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, 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, 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 do_search(self, title, localtitle, year, is_movie_search):
try:
url = urlparse.urljoin(self.base_link, self.search_link)
url = url % urllib.quote(title)
result = client.request(url)
result = result.decode('utf-8')
result = client.parseDOM(result, 'ul', attrs={'id': 'resultList2'})
li_list = []
for el in result:
li_list.extend(client.parseDOM(el, 'li'))
result = [(client.parseDOM(i, 'a', ret='href')[0],
client.parseDOM(i, 'div', attrs={'class': 'title'})[0],
(client.parseDOM(i, 'div', attrs={'class': 'title_org'}) + [None])[0],
client.parseDOM(i, 'div', attrs={'class': 'info'})[0],
) for i in li_list]
search_type = 'Film' if is_movie_search else 'Serial'
cleaned_titles = [cleantitle.get(title), cleantitle.get(localtitle)]
# filter by name
result = [x for x in result if self.check_titles(cleaned_titles, [x[2], x[1]])]
# filter by type
result = [x for x in result if x[3].startswith(search_type)]
# filter by year
result = [x for x in result if x[3].endswith(str(year))]
if len(result) > 0:
return result[0][0]
else:
return
except :
return
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, 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, titles, year, imdb):
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': 'movie_cell'})
r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'bottom'}), dom_parser.parse_dom(i, 'div', attrs={'class': 'year'})) for i in r]
r = [(dom_parser.parse_dom(i[0], 'a', req=['href', 'title']), re.findall('[(](\d{4})[)]', i[1][0].content)) for i in r if i[0] and i[1]]
r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0]) for i in r if i[0] and i[1]]
r = [(i[0], i[1].lower(), i[2]) for i in r if i[2] in y]
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]
if len(r) > 1:
for i in r:
data = client.request(urlparse.urljoin(self.base_link, i))
data = dom_parser.parse_dom(data, 'a', attrs={'name': re.compile('.*/tt\d+.*')}, req='name')
data = [re.findall('.+?(tt\d+).*?', d.attrs['name']) for d in data]
data = [d[0] for d in data if len(d) > 0 and d[0] == imdb]
if len(data) >= 1:
url = i
else:
url = r[0]
if url:
return source_utils.strip_domain(url)
except:
return
def search(self, localtitle, year):
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, 'article')
for row in result:
a_href = client.parseDOM(row, 'h3')[0]
url = client.parseDOM(a_href, 'a', ret='href')[0]
name = client.parseDOM(a_href, 'a')[0]
name = cleantitle.get(name)
year_found = client.parseDOM(row,
'span',
attrs={'class': 'dtyear'})
if year_found:
year_found = year_found[0]
if (name == simply_name and
(not year_found or not year or year_found == year)):
return url
except:
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 = client.request(query)
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 episode(self, url, imdb, tvdb, title, premiered, season, episode):
try:
if url == None: return
url = urlparse.parse_qs(url)
url = dict([(i, url[i][0]) if url[i] else (i, '') for i in url])
url['premiered'], url['season'], url[
'episode'] = premiered, season, episode
try:
clean_title = cleantitle.geturl(
url['tvshowtitle']) + '-season-%d' % int(season)
search_url = urlparse.urljoin(
self.base_link,
self.search_link % clean_title.replace('-', '+'))
search_results = self.scraper.get(search_url).content
parsed = client.parseDOM(search_results, 'div',
{'id': 'movie-featured'})
parsed = [(client.parseDOM(i, 'a', ret='href'),
re.findall('<b><i>(.+?)</i>', i)) for i in parsed]
parsed = [
(i[0][0], i[1][0]) for i in parsed
if cleantitle.get(i[1][0]) == cleantitle.get(clean_title)
]
url = parsed[0][0]
except:
pass
data = self.scraper.get(url).content
data = client.parseDOM(data, 'div', attrs={'id': 'details'})
data = zip(client.parseDOM(data, 'a'),
client.parseDOM(data, 'a', ret='href'))
url = [(i[0], i[1]) for i in data if i[0] == str(int(episode))]
return url[0][1]
except:
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, 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={'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 matchAlias(self, title, aliases):
try:
for alias in aliases:
if cleantitle.get(title) == cleantitle.get(alias['title']):
return True
except:
return False
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 __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(urlparse.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 __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, 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 episode(self, url, imdb, tvdb, title, premiered, season, episode):
try:
if url == None: return
url = '%s/serie/%s' % (self.base_link, url)
r = proxy.request(url, 'tv shows')
r = client.parseDOM(r, 'li', attrs = {'itemprop': 'episode'})
t = cleantitle.get(title)
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'span', attrs = {'itemprop': 'name'}), re.compile('(\d{4}-\d{2}-\d{2})').findall(i)) for i in r]
r = [(i[0], i[1][0].split(' ')[-1], i[2]) for i in r if i[1]] + [(i[0], None, i[2]) for i in r if not i[1]]
r = [(i[0], i[1], i[2][0]) for i in r if i[2]] + [(i[0], i[1], None) for i in r if not i[2]]
r = [(i[0][0], i[1], i[2]) for i in r if i[0]]
url = [i for i in r if t == cleantitle.get(i[1]) and premiered == i[2]][:1]
