Compare commits
36 Commits
2008.07.22
...
2009.02.07
| Author | SHA1 | Date | |
|---|---|---|---|
|
fd20984889 | ||
|
|
111ae3695c | ||
|
|
0beeff4b3e | ||
|
|
64a6f26c5d | ||
|
|
a9633f1457 | ||
|
|
a20e4c2f96 | ||
|
|
d1536018a8 | ||
|
|
25af2bce3a | ||
|
|
d1580ed990 | ||
|
|
eb0d2909a8 | ||
|
|
ba72f8a5d1 | ||
|
|
c6fd0bb806 | ||
|
|
72ac78b8b0 | ||
|
|
240b737ebd | ||
|
|
27d98b6e25 | ||
|
|
5487aea5d8 | ||
|
|
9ca4851a00 | ||
|
|
1e9daf2a48 | ||
|
|
d853063955 | ||
|
|
2546e7679f | ||
|
|
0ddf38df18 | ||
|
|
65cd34c5d7 | ||
|
|
5352678576 | ||
|
|
a7d06f400c | ||
|
|
b1a1f8ea8f | ||
|
|
f807dc157e | ||
|
|
97accc0ece | ||
|
|
76a7f36400 | ||
|
|
0c2dc87d9e | ||
|
|
020f7150aa | ||
|
|
3af1e17284 | ||
|
|
acd3d84298 | ||
|
|
7337efbfe4 | ||
|
|
3c53b78720 | ||
|
|
bb02834692 | ||
|
|
3e1cabc338 |
15
generate-index
Executable file
15
generate-index
Executable file
@@ -0,0 +1,15 @@
|
||||
#!/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)
|
||||
229
index.html.in
Normal file
229
index.html.in
Normal file
@@ -0,0 +1,229 @@
|
||||
<!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>The program can be told not to overwrite existing files using the -w or
|
||||
--no-overwrites option.</li>
|
||||
|
||||
<li>For YouTube, you can also use the URL of a playlist, and it will download
|
||||
all the videos in that playlist.</li>
|
||||
|
||||
<li>For YouTube, you can also use the special word <em>ytsearch</em> to
|
||||
download search results. With <em>ytsearch</em> it will download the
|
||||
first search result. With <em>ytsearchN</em>, where N is a number, it
|
||||
will download the first N results. With <em>ytsearchall</em> it will
|
||||
download every result for that search. In most systems you'll need to
|
||||
use quotes for multiple words. Example: <em>youtube-dl "ytsearch3:cute
|
||||
kittens"</em>.
|
||||
|
||||
<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>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 id="otpl">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>Danny Colligan: YouTube search InfoExtractor, ideas and patches.</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>
|
||||
528
youtube-dl
528
youtube-dl
@@ -1,9 +1,11 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
# Author: Ricardo Garcia Gonzalez
|
||||
# Author: Danny Colligan
|
||||
# License: Public domain code
|
||||
import htmlentitydefs
|
||||
import httplib
|
||||
import locale
|
||||
import math
|
||||
import netrc
|
||||
import os
|
||||
@@ -17,7 +19,7 @@ import urllib
|
||||
import urllib2
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
|
||||
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
||||
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
|
||||
'Accept-Language': 'en-us,en;q=0.5',
|
||||
@@ -42,6 +44,14 @@ class SameFileError(Exception):
|
||||
"""
|
||||
pass
|
||||
|
||||
class PostProcessingError(Exception):
|
||||
"""Post Processing exception.
|
||||
|
||||
This exception may be raised by PostProcessor's .run() method to
|
||||
indicate an error in the postprocessing task.
|
||||
"""
|
||||
pass
|
||||
|
||||
class FileDownloader(object):
|
||||
"""File Downloader class.
|
||||
|
||||
@@ -78,14 +88,18 @@ class FileDownloader(object):
|
||||
format: Video format code.
|
||||
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
|
||||
_ies = []
|
||||
_pps = []
|
||||
|
||||
def __init__(self, params):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
self._ies = []
|
||||
self._pps = []
|
||||
self.set_params(params)
|
||||
|
||||
@staticmethod
|
||||
@@ -93,6 +107,7 @@ class FileDownloader(object):
|
||||
"""Create directory components in filename. Similar to Unix "mkdir -p"."""
|
||||
components = filename.split(os.sep)
|
||||
aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
|
||||
aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
|
||||
for dir in aggregate:
|
||||
if not os.path.exists(dir):
|
||||
os.mkdir(dir)
|
||||
@@ -149,6 +164,16 @@ class FileDownloader(object):
|
||||
return int(new_min)
|
||||
return int(rate)
|
||||
|
||||
@staticmethod
|
||||
def parse_bytes(bytestr):
|
||||
"""Parse a string indicating a byte quantity into a long integer."""
|
||||
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
|
||||
if matchobj is None:
|
||||
return None
|
||||
number = float(matchobj.group(1))
|
||||
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
|
||||
return long(round(number * multiplier))
|
||||
|
||||
def set_params(self, params):
|
||||
"""Sets parameters."""
|
||||
if type(params) != dict:
|
||||
@@ -164,15 +189,20 @@ class FileDownloader(object):
|
||||
self._ies.append(ie)
|
||||
ie.set_downloader(self)
|
||||
|
||||
def add_post_processor(self, pp):
|
||||
"""Add a PostProcessor object to the end of the chain."""
|
||||
self._pps.append(pp)
|
||||
pp.set_downloader(self)
|
||||
|
||||
def to_stdout(self, message, skip_eol=False):
|
||||
"""Print message to stdout if not in quiet mode."""
|
||||
if not self._params.get('quiet', False):
|
||||
sys.stdout.write('%s%s' % (message, ['\n', ''][skip_eol]))
|
||||
print u'%s%s' % (message, [u'\n', u''][skip_eol]),
|
||||
sys.stdout.flush()
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
sys.stderr.write('%s\n' % message)
|
||||
print >>sys.stderr, message
|
||||
|
||||
def fixed_template(self):
|
||||
"""Checks if the output template is fixed."""
|
||||
@@ -193,18 +223,31 @@ class FileDownloader(object):
|
||||
raise DownloadError(message)
|
||||
return 1
|
||||
|
||||
def slow_down(self, start_time, byte_counter):
|
||||
"""Sleep if the download speed is over the rate limit."""
|
||||
rate_limit = self._params.get('ratelimit', None)
|
||||
if rate_limit is None or byte_counter == 0:
|
||||
return
|
||||
now = time.time()
|
||||
elapsed = now - start_time
|
||||
if elapsed <= 0.0:
|
||||
return
|
||||
speed = float(byte_counter) / elapsed
|
||||
if speed > rate_limit:
|
||||
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
|
||||
|
||||
def report_destination(self, filename):
|
||||
"""Report destination filename."""
|
||||
self.to_stdout('[download] Destination: %s' % filename)
|
||||
self.to_stdout(u'[download] Destination: %s' % filename)
|
||||
|
||||
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
||||
"""Report download progress."""
|
||||
self.to_stdout('\r[download] %s of %s at %s ETA %s' %
|
||||
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
|
||||
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
||||
|
||||
def report_finish(self):
|
||||
"""Report download finished."""
|
||||
self.to_stdout('')
|
||||
self.to_stdout(u'')
|
||||
|
||||
def download(self, url_list):
|
||||
"""Download a given list of URLs."""
|
||||
@@ -228,7 +271,6 @@ class FileDownloader(object):
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
|
||||
for result in results:
|
||||
|
||||
# Forced printings
|
||||
if self._params.get('forcetitle', False):
|
||||
print result['title']
|
||||
@@ -243,7 +285,10 @@ class FileDownloader(object):
|
||||
filename = self._params['outtmpl'] % result
|
||||
self.report_destination(filename)
|
||||
except (ValueError, KeyError), err:
|
||||
retcode = self.trouble('ERROR: invalid output template: %s' % str(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)
|
||||
@@ -264,11 +309,26 @@ class FileDownloader(object):
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
retcode = self.trouble('ERROR: unable to download video data: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
self.post_process(filename, result)
|
||||
except (PostProcessingError), err:
|
||||
retcode = self.trouble('ERROR: postprocessing: %s' % str(err))
|
||||
continue
|
||||
|
||||
break
|
||||
if not suitable_found:
|
||||
retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
|
||||
|
||||
return retcode
|
||||
|
||||
def post_process(self, filename, ie_info):
|
||||
"""Run the postprocessing chain on the given file."""
|
||||
info = dict(ie_info)
|
||||
info['filepath'] = filename
|
||||
for pp in self._pps:
|
||||
info = pp.run(info)
|
||||
if info is None:
|
||||
break
|
||||
|
||||
def _do_download(self, stream, url):
|
||||
request = urllib2.Request(url, None, std_headers)
|
||||
@@ -296,6 +356,9 @@ class FileDownloader(object):
|
||||
stream.write(data_block)
|
||||
block_size = self.best_block_size(after - before, data_block_len)
|
||||
|
||||
# Apply rate limit
|
||||
self.slow_down(start, byte_counter)
|
||||
|
||||
self.report_finish()
|
||||
if data_len is not None and str(byte_counter) != data_len:
|
||||
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
||||
@@ -335,7 +398,7 @@ class InfoExtractor(object):
|
||||
@staticmethod
|
||||
def suitable(url):
|
||||
"""Receives a URL and returns True if suitable for this IE."""
|
||||
return True
|
||||
return False
|
||||
|
||||
def initialize(self):
|
||||
"""Initializes an instance (authentication, etc)."""
|
||||
@@ -359,7 +422,7 @@ class InfoExtractor(object):
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
sys.stderr.write('%s\n' % message)
|
||||
print >>sys.stderr, message
|
||||
|
||||
def _real_initialize(self):
|
||||
"""Real initialization process. Redefine in subclasses."""
|
||||
@@ -372,29 +435,39 @@ class InfoExtractor(object):
|
||||
class YoutubeIE(InfoExtractor):
|
||||
"""Information extractor for youtube.com."""
|
||||
|
||||
_LOGIN_URL = 'http://www.youtube.com/login?next=/'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
|
||||
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
|
||||
_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
|
||||
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
||||
_NETRC_MACHINE = 'youtube'
|
||||
|
||||
@staticmethod
|
||||
def suitable(url):
|
||||
return (re.match(YoutubeIE._VALID_URL, url) is not None)
|
||||
|
||||
def report_lang(self):
|
||||
"""Report attempt to set language."""
|
||||
self.to_stdout(u'[youtube] Setting language')
|
||||
|
||||
def report_login(self):
|
||||
"""Report attempt to log in."""
|
||||
self.to_stdout('[youtube] Logging in')
|
||||
self.to_stdout(u'[youtube] Logging in')
|
||||
|
||||
def report_age_confirmation(self):
|
||||
"""Report attempt to confirm age."""
|
||||
self.to_stdout('[youtube] Confirming age')
|
||||
self.to_stdout(u'[youtube] Confirming age')
|
||||
|
||||
def report_webpage_download(self, video_id):
|
||||
"""Report attempt to download webpage."""
|
||||
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
|
||||
self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
|
||||
|
||||
def report_information_extraction(self, video_id):
|
||||
"""Report attempt to extract video information."""
|
||||
self.to_stdout('[youtube] %s: Extracting video information' % video_id)
|
||||
self.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
|
||||
|
||||
def report_video_url(self, video_id, video_real_url):
|
||||
"""Report extracted video URL."""
