Max Resource
High Quality
Medium Quality
Last active
October 13, 2017 04:03
-
-
Save borgle/9c463a1bc3a7db69e40720b2b7ddb876 to your computer and use it in GitHub Desktop.
fetch youtube video urls
This file contains hidden or 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
| #!/usr/bin/python | |
| #coding: utf-8 | |
| import requests | |
| import sys, re, urllib | |
| reload(sys) | |
| sys.setdefaultencoding('utf-8') | |
| proxies = {'all': '127.0.0.1:8088'} | |
| headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537.36', | |
| 'Accept-Language':'en-US,en;q=0.8,zh-CN;q=0.6,zh;q=0.4,zh-TW;q=0.2', | |
| 'Accept-Encoding':'gzip, deflate, sdch', | |
| 'Cache-Control': 'no-cache', | |
| 'Referer': 'https://www.youtube.com', | |
| } | |
| vmaps = { | |
| "13": ("3GP" , "Low Quality - 176x144"), | |
| "17": ("3GP" , "Medium Quality - 176x144"), | |
| "36": ("3GP" , "High Quality - 320x240"), | |
| "5" : ("FLV" , "Low Quality - 400x226"), | |
| "6" : ("FLV" , "Medium Quality - 640x360"), | |
| "34": ("FLV" , "Medium Quality - 640x360"), | |
| "35": ("FLV" , "High Quality - 854x480"), | |
| "43": ("WEBM", "Low Quality - 640x360"), | |
| "44": ("WEBM", "Medium Quality - 854x480"), | |
| "45": ("WEBM", "High Quality - 1280x720"), | |
| "18": ("MP4" , "Medium Quality - 480x360"), | |
| "22": ("MP4" , "High Quality - 1280x720"), | |
| "37": ("MP4" , "High Quality - 1920x1080"), | |
| "38": ("MP4" , "High Quality - 4096x230") | |
| } | |
| def get_youtube_video_urls(vid): | |
| vurls = {'MP4': [], 'FLV': [], '3GP': [], 'WEBM': []} | |
| watch_url = 'https://www.youtube.com/watch?v=' + vid | |
| r = requests.get(watch_url, headers=headers, proxies=proxies, verify=False) | |
| html = r.content | |
| r.close() | |
| s = re.findall('"url_encoded_fmt_stream_map":"([^"]+)"', html) | |
| js = s[0].split(',') | |
| for s in js: | |
| ars = s.split('\\u0026') | |
| sig, vurl, itag = '', '', 0 | |
| for a in ars: | |
| if a.startswith('sig'): | |
| sig = a[4:] | |
| if a.startswith('url'): | |
| vurl = urllib.unquote(a[4:]) | |
| if a.startswith('itag'): | |
| itag = a[5:] | |
| vt = vmaps.get(itag) | |
| if vt: | |
| vurls[vt[0]] = (vt[1], vurl) | |
| # print vt[0], vt[1], vurl | |
| else: | |
| print 'no vmap', itag, vurl | |
| print vurls | |
| if __name__ == '__main__': | |
| get_youtube_video_urls('HLx1R39kc38') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment