def __get_links_from_xml(self, xml, video):
sources = {}
try:
root = ET.fromstring(xml)
for item in root.findall('.//item'):
title = item.find('title').text
for source in item.findall('{http://rss.jwpcdn.com/}source'):
stream_url = source.get('file')
label = source.get('label')
if self._get_direct_hostname(stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif label:
quality = scraper_utils.height_get_quality(label)
else:
quality = scraper_utils.blog_get_quality(
video, title, '')
sources[stream_url] = {'quality': quality, 'direct': True}
log_utils.log(
'Adding stream: %s Quality: %s' %
(stream_url, quality), log_utils.LOGDEBUG)
except Exception as e:
log_utils.log('Exception during 123Movies XML Parse: %s' % (e),
log_utils.LOGWARNING)
return sources
def __get_links_from_json2(self, url, page_url, video_type):
sources = {}
headers = {'Referer': page_url}
headers.update(XHR)
html = self._http_get(url, headers=headers, cache_limit=0)
js_data = scraper_utils.parse_json(html, url)
try:
playlist = js_data.get('playlist', [])
for source in playlist[0].get('sources', []):
stream_url = source['file']
if scraper_utils.get_direct_hostname(self,
stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in source:
quality = scraper_utils.height_get_quality(source['label'])
else:
if video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(stream_url)
else:
meta = scraper_utils.parse_episode_link(stream_url)
quality = scraper_utils.height_get_quality(meta['height'])
sources[stream_url] = {'quality': quality, 'direct': True}
logger.log(
'Adding stream: %s Quality: %s' % (stream_url, quality),
log_utils.LOGDEBUG)
except Exception as e:
logger.log('Exception during yesmovies extract: %s' % (e),
log_utils.LOGDEBUG)
return sources
def __get_gk_links(self, html, page_url):
sources = {}
match = re.search('{link\s*:\s*"([^"]+)', html)
if match:
data = {'link': match.group(1)}
url = urlparse.urljoin(self.base_url, LINK_URL)
headers = {'Referer': page_url}
html = self._http_get(url,
data=data,
headers=headers,
cache_limit=.25)
js_data = scraper_utils.parse_json(html, url)
if 'link' in js_data:
for link in js_data['link']:
if 'type' in link and link[
'type'] == 'mp4' and 'link' in link:
if self._get_direct_hostname(link['link']) == 'gvideo':
quality = scraper_utils.gv_get_quality(
link['link'])
elif 'label' in link:
quality = scraper_utils.height_get_quality(
link['label'])
else:
quality = QUALITIES.HIGH
sources[link['link']] = quality
return sources
def __get_king_links(self, iframe_url):
hosters = []
match = re.search('v=(.*)', iframe_url)
if match:
data = {'ID': match.group(1)}
headers = {'Referer': iframe_url}
headers.update(XHR)
xhr_url = iframe_url.split('?')[0]
html = self._http_get(xhr_url, params={'p': 'GetVideoSources'}, data=data, headers=headers, cache_limit=.5)
js_data = scraper_utils.parse_json(html, xhr_url)
try:
for source in js_data['VideoSources']:
stream_url = source['file'] + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
host = scraper_utils.get_direct_hostname(self, source['file'])
label = source.get('label', '')
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source['file'])
elif re.search('\d+p?', label):
quality = scraper_utils.height_get_quality(label)
else:
quality = QUALITY_MAP.get(label, QUALITIES.HIGH)
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True, 'subs': 'Turkish Subtitles'}
hosters.append(hoster)
except:
pass
return hosters
def get_sources(self, video):
hosters = []
sources = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.25)
match = re.search('var\s+view_id\s*=\s*"([^"]+)', html)
if not match: return hosters
view_id = match.group(1)
for lang in ['or', 'tr']:
subs = True if lang == 'tr' else False
view_data = {'id': view_id, 'tip': 'view', 'dil': lang}
html = self._http_get(self.ajax_url, data=view_data, headers=XHR, cache_limit=.25)
html = html.strip()
html = re.sub(r'\\n|\\t', '', html)
match = re.search('var\s+sources\s*=\s*(\[.*?\])', html)
if match:
raw_data = match.group(1)
raw_data = raw_data.replace('\\', '')
else:
raw_data = html
js_data = scraper_utils.parse_json(raw_data, self.ajax_url)