|
||||
self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||
self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||
|
||||
def _real_initialize(self):
|
||||
if self._downloader is None:
|
||||
@@ -417,13 +490,22 @@ class YoutubeIE(InfoExtractor):
|
||||
else:
|
||||
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
|
||||
except (IOError, netrc.NetrcParseError), err:
|
||||
self.to_stderr('WARNING: parsing .netrc: %s' % str(err))
|
||||
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)
|
||||
try:
|
||||
self.report_lang()
|
||||
urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
|
||||
return
|
||||
|
||||
# Log in
|
||||
login_form = {
|
||||
'current_form': 'loginForm',
|
||||
@@ -437,10 +519,10 @@ class YoutubeIE(InfoExtractor):
|
||||
self.report_login()
|
||||
login_results = urllib2.urlopen(request).read()
|
||||
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
|
||||
self.to_stderr('WARNING: unable to log in: bad username or password')
|
||||
self.to_stderr(u'WARNING: unable to log in: bad username or password')
|
||||
return
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('WARNING: unable to log in: %s' % str(err))
|
||||
self.to_stderr(u'WARNING: unable to log in: %s' % str(err))
|
||||
return
|
||||
|
||||
# Confirm age
|
||||
@@ -453,14 +535,14 @@ class YoutubeIE(InfoExtractor):
|
||||
self.report_age_confirmation()
|
||||
age_results = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
|
||||
self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract video id from URL
|
||||
mobj = re.match(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$', url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: invalid URL: %s' % url)
|
||||
self.to_stderr(u'ERROR: invalid URL: %s' % url)
|
||||
return [None]
|
||||
video_id = mobj.group(2)
|
||||
|
||||
@@ -474,7 +556,7 @@ class YoutubeIE(InfoExtractor):
|
||||
video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
|
||||
|
||||
# Normalize URL, including format
|
||||
normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id
|
||||
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
|
||||
if format_param is not None:
|
||||
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
||||
request = urllib2.Request(normalized_url, None, std_headers)
|
||||
@@ -482,14 +564,14 @@ class YoutubeIE(InfoExtractor):
|
||||
self.report_webpage_download(video_id)
|
||||
video_webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('ERROR: unable to download video webpage: %s' % str(err))
|
||||
self.to_stderr(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return [None]
|
||||
self.report_information_extraction(video_id)
|
||||
|
||||
# "t" param
|
||||
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract "t" parameter')
|
||||
self.to_stderr(u'ERROR: unable to extract "t" parameter')
|
||||
return [None]
|
||||
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
|
||||
if format_param is not None:
|
||||
@@ -497,16 +579,16 @@ class YoutubeIE(InfoExtractor):
|
||||
self.report_video_url(video_id, video_real_url)
|
||||
|
||||
# uploader
|
||||
mobj = re.search(r'More From: ([^<]*)<', video_webpage)
|
||||
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract uploader nickname')
|
||||
self.to_stderr(u'ERROR: unable to extract uploader nickname')
|
||||
return [None]
|
||||
video_uploader = mobj.group(1)
|
||||
|
||||
# title
|
||||
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract video title')
|
||||
self.to_stderr(u'ERROR: unable to extract video title')
|
||||
return [None]
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
|
||||
@@ -518,14 +600,333 @@ class YoutubeIE(InfoExtractor):
|
||||
|
||||
# Return information
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': video_real_url,
|
||||
'uploader': video_uploader,
|
||||
'id': video_id.decode('utf-8'),
|
||||
'url': video_real_url.decode('utf-8'),
|
||||
'uploader': video_uploader.decode('utf-8'),
|
||||
'title': video_title,
|
||||
'stitle': simple_title,
|
||||
'ext': video_extension,
|
||||
'ext': video_extension.decode('utf-8'),
|
||||
}]
|
||||
|
||||
class MetacafeIE(InfoExtractor):
|
||||
"""Information Extractor for metacafe.com."""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
|
||||
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
|
||||
_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(MetacafeIE._VALID_URL, url) is not None)
|
||||
|
||||
def report_disclaimer(self):
|
||||
"""Report disclaimer retrieval."""
|
||||
self.to_stdout(u'[metacafe] Retrieving disclaimer')
|
||||
|
||||
def report_age_confirmation(self):
|
||||
"""Report attempt to confirm age."""
|
||||
self.to_stdout(u'[metacafe] Confirming age')
|
||||
|
||||
def report_download_webpage(self, video_id):
|
||||
"""Report webpage download."""
