rpms/metacafe-dl/F-8 index.html, NONE, 1.1 metacafe-dl, NONE, 1.1 metacafe-dl.spec, NONE, 1.1

Sun Jan 20 22:14:00 UTC 2008

Author: rafalzaq

Update of /cvs/extras/rpms/metacafe-dl/F-8
In directory cvs-int.fedora.redhat.com:/tmp/cvs-serv12030/F-8

Added Files:
	index.html metacafe-dl metacafe-dl.spec 
Log Message:
import metacafe-dl 2007.10.09

--- NEW FILE index.html ---
<!DOCTYPE html 
     PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
     "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
	<meta http-equiv="Content-type" content="text/html; charset=UTF-8" />
	<title>metacafe-dl: Download videos from metacafe.com</title>
	<style type="text/css"><!--
		body {
			font-family: sans-serif;
			font-size: small;
		}
		h1 {
			text-align: center;
			text-decoration: underline;
			color: #006699;
		}
		h2 {
			color: #006699;
		}
		p {
			text-align: justify;
			margin-left: 5%;
			margin-right: 5%;
		}
		ul {
			margin-left: 5%;
			margin-right: 5%;
			list-style-type: square;
		}
		li {
			margin-bottom: 0.5ex;
		}
		#copyright {
			font-size: x-small;
			text-align: center;
		}
		--></style>
</head>
<body>
<h1>metacafe-dl: Download videos from metacafe.com</h1>

<h2>What is it?</h2>

metacafe-dl is a small command-line program to download videos
from metacafe.com, based on the code of
<a href="http://www.arrakis.es/~rggi3/youtube-dl/">youtube-dl</a>. Hence,
it has the same requirements and features, and its syntax is very similar.
The latest version is 2007.10.09. It's also licensed under
the MIT License.

As with youtube-dl, I'll try to keep it updated if metacafe.com
changes the way you access their videos, but the same circumstances apply.
My contact information is at
<a href="http://freshmeat.net/~rg3/">freshmeat.net</a>.

<h2>Usage instructions</h2>

In Windows, once you have installed the Python interpreter, save the
program with the .py extension and put it somewhere in the PATH.
Follow the
<a href="http://rg03.wordpress.com/youtube-dl-under-windows-xp/">guide to
install youtube-dl under Windows XP</a>, as the instructions for
metacafe-dl are identical.

<p>In Unix, download it, give it execution permission and copy it to one
of the PATH directories (typically, <em>/usr/local/bin</em>).</p>

After that, you should be able to call it from the command line as
metacafe-dl or metacafe-dl.py. I will use metacafe-dl
in the following examples. Usage instructions are easy. Use metacafe-dl
followed by a video URL. Example: metacafe-dl
"http://www.metacafe.com/watch/somecode/blah/etc". The video will be saved
to the file somecode.flv in that example. As metacafe.com
videos are in Flash Video format, their extension should be flv.
In Linux and other unices, video players using a recent version of
ffmpeg can play them. That includes MPlayer, VLC, etc. Those two
work under Windows and other platforms, but you could also get a
specific FLV player of your taste.

<p>If you try to run the program and you receive an error message containing the
keyword <em>SyntaxError</em> near the end, it means your Python interpreter
is too old.</p>

<h2>More usage tips</h2>

<ul>

<li>You can change the file name of the video using the -o option, like in
<em>metacafe-dl -o vid.flv
"http://www.metacafe.com/watch/somecode/blah/etc"</em>.</li>

<li>The <em>simulate mode</em> (activated with -s or --simulate) can be used
to just get the real video URL and use it with a download manager if you
prefer that option.</li>

<li>The quiet mode (activated with -q or --quiet) can be used to
supress all output messages. This allows, in systems featuring /dev/stdout
and other similar special files, outputting the video data to standard output
in order to pipe it to another program without interferences.</li>

<li>The default filename is video_id.flv. But you can also use the
video title in the filename with the -t or --title option. For this, the URL
must include the video title, which is the typical case.</li>

<li>The program can be told to simply print the final video URL to standard
output using the -g or --get-url option.</li>

<li>metacafe-dl honors the http_proxy environment variable
if you want to use a proxy. Set it to something like
http://proxy.example.com:8080, and do not leave the http://
prefix out.</li>

<li>You can get the program version by calling it as <em>metacafe-dl
-v</em> or <em>metacafe-dl --version</em>.</li>

<li>For usage instructions, use <em>metacafe-dl -h</em> or <em>metacafe-dl
--help.</em></li>

<li>You can cancel the program at any time pressing Ctrl+C. It may print
some error lines saying something about KeyboardInterrupt.
That's ok.</li>

</ul>

<h2>Download it</h2>

Note that if you directly click on these hyperlinks, your web browser will
most likely display the program contents. It's usually better to
right-click on it and choose the appropriate option, normally called Save
Target As or Save Link As, depending on the web browser you
are using.

