Compare commits
28 Commits
2009.02.07
...
2009.04.25
| Author | SHA1 | Date | |
|---|---|---|---|
|
27c3383e2d | ||
|
|
dbccb6cd84 | ||
|
|
98164eb3b9 | ||
|
|
2851b2ca18 | ||
|
|
6f21f68629 | ||
|
|
147753eb33 | ||
|
|
3aaf887e98 | ||
|
|
9bf386d74b | ||
|
|
2f4d18a9f7 | ||
|
|
b0eddb2eb4 | ||
|
|
9cee6d9035 | ||
|
|
c8619e0163 | ||
|
257453b92b | ||
|
fd9288c315 | ||
|
|
1db4ff6054 | ||
|
|
763826cf2c | ||
|
|
af6a92f4c9 | ||
|
|
f995f7127c | ||
|
|
e54930cf71 | ||
|
|
c6b311c524 | ||
|
|
79e75f66c8 | ||
|
|
053e77d6ed | ||
|
|
d0a9affb46 | ||
|
|
76800042fd | ||
|
|
7ab2043c9c | ||
|
|
3e703dd1cd | ||
|
|
cc10940385 | ||
|
|
5121ef2071 |
@@ -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)
|
||||
229
index.html.in
229
index.html.in
@@ -1,229 +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>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>
|
||||
420
youtube-dl
420
youtube-dl
@@ -18,8 +18,8 @@ import time
|
||||
import urllib
|
||||
import urllib2
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
|
||||
'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',
|
||||
@@ -65,16 +65,17 @@ class FileDownloader(object):
|
||||
For this, file downloader objects have a method that allows
|
||||
InfoExtractors to be registered in a given order. When it is passed
|
||||
a URL, the file downloader handles it to the first InfoExtractor it
|
||||
finds that reports being able to handle it. The InfoExtractor returns
|
||||
all the information to the FileDownloader and the latter downloads the
|
||||
file or does whatever it's instructed to do.
|
||||
finds that reports being able to handle it. The InfoExtractor extracts
|
||||
all the information about the video or videos the URL refers to, and
|
||||
asks the FileDownloader to process the video information, possibly
|
||||
downloading the video.
|
||||
|
||||
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:
|
||||
|
||||
@@ -92,15 +93,17 @@ class FileDownloader(object):
|
||||
nooverwrites: Prevent overwriting files.
|
||||
"""
|
||||
|
||||
_params = None
|
||||
params = None
|
||||
_ies = []
|
||||
_pps = []
|
||||
_download_retcode = None
|
||||
|
||||
def __init__(self, params):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
self._ies = []
|
||||
self._pps = []
|
||||
self.set_params(params)
|
||||
self._download_retcode = 0
|
||||
self.params = params
|
||||
|
||||
@staticmethod
|
||||
def pmkdir(filename):
|
||||
@@ -144,7 +147,7 @@ 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
|
||||
@@ -174,16 +177,6 @@ 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)
|
||||
@@ -196,8 +189,8 @@ 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):
|
||||
print u'%s%s' % (message, [u'\n', u''][skip_eol]),
|
||||
if not self.params.get('quiet', False):
|
||||
print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()),
|
||||
sys.stdout.flush()
|
||||
|
||||
def to_stderr(self, message):
|
||||
@@ -206,26 +199,24 @@ 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.
|
||||
|
||||
Depending on if the downloader has been configured to ignore
|
||||
download errors or not, this method may throw an exception or
|
||||
not when errors are found, after printing the message. If it
|
||||
doesn't raise, it returns an error code suitable to be returned
|
||||
later as a program exit code to indicate error.
|
||||
not when errors are found, after printing the message.
|
||||
"""
|
||||
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
|
||||
self._download_retcode = 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()
|
||||
@@ -249,77 +240,78 @@ class FileDownloader(object):
|
||||
"""Report download finished."""
|
||||
self.to_stdout(u'')
|
||||
|
||||
def process_info(self, info_dict):
|
||||
"""Process a single dictionary returned by an InfoExtractor."""
|
||||
# Forced printings
|
||||
if self.params.get('forcetitle', False):
|
||||
print info_dict['title'].encode(locale.getpreferredencoding())
|
||||
if self.params.get('forceurl', False):
|
||||
print info_dict['url'].encode(locale.getpreferredencoding())
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self.params.get('simulate', False):
|
||||
return
|
||||
|
||||
try:
|
||||
filename = self.params['outtmpl'] % info_dict
|
||||
self.report_destination(filename)
|
||||
except (ValueError, KeyError), err:
|
||||
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
|
||||
if self.params['nooverwrites'] and os.path.exists(filename):
|
||||
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
|
||||
return
|
||||
try:
|
||||
self.pmkdir(filename)
|
||||
except (OSError, IOError), err:
|
||||
self.trouble('ERROR: unable to create directories: %s' % str(err))
|
||||
return
|
||||
try:
|
||||
outstream = open(filename, 'wb')
|
||||
except (OSError, IOError), err:
|
||||
self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
||||
return
|
||||
try:
|
||||
self._do_download(outstream, info_dict['url'])
|
||||
outstream.close()
|
||||
except (OSError, IOError), err:
|
||||
self.trouble('ERROR: unable to write video data: %s' % str(err))
|
||||
return
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.trouble('ERROR: unable to download video data: %s' % str(err))
|
||||
return
|
||||
try:
|
||||
self.post_process(filename, info_dict)
|
||||
except (PostProcessingError), err:
|
||||
self.trouble('ERROR: postprocessing: %s' % str(err))
|
||||
return
|
||||
|
||||
return
|
||||
|
||||
def download(self, url_list):
|
||||
"""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
|
||||
for ie in self._ies:
|
||||
# Go to next InfoExtractor if not suitable
|
||||
if not ie.suitable(url):
|
||||
continue
|
||||
|
||||
# Suitable InfoExtractor found
|
||||
suitable_found = True
|
||||
all_results = ie.extract(url)
|
||||
results = [x for x in all_results if x is not None]
|
||||
if len(results) != len(all_results):
|
||||
retcode = self.trouble()
|
||||
|
||||
if len(results) > 1 and self.fixed_template():
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
|
||||
for result in results:
|
||||
# Forced printings
|
||||
if self._params.get('forcetitle', False):
|
||||
print result['title']
|
||||
if self._params.get('forceurl', False):
|
||||
print result['url']
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self._params.get('simulate', False):
|
||||
continue
|
||||
|
||||
try:
|
||||
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:
|
||||
retcode = self.trouble('ERROR: unable to create directories: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
outstream = open(filename, 'wb')
|
||||
except (OSError, IOError), err:
|
||||
retcode = self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
self._do_download(outstream, result['url'])
|
||||
outstream.close()
|
||||
except (OSError, IOError), err:
|
||||
retcode = self.trouble('ERROR: unable to write video data: %s' % str(err))
|
||||
continue
|
||||
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
|
||||
# Extract information from URL and process it
|
||||
ie.extract(url)
|
||||
|
||||
# Suitable InfoExtractor had been found; go to next URL
|
||||
break
|
||||
if not suitable_found:
|
||||
retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
|
||||
|
||||
return retcode
|
||||
if not suitable_found:
|
||||
self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
|
||||
|
||||
return self._download_retcode
|
||||
|
||||
def post_process(self, filename, ie_info):
|
||||
"""Run the postprocessing chain on the given file."""
|
||||
@@ -369,9 +361,10 @@ class InfoExtractor(object):
|
||||
Information extractors are the classes that, given a URL, extract
|
||||
information from the video (or videos) the URL refers to. This
|
||||
information includes the real video URL, the video title and simplified
|
||||
title, author and others. It is returned in a list of dictionaries when
|
||||
calling its extract() method. It is a list because a URL can refer to
|
||||
more than one video (think of playlists). The dictionaries must include
|
||||
title, author and others. The information is stored in a dictionary
|
||||
which is then passed to the FileDownloader. The FileDownloader
|
||||
processes this information possibly downloading the video to the file
|
||||
system, among other possible outcomes. The dictionaries must include
|
||||
the following fields:
|
||||
|
||||
id: Video identifier.
|
||||
@@ -415,15 +408,6 @@ class InfoExtractor(object):
|
||||
"""Sets the downloader for this IE."""
|
||||
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 _real_initialize(self):
|
||||
"""Real initialization process. Redefine in subclasses."""
|
||||
pass
|
||||
@@ -445,37 +429,60 @@ class YoutubeIE(InfoExtractor):
|
||||
def suitable(url):
|
||||
return (re.match(YoutubeIE._VALID_URL, url) is not None)
|
||||
|
||||
@staticmethod
|
||||
def htmlentity_transform(matchobj):
|
||||
"""Transforms an HTML entity to a Unicode character."""
|
||||
entity = matchobj.group(1)
|
||||
|
||||
# Known non-numeric HTML entity
|
||||
if entity in htmlentitydefs.name2codepoint:
|
||||
return unichr(htmlentitydefs.name2codepoint[entity])
|
||||
|
||||
# Unicode character
|
||||
mobj = re.match(ur'(?u)#(x?\d+)', entity)
|
||||
if mobj is not None:
|
||||
numstr = mobj.group(1)
|
||||
if numstr.startswith(u'x'):
|
||||
base = 16
|
||||
numstr = u'0%s' % numstr
|
||||
else:
|
||||
base = 10
|
||||
return unichr(long(numstr, base))
|
||||
|
||||
# Unknown entity in name, return its literal representation
|
||||
return (u'&%s;' % entity)
|
||||
|
||||
def report_lang(self):
|
||||
"""Report attempt to set language."""
