def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
js_url = scraper_utils.urljoin(self.base_url, '/javascript/movies.js')
html = self._http_get(js_url, cache_limit=48)
if source_url.startswith('/'):
source_url = source_url[1:]
pattern = '''getElementById\(\s*"%s".*?play\(\s*'([^']+)''' % (source_url)
match = re.search(pattern, html, re.I)
if match:
stream_url = match.group(1)
if 'drive.google' in stream_url or 'docs.google' in stream_url:
sources = scraper_utils.parse_google(self, stream_url)
else:
sources = [stream_url]
for source in sources:
stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
host = scraper_utils.get_direct_hostname(self, source)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source)
direct = True
elif 'youtube' in stream_url:
quality = QUALITIES.HD720
direct = False
host = 'youtube.com'
else:
quality = QUALITIES.HIGH
direct = True
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct}
hosters.append(hoster)
return hosters
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_gk_links(self, link, iframe_url):
sources = {}
data = {'link': link}
headers = XHR
headers.update({'Referer': iframe_url, 'User-Agent': USER_AGENT})
html = self._http_get(GK_URL, data=data, headers=headers, cache_limit=.25)
js_data = scraper_utils.parse_json(html, GK_URL)
if 'link' in js_data:
if isinstance(js_data['link'], basestring):
stream_url = js_data['link']
if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
for source in scraper_utils.parse_google(self, stream_url):
sources[source] = {'quality': scraper_utils.gv_get_quality(source), 'direct': True}
else:
sources[stream_url] = {'quality': QUALITIES.HIGH, 'direct': False}
else:
for link in js_data['link']:
stream_url = link['link']
if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in link:
quality = scraper_utils.height_get_quality(link['label'])
else:
quality = QUALITIES.HIGH
sources[stream_url] = {'quality': quality, 'direct': True}
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
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=8)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'playex'})
if fragment: html = fragment[0].content
iframe_url = dom_parser2.parse_dom(html, 'iframe', req='src')
if not iframe_url: return hosters
iframe_url = iframe_url[0].attrs['src']
if iframe_url.startswith('/'):
iframe_url = scraper_utils.urljoin(self.base_url, iframe_url)
html = self._http_get(iframe_url, headers={'Referer': page_url}, cache_limit=.5)
obj = dom_parser2.parse_dom(html, 'object', req='data')
if obj:
streams = dict((stream_url, {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True}) for stream_url in
scraper_utils.parse_google(self, obj[0].attrs['data']))
else:
streams = scraper_utils.parse_sources_list(self, html)
for stream_url, values in streams.iteritems():
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = values['quality']
stream_url += scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': page_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, require_debrid=True, cache_limit=.5)
fragment = dom_parser2.parse_dom(html, 'table',
{'class': 'links-table'})
if not fragment: return hosters
for _attrs, row in dom_parser2.parse_dom(fragment[0].content, 'tr'):
match = re.search(
"playVideo\.bind\(.*?'([^']+)(?:[^>]*>){2}(.*?)</td>", row,
re.DOTALL)
if not match: continue
stream_url, release = match.groups()
if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
sources = scraper_utils.parse_google(self, stream_url)
else:
sources = [stream_url]
for source in sources:
host = scraper_utils.get_direct_hostname(self, source)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source)
direct = True
else:
host = urlparse.urlparse(source).hostname
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(release)
else:
meta = scraper_utils.parse_episode_link(release)
base_quality = scraper_utils.height_get_quality(
meta['height'])
quality = scraper_utils.get_quality(
video, host, base_quality)
direct = False
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': source,
'direct': direct
}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
sources = {}
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=0)
for match in re.finditer("embeds\[(\d+)\]\s*=\s*'([^']+)", html):
match = re.search('src="([^"]+)', match.group(2))
if match:
iframe_url = match.group(1)
if 'play-en.php' in iframe_url:
match = re.search('id=([^"&]+)', iframe_url)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
picasa_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY, proxy_link)
for stream_url in scraper_utils.parse_google(self, picasa_url):
sources[stream_url] = {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True}
else:
html = self._http_get(iframe_url, cache_limit=0)
temp_sources = scraper_utils.parse_sources_list(self, html)
for source in temp_sources:
if 'download.php' in source:
redir_html = self._http_get(source, allow_redirect=False, method='HEAD', cache_limit=0)
if redir_html.startswith('http'):
temp_sources[redir_html] = temp_sources[source]
del temp_sources[source]
sources.update(temp_sources)
for source in dom_parser2.parse_dom(html, 'source', {'type': 'video/mp4'}, req='src'):
sources[source.attrs['src']] = {'quality': QUALITIES.HD720, 'direct': True, 'referer': iframe_url}
for source, values in sources.iteritems():
host = scraper_utils.get_direct_hostname(self, source)
headers = {'User-Agent': scraper_utils.get_ua()}
if 'referer' in values: headers['Referer'] = values['referer']
stream_url = source + scraper_utils.append_headers(headers)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source)
else:
quality = values['quality']
if quality not in Q_ORDER:
quality = QUALITY_MAP.get(values['quality'], QUALITIES.HIGH)
hoster = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': True}
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
js_url = scraper_utils.urljoin(self.base_url, '/javascript/movies.js')
html = self._http_get(js_url, cache_limit=48)
if source_url.startswith('/'):
source_url = source_url[1:]
pattern = '''getElementById\(\s*"%s".*?play\(\s*'([^']+)''' % (
source_url)
match = re.search(pattern, html, re.I)
if match:
stream_url = match.group(1)
if 'drive.google' in stream_url or 'docs.google' in stream_url:
sources = scraper_utils.parse_google(self, stream_url)
else:
sources = [stream_url]
for source in sources:
stream_url = source + scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
host = scraper_utils.get_direct_hostname(self, source)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source)
direct = True
elif 'youtube' in stream_url:
quality = QUALITIES.HD720
direct = False
host = 'youtube.com'
else:
quality = QUALITIES.HIGH
direct = True
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': direct
}
hosters.append(hoster)
return hosters
def __get_gk_links(self, link, iframe_url):
sources = {}
data = {'link': link}
headers = XHR
headers.update({'Referer': iframe_url, 'User-Agent': USER_AGENT})
html = self._http_get(GK_URL,
data=data,
headers=headers,
cache_limit=.25)
js_data = scraper_utils.parse_json(html, GK_URL)
if 'link' in js_data:
if isinstance(js_data['link'], basestring):
stream_url = js_data['link']
if scraper_utils.get_direct_hostname(self,
stream_url) == 'gvideo':
for source in scraper_utils.parse_google(self, stream_url):
sources[source] = {
'quality': scraper_utils.gv_get_quality(source),
'direct': True
}
else:
sources[stream_url] = {
'quality': QUALITIES.HIGH,
'direct': False
}
else:
for link in js_data['link']:
stream_url = link['link']
if scraper_utils.get_direct_hostname(
self, stream_url) == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
elif 'label' in link:
quality = scraper_utils.height_get_quality(
link['label'])
else:
quality = QUALITIES.HIGH
sources[stream_url] = {'quality': quality, 'direct': True}
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