def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
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)
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
if len(proxy_link) <= 224:
picasa_url = scraper_utils.gk_decrypt(
self.get_name(), GK_KEY1, proxy_link)
else:
picasa_url = scraper_utils.gk_decrypt(
self.get_name(), GK_KEY2, proxy_link)
if self._get_direct_hostname(picasa_url) == 'gvideo':
sources = self._parse_google(picasa_url)
for source in sources:
hoster = {
'multi-part': False,
'url': source,
'class': self,
'quality': scraper_utils.gv_get_quality(source),
'host': self._get_direct_hostname(source),
'rating': None,
'views': None,
'direct': True
}
hosters.append(hoster)
return hosters
def __get_gk_links2(self, html):
sources = {}
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
if len(proxy_link) <= 224:
vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY1, proxy_link)
else:
vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY2, proxy_link)
if scraper_utils.get_direct_hostname(self, vid_url) == 'gvideo':
for source in self._parse_gdocs(vid_url):
sources[source] = {'quality': scraper_utils.gv_get_quality(source), 'direct': True}
return sources
def __get_gk_links2(self, html):
sources = {}
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
if len(proxy_link) <= 224:
vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY1, proxy_link)
else:
vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY2, proxy_link)
if self._get_direct_hostname(vid_url) == 'gvideo':
for source in self._parse_gdocs(vid_url):
sources[source] = scraper_utils.gv_get_quality(source)
return sources
def get_sources(self, video):
source_url = self.get_url(video)
sources = {}
hosters = []
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 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 self._parse_google(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 = self._parse_sources_list(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 sources:
host = self._get_direct_hostname(source)
stream_url = source + '|User-Agent=%s' % (scraper_utils.get_ua())
quality = QUALITY_MAP.get(sources[source]['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)
sources = {}
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=0.5)
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 self._parse_google(picasa_url):
sources[stream_url] = {
"quality": scraper_utils.gv_get_quality(stream_url),
"direct": True,
}
else:
html = self._http_get(iframe_url, cache_limit=0.25)
temp_sources = self._parse_sources_list(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_parser.parse_dom(html, "source", {"type": "video/mp4"}, ret="src"):
sources[source] = {"quality": QUALITIES.HD720, "direct": True}
for source in sources:
host = self._get_direct_hostname(source)
stream_url = source + "|User-Agent=%s" % (scraper_utils.get_ua())
if host == "gvideo":
quality = scraper_utils.gv_get_quality(source)
else:
quality = sources[source]["quality"]
if quality not in Q_ORDER:
quality = QUALITY_MAP.get(sources[source]["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)
sources = []
stream_urls = []
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 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)
stream_urls += self._parse_google(picasa_url)
else:
html = self._http_get(iframe_url, cache_limit=0)
match = re.search('sources\s*:\s*\[(.*?)\]', html,
re.DOTALL)
if match:
for match in re.finditer(
'''['"]*file['"]*\s*:\s*['"]*([^'"]+).*?['"]*label['"]*\s*:\s*['"]*([^'"]+)''',
match.group(1), re.DOTALL):
stream_url, label = match.groups()
if 'download.php' in stream_url:
redir_html = self._http_get(
stream_url,
allow_redirect=False,
method='HEAD',
cache_limit=0)
if stream_url.startswith('http'):
stream_url = redir_html
stream_urls.append(stream_url)
for stream_url in list(set(stream_urls)):
host = self._get_direct_hostname(stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = QUALITY_MAP.get(label, QUALITIES.HIGH)
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_google_links(self, link):
sources = {}
html = self._http_get(link, cache_limit=.5)
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))
sources = self._parse_google(picasa_url)
return sources
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
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)
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
if len(proxy_link) <= 224:
picasa_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY1, proxy_link)
else:
picasa_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY2, proxy_link)
if self._get_direct_hostname(picasa_url) == 'gvideo':
sources = self._parse_google(picasa_url)
for source in sources:
hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': scraper_utils.gv_get_quality(source), 'host': self._get_direct_hostname(source), 'rating': None, 'views': None, 'direct': True}
hosters.append(hoster)
return hosters
def __get_google_links(self, link):
sources = {}
html = self._http_get(link, cache_limit=.5)
match = re.search('base64\.decode\("([^"]+)', html, re.I)
if match:
log_utils.log(match.group(1))
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))
sources = self._parse_google(picasa_url)
return sources
