Created
June 27, 2013 06:51
-
-
Save nriley/5874460 to your computer and use it in GitHub Desktop.
Extract English subtitle text for WWDC 2013 videos.
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
| import requests | |
| import os, re, sys | |
| RE_SD_VIDEO = re.compile( | |
| r'<a href="(http://devstreaming.apple.com/videos/wwdc/2013/[^"]*-SD.mov)') | |
| RE_WEBVTT = re.compile(r'fileSequence[0-9]+\.webvtt') | |
| # stdin: dump of https://developer.apple.com/wwdc/videos/ | |
| for l in sys.stdin: | |
| m = RE_SD_VIDEO.search(l) | |
| if not m: | |
| continue | |
| video_url = m.group(1) | |
| video_dir = video_url[:video_url.rindex('/')] | |
| session = video_dir[video_dir.rindex('/') + 1:] | |
| prog_index = requests.get(video_dir + '/subtitles/eng/prog_index.m3u8') | |
| os.mkdir(session) | |
| webvtt_names = RE_WEBVTT.findall(prog_index.text) | |
| for webvtt_name in webvtt_names: | |
| webvtt = requests.get(video_dir + '/subtitles/eng/' + webvtt_name) | |
| open(os.path.join(session, webvtt_name), 'w').write(webvtt.text) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
How could I extract wwdc 2012 or older subtitles?