def findPHP(data, streamId):
regex = "document.write\('.*?src=['\"]*(.*?.php\?.*?=).*?['\" ]*.*?\)"
php = regexUtils.findall(data, regex)
if php:
return php[0] + streamId
regex = "document.write\('.*?src=['\"]*(.*?f*id\s*\+'\.html).*?['\" ]*.*?\)"
html = regexUtils.findall(data, regex)
if html:
return re.sub(r"\'\+\s*f*id\s*\+\'", "%s" % streamId,html[0])
return None
def findPHP(data, streamId):
regex = "document.write\('.*?src=['\"]*(.*?.(?:php|html)[^&\"]*).*?['\" ]*.*?\)"
php = regexUtils.findall(data, regex)
if php:
return re.sub(r"\'\+\s*(?:[fc]*id|ch)\s*\+\'", "%s" % streamId,php[0])
regex = "document.write\('.*?src=['\"]*(.*?(?:f*id|ch)\s*\+'\.html*).*?['\" ]*.*?\)"
html = regexUtils.findall(data, regex)
if html:
return re.sub(r"\'\+\s*(?:f*id|ch)\s*\+\'", "%s" % streamId,html[0])
return None
def findVideoFrameLink(page, data):
minheight = 300
minwidth = 300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(
data,
"(frame(?![^>]*cbox\.ws)(?![^>]*Publi)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*blacktvlive\.com)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)",
)
if iframes:
for iframe in iframes:
if iframe[1] == "100%":
height = minheight + 1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == "100%":
width = minwidth + 1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], "['\"\s]src=[\"']*\s*([^>\"' ]+)\s*[>\"']*")
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(
data, '(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*blacktvlive\.com)[^>]*["; ]height:\s*(\d+)[^>]*>)'
)
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], '["; ]width:\s*(\d+)')
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '["; ]src=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(data, '<FRAMESET[^>]+100%[^>]+>\s*<FRAME[^>]+src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(
data, '<a href="([^"]+)" target="_blank"><img src="[^"]+" height="450" width="600" longdesc="[^"]+"/></a>'
)
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
def findVCods(data):
regex = "function getURL03.*?sUrl.*?'([^']+)'.*?cod1.*?'([^']+)'.*?cod2.*?'([^']+)'.*?SWFObject\('([^']+)'"
vcods = regexUtils.findall(data, regex)
if vcods:
return vcods[0]
return None
def findVCods(data):
regex = "function getURL03.*?sUrl.*?'([^']+)'.*?cod1.*?'([^']+)'.*?cod2.*?'([^']+)'.*?SWFObject\('([^']+)'"
vcods = re.findall(data, regex)
if vcods:
return vcods[0]
return None
def findEmbedPHPLink(data):
regex = '<script type="text/javascript" src="([^"]+\.php\?[^"]+)"\s*>\s*</script>'
links = re.findall(data, regex)
if links:
return links[0]
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*Publi)(?![^>]*dailymotion)(?![^>]*blacktvlive\.)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*waframedia)(?![^>]*Beba.tv/embed)(?![^>]*maxtags)(?![^>]*s/a1\.php)(?![^>]*right-sidebar)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight+1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\'"\s]+(?:src|SRC)\s*=\s*["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
if 'premiertv' in page:
page = page+'/'
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*dailymotion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\"; ](?:src|SRC)=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(data, '<(?:FRAMESET|frameset)[^>]+100%[^>]+>\s*<(?:FRAME|frame)[^>]+src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(data, r'playStream\(\'iframe\', \'[^\']*(https*:[^\']+)\'\)')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*Publi)(?![^>]*dailymotion)(?![^>]*blacktvlive\.)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*waframedia)(?![^>]*Beba.tv/embed)(?![^>]*maxtags)(?![^>]*s/a1\.php)(?![^>]*right-sidebar)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight+1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\'"\s]+(?:src|SRC)\s*=\s*["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
if 'premiertv' in page:
page = page+'/'
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*dailymotion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\"; ](?:src|SRC)=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(data, '<(?:FRAMESET|frameset)[^>]+100%[^>]+>\s*<(?:FRAME|frame)[^>]+src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(data, r'playStream\(\'iframe\', \'[^\']*(https*:[^\']+)\'\)')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
def findContentRefreshLink(data):
maxLength = 100
if len(data.replace(' ','')) > maxLength:
return None
regex = '0;\s*url=([^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
else:
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findEmbedPHPLink(data):