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_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 source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
ele = dom_parser.parse_dom(html, 'video')
if ele:
stream_url = dom_parser.parse_dom(ele, 'source', ret='src')
if stream_url:
hoster = {'multi-part': False, 'url': stream_url[0], 'class': self, 'quality': QUALITIES.HD720, 'host': self._get_direct_hostname(stream_url[0]), 'rating': None, 'views': None, 'direct': True}
if hoster['host'] == 'gvideo':
hoster['quality'] = scraper_utils.gv_get_quality(hoster['url'])
hosters.append(hoster)
sources = dom_parser.parse_dom(html, 'iframe', ret='src')
for src in sources:
if 'facebook' in src: continue
host = urlparse.urlparse(src).hostname
hoster = {'multi-part': False, 'url': src, 'class': self, 'quality': QUALITIES.HIGH, 'host': host, 'rating': None, 'views': None, 'direct': False}
hosters.append(hoster)
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
stream_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY, proxy_link)
if 'vk.com' in stream_url.lower():
hoster = {'multi-part': False, 'host': 'vk.com', 'class': self, 'url': stream_url, 'quality': QUALITIES.HD720, 'views': None, 'rating': None, 'direct': False}
hosters.append(hoster)
if 'picasaweb' in stream_url.lower():
for source in self._parse_google(stream_url):
quality = scraper_utils.gv_get_quality(source)
hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': quality, 'host': self._get_direct_hostname(source), 'rating': None, 'views': None, 'direct': True}
hosters.append(hoster)
if 'docs.google' in stream_url.lower():
for source in self._parse_gdocs(stream_url):
quality = scraper_utils.gv_get_quality(source)
hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': quality, 'host': self._get_direct_hostname(source), 'rating': None, 'views': None, '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:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
ele = dom_parser.parse_dom(html, 'video')
if ele:
stream_url = dom_parser.parse_dom(ele, 'source', ret='src')
if stream_url:
hoster = {'multi-part': False, 'url': stream_url[0], 'class': self, 'quality': QUALITIES.HD720, 'host': self._get_direct_hostname(stream_url[0]), 'rating': None, 'views': None, 'direct': True}
if hoster['host'] == 'gvideo':
hoster['quality'] = scraper_utils.gv_get_quality(hoster['url'])
hosters.append(hoster)
sources = dom_parser.parse_dom(html, 'iframe', ret='src')
for src in sources:
if 'facebook' in src: continue
host = urlparse.urlparse(src).hostname
hoster = {'multi-part': False, 'url': src, 'class': self, 'quality': QUALITIES.HIGH, 'host': host, 'rating': None, 'views': None, 'direct': False}
hosters.append(hoster)
match = re.search('proxy\.link=([^"&]+)', html)
if match:
proxy_link = match.group(1)
proxy_link = proxy_link.split('*', 1)[-1]
stream_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY, proxy_link)
if 'vk.com' in stream_url.lower():
hoster = {'multi-part': False, 'host': 'vk.com', 'class': self, 'url': stream_url, 'quality': QUALITIES.HD720, 'views': None, 'rating': None, 'direct': False}
hosters.append(hoster)
if 'picasaweb' in stream_url.lower():
for source in self._parse_google(stream_url):
quality = scraper_utils.gv_get_quality(source)
hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': quality, 'host': self._get_direct_hostname(source), 'rating': None, 'views': None, 'direct': True}
hosters.append(hoster)
if 'docs.google' in stream_url.lower():
for source in self._parse_google(stream_url):
quality = scraper_utils.gv_get_quality(source)
hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': quality, 'host': self._get_direct_hostname(source), 'rating': None, 'views': None, 'direct': True}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
sources = {}
hosters = []
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 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 self._parse_google(picasa_url):
sources[stream_url] = {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True}
else:
html = self._http_get(iframe_url, cache_limit=.25)
temp_sources = self._parse_sources_list(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 sources:
host = self._get_direct_hostname(source)
stream_url = source + '|User-Agent=%s' % (scraper_utils.get_ua())
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(source)
else:
quality = QUALITY_MAP.get(sources[source]['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)
sources = []
stream_urls = []
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 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)
stream_urls += self._parse_google(picasa_url)
else:
html = self._http_get(iframe_url, cache_limit=0)
match = re.search('sources\s*:\s*\[(.*?)\]', html, re.DOTALL)
if match:
for match in re.finditer('''['"]*file['"]*\s*:\s*['"]*([^'"]+).*?['"]*label['"]*\s*:\s*['"]*([^'"]+)''', match.group(1), re.DOTALL):
stream_url, label = match.groups()
if 'download.php' in stream_url:
redir_html = self._http_get(stream_url, allow_redirect=False, cache_limit=0)
if stream_url.startswith('http'): stream_url = redir_html
stream_urls.append(stream_url)
for stream_url in list(set(stream_urls)):
host = self._get_direct_hostname(stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = QUALITY_MAP.get(label, QUALITIES.HIGH)
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