<p><a href="metacafe-dl">2007.10.09</a></p>
<ul>
        <li><strong>MD5</strong>: 69348e455f70b048b8db1263b35f16c2</li>
        <li><strong>SHA1</strong>: 766e17c0cee0d3416d7120b4fc7397ce87e74ea7</li>
        <li><strong>SHA256</strong>: 44da4e8f6dc1b250f354e8159199252782b2c847df9face30feb92e66a5a88ce</li>
</ul>

<p id="copyright">Copyright © 2006-2007 Ricardo Garcia Gonzalez</p>
</body>
</html>

--- NEW FILE metacafe-dl ---
#!/usr/bin/env python
#
# Copyright (c) 2006-2007 Ricardo Garcia Gonzalez
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
# 
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
# 
# Except as contained in this notice, the name(s) of the above copyright
# holders shall not be used in advertising or otherwise to promote the
# sale, use or other dealings in this Software without prior written
# authorization.
#
import httplib
import math
import optparse
import re
import socket
import sys
import time
import urllib2

# Global constants
const_video_url_re = re.compile(r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+/)?.*')
const_normalized_url_str = 'http://www.metacafe.com/watch/%s/'
const_disclaimer_url = 'http://www.metacafe.com/disclaimer'
const_age_post_data = r'allowAdultContent=1&submit=Continue+-+I%27m+over+18'
const_video_mediaurl_re = re.compile(r'&mediaURL=([^&]+)&', re.M)
const_1k = 1024
const_initial_block_size = 10 * const_1k
const_epsilon = 0.0001

# Print error message, followed by standard advice information, and then exit
def error_advice_exit(error_text):
	sys.stderr.write('Error: %s.\n' % error_text)
	sys.stderr.write('Try again several times. It may be a temporary problem.\n')
	sys.stderr.write('Other typical problems:\n\n')
	sys.stderr.write('* URL is wrong.\n')
	sys.stderr.write('* Content is not a flash video.\n')
	sys.stderr.write('* Video no longer exists.\n')
	sys.stderr.write('* The connection was cut suddenly for some reason.\n')
	sys.stderr.write('* metacafe changed their system, and the program no longer works.\n')
	sys.stderr.write('\nTry to confirm you are able to view the video using a web browser.\n')
	sys.stderr.write('When using a proxy, make sure http_proxy has http://host:port format.\n')
	sys.stderr.write('Try again several times and contact me if the problem persists.\n')
	sys.exit('\n')

# Wrapper to create custom requests with typical headers
def request_create(url, data=None):
	retval = urllib2.Request(url)
	if data is not None:
		retval.add_data(data)
	# Try to mimic Firefox, at least a little bit
	retval.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1) Gecko/20061010 Firefox/2.0')
	retval.add_header('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7')
	retval.add_header('Accept', 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5')
	retval.add_header('Accept-Language', 'en-us,en;q=0.5')
	return retval

# Perform a request, process headers and return response
def perform_request(url, data=None):
	request = request_create(url, data)
	response = urllib2.urlopen(request)
	return response

# Conditional print
def cond_print(str):
	global cmdl_opts
	if not (cmdl_opts.quiet or cmdl_opts.get_url):
		sys.stdout.write(str)
		sys.stdout.flush()

# Generic download step
def download_step(return_data_flag, step_title, step_error, url, post_data=None):
	try:
		cond_print('%s... ' % step_title)
		data = perform_request(url, post_data).read()
		cond_print('done.\n')
		if return_data_flag:
			return data
		return None

	except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
		cond_print('failed.\n')
		error_advice_exit(step_error)

	except KeyboardInterrupt:
		sys.exit('\n')

# Generic extract step
def extract_step(step_title, step_error, regexp, data):
	try:
		cond_print('%s... ' % step_title)
		match = regexp.search(data)

		if match is None:
			cond_print('failed.\n')
			error_advice_exit(step_error)

		extracted_data = match.group(1)
		cond_print('done.\n')
		return extracted_data

	except KeyboardInterrupt:
		sys.exit('\n')

