def scrape_movie(self, title, year, imdb, debrid = False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = '%s/?s=%s' % (self.base_link, urllib.quote_plus(search_id))
headers = {'User-Agent': client.agent()}
html = client.request(start_url, headers=headers)
posts = client.parseDOM(html, 'div', attrs={'class': 'result-item'})
posts = [(client.parseDOM(i, 'div', attrs={'class': 'details'})[0]) for i in posts if i]
posts = [i for i in posts if not 'SEO Checker' in i]
for post in posts:
try:
name = client.parseDOM(post, 'a')[0]
url = client.parseDOM(post, 'a', ret='href')[0]
date = client.parseDOM(post, 'span', attrs={'class': 'year'})[0]
except:
raise Exception()
name = re.sub('<.+?>', '', name)
tit = re.sub('(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not clean_title(title) == clean_title(tit):
continue
if not year == date:
continue
self.get_source(url, title, year, '', '', start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = '%s/search?query=%s' % (self.base_link,
urllib.quote_plus(search_id))
#print 'scraperchk - scrape_movie - start_url: ' + start_url
html = client.request(start_url)
posts = client.parseDOM(html,
'div',
attrs={'class': 'one_movie-item'})
for post in posts:
data = dom.parse_dom(post,
'a',
req='href',
attrs={'class': 'movie-title'})[0]
if not clean_title(title) == clean_title(data.content):
continue
qual = client.parseDOM(post,
'span',
attrs={'data-title': 'Quality'})[0]
qual = client.replaceHTMLCodes(qual)
item_url = urlparse.urljoin(self.base_link, data.attrs['href'])
self.get_source(item_url, title, year, start_time, qual)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_episode(self, title, show_year, year, season, episode, imdb, tvdb, debrid = False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = '%s/?s=%s+season+%s' % (self.base_link, urllib.quote_plus(search_id), season)
headers = {'User_Agent': client.agent()}
html = client.request(start_url, headers=headers)
#print 'PAGE>>>>>>>>>>>>>>>>>'+html
posts = client.parseDOM(html, 'div', attrs={'class': 'result-item'})
posts = [(client.parseDOM(i, 'div', attrs={'class': 'details'})[0]) for i in posts if i]
posts = [i for i in posts if not 'SEO Checker' in i]
for post in posts:
try:
name = client.parseDOM(post, 'a')[0]
name = re.sub('<.+?>', '', name)
url = client.parseDOM(post, 'a', ret='href')[0]
except:
raise Exception()
tit = re.sub('(\.|\(|\[|\s)(Season)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not clean_title(title).lower() == clean_title(tit).lower():
continue
epi_id = '%sx%s/' % (season, episode)
ep_link = url.replace('/seasons/', '/episodes/')
ep_link = ep_link.split('-season')[0] + '-%s' % epi_id
self.get_source(ep_link, title, year, season, episode, start_time)
#print self.sources
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def get_source(self,item_url,title,year,start_time):
try:
#print 'PASSEDURL >>>>>>'+item_url
count = 0
headers = {'User-Agent': client.agent()}
OPEN = client.request(item_url, headers=headers)
frame = client.parseDOM(OPEN, 'iframe', ret='src')[0]
data = client.request(frame, headers=headers)
data = client.parseDOM(data, 'ul', attrs={'class': 'menuPlayer'})[0]
links = client.parseDOM(data, 'a', ret='href')
for link in links:
#print link+'<<<<<<<<<<<<<<<<<<<<<<<<<<'
qual = quality_tags.check_sd_url(link)
if qual == 'SD' and 'openload' in link:
data = client.request(link, headers=headers)
data = client.parseDOM(data, 'meta', ret='content')[0]
qual2, info = quality_tags.get_release_quality(data, None)
else:
qual2 = qual
count += 1
host = link.split('//')[1].replace('www.','')
host = host.split('/')[0].split('.')[0].title()
self.sources.append({'source':host, 'quality':qual2, 'scraper': self.name, 'url':link, 'direct':False})
if dev_log=='true':
end_time = time.time() - start_time
send_log(self.name,end_time,count,title,year)
except Exception, argument:
if dev_log=='true':
error_log(self.name, argument)
#hdvix().scrape_movie('Black Panther', '2018', 'tt1825683', False)
def scrape_episode(self, title, show_year, year, season, episode, imdb, tvdb, debrid = False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = '%s/?s=%s+season+%s' % (self.base_link, urllib.quote_plus(search_id), season)
headers = {'User_Agent': client.agent()}
html = client.request(start_url, headers=headers)
#print 'PAGE>>>>>>>>>>>>>>>>>'+html
posts = client.parseDOM(html, 'div', attrs={'class': 'result-item'})
posts = [(client.parseDOM(i, 'div', attrs={'class': 'details'})[0]) for i in posts if i]
posts = [i for i in posts if not 'SEO Checker' in i]
for post in posts:
try:
name = client.parseDOM(post, 'a')[0]
name = re.sub('<.+?>', '', name)
url = client.parseDOM(post, 'a', ret='href')[0]
except:
raise Exception()
tit = re.sub('(\.|\(|\[|\s)(Season)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not clean_title(title).lower() == clean_title(tit).lower():
continue
epi_id = '%sx%s/' % (season, episode)
ep_link = url.replace('/seasons/', '/episodes/')
ep_link = ep_link.split('-season')[0] + '-%s' % epi_id
self.get_source(ep_link, title, year, season, episode, start_time)
#print self.sources
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def get_source(self,url,title,year,season,episode,start_time):
try:
headers = {'User-Agent': client.agent()}
OPEN = client.request(url, headers=headers)
holder = client.parseDOM(OPEN, 'div', attrs={'class':'bwa-content'})[0]
holder = client.parseDOM(holder, 'a', ret='href')[0]
links = client.request(holder, headers=headers)
Regex = client.parseDOM(links, 'iframe', ret='src', attrs={'class': 'metaframe rptss'})
count = 0
for link in Regex:
if 'player.php' in link:
link = client.request(link, headers=headers, output='geturl')
qual = client.request(link, headers=headers)
qual = client.parseDOM(qual, 'meta', ret='content')[0]
else:
link = link
host = link.split('//')[1].replace('www.','')
host = host.split('/')[0].split('.')[0].title()
if '1080p' in qual:
rez = '1080p'
elif '720p' in qual:
rez = '720p'
else: rez = 'SD'
count += 1
self.sources.append({'source': host, 'quality': rez, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year, season=season, episode=episode)
except:
pass
#movie4u().scrape_movie('Wonder Woman', '2017','')
#movie4u().scrape_episode('Suits','2011','','8','5','','')
def get_source(self,url,title,year,season,episode,start_time):
try:
headers = {'User-Agent': client.agent()}
OPEN = client.request(url, headers=headers)
holder = client.parseDOM(OPEN, 'div', attrs={'class':'bwa-content'})[0]
holder = client.parseDOM(holder, 'a', ret='href')[0]
links = client.request(holder, headers=headers)
Regex = client.parseDOM(links, 'iframe', ret='src', attrs={'class': 'metaframe rptss'})
count = 0
for link in Regex:
if 'player.php' in link:
link = client.request(link, headers=headers, output='geturl')
qual = client.request(link, headers=headers)
qual = client.parseDOM(qual, 'meta', ret='content')[0]
else:
link = link
host = link.split('//')[1].replace('www.','')
host = host.split('/')[0].split('.')[0].title()
if '1080p' in qual:
rez = '1080p'
elif '720p' in qual:
rez = '720p'
else: rez = 'SD'
count += 1
self.sources.append({'source': host, 'quality': rez, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year, season=season, episode=episode)
except:
pass
#movie4u().scrape_movie('Wonder Woman', '2017','')
#movie4u().scrape_episode('Suits','2011','','8','5','','')
def scrape_movie(self, title, year, imdb, debrid=False):
if int(year) > 1980:
return self.sources
try:
start_time = time.time()
query = urllib.quote_plus(clean_search(title.lower()))
start_url = urlparse.urljoin(self.base_link, self.search_link % query)
headers = {'User-Agent': client.agent(), 'Referer': self.base_link}
count = 0
html = client.request(start_url, headers=headers)
posts = client.parseDOM(html, 'div', attrs={'class': 'post'})
posts = [(dom_parser.parse_dom(i, 'a', req='href')[0]) for i in posts if i]
posts = [(i.attrs['href'], i.content) for i in posts if i]
post = [(i[0]) for i in posts if clean_title(i[1]) == clean_title(title)][0]
r = client.request(post, headers=headers)
y = client.parseDOM(r, 'h1')[0]
if not year in y:
return self.sources
links = client.parseDOM(r, 'source', ret='src')
link = [i for i in links if i.endswith('mp4')][0]
link += '|User-Agent=%s&Referer=%s' % (client.agent(), post)
link = urllib.quote(link, ':/-_|&+=')
count += 1
self.sources.append({'source': 'bnw', 'quality': 'SD', 'scraper': self.name, 'url': link, 'direct': True})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,end_time,count,title,year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
if int(year) > 1980: return self.sources
try:
start_time = time.time()
query = urllib.quote_plus(clean_search(title.lower()))
start_url = urlparse.urljoin(self.base_link, self.search_link % query)
headers = {'User-Agent': client.agent(), 'Referer': self.base_link}
count = 0
html = client.request(start_url, headers=headers)
posts = client.parseDOM(html, 'div', attrs={'class': 'post'})
posts = [(dom_parser.parse_dom(i, 'a', req='href')[0]) for i in posts if i]
posts = [(i.attrs['href'], i.content) for i in posts if i]
post = [(i[0]) for i in posts if clean_title(i[1]) == clean_title(title)][0]
r = client.request(post, headers=headers)
y = client.parseDOM(r, 'h1')[0]
if not year in y: return self.sources
links = client.parseDOM(r, 'source', ret='src')
link = [i for i in links if i.endswith('mp4')][0]
link += '|User-Agent=%s&Referer=%s' % (client.agent(), post)
link = urllib.quote(link, ':/-_|&+=')
count += 1
self.sources.append({'source': 'bnw', 'quality': 'SD', 'scraper': self.name, 'url': link, 'direct': True})
if dev_log=='true':
end_time = time.time() - start_time
send_log(self.name,end_time,count,title,year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def scrape_episode(self, title, show_year, year, season, episode, imdb, tvdb, debrid=False):
try:
start_time = time.time()
hdlr = 'S%02dE%02d' % (int(season), int(episode))
query = clean_search(title)
query = urllib.quote_plus(query + ' ' + hdlr)
urls = []
for link in self.search_links:
try:
url = urlparse.urljoin(self.base_link, link % query)
url = urlparse.urljoin(self.base_link, url)
r = client.request(url)
posts = client.parseDOM(r, 'tbody')
posts = client.parseDOM(posts, 'tr')
urls += [(client.parseDOM(i, 'button', ret='data-clipboard-text')[0]) for i in posts if i]
except:
pass
count = 0
for url in urls:
name = url.split('/')[-1].lower()
name = client.replaceHTMLCodes(name).replace('%20', '')
if 'movies' in url:
continue
if any(x in url for x in ['italian', 'dubbed', 'teaser', 'subs', 'sub', 'dub',
'samples', 'extras', 'french', 'trailer', 'trailers', 'sample']):
continue
t = re.sub('(\.|\(|\[|\s)(S\d+E\d+|S\d+)(\.|\)|\]|\s)(.+|)', '', name, flags=re.I)
if clean_title(t) not in clean_title(title): continue
y = re.findall('[\.|\(|\[|\s](S\d+E\d+|S\d+)[\.|\)|\]|\s]', name, re.I)[-1].upper()
if not y == hdlr: continue
res, info = quality_tags.get_release_quality(name, url)
if any(x in url for x in ['hastidl', '1tehmovies', '62.210.103.107', '79.127', '213.32.113.82',
'dl5.downloadha', '89.163.255.42', '185.56.20.142', 's1.0music',
'dl3.yoozdl', 'dl4.lavinmovie.net', 'dl6.lavinmovie.net',
'dl3.upload08.com', 'dl8.uploadt.com', '163.172.6.218',