|
||||
self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
# Retrieve disclaimer
|
||||
request = urllib2.Request(self._DISCLAIMER, None, std_headers)
|
||||
try:
|
||||
self.report_disclaimer()
|
||||
disclaimer = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
|
||||
return
|
||||
|
||||
# Confirm age
|
||||
disclaimer_form = {
|
||||
'filters': '0',
|
||||
'submit': "Continue - I'm over 18",
|
||||
}
|
||||
request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
|
||||
try:
|
||||
self.report_age_confirmation()
|
||||
disclaimer = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id and simplified title from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: invalid URL: %s' % url)
|
||||
return [None]
|
||||
|
||||
video_id = mobj.group(1)
|
||||
|
||||
# Check if video comes from YouTube
|
||||
mobj2 = re.match(r'^yt-(.*)$', video_id)
|
||||
if mobj2 is not None:
|
||||
return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
|
||||
|
||||
simple_title = mobj.group(2).decode('utf-8')
|
||||
video_extension = 'flv'
|
||||
|
||||
# Retrieve video webpage to extract further information
|
||||
request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
|
||||
try:
|
||||
self.report_download_webpage(video_id)
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err))
|
||||
return [None]
|
||||
|
||||
# Extract URL, uploader and title from webpage
|
||||
self.report_extraction(video_id)
|
||||
mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract media URL')
|
||||
return [None]
|
||||
mediaURL = mobj.group(1).replace('\\', '')
|
||||
|
||||
mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract gdaKey')
|
||||
return [None]
|
||||
gdaKey = mobj.group(1)
|
||||
|
||||
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
|
||||
|
||||
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract title')
|
||||
return [None]
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
|
||||
mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract uploader nickname')
|
||||
return [None]
|
||||
video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
|
||||
|
||||
# Return information
|
||||
return [{
|
||||
'id': video_id.decode('utf-8'),
|
||||
'url': video_url.decode('utf-8'),
|
||||
'uploader': video_uploader.decode('utf-8'),
|
||||
'title': video_title,
|
||||
'stitle': simple_title,
|
||||
'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."""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
|
||||
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
||||
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
|
||||
_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(YoutubePlaylistIE._VALID_URL, url) is not None)
|
||||
|
||||
def report_download_page(self, playlist_id, pagenum):
|
||||
"""Report attempt to download playlist page with given number."""
|
||||
self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
|
||||
|
||||
def _real_initialize(self):
|
||||
self._youtube_ie.initialize()
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract playlist id
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: invalid url: %s' % url)
|
||||
return [None]
|
||||
|
||||
# Download playlist pages
|
||||
playlist_id = mobj.group(1)
|
||||
video_ids = []
|
||||
pagenum = 1
|
||||
|
||||
while True:
|
||||
self.report_download_page(playlist_id, pagenum)
|
||||
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), 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
|
||||
ids_in_page = []
|
||||
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
|
||||
if mobj.group(1) not in ids_in_page:
|
||||
ids_in_page.append(mobj.group(1))
|
||||
video_ids.extend(ids_in_page)
|
||||
|
||||
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
|
||||
break
|
||||
pagenum = pagenum + 1
|
||||
|
||||
information = []
|
||||
for id in video_ids:
|
||||
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
|
||||
return information
|
||||
|
||||
class PostProcessor(object):
|
||||
"""Post Processor class.
|
||||
|
||||
PostProcessor objects can be added to downloaders with their
|
||||
add_post_processor() method. When the downloader has finished a
|
||||
successful download, it will take its internal chain of PostProcessors
|
||||
and start calling the run() method on each one of them, first with
|
||||
an initial argument and then with the returned value of the previous
|
||||
PostProcessor.
|
||||
|
||||
The chain will be stopped if one of them ever returns None or the end
|
||||
of the chain is reached.
|
||||
|
||||
PostProcessor objects follow a "mutual registration" process similar
|
||||
to InfoExtractor objects.
|
||||
"""
|
||||
|
||||
_downloader = None
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
self._downloader = downloader
|
||||
|
||||
def to_stdout(self, message):
|
||||
"""Print message to stdout if downloader is not in quiet mode."""
|
||||
if self._downloader is None or not self._downloader.get_params().get('quiet', False):
|
||||
print message
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
print >>sys.stderr, message
|
||||
|
||||
def set_downloader(self, downloader):
|
||||
"""Sets the downloader for this PP."""
|
||||
self._downloader = downloader
|
||||
|
||||
def run(self, information):
|
||||
"""Run the PostProcessor.
|
||||
|
||||
The "information" argument is a dictionary like the ones
|
||||
returned by InfoExtractors. The only difference is that this
|
||||
one has an extra field called "filepath" that points to the
|
||||
downloaded file.
|
||||
|
||||
When this method returns None, the postprocessing chain is
|
||||
stopped. However, this method may return an information
|
||||
dictionary that will be passed to the next postprocessing
|
||||
object in the chain. It can be the one it received after
|
||||
changing some fields.
