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
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.5)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'film-container'})
if fragment:
iframe_url = dom_parser2.parse_dom(fragment[0].content, 'iframe', req='src')
if iframe_url:
iframe_url = scraper_utils.urljoin(self.base_url, iframe_url[0].attrs['src'])
headers = {'Referer': page_url}
html = self._http_get(iframe_url, headers=headers, cache_limit=.5)
sources = scraper_utils.parse_sources_list(self, html)
for source in sources:
quality = sources[source]['quality']
host = scraper_utils.get_direct_hostname(self, source)
stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': iframe_url})
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
match = re.search('(\d+[a-z]bps)', source)
if match:
hoster['extra'] = match.group(1)
hosters.append(hoster)
hosters.sort(key=lambda x: x.get('extra', ''), reverse=True)
return hosters
def __parse_streams(self, iframe_url, page_url):
headers = {'Referer': page_url}
html = self._http_get(iframe_url, headers=headers, cache_limit=.5)
if jsunpack.detect(html):
html = jsunpack.unpack(html)
return scraper_utils.parse_sources_list(self, html)
def __get_embed_links(self, html):
hosters = []
sources = scraper_utils.parse_sources_list(self, html)
for source in sources:
quality = source['quality']
stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
hoster = {'multi-part': False, 'host': scraper_utils.get_direct_hostname(self, source), 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True, 'subs': 'Turkish Subtitles'}
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=.5)
for _attrs, div in dom_parser2.parse_dom(html, 'div',
{'class': 'tabcontent'}):
for attrs, _content in dom_parser2.parse_dom(div,
'source',
req='src'):
source = attrs['src'] + scraper_utils.append_headers(
{
'User-Agent': scraper_utils.get_ua(),
'Referer': page_url
})
sources[source] = {'quality': None, 'direct': True}
iframe_url = dom_parser2.parse_dom(div, 'iframe', req='src')
if iframe_url:
iframe_url = iframe_url[0].attrs['src']
if 'songs2dl' in iframe_url:
headers = {'Referer': page_url}
iframe_html = self._http_get(iframe_url,
headers=headers,
cache_limit=1)
sources.update(
scraper_utils.parse_sources_list(self, iframe_html))
else:
sources[iframe_url] = {'quality': None, 'direct': False}
sources.update(self.__get_mirror_links(html, video))
page_quality = self.__get_best_quality(sources)
for source, values in sources.iteritems():
direct = values['direct']
if direct:
host = scraper_utils.get_direct_hostname(self, source)
else:
host = urlparse.urlparse(source).hostname
if values['quality'] is None:
values['quality'] = page_quality
hoster = {
'multi-part': False,
'host': host,
'class': self,
'views': None,
'url': source,
'rating': None,
'quality': values['quality'],
'direct': direct
}
hosters.append(hoster)
return hosters
def __get_embedded_links(self, html, sub):
hosters = []
html = html.replace('\\"', '"').replace('\\/', '/')
sources = scraper_utils.parse_sources_list(self, html)
for source in sources:
host = scraper_utils.get_direct_hostname(self, source)
quality = sources[source]['quality']
direct = sources[source]['direct']
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': source, 'direct': direct}
hoster['subs'] = sub
hosters.append(hoster)
return hosters
def __get_embedded(self, html, page_url):
sources = {}
match = dom_parser2.parse_dom(html, 'div', {'id': 'videoreklam'})
if not match: return sources
match = dom_parser2.parse_dom(match[0].content, 'iframe', req='src')
if not match: return sources
headers = {'Referer': page_url}
html = self._http_get(match[0].attrs['src'],
headers=headers,
cache_limit=.5)
for match in re.finditer('(eval\(function\(.*?)</script>', html,
re.DOTALL):
js_data = jsunpack.unpack(match.group(1))
js_data = js_data.replace('\\', '')
html += js_data
return dict((key, value['quality'])
for key, value in scraper_utils.parse_sources_list(
self, html, var='source').iteritems())
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