Downloads most hqq.tv streams

hqq.py

import json
import re
import urllib.request
from base64 import b64decode
from subprocess import call
from sys import argv

UA = 'Mozilla/6.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.5) Gecko/2008092417 Firefox/3.0.3'
headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Content-Type': 'text/html; charset=utf-8'}

def request(url, headers={}):
	# print(('request: %s' % url))
	req = urllib.request.Request(url, headers=headers)
	req.add_header('User-Agent', UA)
	try:
		response = urllib.request.urlopen(req)
		data = response.read().decode('utf-8')
		response.close()
	except urllib.error.HTTPError as error:
		data=error.read().decode('utf-8')
	# print(('len(data) %s' % len(data)))
	return data

def post(url, data, headers={}):
	postdata = urllib.parse.urlencode(data).encode('utf-8')
	req = urllib.request.Request(url, postdata, headers)
	req.add_header('User-Agent', UA)
	try:
		response = urllib.request.urlopen(req)
		data = response.read().decode('utf-8')
		response.close()
	except urllib.error.HTTPError as error:
		data=error.read().decode('utf-8')
	# print(('len(data) %s' % len(data)))
	return data
	
def request_noagent(url, headers={}):
	# print(('request: %s' % url))
	req = urllib.request.Request(url, headers=headers)
	req.add_header('User-Agent', ' ')
	try:
		response = urllib.request.urlopen(req)
		data = response.read().decode('utf-8')
		response.close()
	except urllib.error.HTTPError as error:
		data=error.read().decode('utf-8')
	# print(('len(data) %s' % len(data)))
	return data

def _decode(data):
	b64dec = b64decode(re.search(r'base64([^\"]+)', data).group(1))
	enc = re.search(r"\'([^']+)\'", b64dec.decode('utf-8')).group(1)
	escape = re.search(r"var _escape=\'([^\']+)", b64decode(enc[::-1]).decode('utf-8')).group(1)
	escape = escape.replace('%', '\\').encode('utf-8').decode('unicode-escape')
	data = re.findall(r'<input name="([^"]+?)" [^>]+? value="([^"]*)">', escape)
	return dict(data)

def _decode2(data):
	s = ''
	for n in re.findall(r'(...)', b64decode(data).decode('ascii')):
		s += chr(int(n) - 156)
	return(s)

url = argv[1]
if not url.startswith('http'):
	url = 'http://' + url
page = request(url)
vid = re.search(r'(?:hqq|netu)\.tv/player/embed_player\.php\?vid=([0-9A-Za-z]+)', page)
if not vid:
	vid = re.search(r'(?:hqq|netu)\.tv/watch_video\.php\?v=([0-9A-Za-z]+)', url)
	if not vid:
		vid = re.search(r'(hqq|netu)\.tv/player/hash\.php\?hash=\d+', url)
		if vid:
			vid = re.search(r'var vid = \'([^\']+)\'', urllib.parse.unquote(request(url)))

vid = vid.group(1)
player_url = 'http://hqq.tv/player/embed_player.php?vid={}&autoplay=no'.format(vid)

data = request(player_url, headers)
post_data = _decode(data)
data = post(player_url, post_data, headers)
post_data = _decode(data)
data = urllib.parse.unquote(request("http://hqq.tv/sec/player/embed_player.php?" + urllib.parse.urlencode(post_data), headers))
linkvarname, servervarname = re.findall(r'link_1: ([^,]+), server_1: ([^,]+)', data)[0]
vid_server = re.search(r'var {} = "([^"]+?)"'.format(servervarname), data)
vid_link = re.search(r'var {} = "([^"]+?)"'.format(linkvarname), data)
at = re.search(r'var at = "([^"]+?)"', data)
if vid_server and vid_link and at:
	# print(at)
	# at = '0'*32
	get_data = {'server_1': vid_server.group(1), 'link_1': re.sub(r'\?socket=?$', '.mp4.m3u8', vid_link.group(1)), 'at': at.group(1), 'adb': '1/', 'b' : '1', 'vid' : vid}
	data = request("http://hqq.tv/player/get_md5.php?" + urllib.parse.urlencode(get_data), {**headers, **{'X-Requested-With':'XMLHttpRequest'}})
	jsondata = json.loads(data)
	decodedm3u = urllib.parse.unquote('%' + '%'.join(re.findall(r'.(..)', jsondata['html5_file'][1:])))
	# print(decodedm3u)
	filename = decodedm3u.split('/')[-1][:-9]
	call('ffmpeg -user_agent "Mozilla/5.0 (iPhone; U; CPU iPhone OS 3_0 like Mac OS X; en-us)" -i "{}" -c copy {}.mkv'.format(decodedm3u, filename), shell=True)

It might not work because:

A) I believe they updated their streaming protection
B) As far as I can tell this script uses regex to search the URL passed as an argument in the entire webpage source code so you might not get past the AttributeError since it didn't find it, which means the video url wasn't in plain view

What I have seen is that they use as of the time of this post an iframe and they break the stream into smaller peaces so even if you download something you only get 20 second videos and it might have something to do with the uploader preferences of not sharing outside of the their site, if you stop certain scripts you can see loading a player for the video its thumbnails but you won't be able to play it since you also need the scripts to start the streaming process and once you enable them again it probably checks these settings/preferences and you get a 404.

You can use Stream Recorder to download video from hqq.tv