def _get_data(self):
url = self.url + '&q=' + self.quality
logging.debug('Calling Rapid url: {}'.format(url))
headers = self.headers
headers['referer'] = url
try:
r = session.get(url, headers=headers)
# This is a fix for new rapidvideo logic
# It will return OK for a get request
# even if there is a click button
# This will make sure a source link is present
soup = BeautifulSoup(r.text, 'html.parser')
get_source(soup, self.quality)
except:
r = session.post(url, {
'confirm.x': 12,
'confirm.y': 12,
'block': 1,
},
headers=headers)
soup = BeautifulSoup(r.text, 'html.parser')
# TODO: Make these a different function. Can be reused in other classes
# too
title_re = re.compile(r'"og:title" content="(.*)"')
image_re = re.compile(r'"og:image" content="(.*)"')
try:
stream_url = get_source(soup, self.quality)
except IndexError:
stream_url = None
try:
title = str(title_re.findall(r.text)[0])
thumbnail = str(image_re.findall(r.text)[0])
except Exception as e:
title = ''
thumbnail = ''
logging.debug(e)
pass
return {
'stream_url': stream_url,
'meta': {
'title': title,
'thumbnail': thumbnail,
},
}
def _get_data(self):
url = self.url + '&q=' + self.quality
logging.debug('Calling Rapid url: {}'.format(url))
headers = self.headers
headers['referer'] = url
try:
r = session.get(url, headers=headers)
except:
r = session.post(url, {
'cursor.x': 12,
'cursor.y': 12,
'block': 1,
},
headers=headers)
soup = BeautifulSoup(r.text, 'html.parser')
# TODO: Make these a different function. Can be reused in other classes
# too
src_re = re.compile(r'src: "(.*)"')
title_re = re.compile(r'"og:title" content="(.*)"')
image_re = re.compile(r'"og:image" content="(.*)"')
try:
stream_url = soup.find_all('source')[0].get('src')
except IndexError:
try:
stream_url = str(src_re.findall(r.text)[0])
except IndexError:
stream_url = None
try:
title = str(title_re.findall(r.text)[0])
thumbnail = str(image_re.findall(r.text)[0])
except Exception as e:
title = ''
thumbnail = ''
logging.debug(e)
pass
return {
'stream_url': stream_url,
'meta': {
'title': title,
'thumbnail': thumbnail,
},
}
def _get_data(self):
#Need a javascript deobsufication api/python, so someone smarter
#than me can work on that for now I will add the pattern I observed
#alternatively you can pattern match on `src` for stream_url part
source_parts_re = re.compile(
r'action=\"([^"]+)\".*value=\"([^"]+)\".*Click Here to Download',
re.DOTALL)
#Kwik servers don't have direct link access you need to be referred
#from somewhere, I will just use the url itself.
download_url = self.url.replace('kwik.cx/e/', 'kwik.cx/f/')
kwik_text = session.get(download_url,
headers={
'referer': download_url
}).text
post_url, token = source_parts_re.search(kwik_text).group(1, 2)
stream_url = session.post(post_url,
headers={
'referer': download_url
},
data={
'_token': token
},
allow_redirects=False).headers['Location']
title = stream_url.rsplit('/', 1)[-1].rsplit('.', 1)[0]
logging.debug('Stream URL: %s' % stream_url)
return {
'stream_url': stream_url,
'meta': {
'title': title,
'thumbnail': ''
},
'referer': None
}
def bypass_hcaptcha(url):
"""
:param url: url to page which gives hcaptcha
:return: Returns Response object (cookies stored for future use)
"""
host = urlparse(url).netloc
bypassed = False
session = requests.session()
headers = {
'User-Agent':
choice((
'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/605.1.15 (KHTML, like Gecko)',
'Mozilla/5.0 (iPad; CPU OS 9_3_5 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Mobile/13G36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
))
}
logger.info("Bypassing captcha...")
#Retry until success
while not bypassed:
site_key = str(uuid4())
response = session.post('https://hcaptcha.com/getcaptcha',
headers=headers,
data={
'sitekey': site_key,
'host': host
}).json()
try:
key = response['key']
tasks = [row['task_key'] for row in response['tasklist']]
job = response['request_type']
timestamp = round(time()) + choice(range(30, 120))
answers = dict(
zip(tasks,
[choice(['true', 'false'])
for index in range(len(tasks))]))
mouse_movements = []
last_movement = timestamp
for index in range(choice(range(1000, 10000))):
last_movement += choice(range(10))
mouse_movements.append(
[choice(range(500)),
choice(range(500)), last_movement])
json = {
'job_mode': job,
'answers': answers,
'serverdomain': host,
'sitekey': site_key,
'motionData': {
'st': timestamp,
'dct': timestamp,
'mm': mouse_movements
}
}
response = session.post(f'https://hcaptcha.com/checkcaptcha/{key}',
json=json)
response = response.json()
bypassed = response['pass']
except (TypeError, KeyError):
pass
if bypassed:
token = response['generated_pass_UUID']
resp = helpers.soupify(session.get(url))
bypass_url = f'https://{host}{resp.form.get("action")}'
data = dict((x.get('name'), x.get('value'))
for x in resp.select('form > input'))
data.update({
'id': resp.strong.text,
'g-recaptcha-response': token,
'h-captcha-response': token
})
resp = session.post(bypass_url, data=data)
if resp.status_code == 200:
pickle.dump(resp.cookies,
open(f'{tempfile.gettempdir()}/{host}', 'wb'))
logger.info("Succesfully bypassed captcha!")
return resp
else:
bypassed = False