'samba.allunix.ru', 'server417']):
count += 1
url += '|User-Agent=%s&Referer=%s' % (client.agent(), self.base_link)
url = urllib.quote(url, '|:?/&+=_-')
self.sources.append(
{'source': 'DirectLink', 'quality': res, 'scraper': self.name, 'url': url, 'direct': True})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
#filepursuit().scrape_movie('Black Panther', '2018', '')
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = '%s %s' % (clean_search(title.lower()), year)
start_url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(search_id))
headers={'User-Agent': client.agent()}
scraper = cfscrape.create_scraper()
html = scraper.get(start_url, headers=headers).content
#xbmc.log('@#@DATA:%s' % html, xbmc.LOGNOTICE)
data = client.parseDOM(html, 'div', attrs={'id': 'content_box'})[0]
data = client.parseDOM(data, 'h2') #returns a list with all search results
data = [dom_parser.parse_dom(i, 'a', req=['href', 'title'])[0] for i in data if i] #scraping url-title
links = [(i.attrs['href'], i.attrs['title']) for i in data if i] #list with link-title for each result
#links = re.compile('<header>.+?href="(.+?)" title="(.+?)"',re.DOTALL).findall(html)
#xbmc.log('@#@LINKS:%s' % links, xbmc.LOGNOTICE)
for m_url, m_title in links:
movie_year = re.findall("(\d{4})", re.sub('\d{3,4}p', '', m_title))[-1]
movie_name = m_title.split(movie_year)[0]
if not clean_title(title) == clean_title(movie_name):
continue
if not year in movie_year:
continue
url = m_url
#error_log(self.name + ' Pass',url)
self.get_source(url, title, year, '', '', start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def scrape_episode(self,
title,
show_year,
year,
season,
episode,
imdb,
tvdb,
debrid=False):
try:
start_time = time.time()
hdlr = 'S%02dE%02d' % (int(season), int(episode))
search_id = '%s %s' % (title, hdlr)
start_url = self.base_link + self.search_link % urllib.quote_plus(
search_id)
html = client.request(start_url)
items = client.parseDOM(html, 'item')
for item in items:
name = client.parseDOM(item, 'title')[0]
name = client.replaceHTMLCodes(name)
t = name.split(hdlr)[0]
if not clean_title(title) == clean_title(t):
continue
if not hdlr in name:
continue
self.get_source(item, title, year, season, episode, debrid,
start_time)
#print self.sources
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def scrape_movie(self, title, year, imdb, debrid = False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = '%s/?s=%s' % (self.base_link, urllib.quote_plus(search_id))
headers = {'User-Agent': client.agent()}
html = client.request(start_url, headers=headers)
posts = client.parseDOM(html, 'div', attrs={'class': 'result-item'})
posts = [(client.parseDOM(i, 'div', attrs={'class': 'details'})[0]) for i in posts if i]
posts = [i for i in posts if not 'SEO Checker' in i]
for post in posts:
try:
name = client.parseDOM(post, 'a')[0]
url = client.parseDOM(post, 'a', ret='href')[0]
date = client.parseDOM(post, 'span', attrs={'class': 'year'})[0]
except:
raise Exception()
name = re.sub('<.+?>', '', name)
tit = re.sub('(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not clean_title(title) == clean_title(tit):
continue
if not year == date:
continue
self.get_source(url, title, year, '', '', start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
def get_source(self, item_url, title, year, season, episode, start_time):
try:
count = 0
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
'Referer': self.base_link}
scraper = cfscrape.create_scraper()
r = scraper.get(item_url, headers=headers).content
data = client.parseDOM(r, 'tr')
for item in data:
qual = client.parseDOM(item, 'span', ret='class')[0]
qual = qual.replace('quality_', '')
link = client.parseDOM(item, 'a', ret='data-href')[0]
host = link.split('//')[1].replace('www.', '')
host = host.split('/')[0]
if not filter_host(host): continue
count += 1
self.sources.append({'source': host, 'quality': qual, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year, season='', episode='')
return self.sources
except BaseException:
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
count = 0
try:
start_time = time.time()
search_id = '%s %s' % (clean_search(title), year)
start_url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(search_id))
headers = {'User-Agent': client.agent()}
html = requests.get(start_url, headers=headers, timeout=5).content
posts = client.parseDOM(html, 'item')
posts = [(client.parseDOM(i, 'title')[0], client.parseDOM(i, 'a', ret='href')) for i in posts if i]
posts = [i[1] for i in posts if clean_title(i[0]) == clean_title(title)][0]
for url in posts:
if 'cmovies' in url:
continue
link = 'https:' + url if url.startswith('//') else url
if '1080' in link:
qual = '1080p'
elif '720' in link:
qual = '720p'
else:
qual = 'SD'
host = url.split('//')[1].replace('www.', '')
host = host.split('/')[0].split('.')[0].title()
count += 1
self.sources.append({'source': host, 'quality': qual, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def get_source(self, item_url, title, year, season, episode, debrid,
start_time):
try:
count = 0
frames = []
frames += client.parseDOM(item_url, 'iframe', ret='src')
frames += client.parseDOM(item_url, 'a', ret='href')
frames += client.parseDOM(item_url, 'source', ret='src')
frames += client.parseDOM(item_url, 'enclosure', ret='url')
try:
q = re.findall('<strong>Quality:</strong>([^<]+)', item_url,
re.DOTALL)[0]
if 'high' in q.lower():
qual = '720p'
elif 'cam' in q.lower():
qual = 'CAM'
else:
qual = 'SD'
except:
qual = 'SD'
for link in frames:
if 'http://24hd.org' in link:
continue
if '.pl/link/' in link:
continue
if 'seehd.pl/d/' in link:
r = self.scraper.get(link).content
link = client.parseDOM(r, 'iframe', ret='src')[0]
host = link.split('//')[1].replace('www.', '')
host = host.split('/')[0].lower()
if debrid is True:
rd_domains = get_rd_domains()
if host not in rd_domains:
continue
count += 1
self.sources.append({
'source': host,
'quality': qual,
'scraper': self.name,
'url': link,
'direct': False,
'debridonly': True
})
if not filter_host(host):
continue
count += 1
self.sources.append({
'source': host,
'quality': qual,
'scraper': self.name,
'url': link,
'direct': False
})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def resolve(self, link):
try:
r = client.request(link)
r = client.parseDOM(r, 'div', attrs={'class': 'wb-main'})[0]
url = client.parseDOM(r, 'a', ret='href')[0]
return url
except:
return link
def get_sources(self, url, title, year, season, episode, start_time):
try:
count = 0
url = urlparse.urljoin(self.base_link,
url) if url.startswith('/') else url
r = client.request(url)
data = re.findall(r'\s*(eval.+?)\s*</script', r, re.DOTALL)[1]
data = jsunpack.unpack(data).replace('\\', '')
# https://www.primewire.ink/ajax-78583.php?slug=watch-2809620-Black-Panther&cp=7TYP4N
# var rtv=\'aja\';var aa=\'x-7\';var ba=\'85\';var ca=\'83\';var da=\'.ph\';var ea=\'p?sl\';var fa=\'ug=\';var ia=\'&cp=7T\';var ja=\'YP\';var ka=\'4N\';var code=ia+ja+ka;var page=rtv+aa+ba+ca+da+ea+fa;function goml(loc){$(\'#div1\').load(domain+page+loc+code)}
patern = '''rtv='(.+?)';var aa='(.+?)';var ba='(.+?)';var ca='(.+?)';var da='(.+?)';var ea='(.+?)';var fa='(.+?)';var ia='(.+?)';var ja='(.+?)';var ka='(.+?)';'''
links_url = re.findall(patern, data, re.DOTALL)[0]
slug = 'slug={}'.format(url.split('/')[-1])
links_url = self.base_link + [''.join(links_url)][0].replace(
'slug=', slug)
links = client.request(links_url)
links = client.parseDOM(links, 'tbody')
#xbmc.log('@#@LINKSSSS: %s' % links, xbmc.LOGNOTICE)
for link in links:
try:
data = [(client.parseDOM(link, 'a', ret='href')[0],
client.parseDOM(link,
'span',
attrs={'class':
'version_host'})[0])][0]
link = urlparse.urljoin(self.base_link, data[0])
host = data[1]
if not filter_host(host): continue
self.sources.append({
'source': host,
'quality': 'SD',
'scraper': self.name,
'url': link,
'direct': False
})
except:
pass
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,
end_time,
count,
title,
year,
season=season,
episode=episode)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def get_source(self, item_url, title, year, season, episode, start_time):
count = 0
try:
if item_url is None:
return self.sources
qual = re.search('Quality\s*:(.+?)<br', item_url,
re.DOTALL).groups()[0]
qual = re.sub('<.+?>', '', qual)
qual, info = quality_tags.get_release_quality(qual, qual)
headers = {
'Origin': self.base_link,
'Referer': client.parseDOM(item_url, 'link')[0],
'X-Requested-With': 'XMLHttpRequest',
'User_Agent': client.agent()
}
fn = client.parseDOM(item_url,
'input',
attrs={'name': 'FName'},
ret='value')[0]
fs = client.parseDOM(item_url,
'input',
attrs={'name': 'FSize'},
ret='value')[0]
fsid = client.parseDOM(item_url,
'input',
attrs={'name': 'FSID'},
ret='value')[0]
#params = re.compile('<input name="FName" type="hidden" value="(.+?)" /><input name="FSize" type="hidden" value="(.+?)" /><input name="FSID" type="hidden" value="(.+?)"').findall(html)
post_url = self.base_link + '/thanks-for-downloading/'
form_data = {'FName': fn, 'FSize': fs, 'FSID': fsid}
#link = requests.post(request_url, data=form_data, headers=headers).content
link = client.request(post_url, post=form_data, headers=headers)
stream_url = client.parseDOM(link,
'meta',
attrs={'http-equiv': 'refresh'},
ret='content')[0]
stream_url = client.replaceHTMLCodes(stream_url).split('url=')[-1]
stream_url += '|User-Agent=%s' % urllib.quote(client.agent())
count += 1
self.sources.append({
'source': 'DirectLink',
'quality': qual,
'scraper': self.name,
'url': stream_url,
'direct': True
})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,
end_time,
count,
title + ' | ' + stream_url,
year,
season=season,
episode=episode)
except:
pass
def get_source(self, item_url, title, year, season, episode, start_time):
try:
#print 'coolmovies pass ' + item_url
headers = {'User-Agent': client.agent()}
r = client.request(item_url, headers=headers)
#xbmc.log('@#@HTML:%s' % r, xbmc.LOGNOTICE)
data = client.parseDOM(r, 'table', attrs={'class':
'source-links'})[0]
data = client.parseDOM(data, 'tr')
data = [(client.parseDOM(i, 'a',
ret='href')[0], client.parseDOM(i,
'td')[1])
for i in data if 'version' in i.lower()] #Watch Version
Endlinks = [(i[0], re.sub('<.+?>', '', i[1])) for i in data if i]
#Endlinks = re.compile('<td align="center"><strong><a href="(.+?)"',re.DOTALL).findall(r)
#print 'coolmoviezone - scrape_movie - EndLinks: '+str(Endlinks)
count = 0
for link, host in Endlinks:
if 'filebebo' in host: continue #host with captcha
if 'fruitad' in host:
link = client.request(link)
link = client.parseDOM(
link, 'meta', attrs={'name': 'og:url'},
ret='content')[0] #returns the real url
if not link: continue
import resolveurl
if resolveurl.HostedMediaFile(link):
from universalscrapers.modules import quality_tags
quality, info = quality_tags.get_release_quality(
link, link)
if quality == 'SD':
quality = 'DVD'
host = host.split('/')[0].split('.')[0].title()
count += 1
self.sources.append({
'source': host,
'quality': quality,
'scraper': self.name,
'url': link,
'direct': False
})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,
end_time,
count,
title,
year,
season='',
episode='')
except:
pass
def get_source(self, url, title, year, season, episode, start_time):
sources = []
try:
count = 0
if url is None:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
tit = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (data['tvshowtitle'], int(data['season']), int(data['episode'])) \
if 'tvshowtitle' in data else '%s %s' % (data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = urlparse.urljoin(self.base_link, self.search_link%(urllib.quote(query)))
r = client.request(url)
r = client.parseDOM(r, 'table', attrs={'id': 'searchResult'})[0]
posts = client.parseDOM(r, 'td')
posts = [i for i in posts if 'detName' in i]
for post in posts:
post = post.replace(' ', ' ')
name = client.parseDOM(post, 'a')[0]
t = name.split(hdlr)[0]
if not clean_title(re.sub('(|)', '', t)) == clean_title(tit):
continue
try:
y = re.findall('[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper()
except BaseException:
y = re.findall('[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper()
if not y == hdlr:
continue
links = client.parseDOM(post, 'a', ret='href')
magnet = [i for i in links if 'magnet:' in i][0]
url = magnet.split('&tr')[0]
count += 1
quality, info = quality_tags.get_release_quality(name, name)
try:
size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', post)[0]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div
size = '%.2f GB' % size
except BaseException:
size = '0'
info.append(size)
info = ' | '.join(info)
qual = '{0} | {1}'.format(quality, info)
self.sources.append({'source': 'Torrent', 'quality': qual, 'scraper': self.name, 'url': url, 'direct': False, 'debridonly': True})
if dev_log == 'true':
end_time = time.time() - float(start_time)
send_log(self.name, end_time, count, title, year, season=season, episode=episode)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_episode(self,
title,
show_year,
year,
season,
episode,
imdb,
tvdb,
debrid=False):
try:
start_time = time.time()
#season_pull = '%02d' % int(season) #"0%s"%season if len(season)<2 else season
#episode_pull = '%02d' % int(episode) #"0%s"%episode if len(episode)<2 else episode
sepi = 'S%02dE%02d' % (int(season), int(episode))
search_id = '%s %s' % (title, sepi)
movie_url = self.base_link + self.search_link % urllib.quote_plus(
search_id)
#print ' ##MOVIE URL## %s' % movie_url
r = client.request(movie_url)
items = client.parseDOM(r, 'article', attrs={'id': 'post-\d+'})
for item in items:
name = client.parseDOM(item, 'a')[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+|3D)(\.|\)|\]|\s|)(.+|)',
'',
name,
flags=re.I)
if not clean_title(title).lower() in clean_title(t).lower():
continue
y = re.findall('[\.|\(|\[|\s](S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name,
flags=re.I)[-1].upper()
if y not in sepi:
continue
link = client.parseDOM(item, 'a', ret='href')[0]
if not y == sepi:
link = link
else:
link += '2' if link.endswith('/') else '/2'
#print ' ##final Item to pass## %s' % link
self.get_source(link, title, year, season, episode, start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def _get_items(self, url):
items = []
try:
headers = {'User-Agent': client.agent()}
#scraper = cfscrape.create_scraper()
#r = scraper.get(url, headers=headers)
r= client.request(url, headers=headers)
#print r
posts = client.parseDOM(r, 'tr', attrs={'name': 'hover'})
for post in posts:
data = dom.parse_dom(post, 'a', {'class': 'magnet'}, req=['href', 'title'])[0]
url = data.attrs['href']
name = data.attrs['title']
t = name.split(self.hdlr)[0]
if not clean_title(re.sub('(|)', '', t)) == clean_title(self.title):
continue
try:
y = re.findall('[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper()
except BaseException:
y = re.findall('[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper()
if not y == self.hdlr:
continue
try:
size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', post)[0]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div
size = '%.2f GB' % size
except BaseException:
size = '0'
items.append((name, url, size))
return items
except BaseException:
return items
def get_source(self, item_url, title, year, start_time):
try:
count = 0
data = requests.get(item_url).json()
for item in data:
title = item["title"]["rendered"]
content = item["content"]["rendered"]
year2 = item["date"][:4]
if int(year) != int(year2):
continue
#Links = re.findall(r"(http.*streamango.com\/embed\/\w{1,}|https:\/\/openload\.co\/embed\/\w{1,}\/)",content)
Links = client.parseDOM(content, 'iframe', ret='src')
for link in Links:
count += 1
host = link.split('//')[1].replace('www.', '')
host = host.split('/')[0].split('.')[0].title()
label = "DVD"
self.sources.append({
'source': host,
'quality': label,
'scraper': self.name,
'url': link,
'direct': False
})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
start_url = urlparse.urljoin(
self.base_link,
self.moviesearch_link % urllib.quote_plus(clean_search(title)))
html = client.request(start_url)
posts = client.parseDOM(html,
'div',
attrs={'class': 'index_item.+?'})
posts = [(dom.parse_dom(i, 'a', req='href')[0]) for i in posts
if i]
post = [(i.attrs['href']) for i in posts
if clean_title(title) == clean_title(
re.sub('(\.|\(|\[|\s)(\d{4})(\.|\)|\]|\s|)(.+|)', '',
i.attrs['title'], re.I))][0]
#xbmc.log('@#@POST: %s' % post, xbmc.LOGNOTICE)
self.get_sources(post, title, year, '', '', start_time)
return self.sources
except Exception as argument:
if dev_log == 'true':
error_log(self.name, argument)
return []
def get_sources(self, episode_url, title, year, season, episode,
start_time):
try:
links = client.request(episode_url)
links = client.parseDOM(links, 'div', attrs={'class': 'll-item'})
count = 0
for link in links:
data = dom.parse_dom(link, 'a')[0]
host = data.content
