Last active
June 2, 2019 01:51
-
-
Save nightcoffee/dad38232a532b36a61b6 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import urllib | |
import requests | |
import json | |
import execjs | |
VIDEO_ID = 'lZnqmZ4ZTP8' | |
START_TOKEN = 'ytplayer.config = ' | |
END_TOKEN = ';ytplayer.load' | |
def convert_to_dict(data): | |
result = {} | |
list = data.split('&') | |
for item in list: | |
pair = item.split('=') | |
key = urllib.unquote_plus(pair[0]) | |
value = urllib.unquote_plus(pair[1]) | |
result[key] = value | |
return result | |
def parse_js(data): | |
start = data.find("""a.splice(0,b)""") | |
start = data.rfind(";var", 0 , start) | |
end = data.find("""return a.join("")};""", start) | |
js = data[start:end+len("""return a.join("")};""")] | |
start = js.find("""function """) | |
end = js.find("""(a)""" , start) | |
name = js[start+len("""function """):end] | |
return name, js | |
if __name__ == '__main__': | |
print "Using javascript interpreter:", execjs.get().name | |
headers = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36', | |
'Accept-Language':'zh-CN,zh;q=0.8,zh-TW;q=0.6,en;q=0.4', | |
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', | |
'Accept-Encoding': 'gzip, deflate, sdch'} | |
response = requests.get("https://www.youtube.com/watch?v=%s" % VIDEO_ID, headers=headers) | |
data = response.content | |
start = data.find(START_TOKEN) | |
end = data.find(END_TOKEN) | |
data = data[start+len(START_TOKEN):end] | |
data = json.loads(data) | |
js = 'https:' + data['assets']['js'] | |
response = requests.get(js) | |
jscontent = response.content | |
func, jscontent = parse_js(jscontent) | |
ctxt = execjs.compile(jscontent) | |
data = data['args'] | |
print "Title:", data['title'] | |
list = data['adaptive_fmts'].split(',') | |
parsed = [] | |
for item in list: | |
info = convert_to_dict(item) | |
if info['url'].find("&signature=") == -1: | |
info['url'] = info['url'] +"&signature=" + ctxt.call(func, info['s']) | |
parsed.append(info) | |
for item in parsed: | |
if item['type'].startswith("video"): | |
print "%-35s|%-10s%2sfps|%-10s|%s" % (item['type'], item['size'], item['fps'], "%0.2fMiB" % (float(item['clen'])/1024/1024), item['url']) | |
else: | |
print "%-35s|%-10s%5s|%-10s|%s" % (item['type'], "" , "" , "%0.2fMiB" % (float(item['clen'])/1024/1024), item['url']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment