']
items = client.parseDOM(items, 'li')
except:
return
for item in items:
try:
title = client.parseDOM(item,
'div',
attrs={'class':
'views-field-title'})[0]
title = client.parseDOM(title, 'a')[0]
title = client.replaceHTMLCodes(title)
title = title.encode('utf-8')
url = client.parseDOM(item, 'a', ret='href')[0]
flt = True if any(url == i for i in filter) else False
url = urlparse.urljoin(self.base_link, url)
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
image = client.parseDOM(item, "img", ret="src")[0]
image = urlparse.urljoin(self.base_link, image)
image = client.replaceHTMLCodes(image)
image = image.encode('utf-8')
self.list.append({
'title': title,
'url': url,
'image': image,
'filter': flt
})
except:
pass
return self.list
def get(self, query):
try:
title, season, episode = re.findall('(.+?) S(\d+)E(\d+)$', query)[0]
season, episode = '%01d' % int(season), '%02d' % int(episode)
title = re.sub('^THE\s+|^A\s+', '', title.strip().upper())
title = cleantitle.get(title)
url = 'http://www.xsubs.tv/series/all.xml'
srsid = cache.get(self.cache, 48, url)
srsid = [i[0] for i in srsid if title == i[1]][0]
url = 'http://www.xsubs.tv/series/%s/main.xml' % srsid
result = client.request(url)
ssnid = client.parseDOM(result, 'series_group', ret='ssnid', attrs = {'ssnnum': season})[0]
url = 'http://www.xsubs.tv/series/%s/%s.xml' % (srsid, ssnid)
result = client.request(url)
items = client.parseDOM(result, 'subg')
items = [(client.parseDOM(i, 'etitle', ret='number'), i) for i in items]
items = [i[1] for i in items if len(i[0]) > 0 and i[0][0] == episode][0]
items = re.findall('(<sr .+?</sr>)', items)
except:
return
for item in items:
try:
p = client.parseDOM(item, 'sr', ret='published_on')[0]
if p == '': raise Exception()
name = client.parseDOM(item, 'sr')[0]
name = name.rsplit('<hits>', 1)[0]
name = re.sub('</.+?><.+?>|<.+?>', ' ', name).strip()
name = '%s %s' % (query, name)
name = client.replaceHTMLCodes(name)
name = name.encode('utf-8')
url = client.parseDOM(item, 'sr', ret='rlsid')[0]
url = 'http://www.xsubs.tv/xthru/getsub/%s' % url
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
self.list.append({'name': name, 'url': url, 'source': 'xsubstv', 'rating': 5})
except:
pass
return self.list
def item_list(self, url):
try:
url = urlparse.urljoin(self.base_link, url)
result = client.request(url)
items = client.parseDOM(result, 'item')
except:
return
for item in items:
try:
title = client.parseDOM(item, 'title')[0]
title = client.replaceHTMLCodes(title)
title = title.encode('utf-8')
image = client.parseDOM(item, 'media:thumbnail', ret='url')[0]
image = image.split('?')[0]
image = client.replaceHTMLCodes(image)
image = image.encode('utf-8')
url = client.parseDOM(item, 'enclosure', ret='url')
check = False if len(url) > 0 else True
url = url[0] if len(url) > 0 else '0'
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
link = client.parseDOM(item, 'link')[0]
link = re.sub('.+?//.+?/','/', link)
link = client.replaceHTMLCodes(link)
link = link.encode('utf-8')
self.list.append({'title': title, 'url': url, 'image': image, 'link': link, 'check': check})
except:
pass
threads = []
for i in range(0, len(self.list)): threads.append(workers.Thread(self.item_list_worker, i))
[i.start() for i in threads]
[i.join() for i in threads]
self.list = [i for i in self.list if i['check'] == False]
threads = []
for i in range(0, len(self.list)): threads.append(workers.Thread(self.item_list_worker_2, i))
[i.start() for i in threads]
[i.join() for i in threads]
return self.list
def get(self, query):
try:
filter = ['freeprojectx', 'subs4series', 'Εργαστήρι Υποτίτλων'.decode('iso-8859-7')]
query = ' '.join(urllib.unquote_plus(re.sub('%\w\w', ' ', urllib.quote_plus(query))).split())
url = 'http://www.subtitles.gr/search.php?name=%s&sort=downloads+desc' % urllib.quote_plus(query)
result = client.request(url)
#result = result.decode('iso-8859-7').encode('utf-8')
items = client.parseDOM(result, 'tr', attrs = {'on.+?': '.+?'})
except:
return
for item in items:
try:
if not 'flags/el.gif' in item: raise Exception()
try: uploader = client.parseDOM(item, 'a', attrs = {'class': 'link_from'})[0].strip()
except: uploader = 'other'
if uploader in filter: raise Exception()
if uploader == '': uploader = 'other'
try: downloads = client.parseDOM(item, 'td', attrs = {'class': 'latest_downloads'})[0]
except: downloads = '0'
downloads = re.sub('[^0-9]', '', downloads)
name = client.parseDOM(item, 'a', attrs = {'onclick': 'runme.+?'})[0]
name = ' '.join(re.sub('<.+?>', '', name).split())
name = '[%s] %s [%s DLs]' % (uploader, name, downloads)
name = client.replaceHTMLCodes(name)
name = name.encode('utf-8')
url = client.parseDOM(item, 'a', ret='href', attrs = {'onclick': 'runme.+?'})[0]
