Compare commits
12 Commits
2009.01.31
...
2009.03.03
| Author | SHA1 | Date | |
|---|---|---|---|
|
7ab2043c9c | ||
|
|
3e703dd1cd | ||
|
|
cc10940385 | ||
|
|
5121ef2071 | ||
|
|
fd20984889 | ||
|
|
111ae3695c | ||
|
|
0beeff4b3e | ||
|
|
64a6f26c5d | ||
|
|
a9633f1457 | ||
|
|
a20e4c2f96 | ||
|
|
d1536018a8 | ||
|
|
25af2bce3a |
@@ -1,15 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
import hashlib
|
||||
import subprocess
|
||||
|
||||
template = file('index.html.in', 'r').read()
|
||||
version = subprocess.Popen(['./youtube-dl', '--version'], stdout=subprocess.PIPE).communicate()[0].strip()
|
||||
data = file('youtube-dl', 'rb').read()
|
||||
md5sum = hashlib.md5(data).hexdigest()
|
||||
sha1sum = hashlib.sha1(data).hexdigest()
|
||||
sha256sum = hashlib.sha256(data).hexdigest()
|
||||
template = template.replace('@PROGRAM_VERSION@', version)
|
||||
template = template.replace('@PROGRAM_MD5SUM@', md5sum)
|
||||
template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
|
||||
template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
|
||||
file('index.html', 'w').write(template)
|
||||
214
index.html.in
214
index.html.in
@@ -1,214 +0,0 @@
|
||||
<!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>youtube-dl: Download videos from YouTube.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;
|
||||
}
|
||||
.smallnote {
|
||||
font-size: x-small;
|
||||
text-align: center;
|
||||
}
|
||||
--></style>
|
||||
</head>
|
||||
<body>
|
||||
<h1>youtube-dl: Download videos from YouTube.com</h1>
|
||||
|
||||
<p class="smallnote">(and more...)</p>
|
||||
|
||||
<h2>What is it?</h2>
|
||||
|
||||
<p><em>youtube-dl</em> is a small command-line program to download videos
|
||||
from YouTube.com. It requires the <a href="http://www.python.org/">Python
|
||||
interpreter</a>, version 2.4 or later, and it's not platform specific.
|
||||
It should work in your Unix box, in Windows or in Mac OS X. The latest version
|
||||
is <strong>@PROGRAM_VERSION@</strong>. It's released to the public domain,
|
||||
which means you can modify it, redistribute it or use it however you like.</p>
|
||||
|
||||
<p>I'll try to keep it updated if YouTube.com changes the way you access
|
||||
their videos. After all, it's a simple and short program. However, I can't
|
||||
guarantee anything. If you detect it stops working, check for new versions
|
||||
and/or inform me about the problem, indicating the program version you
|
||||
are using. If the program stops working and I can't solve the problem but
|
||||
you have a solution, I'd like to know it. If that happens and you feel you
|
||||
can maintain the program yourself, tell me. My contact information is
|
||||
at <a href="http://freshmeat.net/~rg3/">freshmeat.net</a>.</p>
|
||||
|
||||
<p>Thanks for all the feedback received so far. I'm glad people find my
|
||||
program useful.</p>
|
||||
|
||||
<h2>Usage instructions</h2>
|
||||
|
||||
<p>In Windows, once you have installed the Python interpreter, save the
|
||||
program with the <em>.py</em> extension and put it somewhere in the PATH.
|
||||
Try to follow the
|
||||
<a href="http://rg03.wordpress.com/youtube-dl-under-windows-xp/">guide to
|
||||
install youtube-dl under Windows XP</a>.</p>
|
||||
|
||||
<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>
|
||||
|
||||
<p>After that, you should be able to call it from the command line as
|
||||
<em>youtube-dl</em> or <em>youtube-dl.py</em>. I will use <em>youtube-dl</em>
|
||||
in the following examples. Usage instructions are easy. Use <em>youtube-dl</em>
|
||||
followed by a video URL or identifier. Example: <em>youtube-dl
|
||||
"http://www.youtube.com/watch?v=foobar"</em>. The video will be saved
|
||||
to the file <em>foobar.flv</em> in that example. As YouTube.com
|
||||
videos are in Flash Video format, their extension should be <em>flv</em>.