|
||||
|
||||
In addition, this method may raise a PostProcessingError
|
||||
exception that will be taken into account by the downloader
|
||||
it was called from.
|
||||
"""
|
||||
return information # by default, do nothing
|
||||
|
||||
### MAIN PROGRAM ###
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
# Modules needed only when running the main program
|
||||
@@ -540,7 +941,7 @@ if __name__ == '__main__':
|
||||
# Parse command line
|
||||
parser = optparse.OptionParser(
|
||||
usage='Usage: %prog [options] url...',
|
||||
version='2008.07.22',
|
||||
version='2009.02.07',
|
||||
conflict_handler='resolve',
|
||||
)
|
||||
parser.add_option('-h', '--help',
|
||||
@@ -575,26 +976,52 @@ if __name__ == '__main__':
|
||||
action='store_const', dest='format', help='alias for -f 17', const='17')
|
||||
parser.add_option('-i', '--ignore-errors',
|
||||
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
||||
parser.add_option('-r', '--rate-limit',
|
||||
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
|
||||
batchurls = []
|
||||
if opts.batchfile is not None:
|
||||
try:
|
||||
batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
|
||||
except IOError:
|
||||
sys.exit(u'ERROR: batch file could not be read')
|
||||
all_urls = batchurls + args
|
||||
|
||||
# Conflicting, missing and erroneous options
|
||||
if len(args) < 1:
|
||||
sys.exit('ERROR: you must provide at least one URL')
|
||||
if len(all_urls) < 1:
|
||||
sys.exit(u'ERROR: you must provide at least one URL')
|
||||
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
||||
sys.exit('ERROR: using .netrc conflicts with giving username/password')
|
||||
sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
|
||||
if opts.password is not None and opts.username is None:
|
||||
sys.exit('ERROR: account username missing')
|
||||
sys.exit(u'ERROR: account username missing')
|
||||
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
|
||||
sys.exit('ERROR: using output template conflicts with using title or literal title')
|
||||
sys.exit(u'ERROR: using output template conflicts with using title or literal title')
|
||||
if opts.usetitle and opts.useliteral:
|
||||
sys.exit('ERROR: using title conflicts with using literal title')
|
||||
sys.exit(u'ERROR: using title conflicts with using literal title')
|
||||
if opts.username is not None and opts.password is None:
|
||||
opts.password = getpass.getpass('Type account password and press return:')
|
||||
opts.password = getpass.getpass(u'Type account password and press return:')
|
||||
if opts.ratelimit is not None:
|
||||
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
|
||||
if numeric_limit is None:
|
||||
sys.exit(u'ERROR: invalid rate limit specified')
|
||||
opts.ratelimit = numeric_limit
|
||||
|
||||
# Information extractors
|
||||
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]
|
||||
if charset is None:
|
||||
charset = 'ascii'
|
||||
fd = FileDownloader({
|
||||
'usenetrc': opts.usenetrc,
|
||||
'username': opts.username,
|
||||
@@ -604,19 +1031,24 @@ if __name__ == '__main__':
|
||||
'forcetitle': opts.gettitle,
|
||||
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
|
||||
'format': opts.format,
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl)
|
||||
or (opts.usetitle and '%(stitle)s-%(id)s.%(ext)s')
|
||||
or (opts.useliteral and '%(title)s-%(id)s.%(ext)s')
|
||||
or '%(id)s.%(ext)s'),
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
|
||||
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
|
||||
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
|
||||
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)
|
||||
retcode = fd.download(args)
|
||||
retcode = fd.download(all_urls)
|
||||
sys.exit(retcode)
|
||||
|
||||
except DownloadError:
|
||||
sys.exit(1)
|
||||
except SameFileError:
|
||||
sys.exit('ERROR: fixed output name but more than one file to download')
|
||||
sys.exit(u'ERROR: fixed output name but more than one file to download')
|
||||
except KeyboardInterrupt:
|
||||
sys.exit('\nERROR: Interrupted by user')
|
||||
sys.exit(u'\nERROR: Interrupted by user')
|
||||
|
||||
Reference in New Issue
Block a user