# Calculate new block size based on previous block size
def new_block_size(before, after, bytes):
	new_min = max(bytes / 2.0, 1.0)
	new_max = max(bytes * 2.0, 1.0)
	dif = after - before
	if dif < const_epsilon:
		return int(new_max)
	rate = bytes / dif
	if rate > new_max:
		return int(new_max)
	if rate < new_min:
		return int(new_min)
	return int(rate)

# Get optimum 1k exponent to represent a number of bytes
def optimum_k_exp(num_bytes):
	global const_1k
	if num_bytes == 0:
		return 0
	return long(math.log(num_bytes, const_1k))

# Get optimum representation of number of bytes
def format_bytes(num_bytes):
	global const_1k
	try:
		exp = optimum_k_exp(num_bytes)
		suffix = 'bkMGTPEZY'[exp]
		if exp == 0:
			return '%s%s' % (num_bytes, suffix)
		converted = float(num_bytes) / float(const_1k**exp)
		return '%.2f%s' % (converted, suffix)
	except IndexError:
		sys.exit('Error: internal error formatting number of bytes.')

# Calculate ETA and return it in string format as MM:SS
def calc_eta(start, now, total, current):
	dif = now - start
	if current == 0 or dif < const_epsilon:
		return '--:--'
	rate = float(current) / dif
	eta = long((total - current) / rate)
	eta_mins = eta / 60
	eta_secs = eta % 60
	if eta_mins > 99:
		return '--:--'
	return '%02d:%02d' % (eta_mins, eta_secs)

# Calculate speed and return it in string format
def calc_speed(start, now, bytes):
	dif = now - start
	if bytes == 0 or dif < const_epsilon:
		return 'N/A b'
	return format_bytes(float(bytes) / dif)

# Create the command line options parser and parse command line
cmdl_usage = 'usage: %prog [options] video_url'
cmdl_version = '2007.10.09'
cmdl_parser = optparse.OptionParser(usage=cmdl_usage, version=cmdl_version, conflict_handler='resolve')
cmdl_parser.add_option('-h', '--help', action='help', help='print this help text and exit')
cmdl_parser.add_option('-v', '--version', action='version', help='print program version and exit')
cmdl_parser.add_option('-o', '--output', dest='outfile', metavar='FILE', help='output video file name')
cmdl_parser.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode')
cmdl_parser.add_option('-s', '--simulate', action='store_true', dest='simulate', help='do not download video')
cmdl_parser.add_option('-t', '--title', action='store_true', dest='use_title', help='use title in file name')
cmdl_parser.add_option('-g', '--get-url', action='store_true', dest='get_url', help='print final video URL only')
(cmdl_opts, cmdl_args) = cmdl_parser.parse_args()

# Get video URL
if len(cmdl_args) != 1:
	cmdl_parser.print_help()
	sys.exit('\n')
video_url = cmdl_args[0]

# Verify video URL format and extract URL data to normalize URL
video_url_mo = const_video_url_re.match(video_url)
if video_url_mo is None:
	sys.exit('Error: URL does not seem to be a metacafe video URL. If it is, report a bug.')
video_url_id = video_url_mo.group(1)
video_url_title = (video_url_mo.group(2) is not None) and video_url_mo.group(2)[:-1] or None
video_url = const_normalized_url_str % video_url_id

# Check conflicting options
if cmdl_opts.outfile is not None and (cmdl_opts.simulate or cmdl_opts.get_url):
	sys.stderr.write('Warning: video file name given but will not be used.\n')

if cmdl_opts.outfile is not None and cmdl_opts.use_title:
	sys.exit('Error: using the video title conflicts with using a given file name.')

if cmdl_opts.quiet and cmdl_opts.get_url:
	sys.exit('Error: cannot be quiet and print final URL at the same time.')