|
||||
In Linux and other unices, video players using a recent version of
|
||||
<em>ffmpeg</em> 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>
|
||||
|
||||
<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>youtube-dl -o vid.flv "http://www.youtube.com/watch?v=foobar"</em>.
|
||||
Read the <a href="#otpl">Output template</a> section for more details on
|
||||
this.</li>
|
||||
|
||||
<li>Some videos require an account to be downloaded, mostly because they're
|
||||
flagged as mature content. You can pass the program a username and password
|
||||
for a YouTube.com account with the -u and -p options, like <em>youtube-dl
|
||||
-u myusername -p mypassword "http://www.youtube.com/watch?v=foobar"</em>.</li>
|
||||
|
||||
<li>The account data can also be read from the user .netrc file by indicating
|
||||
the -n or --netrc option. The machine name is <em>youtube</em> in that
|
||||
case.</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 <em>quiet mode</em> (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 program can be told to simply print the final video URL to standard
|
||||
output using the -g or --get-url option.</li>
|
||||
|
||||
<li>In a similar line, the -e or --get-title option tells the program to print
|
||||
the video title.</li>
|
||||
|
||||
<li>The default filename is <em>video_id.flv</em>. But you can also use the
|
||||
video title in the filename with the -t or --title option, or preserve the
|
||||
literal title in the filename with the -l or --literal option.</li>
|
||||
|
||||
<li>You can make the program append <em>&fmt=something</em> to the URL
|
||||
by using the -f or --format option. This makes it possible to download high
|
||||
quality versions of the videos when available.</li>
|
||||
|
||||
<li>The -b or --best-quality option is an alias for -f 18.</li>
|
||||
|
||||
<li>The -m or --mobile-version option is an alias for -f 17.</li>
|
||||
|
||||
<li>Normally, the program will stop on the first error, but you can tell it
|
||||
to attempt to download every video with the -i or --ignore-errors option.</li>
|
||||
|
||||
<li>The -a or --batch-file option lets you specify a file to read URLs from.
|
||||
The file must contain one URL per line.</li>
|
||||
|
||||
<li><em>youtube-dl</em> honors the <em>http_proxy</em> environment variable
|
||||
if you want to use a proxy. Set it to something like
|
||||
<em>http://proxy.example.com:8080</em>, and do not leave the <em>http://</em>
|
||||
prefix out.</li>
|
||||
|
||||
<li>You can get the program version by calling it as <em>youtube-dl
|
||||
-v</em> or <em>youtube-dl --version</em>.</li>
|
||||
|
||||
<li>For usage instructions, use <em>youtube-dl -h</em> or <em>youtube-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 <em>KeyboardInterrupt</em>.
|
||||
That's ok.</li>
|
||||
|
||||
</ul>
|
||||
|
||||
<h2 id="otpl">Download it</h2>
|
||||
|
||||
<p>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 <em>Save
|
||||
Target As</em> or <em>Save Link As</em>, depending on the web browser you
|
||||
are using.</p>
|
||||
|
||||
<p><a href="youtube-dl">@PROGRAM_VERSION@</a></p>
|
||||
<ul>
|
||||
<li><strong>MD5</strong>: @PROGRAM_MD5SUM@</li>
|
||||
<li><strong>SHA1</strong>: @PROGRAM_SHA1SUM@</li>
|
||||
<li><strong>SHA256</strong>: @PROGRAM_SHA256SUM@</li>
|
||||
</ul>
|
||||
|
||||
<h2>Output template</h2>
|
||||
|
||||
<p>The -o option allows users to indicate a template for the output file names.
|
||||
The basic usage is not to set any template arguments when downloading a single
|
||||
file, like in <em>youtube-dl -o funny_video.flv 'http://some/video'</em>.