if not filter_host(host):
continue
count += 1
url = data.attrs['href']
self.sources.append({
'source': host,
'quality': 'DVD',
'scraper': self.name,
'url': url,
'direct': False
})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,
end_time,
count,
title,
year,
season=season,
episode=episode)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = urllib.quote_plus(clean_search(title))
query = self.search_url % search_id
headers = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
'Referer': self.base_link
}
scraper = cfscrape.create_scraper()
r = scraper.get(query, headers=headers).content
posts = client.parseDOM(
r,
'div',
attrs={'class': 'col-xs-4 col-sm-4 col-md-3 col-lg-3'})
posts = [
dom.parse_dom(i, 'a', req='href')[0] for i in posts
if year in i
]
post = [
i.attrs['href'] for i in posts
if clean_title(title) == clean_title(i.attrs['title'])
][0]
self.get_source(post, title, year, '', '', start_time)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, 'Check Search')
return self.sources
def get_source(self, item_url, title, year, start_time, qual):
try:
#print 'PASSEDURL >>>>>>'+item_url
count = 0
OPEN = client.request(item_url)
frame = client.parseDOM(OPEN, 'iframe', ret='src')[0]
if 'openload' in frame:
count += 1
self.sources.append(
{'source': 'openload', 'quality': qual, 'scraper': self.name, 'url': frame, 'direct': False})
extra_links = re.findall('''window.open\(['"]([^'"]+)['"]\).+?server:([^<]+)''', OPEN, re.DOTALL)
for link, host in extra_links:
if not filter_host(host.replace(' ', '')): continue
link = client.replaceHTMLCodes(link).encode('utf-8')
link = urlparse.urljoin(self.base_link, link)
count += 1
self.sources.append({'source': host, 'quality': qual, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def scrape_episode(self,
title,
show_year,
year,
season,
episode,
imdb,
tvdb,
debrid=False):
try:
start_time = time.time()
scrape = clean_search(title.lower())
start_url = urlparse.urljoin(
self.base_link,
self.search_link % urllib.quote_plus(clean_search(title)))
html = client.request(start_url)
data = json.loads(html)
posts = data['series']
post = [
i['seo_name'] for i in posts
if clean_title(title) == clean_title(i['original_name'])
][0]
show_page = self.base_link + post
r = client.request(show_page)
sepi = 'season-%s-episode-%s' % (int(season), int(episode))
epi_link = client.parseDOM(r, 'a', ret='href')
epi_link = [i for i in epi_link if sepi in i][0]
self.get_sources(epi_link, title, year, season, episode,
start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
count = 0
start_time = time.time()
search_id = urllib.quote_plus('%s %s' % (clean_search(title), year))
start_url = '%s/?s=%s' % (self.base_link, search_id)
html = client.request(start_url, referer=self.base_link)
match = re.compile('class="thumb".+?title="(.+?)".+?href="(.+?)">', re.DOTALL).findall(html)
for name, item_url in match:
if not year in name:
continue
if not clean_title(title) == clean_title((name.split(year)[0][:-1])):
continue
OPEN = client.request(item_url, referer=self.base_link)
link = client.parseDOM(OPEN, 'iframe', ret='src')[0]
host = link.split('//')[1].replace('www.', '')
host = host.split('/')[0]
if not filter_host(host):
continue
count += 1
self.sources.append({'source': host, 'quality': 'HD', 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = urllib.quote_plus('%s %s' % (title, year))
# search_id.replace(' ','+') = urllib.quote_plus(search_id)
start_url = '%s/index.php?s=%s' % (self.base_link, search_id)
#print 'CoolMovieZone - scrape_movie - start_url: ' + start_url
headers = {'User-Agent': client.agent()}
html = client.request(start_url, headers=headers)
match = client.parseDOM(html, 'h1')
match = [
dom_parser.parse_dom(i, 'a', req='href') for i in match if i
]
match = [(i[0].attrs['href'], i[0].content) for i in match if i]
for item_url, name in match:
if year not in name: continue
if not clean_title(title) == clean_title(name):
continue #.lower() added on clean_title function
self.get_source(item_url, title, year, '', '', start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
scraper = cfscrape.create_scraper()
r = scraper.get(url, headers=headers)
#r = client.request(url, headers=headers)
posts = client.parseDOM(r.content, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = dom.parse_dom(post, 'a', req='href')[1]
link = urlparse.urljoin(self.base_link, data.attrs['href'])
name = data.content
t = name.split(self.hdlr)[0]
if not clean_title(re.sub('(|)', '', t)) == clean_title(
self.title):
continue
try:
y = re.findall(
'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]',
name, re.I)[-1].upper()
except BaseException:
y = re.findall(
'[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name,
re.I)[-1].upper()
if not y == self.hdlr: continue
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(
re.sub('[^0-9|/.|/,]', '', size.replace(',',
'.'))) / div
size = '%.2f GB' % size
except BaseException:
size = '0'
self.items.append((name, link, size))
return self.items
except BaseException:
return self.items
def get_sources(self, url, title, year, season, episode, start_time):
try:
count = 0
url = urlparse.urljoin(self.base_link,
url) if url.startswith('/') else url
r = client.request(url)
links = client.parseDOM(r, 'tbody')
for link in links:
try:
data = [(client.parseDOM(link, 'a', ret='href')[0],
client.parseDOM(link,
'span',
attrs={'class':
'version_host'})[0])][0]
link = urlparse.urljoin(self.base_link, data[0])
#xbmc.log('@#@link: %s' % link, xbmc.LOGNOTICE)
host = data[1]
if not filter_host(host): continue
self.sources.append({
'source': host,
'quality': 'SD',
'scraper': self.name,
