def parse_video(self, soup: BeautifulSoup, url: URL):
content = soup.find('div', {'class': 'player'})
if content is not None:
psp(content.prettify())
script = content.find('script',
text=lambda x: 'flashvars' in str(x))
if script is not None:
data = str(script.string).replace(' ', '').replace(
'\n', '').replace('\t', '')
flashvars = quotes(data, 'flashvars={', '};').split(',')
fv = dict()
for flashvar in flashvars:
# print(flashvar)
split = flashvar.partition(':')
fv[split[0]] = split[2].strip("'\"")
files = dict()
for f in fv:
if fv[f].startswith('http://') and fv[f].endswith('.mp4/'):
file = fv[f]
label = fv.get(f + '_text', f)
files[label] = file
print("=======================didn't work?")
for key in sorted(files.keys(), reverse=True):
self.add_video(key, URL(files[key], referer=url))
def parse_thumbs_tags(self, soup: BeautifulSoup, url: URL):
container=soup.find('section',{'class':'categories'})
if container:
for category in _iter(container.find_all('a',href=True)):
psp(category.prettify())
label=category.find('span',{'class':'highlight'})
self.add_tag(label.string, URL(category.attrs['href'],base_url=url))
def parse_video(self, soup: BeautifulSoup, url: URL):
video = soup.find('div', {'class': 'video'})
if video is not None:
psp(video.prettify())
for i, source in enumerate(_iter(video.find_all('source'))):
# self.add_video('source_' + str(i), URL(source.attrs['src'].replace('https', 'http'), base_url=url))
self.add_video('source_' + str(i), URL(source.attrs['src'], base_url=url, referer=url.get()))
self.set_default_video(-1)
def parse_video(self, soup: BeautifulSoup, url: URL):
video = soup.find('div', {'class': 'video-player'})
if video is not None:
# psp(video.prettify())
for source in _iter(video.find_all('source')):
psp(source)
self.add_video('DEFAULT', URL(source.attrs['src'],
base_url=url))
self.set_default_video(-1)
def parse_video(self, soup: BeautifulSoup, url: URL):
video = soup.find('div', {'class': 'player'})
if video is not None:
psp(video.prettify())
script = video.find(
'script', text=lambda x: 'playerInstance.setup(' in str(x))
if script is not None:
data = str(script.string).replace(
' ', '') #.replace('\t', '').replace('\n', '')
# psp(data)
mp4 = quotes(data, "file:'", "'")
self.add_video('DEFAULT', URL(mp4, base_url=url))
def parse_video_tags(self, soup: BeautifulSoup, url: URL):
for actor_container in _iter(
soup.find_all('div', {'id': 'video-actors'})):
for href in _iter(actor_container.find_all('a')):
psp(href)
self.add_tag(str(href.attrs['title']),
URL(href.attrs['href'], base_url=url),
style={'color': 'blue'})
for tag_container in _iter(soup.find_all('div', {'id': 'cat-list'})):
for href in _iter(tag_container.find_all('a')):
psp(href)
self.add_tag(str(href.attrs['title']),
URL(href.attrs['href'], base_url=url))
def parse_video(self, soup: BeautifulSoup, url: URL):
psp(soup)
video = soup.find('div', {'class': 'watch'})
if video:
script = video.find('script',
text=lambda x: 'redtube_flv_player' in str(x))
if script:
data = str(script.string).replace(' ', '').replace('\\', '')
psp(data)
sources = quotes(data, 'mediaDefinition:[', ']').split('},{')
for item in sources:
file = quotes(item, 'videoUrl":"', '"')
label = quotes(item, 'quality":"', '"')
if file:
self.add_video(label, URL(file, base_url=url))
def parse_video_tags(self, soup: BeautifulSoup, url: URL):
info = soup.find('div', {'class': 'video-info'})
if info:
# psp(info.prettify())
for xref in _iter(
info.find_all('a',
href=lambda x: not 'javascript' in str(x))):
psp(xref)
href = xref.attrs['href']
if '/user/' in href:
self.add_tag(quotes(href, '/user/', '/'),
URL(href.replace('/user/', '/submitted/'),
base_url=url),
style={'color': 'blue'})
else:
self.add_tag(collect_string(xref), URL(href, base_url=url))
def parse_video_tags(self, soup: BeautifulSoup, url: URL):
# info_box=soup.find('div',{'class':'content-container'})
for info_box in _iter(
soup.find_all('div', {'class': 'content-container'})):
# psp(info_box.prettify())
for href in _iter(info_box.find_all('a', href=True)):
psp(href.prettify())
label = collect_string(href)
href_url = URL(href.attrs['href'], base_url=url)
print(label, href_url)
color = None
if href_url.contain('/users/'):
color = 'blue'
href_url = URL(href_url.get() + '/videos/public/')
if href_url.contain('/pornstar/'):
color = 'red'
self.add_tag(label, href_url, style=dict(color=color))