vl-download

#!/usr/bin/env python

######################################################################
#
# vl-download.py : Download videos from videolectures.net
# Author  : Mayank Juneja (mayankjuneja1[AT]gmail[DOT]com)
# Version : 0.1
#
######################################################################


import urllib2
import re
import os
import sys
from BeautifulSoup import BeautifulSoup
from optparse import OptionParser
from operator import itemgetter

# Script Description
desc = "videolectures.net video downloader"
vers = "0.2"
# Initialize Option Parser
parser = OptionParser(description=desc,version = vers)

# Add options

parser.add_option("-u","--url",
                dest="url",
                help="videolecture.net URL",
                metavar="URL")

parser.add_option("-o","--outfile",
                dest="outfile",
                help="Output file Name",
                metavar="outfile")

# Parse arguments
(options,args) = parser.parse_args()

# Check for some mandatory Options
if options.url is None:
        # No URL specified
        parser.error("--url option is required")
        sys.exit(1)
if options.outfile is None :
        # Output file not specified
        options.outfile = ""

url = options.url
outfile = options.outfile

request_headers =  {
        'User-Agent'		: 'User-Agent: Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Accept'		: 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language'	: 'en-us,en;q=0.5',
        'Accept-Charset'	: 'Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Keep-Alive'		: '300',
        'Proxy-Connection'	: 'keep-alive',
        'Cache-Control'		: 'max-age=0'
       }

url = url.rstrip("/")
metadata_url = url + "/video/1/smil.xml"

req = urllib2.Request(metadata_url, None, headers=request_headers)
response = urllib2.urlopen(req)
html_page = response.read()

html_page = BeautifulSoup(html_page)

## Find the metadata (Author, Title, Date)
title = html_page.findAll('meta', {'name':'title'}) or ''
author = html_page.findAll('meta', {'name':'author'}) or ''
if title: title = title[0].get('content', '').encode('ascii','ignore')
if author: author = author[0].get('content', '').encode('ascii','ignore')

videos = []
video_tags = html_page.findAll("video")
for tag in video_tags:
    video = {
        'id' : int(tag.get('id', -1)),
        'proto' : tag.get('proto', ''),
        'width' : int(tag.get('width', -1)),
        'height' : int(tag.get('height', -1)),
        'size' : int(tag.get('size', -1)),
        'ext' : tag.get('ext', ''),
        'type' : tag.get('type', ''),
        'src' : tag.get('src', ''),
        'streamer' : tag.get('streamer', '')
    }
    videos.append(video)

# Get the videos with maximum size
max_size = max(videos, key=itemgetter('size'))['size']
videos = [video for video in videos if video['size'] == max_size]

video_urls = {}
for video in videos:
    video_urls[video['proto']] = {
        'streamer' :  video.get('streamer', ''),
        'src' :  video.get('src', ''),
        'ext' :  video.get('ext', '')
    }

if(outfile==""):
    outfile = title.replace(" ","_") + "-" + author.replace(" ","_")

print "Downloading video: ", outfile

# Try for http
if 'http' in video_urls.keys():
    v = video_urls['http']
    outfile = outfile + "." + v['ext']

    req = urllib2.Request(v['src'], None, headers=request_headers)
    u = urllib2.urlopen(req)
    meta = u.info()
    file_size = int(meta.getheaders("Content-Length")[0])
    f = open(outfile, 'wb')

    file_size_dl = 0
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break
        file_size_dl += len(buffer)
        f.write(buffer)
        status = r"Status: [%3.2f%%]" % (file_size_dl * 100. / file_size)
        status = status + chr(8)*(len(status)+1)
        print status,
    f.close()

# Try for rtmp
elif 'rtmp' in video_urls.keys():
    v = video_urls['rtmp']
    outfile = outfile + "." + v['ext']
    rtmp_path = v['streamer']
    rtmp_url  = v['src']

    cmd = ("rtmpdump -r %s -y %s -o \"%s.flv\"")%(rtmp_url, rtmp_path, outfile)
    print cmd
    os.system(cmd)

else:
    print "Could not find a supported protocol"