regex = '<script type="text/javascript" src="((?![^"]+localtimes)(?![^"]+adcash)[^"]+\.php\?[^"]+)"\s*>\s*</script>'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findEmbedPHPLink(data):
regex = '<script type="text/javascript" src="([^"]+\.php\?[^"]+)"\s*>\s*</script>'
links = re.findall(data, regex)
if links:
return links[0]
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*Publi)(?![^>]*dailymotion)(?![^>]*blacktvlive\.)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*blacktvlive\.com)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight+1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\'"\s]+(?:src|SRC)\s*=\s*["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
if 'premiertv' in page:
page = page+'/'
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*dailymotion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\"; ](?:src|SRC)=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(data, '<(?:FRAMESET|frameset)[^>]+100%[^>]+>\s*<(?:FRAME|frame)[^>]+src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(data, '<a href="([^"]+)" target="_blank"><img src="[^"]+" height="\d+" width="\d+" longdesc="[^"]+"/></a>')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
def findContentRefreshLink(data):
maxLength = 100
if len(data.replace(' ', '')) > maxLength:
return None
regex = '0;url=([^\'" ]+)'
links = re.findall(data, regex)
if links:
return links[0]
else:
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = re.findall(data, regex)
if links:
return links[0]
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*Publi)(?![^>]*dailymotion)(?![^>]*blacktvlive\.)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*blacktvlive\.com)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight+1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\'"\s]+(?:src|SRC)\s*=\s*["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
if 'premiertv' in page:
page = page+'/'
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*dailymotion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\"; ](?:src|SRC)=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(data, '<(?:FRAMESET|frameset)[^>]+100%[^>]+>\s*<(?:FRAME|frame)[^>]+src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(data, '<a\s*href="([^"]+)"\s*target="_blank"><img\s*src="[^"]+"\s*height="\d+"\s*width="\d+"\s*longdesc="[^"]+"\s*/></a>')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
def findEmbedPHPLink(data):
regex = '<script type="text/javascript" src="((?![^"]+localtimes)(?![^"]+adcash)[^"]+\.php\?[^"]+)"\s*>\s*</script>'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = re.findall(data, "(frame[^>]* height=[\"']*(\d+)[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = re.findall(iframe[0], "[\"' ]width=[\"']*(\d+[%]*)[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = re.findall(iframe[0], '[\'"\s]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
up = urlparse.urlparse(urllib.unquote(page))
if link.startswith('/'):
link = urllib.basejoin(up[0] + '://' + up[1],link)
else:
link = urllib.basejoin(up[0] + '://' + up[1] + '/' + up[2],link)
return link.strip()
# Alternative 1
iframes = re.findall(data, "(frame[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = re.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = re.findall(iframe[0], '[ ]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
link = urllib.basejoin(page,link)
return link.strip()
# Alternative 2 (Frameset)
iframes = re.findall(data, '<FRAMESET[^>]+100%[^>]+>\s*<FRAME[^>]+src="([^"]+)"')
if iframes:
link = iframes[0]
if not link.startswith('http://'):
link = urllib.basejoin(page,link)
return link.strip()
return None
def findContentRefreshLink(data):
regex = '0;\s*url=([^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'frame\s*scrolling=\"auto\"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findContentRefreshLink(data):
regex = '0;\s*url=([^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'frame\s*scrolling=\"auto\"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findJS(data):
idName = 'f*id'
jsName = '(.*?\.js)'
regex = "(?:java)?script[^<]+" + idName + "\s*=\s*[\"']([^\"']+)[\"'][^<]*</script\s*>[^<]*<script[^<]*src=[\"']" + jsName + "[\"']"
jscript = re.findall(data, regex)
if jscript:
jscript = filter(lambda x: x[1].find('twitter') == -1, jscript)
return jscript
return None
def findJS(data):
idName = 'f*id'
jsName = '(.*?\.js)'
regex = "(?:java)?script[^<]+" + idName + "\s*=\s*[\"']([^\"']+)[\"'][^<]*</script\s*>[^<]*<script[^<]*src=[\"']" + jsName + "[\"']"
jscript = re.findall(data, regex)
if jscript:
jscript = filter(lambda x: x[1].find('twitter') == -1, jscript)
return jscript
return None
def findJS(data):
idName = '(?:f*id|ch)'
jsName = '([^\"\']+?\.js[^\"\']*?)'