|
||||
self.to_stdout(u'[youtube] Setting language')
|
||||
self._downloader.to_stdout(u'[youtube] Setting language')
|
||||
|
||||
def report_login(self):
|
||||
"""Report attempt to log in."""
|
||||
self.to_stdout(u'[youtube] Logging in')
|
||||
self._downloader.to_stdout(u'[youtube] Logging in')
|
||||
|
||||
def report_age_confirmation(self):
|
||||
"""Report attempt to confirm age."""
|
||||
self.to_stdout(u'[youtube] Confirming age')
|
||||
self._downloader.to_stdout(u'[youtube] Confirming age')
|
||||
|
||||
def report_webpage_download(self, video_id):
|
||||
"""Report attempt to download webpage."""
|
||||
self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
|
||||
self._downloader.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(u'[youtube] %s: Extracting video information' % video_id)
|
||||
self._downloader.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(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||
|
||||
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||
|
||||
def _real_initialize(self):
|
||||
if self._downloader is None:
|
||||
return
|
||||
|
||||
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:
|
||||
@@ -490,20 +497,20 @@ class YoutubeIE(InfoExtractor):
|
||||
else:
|
||||
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
|
||||
except (IOError, netrc.NetrcParseError), err:
|
||||
self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
|
||||
self._downloader.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()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
|
||||
self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
|
||||
return
|
||||
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
return
|
||||
|
||||
# Log in
|
||||
@@ -519,10 +526,10 @@ 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(u'WARNING: unable to log in: bad username or password')
|
||||
self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
|
||||
return
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'WARNING: unable to log in: %s' % str(err))
|
||||
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
|
||||
return
|
||||
|
||||
# Confirm age
|
||||
@@ -535,25 +542,29 @@ class YoutubeIE(InfoExtractor):
|
||||
self.report_age_confirmation()
|
||||
age_results = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
|
||||
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract video id from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: invalid URL: %s' % url)
|
||||
return [None]
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
video_id = mobj.group(2)
|
||||
|
||||
# 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&gl=US&hl=en' % video_id
|
||||
@@ -564,16 +575,16 @@ 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(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return [None]
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return
|
||||
self.report_information_extraction(video_id)
|
||||
|
||||
# "t" param
|
||||
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
||||
if mobj is None:
|
||||
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))
|
||||
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
|
||||
return
|
||||
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
|
||||
if format_param is not None:
|
||||
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
||||
self.report_video_url(video_id, video_real_url)
|
||||
@@ -581,38 +592,39 @@ class YoutubeIE(InfoExtractor):
|
||||
# uploader
|
||||
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract uploader nickname')
|
||||
return [None]
|
||||
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
||||
return
|
||||
video_uploader = mobj.group(1)
|
||||
|
||||
# title
|
||||
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract video title')
|
||||
return [None]
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
|
||||
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
|
||||
video_title = video_title.replace(os.sep, u'%')
|
||||
|
||||
# simplified title
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = simple_title.strip(ur'_')
|
||||
|
||||
# Return information
|
||||
return [{
|
||||
# Process video information
|
||||
self._downloader.process_info({
|
||||
'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.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/'
|
||||
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
|
||||
_youtube_ie = None
|
||||
|
||||
def __init__(self, youtube_ie, downloader=None):
|
||||
@@ -625,19 +637,19 @@ class MetacafeIE(InfoExtractor):
|
||||
|
||||
def report_disclaimer(self):
|
||||
"""Report disclaimer retrieval."""
|
||||
self.to_stdout(u'[metacafe] Retrieving disclaimer')
|
||||
self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
|
||||
|
||||
def report_age_confirmation(self):
|
||||
"""Report attempt to confirm age."""