'url': link,
'direct': False
})
except:
pass
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name,
end_time,
count,
title,
year,
season=season,
episode=episode)
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_episode(self,
title,
show_year,
year,
season,
episode,
imdb,
tvdb,
debrid=False):
try:
start_time = time.time()
start_url = urlparse.urljoin(
self.base_link,
self.tvsearch_link % urllib.quote_plus(clean_search(title)))
#xbmc.log('@#@START: %s' % start_url, xbmc.LOGNOTICE)
html = client.request(start_url)
posts = client.parseDOM(html,
'div',
attrs={'class': 'index_item.+?'})
posts = [(dom.parse_dom(i, 'a', req='href')[0]) for i in posts
if i]
post = [
(i.attrs['href']) for i in posts
if clean_title(title) == clean_title(
re.sub('(\.|\(|\[|\s)(S\d+E\d+|S\d+)(\.|\)|\]|\s|)(.+|)',
'', i.attrs['title'], re.I))
][0]
r = client.request(post)
r = client.parseDOM(r, 'div', attrs={'class': 'tv_episode_item'})
urls = client.parseDOM(r, 'a', ret='href')
epi_link = [
i for i in urls
if 'season-%s-episode-%s' % (int(season), int(episode)) in i
][0]
#xbmc.log('@#@EPI-LINK: %s' % epi_link, xbmc.LOGNOTICE)
self.get_sources(epi_link, title, year, season, episode,
start_time)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = '%s %s' % (title, year)
movie_url = self.base_link + self.search_link % urllib.quote_plus(
search_id)
r = client.request(movie_url)
items = client.parseDOM(r, 'article', attrs={'id': 'post-\d+'})
#xbmc.log('@#@ITEMS:%s' % items, xbmc.LOGNOTICE)
links = []
for item in items:
name = client.parseDOM(item, 'a')[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+|3D)(\.|\)|\]|\s|)(.+|)',
'',
name,
flags=re.I)
if not clean_title(title) == clean_title(t):
continue
if not year in name:
continue
link = client.parseDOM(item, 'a', ret='href')[0]
link += '/2/'
links.append(link)
#xbmc.log('@#@LINKS:%s' % links, xbmc.LOGNOTICE)
threads = []
for i in links:
threads.append(
workers.Thread(self.get_source, i, title, year, '', '',
str(start_time)))
[i.start() for i in threads]
alive = [x for x in threads if x.is_alive() is True]
while alive:
alive = [x for x in threads if x.is_alive() is True]
time.sleep(0.1)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
#print search_id
#xbmc.log('@#@TITLE: %s' % search_id, xbmc.LOGNOTICE)
start_url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(search_id))
headers = {'User-Agent': client.agent()}
r = client.request(start_url, headers=headers)
posts = client.parseDOM(r, 'div', attrs={'id': 'movie-\d+'})
posts = [(client.parseDOM(i, 'h4')[0]) for i in posts if i]
#print posts
posts = [(client.parseDOM(i, 'a', ret='href')[0],
client.parseDOM(i, 'a')[0]) for i in posts if i]
#posts = [(i[0]) for i in posts if clean_title(search_id) == clean_title(i[1])]
count = 0
for link, found_title in posts:
link = urlparse.urljoin(self.base_link, link) if link.startswith('/') else link
if not clean_title(title) == clean_title(found_title): continue
result = client.request(link, headers=headers)
y = client.parseDOM(result, 'div', attrs={'class': 'showValue showValueRelease'})[0]
if not year == y: continue
streams = client.parseDOM(result, 'div', attrs={'class': 'linkTr'})
for stream in streams:
quality = client.parseDOM(stream, 'div', attrs={'class': 'linkQualityText'})[0]
link = client.parseDOM(stream, 'div', attrs={'class':'linkHidden linkHiddenUrl'})[0]
#print link
if 'vidnode' in link:
continue
if 'HD' in quality:
quality = 'HD'
else:
quality = 'SD'
host = quality_tags._give_host(link)
#print host
count += 1
self.sources.append(
{'source': host, 'quality': quality, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year)
return self.sources
except Exception, argument:
if dev_log == 'true':
error_log(self.name, argument)
return self.sources
def get_source(self,media_url, title,year,season,episode,start_time):
#print 'source season ' + media_url
season_bollox = "0%s" % season if len(season) < 2 else season
episode_bollox = "0%s" % episode if len(episode) < 2 else episode
all_bollox = 's%se%s' % (season_bollox, episode_bollox)
try:
headers = {'User-Agent': client.agent()}
html = client.request(media_url,headers=headers)
match = re.findall(r'<li><a href="([^"]+)">([^<>]*)<span.+?>', str(html), re.I | re.DOTALL)
count = 0
for media_url, media_title in match:
if all_bollox in media_title.lower():
link = client.request(media_url, headers=headers)
frame = client.parseDOM(link, 'iframe', ret='src')
print frame
for frame_link in frame:
self.sources.append({'source': 'Openload', 'quality': 'Unknown',
'scraper': self.name, 'url': frame_link, 'direct': False})
cool_links = re.compile('"dwn-box".+?ref="(.+?)" rel="nofollow">(.+?)<span',re.DOTALL).findall(link)
for vid_url, res in cool_links:
if '1080' in res:
res = '1080p'
elif '720' in res:
res = '720p'
elif 'HD' in res:
res = 'HD'
else:
res = 'SD'
count += 1
vid_url += '|User-Agent=%s&Referer=%s' % (client.agent(), media_url)
vid_url = urllib.quote(vid_url, '|:?/&+=_-')
self.sources.append({'source': 'Direct', 'quality': res, 'scraper': self.name, 'url': vid_url,
'direct': True})
if dev_log=='true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year, season='', episode='')
except:
pass
def get_source(self,url, title, year, season, episode, start_time):
try:
scraper = cfscrape.create_scraper()
headers = {'Origin': 'http://hdpopcorns.com', 'Referer': url,
'X-Requested-With': 'XMLHttpRequest',
'User-Agent': client.agent()}
count = 0
data = scraper.get(url, headers=headers).content
data = client.parseDOM(data, 'div', attrs={'class': 'thecontent'})[0]
FN720p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FileName720p'})[0]