|
||||
However, it may contain special sequences that will be replaced when
|
||||
downloading each video. The special sequences have the format
|
||||
<strong>%(NAME)s</strong>. To clarify, that's a percent symbol followed by a
|
||||
name in parenthesis, followed by a lowercase S. Allowed names are:</p>
|
||||
|
||||
<ul>
|
||||
<li><em>id</em>: The sequence will be replaced by the video identifier.</li>
|
||||
<li><em>url</em>: The sequence will be replaced by the video URL.</li>
|
||||
<li><em>uploader</em>: The sequence will be replaced by the nickname of the
|
||||
person who uploaded the video.</li>
|
||||
<li><em>title</em>: The sequence will be replaced by the literal video
|
||||
title.</li>
|
||||
<li><em>stitle</em>: The sequence will be replaced by a simplified video
|
||||
title, restricted to alphanumeric characters and dashes.</li>
|
||||
<li><em>ext</em>: The sequence will be replaced by the appropriate
|
||||
extension (like <em>flv</em> or <em>mp4</em>).</li>
|
||||
</ul>
|
||||
|
||||
<p>As you may have guessed, the default template is <em>%(id)s.%(ext)s</em>.
|
||||
When some command line options are used, it's replaced by other templates like
|
||||
<em>%(title)s-%(id)s.%(ext)s</em>. You can specify your own.</p>
|
||||
|
||||
<h2>Authors</h2>
|
||||
|
||||
<ul>
|
||||
<li>Ricardo Garcia Gonzalez: program core, YouTube.com InfoExtractor,
|
||||
metacafe.com InfoExtractor and YouTube playlist InfoExtractor.</li>
|
||||
<li>Many other people contributing patches, code, ideas and kind messages. Too
|
||||
many to be listed here. You know who you are. Thank you very much.</li>
|
||||
</ul>
|
||||
|
||||
<p class="smallnote">Copyright © 2006-2007 Ricardo Garcia Gonzalez</p>
|
||||
</body>
|
||||
</html>
|
||||
108
youtube-dl
108
youtube-dl
@@ -1,6 +1,7 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
# Author: Ricardo Garcia Gonzalez
|
||||
# Author: Danny Colligan
|
||||
# License: Public domain code
|
||||
import htmlentitydefs
|
||||
import httplib
|
||||
@@ -88,6 +89,7 @@ class FileDownloader(object):
|
||||
outtmpl: Template for output names.
|
||||
ignoreerrors: Do not stop on download errors.
|
||||
ratelimit: Download speed limit, in bytes/sec.
|
||||
nooverwrites: Prevent overwriting files.
|
||||
"""
|
||||
|
||||
_params = None
|
||||
@@ -142,7 +144,7 @@ class FileDownloader(object):
|
||||
return '--:--'
|
||||
return '%02d:%02d' % (eta_mins, eta_secs)
|
||||
|
||||
@staticmethod
|
||||
@staticmethod
|
||||
def calc_speed(start, now, bytes):
|
||||
dif = now - start
|
||||
if bytes == 0 or dif < 0.001: # One millisecond
|
||||
@@ -285,6 +287,9 @@ class FileDownloader(object):
|
||||
except (ValueError, KeyError), err:
|
||||
retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
|
||||
continue
|
||||
if self._params['nooverwrites'] and os.path.exists(filename):
|
||||
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
|
||||
continue
|
||||
try:
|
||||
self.pmkdir(filename)
|
||||
except (OSError, IOError), err:
|
||||
@@ -488,12 +493,8 @@ class YoutubeIE(InfoExtractor):
|
||||
self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
|
||||
return
|
||||
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
return
|
||||
|
||||
# Set language
|
||||
request = urllib2.Request(self._LOGIN_URL, None, std_headers)
|
||||
request = urllib2.Request(self._LANG_URL, None, std_headers)
|
||||
try:
|
||||
self.report_lang()
|
||||
urllib2.urlopen(request).read()
|
||||
@@ -501,6 +502,10 @@ class YoutubeIE(InfoExtractor):
|
||||
self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
|
||||
return
|
||||
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
return
|
||||
|
||||
# Log in
|
||||
login_form = {
|
||||
'current_form': 'loginForm',
|
||||
@@ -721,6 +726,90 @@ class MetacafeIE(InfoExtractor):
|
||||
'ext': video_extension.decode('utf-8'),
|
||||
}]
|
||||
|
||||
|
||||
class YoutubeSearchIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube search queries."""