url = url.split('"')[0].split('\'')[0].split(' ')[0]
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
rating = self._rating(downloads)
self.list.append({'name': name, 'url': url, 'source': 'subtitlesgr', 'rating': rating})
except:
pass
return self.list
def item_list_2(self, url):
try:
base_link = re.findall('(http(?:s|)://.+?)/', url)
if base_link:
base_link = base_link[0]
else:
base_link = self.base_link
if not '/webtv/' in url:
result = client.request(url + '/webtv/')
result = re.findall('"actual_args"\s*:\s*\["(.+?)"', result)[0]
else:
url, result = url.split('/webtv/')
url = '%s/webtv/%s?page=%s' % (url, result.lower(), '%s')
self.data.append('')
self.thread(0, url % '0', None)
try:
result = client.parseDOM(self.data[0],
'div',
attrs={'role': 'main'})[0]
result = client.parseDOM(result,
'div',
attrs={'class': 'view.+?'})[0]
num = client.parseDOM(
result,
'li',
attrs={'class': 'pager__item pager__item--last'})[0]
num = re.findall('page=(\d+)', num)[0]
if num > 9: num = 9
num = int(num) + 1
threads = []
for i in range(1, num):
self.data.append('')
threads.append(
workers.Thread(self.thread, i, url % str(i), None))
[i.start() for i in threads]
[i.join() for i in threads]
except:
pass
items = ''
for i in self.data:
items += i
items = client.parseDOM(items, 'div', attrs={'role': 'main'})
items = [
client.parseDOM(i, 'div', attrs={'class': 'view.+?'})
for i in items
]
items = [i[0] for i in items if len(i) > 0]
items = client.parseDOM(items, 'article')
except:
return
for item in items:
try:
t = client.parseDOM(item, 'div', attrs={'class':
'itemtitle'})[0]
title = client.parseDOM(t, 'span')
if title: title = title[0]
else: title = t
if title == '' or 'sneak preview' in title.lower():
raise Exception()
title = client.replaceHTMLCodes(title)
title = title.encode('utf-8')
tvshowtitle = client.parseDOM(item,
'div',
attrs={'class': 'showtitle'})
if tvshowtitle: tvshowtitle = tvshowtitle[0]
else: tvshowtitle = title
tvshowtitle = client.replaceHTMLCodes(tvshowtitle)
tvshowtitle = tvshowtitle.encode('utf-8')
url = client.parseDOM(item, 'a', ret='href')[0]
url = urlparse.urljoin(base_link, url)
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in [i['url'] for i in self.list]: raise Exception()
image = client.parseDOM(item, 'img', ret='src')[0]
image = urlparse.urljoin(base_link, image)
image = client.replaceHTMLCodes(image)
image = image.encode('utf-8')
self.list.append({
'title': title,
'url': url,
'image': image,
'tvshowtitle': tvshowtitle
})
except:
pass
return self.list
def get(self, query):
try:
match = re.findall('(.+?) \((\d{4})\)$', query)
if len(match) > 0:
title, year = match[0][0], match[0][1]
query = ' '.join(
urllib.unquote_plus(
re.sub('%\w\w', ' ',
urllib.quote_plus(title))).split())
url = 'http://subztv.gr/search?q=%s' % urllib.quote_plus(query)
result = client.request(url)
result = re.sub(r'[^\x00-\x7F]+', ' ', result)
url = client.parseDOM(result, 'div', attrs={'id': 'movies'})[0]
url = re.findall('(/movies/\d+)', url)
url = [x for y, x in enumerate(url) if x not in url[:y]]
url = [urlparse.urljoin('http://subztv.gr', i) for i in url]
url = url[:3]
for i in url:
c = cache.get(self.cache, 2200, i)
if not c == None:
if cleantitle.get(c[0]) == cleantitle.get(
title) and c[1] == year:
try:
item = self.r
except:
item = client.request(i)
break
else:
title, season, episode = re.findall('(.+?) S(\d+)E(\d+)$',
query)[0]
season, episode = '%01d' % int(season), '%01d' % int(episode)
query = ' '.join(
urllib.unquote_plus(
re.sub('%\w\w', ' ',
urllib.quote_plus(title))).split())
url = 'http://subztv.gr/search?q=%s' % urllib.quote_plus(query)
result = client.request(url)
result = re.sub(r'[^\x00-\x7F]+', ' ', result)
url = client.parseDOM(result, 'div', attrs={'id': 'series'})[0]
url = re.findall('(/series/\d+)', url)
url = [x for y, x in enumerate(url) if x not in url[:y]]
url = [urlparse.urljoin('http://subztv.gr', i) for i in url]
url = url[:3]
for i in url:
c = cache.get(self.cache, 2200, i)
if not c == None:
if cleantitle.get(c[0]) == cleantitle.get(title):
item = i
break
item = '%s/seasons/%s/episodes/%s' % (item, season, episode)
item = client.request(item)
item = re.sub(r'[^\x00-\x7F]+', ' ', item)
items = client.parseDOM(item, 'tr', attrs={'data-id': '\d+'})
except:
return
for item in items:
try:
if not 'img/el.png' in item: raise Exception()
name = client.parseDOM(item, 'td', attrs={'class': '.+?'})[-1]
name = name.split('>')[-1].strip()
name = re.sub('\s\s+', ' ', name)
name = client.replaceHTMLCodes(name)
name = name.encode('utf-8')
url = re.findall('\'(http(?:s|)\://.+?)\'', item)[-1]
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
self.list.append({
'name': name,
'url': url,
'source': 'subztvgr',
'rating': 5
})
except:
pass
return self.list