FS720p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FileSize720p'})[0]
FSID720p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FSID720p'})[0]
FN1080p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FileName1080p'})[0]
FS1080p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FileSize1080p'})[0]
FSID1080p = client.parseDOM(data, 'input', ret='value', attrs={'name': 'FSID1080p'})[0]
post = {'FileName720p': FN720p, 'FileSize720p': FS720p, 'FSID720p': FSID720p,
'FileName1080p': FN1080p, 'FileSize1080p': FS1080p, 'FSID1080p': FSID1080p,
'x': 173, 'y': 22}
data = scraper.post('%s/select-movie-quality.php' % self.base_link, data=post).content
data = client.parseDOM(data, 'div', attrs={'id': 'btn_\d+p'})
u = [client.parseDOM(i, 'a', ret='href')[0] for i in data]
for url in u:
quality, info = quality_tags.get_release_quality(url, url)
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
count += 1
self.sources.append(
{'source': 'DirectLink', 'quality': quality, 'scraper': self.name, 'url': url, 'direct': True})
if dev_log=='true':
end_time = time.time() - start_time
send_log(self.name,end_time,count,title,year, season=season,episode=episode)
except:
pass
#hdpopcorn().scrape_movie('Blade Runner 2049', '2017', '', False) title contains 2 years
#hdpopcorn().scrape_movie('Deadpool 2', '2018', '', False) title contains number
def scrape_movie(self, title, year, imdb, debrid=False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(search_id))
headers={'User-Agent': client.agent()}
html = client.request(start_url, headers=headers)
results = client.parseDOM(html, 'div', attrs={'class': 'video_title'})
items = []
for item in results:
try:
data = dom_parser.parse_dom(item, 'a', req=['href', 'title'])[0]
t = data.content
y = re.findall('\((\d{4})\)', data.attrs['title'])[0]
qual = data.attrs['title'].split('-')[1]
link = data.attrs['href']
if not clean_title(t) == clean_title(title): continue
if not y == year: continue
items += [(link, qual)]
except:
pass
for item in items:
count = 0
try:
url = item[0] if item[0].startswith('http') else urlparse.urljoin(self.base_link, item[0])
r = client.request(url)
qual = client.parseDOM(r, 'h1')[0]
res = quality_tags.get_release_quality(item[1], qual)[0]
url = re.findall('''frame_url\s*=\s*["']([^']+)['"]\;''', r, re.DOTALL)[0]
url = url if url.startswith('http') else urlparse.urljoin('https://', url)
if 'vidlink' in url:
html = client.request(url, headers=headers)
action = re.findall("action'\s*:\s*'([^']+)", html)[0]
postID = re.findall("postID\s*=\s*'([^']+)", html)[0]
url = 'https://vidlink.org' + re.findall("var\s*url\s*=\s*'([^']+)", html)[0]
data = {'browserName': 'Firefox',
'platform': 'Win32',
'postID': postID,
'action': action}
headers['X-Requested-With'] = 'XMLHttpRequest'
headers['Referer'] = url
html = client.request(url, post=data, headers=headers)
html = jsunpack.unpack(html).replace('\\', '')
sources = json.loads(re.findall('window\.srcs\s*=\s*([^;]+)', html, re.DOTALL)[0])
for src in sources:
r = requests.head(src['url'], headers={'User-Agent': client.agent()})
if r.status_code < 400:
movie_link = src['url']
count += 1
self.sources.append({'source': 'Googlelink', 'quality': res,
'scraper': self.name, 'url': movie_link, 'direct': True})
else:
continue
except:
pass
if dev_log=='true':
end_time = time.time() - start_time
send_log(self.name,end_time, count, title,year)
#print self.sources
return self.sources
except Exception, argument:
print argument
if dev_log == 'true':
error_log(self.name,argument)
return self.sources
#watch32().scrape_movie('Black Panther', '2018', 'tt1825683', False)
def scrape_episode(self, title, show_year, year, season, episode, imdb, tvdb, debrid=False):
try:
start_time = time.time()
search_id = clean_search(title.lower())
start_url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(search_id))
#print start_url
headers = {'User-Agent': client.agent()}
r = client.request(start_url, headers=headers)
posts = client.parseDOM(r, 'div', attrs={'id': 'movie-\d+'})
posts = [(client.parseDOM(i, 'h4')[0]) for i in posts if i]
for item in posts:
name = client.parseDOM(item, 'a')[0]
link = client.parseDOM(item, 'a', ret='href')[0]
if not clean_title(title) == clean_title(name): continue
link = urlparse.urljoin(self.base_link, link)
html = client.request(link)
#<div class="season" id="season8">
sep_id = 'Season %s Serie %s' % (int(season), int(episode))
#print sep_id
seasons = client.parseDOM(html, 'div', attrs={'class': 'season'})
seasons = [i for i in seasons if 'season %s' % int(season) in i.lower()][0]
epis = re.findall('<h3>(.+?)</div>\s+</div>\s+</div>\s+</div>', seasons, re.DOTALL | re.MULTILINE)
epis = [i for i in epis if sep_id in i][0]
count = 0
streams = client.parseDOM(epis, 'div', attrs={'class': 'linkTr'})
for stream in streams:
quality = client.parseDOM(stream, 'div', attrs={'class': 'linkQualityText'})[0]
link = client.parseDOM(stream, 'div', attrs={'class': 'linkHidden linkHiddenUrl'})[0]
#print link
if 'vidnode' in link:
continue
if 'HD' in quality:
quality = 'HD'
else:
quality = 'SD'
host = quality_tags._give_host(link)
# print host
count += 1
self.sources.append(
{'source': host, 'quality': quality, 'scraper': self.name, 'url': link, 'direct': False})
if dev_log == 'true':
end_time = time.time() - start_time
send_log(self.name, end_time, count, title, year, season=season, episode=episode)
return self.sources
except Exception as argument:
if dev_log == 'true':
error_log(self.name, argument)
return []
#vkflix().scrape_movie('Black Panther', '2018', '', False)
#vkflix().scrape_episode('Suits', '2011','','8','5','','')