# Get output file name 
if cmdl_opts.outfile is None:
	if cmdl_opts.use_title:
		if video_url_title is None:
			sys.exit('Error: cannot use video title: not present in URL.')
		video_filename = '%s-%s.flv' % (video_url_title, video_url_id)
	else:
		video_filename = '%s.flv' % video_url_id
else:
	video_filename = cmdl_opts.outfile

# Check name
if not video_filename.lower().endswith('.flv'):
	sys.stderr.write('Warning: video file name does not end in .flv\n')

# Test writable file
if not (cmdl_opts.simulate or cmdl_opts.get_url):
	try:
		disk_test = open(video_filename, 'wb')
		disk_test.close()

	except (OSError, IOError):
		sys.exit('Error: unable to open %s for writing.' % video_filename)

# Install cookie and proxy handlers
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))

# Retrieve video webpage
download_step(False, 'Retrieving disclaimer', 'unable to retrieve disclaimer', const_disclaimer_url)

# Retrieve video webpage
video_webpage = download_step(True, 'Retrieving video webpage', 'unable to retrieve video webpage', video_url, const_age_post_data)

# Retrieve real video URL
video_url_real = extract_step('Extracting real video URL', 'unable to extract real video URL', const_video_mediaurl_re, video_webpage)

# Retrieve video data
try:
	cond_print('Requesting video file... ')
	video_data = perform_request(video_url_real)
	cond_print('done\n')
	cond_print('Video data found at %s\n' % video_data.geturl())

	if cmdl_opts.get_url:
		print video_data.geturl()

	if cmdl_opts.simulate or cmdl_opts.get_url:
		sys.exit()

	video_file = open(video_filename, 'wb')
	try:
		video_len = long(video_data.info()['Content-length'])
		video_len_str = format_bytes(video_len)
	except KeyError:
		video_len = None
		video_len_str = 'N/A'

	byte_counter = 0
	block_size = const_initial_block_size
	start_time = time.time()
	while True:
		if video_len is not None:
			percent = float(byte_counter) / float(video_len) * 100.0
			percent_str = '%.1f' % percent
			eta_str = calc_eta(start_time, time.time(), video_len, byte_counter)
		else:
			percent_str = '---.-'
			eta_str = '--:--'
		counter = format_bytes(byte_counter)
		speed_str = calc_speed(start_time, time.time(), byte_counter)
		cond_print('\rRetrieving video data: %5s%% (%8s of %s) at %8s/s ETA %s ' % (percent_str, counter, video_len_str, speed_str, eta_str))

		before = time.time()
		video_block = video_data.read(block_size)
		after = time.time()
		dl_bytes = len(video_block)
		if dl_bytes == 0:
			break
		byte_counter += dl_bytes
		video_file.write(video_block)
		block_size = new_block_size(before, after, dl_bytes)

	if video_len is not None and byte_counter != video_len:
		error_advice_exit('server did not send the expected ammount of data')

	video_file.close()
	cond_print('done.\n')
	cond_print('Video data saved to %s\n' % video_filename)

except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
	cond_print('failed.\n')
	error_advice_exit('unable to download video data')

except KeyboardInterrupt:
	sys.exit('\n')

# Finish
sys.exit()

--- NEW FILE metacafe-dl.spec ---
Name:           metacafe-dl
Version:        2007.10.09
Release:        1%{?dist}
Summary:        Command-line program to download videos from metacafe.com
Summary(pl):    Tekstowy program do pobierania filmÃ³w z metacafe.com

Group:          Applications/Internet
License:        MIT
URL:            http://www.arrakis.es/~rggi3/metacafe-dl/
Source0:        http://www.arrakis.es/~rggi3/metacafe-dl/metacafe-dl
Source1:        http://www.arrakis.es/~rggi3/metacafe-dl/index.html
BuildRoot:      %{_tmppath}/%{name}-%{version}-%{release}-root-%(%{__id_u} -n)
BuildArch:      noarch

#BuildRequires:  
Requires:       python

%description
metacafe-dl is a small command line program for downloading videos from
metacafe.com.

%description -l pl
metacafe-dl to maÅ‚y tekstowy program sÅ‚uÅ¼Ä…cy do pobierania filmÃ³w z
metacafe.com.

%prep
%setup -c -T

%build
#nothing to build

%install
rm -rf $RPM_BUILD_ROOT
cp %{SOURCE1} .
mkdir -p $RPM_BUILD_ROOT%{_bindir}
install -p -m 755 %{SOURCE0} $RPM_BUILD_ROOT%{_bindir}/%{name}

%clean
rm -rf $RPM_BUILD_ROOT

%files
%defattr(-,root,root,-)
%doc index.html
%{_bindir}/%{name}

%changelog
* Sat Jan 19 2008 RafaÅ‚ Psota <rafalzaq at gmail.com> 2007.10.09-1
- fixed version and description tags
- removed COPYING file
- index.html from homepage is now marked as doc
* Thu Dec 20 2007 RafaÅ‚ Psota <rafalzaq at gmail.com> 0-1.2007.10.09
- Initial Release