Download all Pycon 2013 Video

download_pycon_2013_videos.py

from urllib2 import urlopen
from subprocess import Popen, PIPE
from bs4 import BeautifulSoup

page = urlopen('http://pyvideo.org/category/33/pycon-us-2013')
soup = BeautifulSoup(page)

video_url_list = []
count = 0

tags = soup.find_all('div', {'class': 'section'})
for t in tags:
    url_page = 'http://pyvideo.org' + t.find('a')['href']
    soup_inner = BeautifulSoup(urlopen(url_page))
    for a in soup_inner.find_all('a'):
        if 'www.youtube.com/watch' in a.get('href', ''):
            video_url_list.append(a['href'])
            break


for url in video_url_list:
    p1 = Popen(["youtube-dl", "-F", url], stdout=PIPE)
    p2 = Popen(["grep", "-i", "mp4"], stdin=p1.stdout, stdout=PIPE)
    p3 = Popen(["head", "-n", "1"], stdin=p2.stdout, stdout=PIPE)
    p4 = Popen(["grep", "-o", r"^[0-9]*"], stdin=p3.stdout, stdout=PIPE)
    output = p4.communicate()[0]
    code_format = output.strip()
    print 'youtube-dl -o "%%(title)s.%%(ext)s" --restrict-filenames -f %s %s' % (code_format, url)