regex = "(?:java)?scr(?:'\+')?ipt.*?" + idName + "\s*=\s*[\"']([^\"']+)[\"'][^<]*</scr(?:'\+')?ipt\s*>[^<]*<scr(?:'\+')?ipt[^<]*src=[\"']" + jsName + "[\"']"
jscript = regexUtils.findall(data, regex)
if jscript:
jscript = filter(lambda x: x[1].find('twitter') == -1, jscript)
return jscript
return None
def findJS(data):
idName = '(?:f*id|ch)'
jsName = '([^\"\']+?\.js[^\"\']*?)'
regex = "(?:java)?scr(?:'\+')?ipt.*?" + idName + "\s*=\s*[\"']([^\"']+)[\"'][^<]*</scr(?:'\+')?ipt\s*>[^<]*<scr(?:'\+')?ipt[^<]*src=[\"']" + jsName + "[\"']"
jscript = regexUtils.findall(data, regex)
if jscript:
jscript = filter(lambda x: x[1].find('twitter') == -1, jscript)
return jscript
return None
def install(self, filename):
destination = xbmc.translatePath(INSTALL_DIR)
files = self.extract(filename, destination)
if files:
addonXml = filter(lambda x: x.filename.endswith('addon.xml'), files)
if addonXml:
path = os.path.join(destination, addonXml[0].filename)
content = getFileContent(path)
addonId = findall(content, '<addon id="([^"]+)"')
if addonId:
return addonId[0]
return None
def install(self, filename):
destination = xbmc.translatePath(INSTALL_DIR)
files = self.extract(filename, destination)
if files:
addonXml = filter(lambda x: x.filename.endswith('addon.xml'), files)
if addonXml:
path = os.path.join(destination, addonXml[0].filename)
content = getFileContent(path)
addonId = findall(content, '<addon id="([^"]+)"')
if addonId:
return addonId[0]
return None
def findContentRefreshLink(data):
regex = "0;\s*url=([^'\" ]+)"
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = "window.location\s*=\s*['\"]([^'\"]+)['\"]"
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'frame\s*scrolling="auto"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = '<center><a\s*href=[\'"]([^\'"]+)[\'"]\s*target="_blank"><img'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findContentRefreshLink(data):
regex = '0;\s*url=([^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'frame\s*scrolling=\"auto\"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'href=[\'"]([^\'"]+)[\'"]\s*target="_blank"><img class="alignnone"'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findContentRefreshLink(data):
regex = '0;\s*url=([^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'frame\s*scrolling=\"auto\"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
regex = 'href=[\'"]([^\'"]+)[\'"]\s*target="_blank"><img class="alignnone"'
links = regexUtils.findall(data, regex)
if links:
return links[0]
return None
def findContentRefreshLink(page, data):
regex = '0;\s*url=((?![^\'" ]+rojadirecta)[^\'" ]+)'
links = regexUtils.findall(data, regex)
if links:
return links[0]
#regex = 'window.location\s*=\s*[\'"]([^\'"]+)[\'"]'
#links = regexUtils.findall(data, regex)
#if links:
#return links[0]
regex = 'frame\s*scrolling=\"auto\"\s*noresize\s*src\s*=\s*[\'"]([^\'"]+)[\'"]'
links = regexUtils.findall(data, regex)
if links:
return links[0]
#hd**ee.fv/cr**hd.fv/sp**ts4u.tv
regex = '<a\s*href="([^"]+)"\s*target="_blank"><img\s*(?:src="[^"]+"\s*height="\d+"\s*width="\d+"\s*longdesc="[^"]+"|class="alignnone"\s*src="[^"]*"\s*alt="[^"]*"\s*width="\d\d\d"\s*height="\d\d\d")'
links = regexUtils.findall(data, regex)
if links:
return urlparse.urljoin(urllib.unquote(page), links[0]).strip()
#cr**hd.com
regex = '<a\s*href="([^"]+)"\s*title="[^"]*"><img\s*(?:src="[^"]+"\s*height="\d+"\s*width="\d+"\s*longdesc="[^"]+"|class="aligncenter"\s*alt="[^"]*"\s*title="[^"]*"\s*src="[^"]*"\s*width="\d\d\d"\s*height="\d\d\d")'
links = regexUtils.findall(data, regex)
if links:
return urlparse.urljoin(urllib.unquote(page), links[0]).strip()
#spo***live.com
regex = '<a\s*href="([^"]+)"\s*title=""><img\s*data-scalestrategy="crop"\s*width="\d\d\d"\s*height="\d\d\d"'
links = regexUtils.findall(data, regex)
if links:
return urlparse.urljoin(urllib.unquote(page), links[0]).strip()
return None
def findFrames(data):
if data.lower().find('frame') == -1:
return None
return regexUtils.findall(data, "(frame[^>]*)>")
def findRTMP(url, data):
# if data.lower().find('rtmp') == -1:
# return None
try:
text = str(data)
except:
text = data
# method 1
# ["'=](http://[^'" ]*.swf[^'" ]*file=([^&"']+)[^'" ]*&streamer=([^"'&]+))
# streamer=([^&"]+).*?file=([^&"]+).*?src="([^"]+.swf)"
# method 2
# "([^"]+.swf\?.*?file=(rtmp[^&]+)&.*?id=([^&"]+)[^"]*)"
sep1 = "['\"&\? ]"
sep2 = "(?:['\"]\s*(?:,|\:)\s*['\"]|=)"
value = "([^'\"&]+)"
method1 = True
method2 = False
radius = 400
playpath = ""
swfUrl = ""
rtmp = regexUtils.findall(text, sep1 + "streamer" + sep2 + value)
if not rtmp:
tryMethod2 = regexUtils.findall(text, sep1 + "file" + sep2 + value)
if tryMethod2 and tryMethod2[0].startswith("rtmp"):
method1 = False
method2 = True
rtmp = tryMethod2
if rtmp:
for r in rtmp:
tmpRtmp = r.replace("/&", "").replace("&", "")
idx = text.find(tmpRtmp)
min_idx = 0
max_idx = len(text) - 1
start = idx - radius
if start < min_idx:
start = min_idx
end = idx + radius
if end > max_idx:
end = max_idx
area = text[start:end]
clipStart = idx + len(tmpRtmp)
if clipStart < max_idx:
text = text[clipStart:]
if method1:
playpath = regexUtils.findall(area, sep1 + "file" + sep2 + value)
if method2:
playpath = regexUtils.findall(area, sep1 + "id" + sep2 + value)
if playpath:
tmpRtmp = tmpRtmp + "/" + playpath[0]
if playpath:
swfUrl = regexUtils.findall(area, "SWFObject\(['\"]([^'\"]+)['\"]")
if not swfUrl:
swfUrl = regexUtils.findall(area, sep1 + "([^'\"& ]+\.swf)")
if not swfUrl:
swfUrl = regexUtils.findall(data, sep1 + "([^'\"& ]+\.swf)")
if swfUrl:
finalSwfUrl = swfUrl[0]
if not finalSwfUrl.startswith("http"):
finalSwfUrl = urlparse.urljoin(url, finalSwfUrl)
regex = "://(.*?)/"
server = regexUtils.findall(tmpRtmp, regex)
if server:
if server[0].find(":") == -1:
tmpRtmp = tmpRtmp.replace(server[0], server[0] + ":1935")
return [tmpRtmp, playpath[0], finalSwfUrl]
return None
def findPHP(data, streamId):
regex = "document.write\('.*?src=['\"]*(.*?.php\?.*?=).*?['\" ]*.*?\)"
php = re.findall(data, regex)
if php:
return php[0] + streamId
return None
def findVideoFrameLink(page, data):
minheight=300
minwidth=300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*capacanal)(?![^>]*programacion)[^>]*\sheight\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight+1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"' ]width\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*")
if m:
if m[0] == '100%':
width = minwidth+1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\'"\s]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
#if not page.endswith('/'):
# page += '/'
up = urlparse.urlparse(urllib.unquote(page))
if link.startswith('/'):
link = urllib.basejoin(up[0] + '://' + up[1],link)
else:
link = urllib.basejoin(up[0] + '://' + up[1] + '/' + up[2],link)
return link.strip()
# Alternative 1
iframes = regexUtils.findall(data, "(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*programacion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(iframe[0], '[\"; ]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
link = urllib.basejoin(page,link)
return link.strip()
# Alternative 2 (Frameset)
iframes = regexUtils.findall(data, '<FRAMESET[^>]+100%[^>]+>\s*<FRAME[^>]+src="([^"]+)"')
if iframes:
link = iframes[0]
if not link.startswith('http://'):
link = urllib.basejoin(page,link)
return link.strip()
return None
def findVideoFrameLink(page, data):
minheight = 300
minwidth = 300
frames = findFrames(data)
if not frames:
return None
iframes = re.findall(data, "(frame[^>]* height=[\"']*(\d+)[\"']*[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = re.findall(iframe[0], "[\"' ]width=[\"']*(\d+[%]*)[\"']*")
if m:
if m[0] == '100%':
width = minwidth + 1
else:
width = int(m[0])
if width > minwidth:
m = re.findall(
iframe[0],
'[\'"\s]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
up = urlparse.urlparse(urllib.unquote(page))
if link.startswith('/'):
link = urllib.basejoin(
up[0] + '://' + up[1], link)
else:
link = urllib.basejoin(
up[0] + '://' + up[1] + '/' + up[2],
link)
return link.strip()
# Alternative 1
iframes = re.findall(data, "(frame[^>]*[\"; ]height:\s*(\d+)[^>]*>)")
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = re.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = re.findall(iframe[0],
'[ ]src=["\']*\s*([^"\' ]+)\s*["\']*')
if m:
link = m[0]
if not link.startswith('http://'):
link = urllib.basejoin(page, link)
return link.strip()
# Alternative 2 (Frameset)
iframes = re.findall(
data, '<FRAMESET[^>]+100%[^>]+>\s*<FRAME[^>]+src="([^"]+)"')
if iframes:
link = iframes[0]
if not link.startswith('http://'):
link = urllib.basejoin(page, link)
return link.strip()
return None
def findPHP(data, streamId):
regex = "document.write\('.*?src=['\"]*(.*?.php\?.*?=).*?['\" ]*.*?\)"
php = re.findall(data, regex)
if php:
return php[0] + streamId
return None
def findFrames(data):
if data.lower().find("frame") == -1:
return None
return re.findall(data, "(frame[^>]*)>")
def findRTMP(url, data):
#if data.lower().find('rtmp') == -1:
# return None
try:
text = str(data)
except:
text = data
#method 1
#["'=](http://[^'" ]*.swf[^'" ]*file=([^&"']+)[^'" ]*&streamer=([^"'&]+))
#streamer=([^&"]+).*?file=([^&"]+).*?src="([^"]+.swf)"
# method 2
#"([^"]+.swf\?.*?file=(rtmp[^&]+)&.*?id=([^&"]+)[^"]*)"
sep1 = '[\'"&\? ]'
sep2 = '(?:[\'"]\s*(?:,|\:)\s*[\'"]|=)'
value = '([^\'"&]+)'
method1 = True
method2 = False
radius = 400
playpath = ''
swfUrl = ''
rtmp = regexUtils.findall(text, sep1 + 'streamer' + sep2 + value)
if not rtmp:
tryMethod2 = regexUtils.findall(text, sep1 + 'file' + sep2 + value)
if tryMethod2 and tryMethod2[0].startswith('rtmp'):
method1 = False
method2 = True
rtmp = tryMethod2
if rtmp:
for r in rtmp:
tmpRtmp = r.replace('/&','').replace('&','')
idx = text.find(tmpRtmp)
min_idx = 0
max_idx = len(text) - 1
start = idx-radius
if start < min_idx:
start = min_idx
end = idx+radius
if end > max_idx:
end = max_idx
area = text[start:end]
clipStart = idx+len(tmpRtmp)
if clipStart < max_idx:
text = text[clipStart:]
if method1:
playpath = regexUtils.findall(area, sep1 + 'file' + sep2 + value)
if method2:
playpath = regexUtils.findall(area, sep1 + 'id' + sep2 + value)
if playpath:
tmpRtmp = tmpRtmp + '/' + playpath[0]
if playpath:
swfUrl = regexUtils.findall(area, 'SWFObject\([\'"]([^\'"]+)[\'"]')
if not swfUrl:
swfUrl = regexUtils.findall(area, sep1 + '([^\'"& ]+\.swf)')
if not swfUrl:
swfUrl = regexUtils.findall(data, sep1 + '([^\'"& ]+\.swf)')
if swfUrl:
finalSwfUrl = swfUrl[0]
if not finalSwfUrl.startswith('http'):
finalSwfUrl = urlparse.urljoin(url, finalSwfUrl)
regex = '://(.*?)/'
server = regexUtils.findall(tmpRtmp, regex)
if server:
if server[0].find(':') == -1:
tmpRtmp = tmpRtmp.replace(server[0], server[0] + ':1935')
return [tmpRtmp, playpath[0], finalSwfUrl]
return None
def findVideoFrameLink(page, data):
minheight = 300
minwidth = 300
frames = findFrames(data)
if not frames:
return None
iframes = regexUtils.findallIgnoreCase(
data,
"((?:frame|FRAME)(?![^>]*cbox\.ws)(?![^>]*publi)(?![^>]*dailymotion)(?![^>]*guide\.)(?![^>]*chat\d*\.\w+)(?![^>]*ad122m)(?![^>]*adshell)(?![^>]*capacanal)(?![^>]*waframedia)(?![^>]*banner)(?![^>]*maxtags)(?![^>]*s/a1\.php)(?![^>]*ads.php)(?![^>]*right-sidebar)[^>]*\s(?:height|HEIGHT)\s*=\s*[\"']*([\%\d]+)(?:px)?[\"']*[^>]*>)"
)
if iframes:
for iframe in iframes:
if iframe[1] == '100%':
height = minheight + 1
else:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(
iframe[0],
"[\"'\s](?:width|WIDTH)\s*=\s*[\"']*(\d+[%]*)(?:px)?[\"']*"
)
if m:
if m[0] == '100%':
width = minwidth + 1
else:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(
iframe[0],
'[\'"\s]+(?:src|SRC)\s*=\s*["\']*\s*([^>"\' ]+)\s*[>"\']*'
)
if m:
if 'premiertv' in page:
page = page + '/'
return urlparse.urljoin(urllib.unquote(page),
m[0]).strip()
# Alternative 1
iframes = regexUtils.findall(
data,
"(frame(?![^>]*cbox\.ws)(?![^>]*capacanal)(?![^>]*dailymotion)[^>]*[\"; ]height:\s*(\d+)[^>]*>)"
)
if iframes:
for iframe in iframes:
height = int(iframe[1])
if height > minheight:
m = regexUtils.findall(iframe[0], "[\"; ]width:\s*(\d+)")
if m:
width = int(m[0])
if width > minwidth:
m = regexUtils.findall(
iframe[0],
'[\"; ](?:src|SRC)=["\']*\s*([^>"\' ]+)\s*[>"\']*')
if m:
return urlparse.urljoin(urllib.unquote(page),
m[0]).strip()
# Alternative 2 (Frameset)
m = regexUtils.findall(
data,
'<(?:FRAMESET|frameset)[^>]+100%[^>]+>\s*<(?:FRAME|frame)[^>]+src="([^"]+)"'
)
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
m = regexUtils.findall(
data, r'playStream\(\'iframe\',\s*\'[^\']*(https*:[^\']+)\'\)')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
#sportsh**tv
m = regexUtils.findall(
data, r'<iframe\s*src="(stream[^"]+)"\s*allowfullscreen>')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
#stre***d
m = regexUtils.findall(
data,
r'<iframe\s*class="embed[^"]+"\s*name="video[^"]+"\s*src="([^"]+)"')
if m:
return urlparse.urljoin(urllib.unquote(page), m[0]).strip()
return None