|
||||
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
|
||||
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
|
||||
_MORE_PAGES_INDICATOR = r'>Next</a>'
|
||||
_youtube_ie = None
|
||||
|
||||
def __init__(self, youtube_ie, downloader=None):
|
||||
InfoExtractor.__init__(self, downloader)
|
||||
self._youtube_ie = youtube_ie
|
||||
|
||||
@staticmethod
|
||||
def suitable(url):
|
||||
return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
|
||||
|
||||
def report_download_page(self, query, pagenum):
|
||||
"""Report attempt to download playlist page with given number."""
|
||||
self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
|
||||
|
||||
def _real_initialize(self):
|
||||
self._youtube_ie.initialize()
|
||||
|
||||
def _real_extract(self, query):
|
||||
mobj = re.match(self._VALID_QUERY, query)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: invalid search query "%s"' % query)
|
||||
return [None]
|
||||
|
||||
prefix, query = query.split(':')
|
||||
prefix = prefix[8:]
|
||||
if prefix == '':
|
||||
return self._download_n_results(query, 1)
|
||||
elif prefix == 'all':
|
||||
return self._download_n_results(query, -1)
|
||||
else:
|
||||
try:
|
||||
n = int(prefix)
|
||||
if n <= 0:
|
||||
self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
|
||||
return [None]
|
||||
return self._download_n_results(query, n)
|
||||
except ValueError: # parsing prefix as int fails
|
||||
return self._download_n_results(query, 1)
|
||||
|
||||
def _download_n_results(self, query, n):
|
||||
"""Downloads a specified number of results for a query"""
|
||||
|
||||
video_ids = []
|
||||
already_seen = set()
|
||||
pagenum = 1
|
||||
|
||||
while True:
|
||||
self.report_download_page(query, pagenum)
|
||||
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
|
||||
request = urllib2.Request(result_url, None, std_headers)
|
||||
try:
|
||||
page = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
|
||||
return [None]
|
||||
|
||||
# Extract video identifiers
|
||||
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
|
||||
video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
|
||||
if video_id not in already_seen:
|
||||
video_ids.append(video_id)
|
||||
already_seen.add(video_id)
|
||||
if len(video_ids) == n:
|
||||
# Specified n videos reached
|
||||
information = []
|
||||
for id in video_ids:
|
||||
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
|
||||
return information
|
||||
|
||||
if self._MORE_PAGES_INDICATOR not in page:
|
||||
information = []
|
||||
for id in video_ids:
|
||||
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
|
||||
return information
|
||||
|
||||
pagenum = pagenum + 1
|
||||
|
||||
class YoutubePlaylistIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube playlists."""
|
||||
|
||||
@@ -852,7 +941,7 @@ if __name__ == '__main__':
|
||||
# Parse command line
|
||||
parser = optparse.OptionParser(
|
||||
usage='Usage: %prog [options] url...',
|
||||
version='2009.01.31',
|
||||
version='2009.03.03',
|
||||
conflict_handler='resolve',
|
||||
)
|
||||
parser.add_option('-h', '--help',
|
||||
@@ -891,6 +980,8 @@ if __name__ == '__main__':
|
||||
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
||||
parser.add_option('-a', '--batch-file',
|
||||
dest='batchfile', metavar='F', help='file containing URLs to download')
|
||||
parser.add_option('-w', '--no-overwrites',
|
||||
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
||||
(opts, args) = parser.parse_args()
|
||||
|
||||
# Batch file verification
|
||||
@@ -925,6 +1016,7 @@ if __name__ == '__main__':
|
||||
youtube_ie = YoutubeIE()
|
||||
metacafe_ie = MetacafeIE(youtube_ie)
|
||||
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
|
||||
youtube_search_ie = YoutubeSearchIE(youtube_ie)
|
||||
|
||||
# File downloader
|
||||
charset = locale.getdefaultlocale()[1]
|
||||
@@ -945,7 +1037,9 @@ if __name__ == '__main__':
|
||||
or u'%(id)s.%(ext)s'),
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
'ratelimit': opts.ratelimit,
|
||||
'nooverwrites': opts.nooverwrites,
|
||||
})
|
||||
fd.add_info_extractor(youtube_search_ie)
|
||||
fd.add_info_extractor(youtube_pl_ie)
|
||||
fd.add_info_extractor(metacafe_ie)
|
||||
fd.add_info_extractor(youtube_ie)
|
||||
|
||||
Reference in New Issue
Block a user