|
||||
self.to_stdout(u'[metacafe] Confirming age')
|
||||
self._downloader.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)
|
||||
self._downloader.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)
|
||||
self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
# Retrieve disclaimer
|
||||
@@ -646,7 +658,7 @@ class MetacafeIE(InfoExtractor):
|
||||
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))
|
||||
self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
|
||||
return
|
||||
|
||||
# Confirm age
|
||||
@@ -654,27 +666,28 @@ class MetacafeIE(InfoExtractor):
|
||||
'filters': '0',
|
||||
'submit': "Continue - I'm over 18",
|
||||
}
|
||||
request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
|
||||
request = urllib2.Request(self._FILTER_POST, 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))
|
||||
self._downloader.trouble(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]
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
|
||||
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))
|
||||
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
|
||||
return
|
||||
|
||||
simple_title = mobj.group(2).decode('utf-8')
|
||||
video_extension = 'flv'
|
||||
@@ -685,46 +698,46 @@ class MetacafeIE(InfoExtractor):
|
||||
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]
|
||||
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
# Extract URL, uploader and title from webpage
|
||||
self.report_extraction(video_id)
|
||||
mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
|
||||
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('\\', '')
|
||||
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
||||
return
|
||||
mediaURL = urllib.unquote(mobj.group(1))
|
||||
|
||||
mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
|
||||
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr(u'ERROR: unable to extract gdaKey')
|
||||
return [None]
|
||||
self._downloader.trouble(u'ERROR: unable to extract gdaKey')
|
||||
return
|
||||
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]
|
||||
self._downloader.trouble(u'ERROR: unable to extract title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
|
||||
mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
|
||||
mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', 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))
|
||||
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
||||
return
|
||||
video_uploader = mobj.group(1)
|
||||
|
||||
# Return information
|
||||
return [{
|
||||
# Process video information
|
||||
self._downloader.process_info({
|
||||
'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):
|
||||
@@ -734,8 +747,9 @@ class YoutubeSearchIE(InfoExtractor):
|
||||
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
|
||||
_MORE_PAGES_INDICATOR = r'>Next</a>'
|
||||
_youtube_ie = None
|
||||
_max_youtube_results = 1000
|
||||
|
||||
def __init__(self, youtube_ie, downloader=None):
|
||||
def __init__(self, youtube_ie, downloader=None):
|
||||
InfoExtractor.__init__(self, downloader)
|
||||
self._youtube_ie = youtube_ie
|
||||
|
||||
@@ -745,7 +759,7 @@ class YoutubeSearchIE(InfoExtractor):
|
||||
|
||||
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))
|
||||
self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
|
||||
|
||||
def _real_initialize(self):
|
||||
self._youtube_ie.initialize()
|
||||
@@ -753,24 +767,31 @@ class YoutubeSearchIE(InfoExtractor):
|
||||
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]
|
||||
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
|
||||
return
|
||||
|
||||
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:
|
||||
if prefix == '':
|
||||
self._download_n_results(query, 1)
|
||||
return
|
||||
elif prefix == 'all':
|
||||
self._download_n_results(query, self._max_youtube_results)
|
||||
return
|
||||
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)
|
||||
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
|
||||
return
|
||||
elif n > self._max_youtube_results:
|
||||
self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
|
||||
n = self._max_youtube_results
|
||||
self._download_n_results(query, n)
|
||||
return
|
||||
except ValueError: # parsing prefix as int fails
|
||||
return self._download_n_results(query, 1)
|
||||
self._download_n_results(query, 1)
|
||||
return
|
||||
|
||||
def _download_n_results(self, query, n):
|
||||
"""Downloads a specified number of results for a query"""
|
||||
@@ -786,8 +807,8 @@ class YoutubeSearchIE(InfoExtractor):
|
||||
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]
|
||||
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
# Extract video identifiers
|
||||
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
|
||||
@@ -797,16 +818,14 @@ class YoutubeSearchIE(InfoExtractor):
|
||||
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
|
||||
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
||||
return
|
||||
|
||||
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
|
||||
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
||||
return
|
||||
|
||||
pagenum = pagenum + 1
|
||||
|
||||
@@ -829,7 +848,7 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
|
||||
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))
|
||||
self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
|
||||
|
||||
def _real_initialize(self):
|
||||
self._youtube_ie.initialize()
|
||||
@@ -838,8 +857,8 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
# 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]
|
||||
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
|
||||
return
|
||||
|
||||
# Download playlist pages
|
||||
playlist_id = mobj.group(1)
|
||||
@@ -852,8 +871,8 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
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]
|
||||
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
# Extract video identifiers
|
||||
ids_in_page = []
|
||||
@@ -866,10 +885,9 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
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
|
||||
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
||||
return
|
||||
|
||||
class PostProcessor(object):
|
||||
"""Post Processor class.
|
||||
@@ -893,15 +911,6 @@ class PostProcessor(object):
|
||||
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
|
||||
@@ -941,7 +950,7 @@ if __name__ == '__main__':
|
||||
# Parse command line
|
||||
parser = optparse.OptionParser(
|
||||
usage='Usage: %prog [options] url...',
|
||||
version='2009.02.07',
|
||||
version='2009.04.25',
|
||||
conflict_handler='resolve',
|
||||
)
|
||||
parser.add_option('-h', '--help',
|
||||
@@ -970,10 +979,10 @@ 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',
|
||||
@@ -1019,9 +1028,6 @@ if __name__ == '__main__':
|
||||
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,
|
||||
@@ -1031,7 +1037,7 @@ 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(charset))
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
|
||||
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'),
|
||||
|
||||
Reference in New Issue
Block a user