if 'data' not in js_data: continue
src = dom_parser2.parse_dom(js_data['data'], 'iframe', req='src')
if not src: continue
html = self._http_get(src[0].attrs['src'], cache_limit=.25)
for attrs, _content in dom_parser2.parse_dom(html, 'iframe', req='src'):
src = attrs['src']
if not src.startswith('http'): continue
sources.append({'label': '720p', 'file': src, 'direct': False, 'subs': subs})
sources += [{'file': url, 'subs': subs} for url in scraper_utils.parse_sources_list(self, html).iterkeys()]
if sources: break
for source in sources:
direct = source.get('direct', True)
stream_url = source['file'] + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
if direct:
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in source:
quality = scraper_utils.height_get_quality(source['label'])
else:
continue
else:
host = urlparse.urlparse(stream_url).hostname
quality = scraper_utils.height_get_quality(source['label'])
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct}
if source.get('subs'): hoster['subs'] = 'Turkish Subtitles'
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=8)
hosts = [
r.content for r in dom_parser2.parse_dom(
html, 'p', {'class': 'server_servername'})
]
links = [
r.content
for r in dom_parser2.parse_dom(html, 'p', {'class': 'server_play'})
]
for host, link_frag in zip(hosts, links):
stream_url = dom_parser2.parse_dom(link_frag, 'a', req='href')
if not stream_url: continue
stream_url = stream_url[0].attrs['href']
host = re.sub('^Server\s*', '', host, re.I)
host = re.sub('\s*Link\s+\d+', '', host)
if host.lower() == 'google':
sources = self.__get_gvideo_links(stream_url)
else:
sources = [{'host': host, 'link': stream_url}]
for source in sources:
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
stream_url = source['link'] + scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
direct = True
else:
stream_url = scraper_utils.pathify_url(source['link'])
host = HOST_SUB.get(source['host'].lower(), source['host'])
quality = scraper_utils.get_quality(
video, host, QUALITIES.HIGH)
direct = False
hoster = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': direct
}
hosters.append(hoster)
return hosters
def __get_gk_links2(self, html):
sources = {}
match = re.search('base64\.decode\("([^"]+)', html, re.I)
if match:
match = re.search('proxy\.link=tunemovie\*([^&]+)',
base64.b64decode(match.group(1)))
if match:
picasa_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY,
match.group(1))
g_links = self._parse_google(picasa_url)
for link in g_links:
sources[link] = scraper_utils.gv_get_quality(link)
return sources
def __get_gk_links(self, html, page_url):
sources = {}
for link in dom_parser.parse_dom(html, 'div',
{'class': '[^"]*server_line[^"]*'}):
film_id = dom_parser.parse_dom(link, 'a', ret='data-film')
name_id = dom_parser.parse_dom(link, 'a', ret='data-name')
server_id = dom_parser.parse_dom(link, 'a', ret='data-server')
if film_id and name_id and server_id:
data = {
'ipplugins': 1,
'ip_film': film_id[0],
'ip_server': server_id[0],
'ip_name': name_id[0]
}
headers = XHR
headers['Referer'] = page_url
url = urlparse.urljoin(self.base_url, LINK_URL)
html = self._http_get(url,
data=data,
headers=headers,
cache_limit=.25)
js_data = scraper_utils.parse_json(html, url)
if 's' in js_data:
url = urlparse.urljoin(self.base_url, LINK_URL2)
params = {'u': js_data['s'], 'w': '100%', 'h': 420}
html = self._http_get(url,
params=params,
data=data,
headers=headers,
cache_limit=.25)
js_data = scraper_utils.parse_json(html, url)
if 'data' in js_data and js_data['data']:
if isinstance(js_data['data'], basestring):
sources[js_data['data']] = QUALITIES.HIGH
else:
for link in js_data['data']:
stream_url = link['files']
if self._get_direct_hostname(
stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(
stream_url)
elif 'quality' in link:
quality = scraper_utils.height_get_quality(
link['quality'])
else:
quality = QUALITIES.HIGH
sources[stream_url] = quality
return sources
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=8)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'playex'})
if fragment: html = fragment[0].content
links = scraper_utils.parse_sources_list(self, html)
