mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2025-08-02 18:39:51 -05:00
Compare commits
29 Commits
2008.08.09
...
2009.03.28
| Author | SHA1 | Date | |
|---|---|---|---|
|
c6b311c524 | ||
|
|
79e75f66c8 | ||
|
|
053e77d6ed | ||
|
|
d0a9affb46 | ||
|
|
76800042fd | ||
|
|
7ab2043c9c | ||
|
|
3e703dd1cd | ||
|
|
cc10940385 | ||
|
|
5121ef2071 | ||
|
|
fd20984889 | ||
|
|
111ae3695c | ||
|
|
0beeff4b3e | ||
|
|
64a6f26c5d | ||
|
|
a9633f1457 | ||
|
|
a20e4c2f96 | ||
|
|
d1536018a8 | ||
|
|
25af2bce3a | ||
|
|
d1580ed990 | ||
|
|
eb0d2909a8 | ||
|
|
ba72f8a5d1 | ||
|
|
c6fd0bb806 | ||
|
|
72ac78b8b0 | ||
|
|
240b737ebd | ||
|
|
27d98b6e25 | ||
|
|
5487aea5d8 | ||
|
|
9ca4851a00 | ||
|
|
1e9daf2a48 | ||
|
|
d853063955 | ||
|
|
2546e7679f |
@@ -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)
|
||||
212
index.html.in
212
index.html.in
@@ -1,212 +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 <em>Output template</em> 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><em>youtube-dl</em> can attempt to download the best quality version of
|
||||
a video by using the -b or --best-quality option.</li>
|
||||
|
||||
<li><em>youtube-dl</em> can attempt to download the mobile quality version of
|
||||
a video by using the -m or --mobile-version option.</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><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>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.</li>
|
||||
<li><em>ext</em>: The sequence will be replaced by the appropriate
|
||||
extension.</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>
|
||||
218
youtube-dl
218
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',
|
||||
@@ -69,10 +71,10 @@ class FileDownloader(object):
|
||||
|
||||
File downloaders accept a lot of parameters. In order not to saturate
|
||||
the object constructor with arguments, it receives a dictionary of
|
||||
options instead. These options are available through the get_params()
|
||||
method for the InfoExtractors to use. The FileDownloader also registers
|
||||
itself as the downloader in charge for the InfoExtractors that are
|
||||
added to it, so this is a "mutual registration".
|
||||
options instead. These options are available through the params
|
||||
attribute for the InfoExtractors to use. The FileDownloader also
|
||||
registers itself as the downloader in charge for the InfoExtractors
|
||||
that are added to it, so this is a "mutual registration".
|
||||
|
||||
Available options:
|
||||
|
||||
@@ -87,9 +89,10 @@ 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
|
||||
params = None
|
||||
_ies = []
|
||||
_pps = []
|
||||
|
||||
@@ -97,7 +100,7 @@ class FileDownloader(object):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
self._ies = []
|
||||
self._pps = []
|
||||
self.set_params(params)
|
||||
self.params = params
|
||||
|
||||
@staticmethod
|
||||
def pmkdir(filename):
|
||||
@@ -141,7 +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
|
||||
@@ -171,16 +174,6 @@ class FileDownloader(object):
|
||||
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:
|
||||
raise ValueError('params: dictionary expected')
|
||||
self._params = params
|
||||
|
||||
def get_params(self):
|
||||
"""Get parameters."""
|
||||
return self._params
|
||||
|
||||
def add_info_extractor(self, ie):
|
||||
"""Add an InfoExtractor object to the end of the list."""
|
||||
self._ies.append(ie)
|
||||
@@ -193,7 +186,7 @@ class FileDownloader(object):
|
||||
|
||||
def to_stdout(self, message, skip_eol=False):
|
||||
"""Print message to stdout if not in quiet mode."""
|
||||
if not self._params.get('quiet', False):
|
||||
if not self.params.get('quiet', False):
|
||||
print u'%s%s' % (message, [u'\n', u''][skip_eol]),
|
||||
sys.stdout.flush()
|
||||
|
||||
@@ -203,7 +196,7 @@ class FileDownloader(object):
|
||||
|
||||
def fixed_template(self):
|
||||
"""Checks if the output template is fixed."""
|
||||
return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None)
|
||||
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
|
||||
|
||||
def trouble(self, message=None):
|
||||
"""Determine action to take when a download problem appears.
|
||||
@@ -216,13 +209,13 @@ class FileDownloader(object):
|
||||
"""
|
||||
if message is not None:
|
||||
self.to_stderr(message)
|
||||
if not self._params.get('ignoreerrors', False):
|
||||
if not self.params.get('ignoreerrors', False):
|
||||
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)
|
||||
rate_limit = self.params.get('ratelimit', None)
|
||||
if rate_limit is None or byte_counter == 0:
|
||||
return
|
||||
now = time.time()
|
||||
@@ -250,7 +243,7 @@ class FileDownloader(object):
|
||||
"""Download a given list of URLs."""
