def findLink(req, url):
link = ''
txt = load(url)
for m in re.finditer(r'"http(s|)://(www.|)(dailymotion|videomega|videowood|youtube|openload)(.com|.tv|.co)([^"]*)', txt):
if m.group()[1:-1] != link:
link = m.group()[1:-1]
image = getImage(link)
page.addVideo(req, link, link, image)
def findImageLink(req, url, unquote=False, showPage=False):
txt = load(url)
for m in re.finditer(r'<a .*?</a>', txt, re.DOTALL):
link = re.search(r'href="([^"]*)"', m.group(0))
image = re.search(r'src="([^"]*)"', m.group(0))
if link and image:
if unquote == True:
link1 = urllib.unquote(link.group(1))
else:
link1 = link.group(1)
image1 = image.group(1)
if showPage == False:
page.addVideo(req, link1, link1, image1)
else:
page.addPage(req, link1, link1, image1)
def findVideoLink(req, url, showPage=False, showImage=False):
parsed_uri = urlparse.urlparse(url)
domain = '{uri.scheme}://{uri.netloc}'.format(uri=parsed_uri)
txt = load(url)
for m in re.finditer(r'<a .*?</a>', txt, re.DOTALL):
link = re.search(r'href="([^"]*)"', m.group(0))
title = re.search(r'title="([^"]*)"', m.group(0))
image = re.search(r'src="([^"]*)"', m.group(0))
if link and title and image:
link1 = absURL(domain, link.group(1))
title1 = title.group(1)
image1 = absURL(domain, image.group(1))
if showPage == False:
page.addVideo(req, link1, title1, image1)
elif showImage == True:
page.addPage(req, link1, title1, image1)
else:
page.addPage(req, link1, title1)
def findFrame(req, url):
for m in re.finditer(r'<iframe (.*?)</iframe>', load(url)):
src = re.search(r'src="([^"]*)"', m.group(1))
if src:
page.addVideo(req, src.group(1))