for link in links:
stream_url = link
if self.base_url in link:
redir_url = self._http_get(link,
headers={'Referer': url},
allow_redirect=False,
method='HEAD')
if redir_url.startswith('http'):
stream_url = redir_url
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = links[link]['quality']
stream_url += scraper_utils.append_headers({
'User-Agent':
scraper_utils.get_ua(),
'Referer':
url
})
source = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': True
}
hosters.append(source)
return hosters
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=0)
match = re.search('var\s*video_id\s*=\s*"([^"]+)', html)
if not match: return hosters
video_id = match.group(1)
headers = {'Referer': page_url}
headers.update(XHR)
# _html = self._http_get(scraper_utils.urljoin(self.base_url, 'av'), headers=headers, method='POST', cache_limit=0)
vid_url = scraper_utils.urljoin(self.base_url, VIDEO_URL)
html = self._http_get(vid_url,
data={'v': video_id},
headers=headers,
cache_limit=0)
for source, value in scraper_utils.parse_json(html,
vid_url).iteritems():
match = re.search('url=(.*)', value)
if not match: continue
stream_url = urllib.unquote(match.group(1))
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(source)
stream_url += scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': True
}
hosters.append(hoster)
return hosters
def __get_ajax(self, html, page_url):
sources = {}
pattern = '\$\.ajax\(\s*"([^"]+)'
match = re.search(pattern, html)
if not match: return sources
post_url = match.group(1)
headers = {'Referer': page_url}
html = self._http_get(post_url, headers=headers, cache_limit=.5)
js_result = scraper_utils.parse_json(html, post_url)
for key in js_result:
stream_url = js_result[key]
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(key)
sources[stream_url] = quality
return sources
def __get_json_links(self, html, sub):
hosters = []
js_data = scraper_utils.parse_json(html)
if 'sources' in js_data:
for source in js_data.get('sources', []):
stream_url = source.get('file')
if stream_url is None: continue
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in source:
quality = scraper_utils.height_get_quality(source['label'])
else:
quality = QUALITIES.HIGH
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
hoster['subs'] = sub
hosters.append(hoster)
return hosters
def __get_iframe_links(self, html, page_url):
sources = {}
urls = dom_parser.parse_dom(
html, 'iframe', ret='data-lazy-src') + dom_parser.parse_dom(
html, 'iframe', ret='src')
for iframe_url in urls:
headers = {'Referer': page_url}
html = self._http_get(iframe_url, headers=headers, cache_limit=0)
for match in re.finditer(
'"file"\s*:\s*"([^"]+)"\s*,\s*"label"\s*:\s*"([^"]+)',
html, re.DOTALL):
stream_url, height = match.groups()
stream_url = re.sub('; .*', '', stream_url)
if self._get_direct_hostname(stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(height)
sources[stream_url] = quality
return sources
def __get_posts(self, html):
sources = {}
pattern = '\$\.post\("([^"]+)"\s*,\s*\{(.*?)\}'
match = re.search(pattern, html)
if not match: return sources
post_url, post_data = match.groups()
data = self.__get_data(post_data)
html = self._http_get(post_url, data=data, cache_limit=.5)
js_result = scraper_utils.parse_json(html, post_url)
for key in js_result:
stream_url = js_result[key]
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(key)
sources[stream_url] = quality
return sources
def __get_linked(self, html):
sources = {}
match = re.search('dizi=([^"]+)', html)
if not match: return sources
html = self._http_get(AJAX_URL,
params={'dizi': match.group(1)},
headers=XHR,
cache_limit=.5)
js_result = scraper_utils.parse_json(html, AJAX_URL)
for source in js_result.get('success', []):
stream_url = source.get('src')
if stream_url is None: continue
if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in source:
quality = scraper_utils.height_get_quality(source['label'])
else:
quality = QUALITIES.HIGH
sources[stream_url] = quality
return sources
def __get_ht_links(self, html, page_url):
sources = {}
match = re.search('Htplugins_Make_Player\("([^"]+)', html)