|
||||
retcode = 0
|
||||
if len(url_list) > 1 and self.fixed_template():
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
raise SameFileError(self.params['outtmpl'])
|
||||
|
||||
for url in url_list:
|
||||
suitable_found = False
|
||||
@@ -265,25 +258,28 @@ class FileDownloader(object):
|
||||
retcode = self.trouble()
|
||||
|
||||
if len(results) > 1 and self.fixed_template():
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
raise SameFileError(self.params['outtmpl'])
|
||||
|
||||
for result in results:
|
||||
# Forced printings
|
||||
if self._params.get('forcetitle', False):
|
||||
if self.params.get('forcetitle', False):
|
||||
print result['title']
|
||||
if self._params.get('forceurl', False):
|
||||
if self.params.get('forceurl', False):
|
||||
print result['url']
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self._params.get('simulate', False):
|
||||
if self.params.get('simulate', False):
|
||||
continue
|
||||
|
||||
try:
|
||||
filename = self._params['outtmpl'] % result
|
||||
filename = self.params['outtmpl'] % result
|
||||
self.report_destination(filename)
|
||||
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:
|
||||
@@ -411,7 +407,7 @@ class InfoExtractor(object):
|
||||
|
||||
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):
|
||||
if self._downloader is None or not self._downloader.params.get('quiet', False):
|
||||
print message
|
||||
|
||||
def to_stderr(self, message):
|
||||
@@ -430,14 +426,19 @@ class YoutubeIE(InfoExtractor):
|
||||
"""Information extractor for youtube.com."""
|
||||
|
||||
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
|
||||
_LOGIN_URL = 'http://www.youtube.com/login?next=/'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
|
||||
_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(u'[youtube] Logging in')
|
||||
@@ -464,7 +465,7 @@ class YoutubeIE(InfoExtractor):
|
||||
|
||||
username = None
|
||||
password = None
|
||||
downloader_params = self._downloader.get_params()
|
||||
downloader_params = self._downloader.params
|
||||
|
||||
# Attempt to use provided username and password or .netrc data
|
||||
if downloader_params.get('username', None) is not None:
|
||||
@@ -482,6 +483,15 @@ class YoutubeIE(InfoExtractor):
|
||||
self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
|
||||
return
|
||||
|
||||
# Set language
|
||||
request = urllib2.Request(self._LANG_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
|
||||
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
return
|
||||
@@ -529,14 +539,18 @@ class YoutubeIE(InfoExtractor):
|
||||
# Downloader parameters
|
||||
format_param = None
|
||||
if self._downloader is not None:
|
||||
params = self._downloader.get_params()
|
||||
params = self._downloader.params
|
||||
format_param = params.get('format', None)
|
||||
|
||||
# Extension
|
||||
video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
|
||||
video_extension = {
|
||||
'17': '3gp',
|
||||
'18': 'mp4',
|
||||
'22': 'mp4',
|
||||
}.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)
|
||||
@@ -592,7 +606,7 @@ class MetacafeIE(InfoExtractor):
|
||||
"""Information Extractor for metacafe.com."""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
|
||||
_DISCLAIMER = 'http://www.metacafe.com/disclaimer'
|
||||
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
|
||||
_youtube_ie = None
|
||||
|
||||
def __init__(self, youtube_ie, downloader=None):
|
||||
@@ -631,10 +645,10 @@ class MetacafeIE(InfoExtractor):
|
||||
|
||||
# Confirm age
|
||||
disclaimer_form = {
|
||||
'allowAdultContent': '1',
|
||||
'filters': '0',
|
||||
'submit': "Continue - I'm over 18",
|
||||
}
|
||||
request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers)
|
||||
request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
|
||||
try:
|
||||
self.report_age_confirmation()
|
||||
disclaimer = urllib2.urlopen(request).read()
|
||||
@@ -684,7 +698,7 @@ class MetacafeIE(InfoExtractor):
|
||||
|
||||
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
|
||||
|
||||
mobj = re.search(r'(?im)<meta name="title" content="Metacafe - ([^"]+)"', webpage)
|
||||
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract title')
|
||||
return [None]
|
||||
@@ -706,11 +720,95 @@ 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."""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s'
|
||||
_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
|
||||
@@ -752,10 +850,11 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
return [None]
|
||||
|
||||
# Extract video identifiers
|
||||
ids_in_page = set()
|
||||
ids_in_page = []
|
||||
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
|
||||
ids_in_page.add(mobj.group(1))
|
||||
video_ids.extend(list(ids_in_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
|
||||
@@ -790,7 +889,7 @@ class PostProcessor(object):
|
||||
|
||||
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):
|
||||
if self._downloader is None or not self._downloader.params.get('quiet', False):
|
||||
print message
|
||||
|
||||
def to_stderr(self, message):
|
||||
@@ -836,7 +935,7 @@ if __name__ == '__main__':
|
||||
# Parse command line
|
||||
parser = optparse.OptionParser(
|
||||
usage='Usage: %prog [options] url...',
|
||||
version='2008.08.09',
|
||||
version='2009.03.28',
|
||||
conflict_handler='resolve',
|
||||
)
|
||||
parser.add_option('-h', '--help',
|
||||
@@ -865,18 +964,31 @@ if __name__ == '__main__':
|
||||
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
||||
parser.add_option('-f', '--format',
|
||||
dest='format', metavar='FMT', help='video format code')
|
||||
parser.add_option('-b', '--best-quality',
|
||||
action='store_const', dest='format', help='alias for -f 18', const='18')
|
||||
parser.add_option('-m', '--mobile-version',
|
||||
action='store_const', dest='format', help='alias for -f 17', const='17')
|
||||
parser.add_option('-d', '--high-def',
|
||||
action='store_const', dest='format', help='alias for -f 22', const='22')
|
||||
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:
|
||||
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(u'ERROR: using .netrc conflicts with giving username/password')
|
||||
@@ -898,8 +1010,12 @@ 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]
|
||||
if charset is None:
|
||||
charset = 'ascii'
|
||||
fd = FileDownloader({
|
||||
'usenetrc': opts.usenetrc,
|
||||
'username': opts.username,
|
||||
@@ -909,17 +1025,19 @@ 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.decode())
|
||||
'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:
|
||||
|
||||
Reference in New Issue
Block a user