if not url: url = [i for i in r if t == cleantitle.get(i[1])]
if len(url) > 1 or not url: url = [i for i in r if premiered == i[2]]
if len(url) > 1 or not url: raise Exception()
url = url[0][0]
url = proxy.parse(url)
url = re.findall('(?://.+?|)(/.+)', url)[0]
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
return url
except:
failure = traceback.format_exc()
log_utils.log('XWatchSeries - Exception: \n' + str(failure))
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 tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
t = cleantitle.get(tvshowtitle)
q = urllib.quote_plus(cleantitle.query(tvshowtitle))
p = urllib.urlencode({'term': q})
r = client.request(self.search_link, post=p, XHR=True)
try: r = json.loads(r)
except: r = None
r = None
if r:
r = [(i['seo_url'], i['value'], i['label']) for i in r if 'value' in i and 'label' in i and 'seo_url' in i]
else:
r = proxy.request(self.search_link_2 % q, 'tv shows')
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]]
r = [(i[0], i[1], re.findall('(\d{4})', i[2])) for i in r]
r = [(i[0], i[1], i[2][-1]) for i in r if i[2]]
r = [i for i in r if t == cleantitle.get(i[1]) and year == i[2]]
url = r[0][0]
url = proxy.parse(url)
url = url.strip('/').split('/')[-1]
url = url.encode('utf-8')
return url
except:
failure = traceback.format_exc()
log_utils.log('XWatchSeries - Exception: \n' + str(failure))
return
def __search(self, title):
try:
t = cleantitle.get(title)
r = client.request(urlparse.urljoin(self.base_link, self.search_link), post={'suchbegriff': title})
r = dom_parser.parse_dom(r, 'a', attrs={'class': 'ausgabe_1'}, req='href')
r = [(i.attrs['href'], i.content) for i in r]
r = [i[0] for i in r if cleantitle.get(i[1]) == t][0]
return source_utils.strip_domain(r)
except:
return
def get_filmdb_data(self, season, episode, title, localtitle, year):
try:
import requests
titles = {localtitle, title}
for item in titles:
try:
if item == 'Vikings':
item = 'Wikingowie'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0',
'Referer': 'http://filmdb.pl/'
}
url = urlparse.urljoin(self.filmdb, self.filmdb_search)
data = {"search_film": item}
r = requests.post(url, data=data, headers=headers)
result = r.text
hrefs = client.parseDOM(result, 'a', ret='href')
for href in hrefs:
result = client.request(self.filmdb + str(href))
fdbtitle = client.parseDOM(result,
'input',
ret='value')[0]
fdbsubtitle = client.parseDOM(result,
'input',
ret='value')[1]
fdbyear = client.parseDOM(result, 'input',
ret='value')[2]
fdbfilmid = client.parseDOM(result,
'input',
ret='value')[3]
fdbsp = client.parseDOM(result, 'input',
ret='value')[4]
local_clean = cleantitle.get(localtitle)
title_clean = cleantitle.get(title)
found_clean = cleantitle.get(fdbsubtitle)
if found_clean == '':
found_clean = cleantitle.get(fdbtitle)
if title_clean == found_clean or local_clean == found_clean:
return {
'sp': fdbsp,
'filmid': fdbfilmid,
'sezon': season,
'odcinek': episode
}
except:
pass
except Exception, e:
print str(e)
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(urlparse.urljoin(self.base_link, self.search_link), post=urllib.urlencode({'val': cleantitle.query(titles[0])}), XHR=True)
r = dom_parser.parse_dom(r, 'li')
r = dom_parser.parse_dom(r, 'a', req='href')
r = [(i.attrs['href'], i.content, re.findall('\((\d{4})', i.content)) for i in r]
r = [(i[0], i[1], i[2][0] if i[2] else '0') for i in r]
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 episode(self, url, imdb, tvdb, title, premiered, season, episode):
try:
if url == None: return
url = urlparse.urljoin(self.base_link, url)
result = client.request(url)
title = cleantitle.get(title)
premiered = re.compile('(\d{4})-(\d{2})-(\d{2})').findall(
premiered)[0]
premiered = '%s/%s/%s' % (premiered[2], premiered[1], premiered[0])
items = dom_parser.parse_dom(result,
'a',
attrs={'itemprop': 'url'})
url = [
i.attrs['href'] for i in items if bool(
re.compile(
'<span\s*>%s<.*?itemprop="episodeNumber">%s<\/span>' %
(season, episode)).search(i.content))
][0]
url = url.encode('utf-8')
return url
except:
return
def movie(self, imdb, title, localtitle, aliases, year):
try:
url = urlparse.urljoin(self.base_link, self.search_link)
url = url % (title.replace(':', ' ').replace(' ', '+'))
search_results = client.request(url)
match = re.compile('<h1><a href="(.+?)" rel="bookmark">(.+?)</a></h1>',re.DOTALL).findall(search_results)
for item_url,item_title in match:
if cleantitle.get(title) in cleantitle.get(item_title):
if year in str(item_title):
return item_url
return
except:
failure = traceback.format_exc()
log_utils.log('CoolMovieZone - Exception: \n' + str(failure))
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):
try:
query = self.search_link % (urllib.quote_plus(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, 'article')
r = dom_parser.parse_dom(r, 'a', attrs={'class': 'rb'}, req='href')
r = [(i.attrs['href'], i.content) 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 % 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 = 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
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 name_matches(self, names_found, titles, year):
for name in names_found:
name = name.strip().encode('utf-8')
# if ends with year
clean_found_title = cleantitle.get(name)
# sometimes they add year to title so we need to check thet
if clean_found_title in titles:
return True
return False