if match:
data = {'data': match.group(1)}
url = scraper_utils.urljoin(self.base_url, LINK_URL2)
headers = {'Referer': page_url}
html = self._http_get(url,
data=data,
headers=headers,
cache_limit=.25)
js_data = scraper_utils.parse_json(html, url)
if 'l' in js_data:
for link in js_data['l']:
if scraper_utils.get_direct_hostname(self,
link) == 'gvideo':
quality = scraper_utils.gv_get_quality(link)
else:
quality = QUALITIES.HIGH
sources[link] = quality
return sources
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
page_url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.5)
match = re.search('var\s*video_id="([^"]+)', html)
if match:
video_id = match.group(1)
data = {'v': video_id}
headers = {'Referer': page_url}
headers.update(XHR)
html = self._http_get(self.info_url,
data=data,
headers=headers,
cache_limit=0)
sources = scraper_utils.parse_json(html, self.info_url)
for source in sources:
match = re.search('url=(.*)', sources[source])
if match:
stream_url = urllib.unquote(match.group(1))
host = self._get_direct_hostname(stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(source)
stream_url += scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': True
}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
html = self._http_get(source_url, cache_limit=.5)
fragment = dom_parser.parse_dom(html, 'div',
{'class': '[^"]*screen[^"]*'})
if fragment:
js_src = dom_parser.parse_dom(fragment[0], 'script', ret='src')
if js_src:
js_url = urlparse.urljoin(self.base_url, js_src[0])
html = self._http_get(js_url, cache_limit=.5)
else:
html = fragment[0]
for match in re.finditer('<source[^>]+src="([^"]+)', html):
stream_url = match.group(1)
host = self._get_direct_hostname(stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
_, _, height, _ = scraper_utils.parse_movie_link(
stream_url)
quality = scraper_utils.height_get_quality(height)
stream_url += '|User-Agent=%s' % (
scraper_utils.get_ua())
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': True
}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
sources = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
for fragment in dom_parser.parse_dom(html, 'div',
{'class': 'player_wraper'}):
iframe_url = dom_parser.parse_dom(fragment,
'iframe',
ret='src')
if iframe_url:
url = urlparse.urljoin(self.base_url, iframe_url[0])
html = self._http_get(url, cache_limit=.5)
for match in re.finditer(
'"(?:url|src)"\s*:\s*"([^"]+)[^}]+"res"\s*:\s*([^,]+)',
html):
stream_url, height = match.groups()
host = self._get_direct_hostname(stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(height)
stream_url += '|User-Agent=%s' % (
scraper_utils.get_ua())
source = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': True
}
sources.append(source)
return sources
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
sources = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=1)
iframes = dom_parser2.parse_dom(html, 'iframe', req='src')
for attrs, _content in iframes:
iframe_url = attrs['src']
if 'docs.google.com' in iframe_url:
sources = scraper_utils.parse_google(self, iframe_url)
break
else:
iframe_url = scraper_utils.urljoin(self.base_url, iframe_url)
html = self._http_get(iframe_url, cache_limit=1)
iframes += dom_parser2.parse_dom(html, 'iframe', req='src')
for source in sources:
host = scraper_utils.get_direct_hostname(self, source)
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': scraper_utils.gv_get_quality(source), 'views': None, 'rating': None, 'url': source, 'direct': True}
hosters.append(hoster)
return hosters
def __get_links_from_xml(self, url, video, page_url, cookies):
sources = {}
try:
headers = {'Referer': page_url}
xml = self._http_get(url,
cookies=cookies,
headers=headers,
cache_limit=.5)
root = ET.fromstring(xml)
for item in root.findall('.//item'):
title = item.find('title').text
if title and title.upper() == 'OOPS!': continue
for source in item.findall(
'{https://yesmovies.to/ajax/movie_sources/'):
stream_url = source.get('file')
label = source.get('label')
if scraper_utils.get_direct_hostname(
self, stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif label:
quality = scraper_utils.height_get_quality(label)
elif title:
quality = scraper_utils.blog_get_quality(
video, title, '')
else:
quality = scraper_utils.blog_get_quality(
video, stream_url, '')
sources[stream_url] = {'quality': quality, 'direct': True}
logger.log(
'Adding stream: %s Quality: %s' %
(stream_url, quality), log_utils.LOGDEBUG)
except Exception as e:
logger.log('Exception during YesMovies XML Parse: %s' % (e),
log_utils.LOGWARNING)
return sources
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
headers = {'Referer': page_url}
html = self._http_get(page_url, headers=headers, cache_limit=.5)
if video.video_type == VIDEO_TYPES.MOVIE:
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'poster'})
if fragment:
movie_url = dom_parser2.parse_dom(fragment[0].content,
'a',
req='href')
if movie_url:
page_url = scraper_utils.urljoin(
self.base_url, movie_url[0].attrs['href'])
html = self._http_get(page_url, cache_limit=.5)
episodes = self.__get_episodes(html)
page_url = self.__get_best_page(episodes)
if not page_url:
return hosters
else:
page_url = scraper_utils.urljoin(
self.base_url, page_url)
html = self._http_get(page_url, cache_limit=.5)
streams = dom_parser2.parse_dom(html, 'iframe', req='src')
if streams:
streams = [(attrs['src'], 480) for attrs, _content in streams]
direct = False
else:
streams = [(attrs['src'], attrs.get('data-res', 480))
for attrs, _content in dom_parser2.parse_dom(
html, 'source', req=['src'])]
direct = True
headers = {'User-Agent': scraper_utils.get_ua(), 'Referer': page_url}
for stream_url, height in streams:
if 'video.php' in stream_url or 'moviexk.php' in stream_url:
if 'title=' in stream_url:
title = stream_url.split('title=')[-1]
stream_url = stream_url.replace(title, urllib.quote(title))
redir_url = self._http_get(stream_url,
headers=headers,
allow_redirect=False,
method='HEAD',
cache_limit=0)
if redir_url.startswith('http'):
redir_url = redir_url.replace(' ', '').split(';codec')[0]
stream_url = redir_url
else:
continue
if direct:
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = scraper_utils.height_get_quality(height)
stream_url += scraper_utils.append_headers(headers)
else:
host = urlparse.urlparse(stream_url).hostname
quality = scraper_utils.height_get_quality(height)
source = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': direct
}
hosters.append(source)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
sources = []
if not source_url or source_url == FORCE_NO_MATCH: return sources
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=8)
for attrs, _content in dom_parser2.parse_dom(
html, 'img', req=['data-id', 'data-name']):
film_id, data_name = attrs['data-id'], attrs['data-name']
data = {'id': film_id, 'n': data_name}
server_url = scraper_utils.urljoin(self.base_url, SERVER_URL)
server_url = server_url % (film_id)
headers = {'Referer': page_url}
headers.update(XHR)
html = self._http_get(server_url,
data=data,
headers=headers,
cache_limit=.5)
for attrs, _content in dom_parser2.parse_dom(html,
'a',
req='data-id'):
data = {'epid': attrs['data-id']}
ep_url = scraper_utils.urljoin(self.base_url, EP_URL)
ep_url = ep_url % (attrs['data-id'])
headers = {'Referer': page_url}
headers.update(XHR)
html = self._http_get(ep_url,
data=data,
headers=headers,
cache_limit=.5)
js_data = scraper_utils.parse_json(html, ep_url)
try:
links = [
r.attrs['src'] for r in dom_parser2.parse_dom(
js_data['link']['embed'], 'iframe', req='src')
]
except:
try:
links = js_data['link']['l']
except:
links = []
try:
heights = js_data['link']['q']
except:
heights = []
for stream_url, height in map(None, links, heights):
match = re.search('movie_url=(.*)', stream_url)
if match:
stream_url = match.group(1)
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
stream_url += scraper_utils.append_headers({
'User-Agent':
scraper_utils.get_ua(),
'Referer':
page_url
})
direct = True
else:
host = urlparse.urlparse(stream_url).hostname
if height:
quality = scraper_utils.height_get_quality(height)
else:
quality = QUALITIES.HD720
direct = False
source = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': direct
}
sources.append(source)
return sources
