Created
December 30, 2013 18:33
-
-
Save hydrogen18/8185934 to your computer and use it in GitHub Desktop.
Python script to download 30c3 audio & video files
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
from HTMLParser import HTMLParser | |
import urllib2 | |
import subprocess | |
import re | |
import os | |
SAVE_DIR = os.path.expanduser("~/30c3") | |
FILE_RE = re.compile("30c3-\d{4}-.*") | |
class DirListingParser(HTMLParser): | |
def init(self): | |
self.anchorIsDir = False | |
self.anchorIsFile = False | |
self.dirs = [] | |
self.files = [] | |
def handle_starttag(self,tag,attrs): | |
attrs = dict((k,v) for k,v in attrs) | |
if tag == "img": | |
altText = attrs.get('alt') | |
if altText == "[DIR]": | |
self.anchorIsDir = True | |
elif tag == "a": | |
if self.anchorIsDir: | |
self.anchorIsDir = False | |
href = attrs.get('href') | |
print href | |
self.dirs.append(href) | |
else: | |
href = attrs.get('href') | |
if None != FILE_RE.match(href): | |
print file | |
self.files.append(href) | |
#def handle_endtag(self,tag): | |
ROOT_URL = "http://ftp.ccc.de/congress/2013/" | |
def download_one(filename,fileurl): | |
print fileurl | |
cmd = ['wget','-v','-t','3','-c','-O',os.path.join(SAVE_DIR,filename),fileurl] | |
print ' '.join(cmd) | |
retcode = subprocess.check_call(cmd) | |
def download_all(dirurl): | |
print dirurl | |
response = urllib2.urlopen(dirurl) | |
body = response.read() | |
parser = DirListingParser() | |
parser.init() | |
parser.feed(body) | |
for dirname in parser.dirs: | |
download_all(dirurl + dirname) | |
for filename in parser.files: | |
fileurl = dirurl + filename | |
download_one(filename,fileurl) | |
os.makedirs(SAVE_DIR) | |
download_all(ROOT_URL) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is somewhat pointless, as you might as well use http://ftp.ccc.de/INDEX and a glob to wget all the files you need.