yt-dlp/youtube-dl

563 lines
19 KiB
Plaintext
Raw Normal View History

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: Ricardo Garcia Gonzalez
# License: Public domain code
import htmlentitydefs
import httplib
import math
import netrc
import os
import os.path
import re
import socket
import string
import sys
import time
import urllib
import urllib2
std_headers = {
2008-07-22 07:55:32 +00:00
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
'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',
}
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
class FileDownloader(object):
"""File Downloader class.
File downloader objects are the ones responsible of downloading the
actual video file and writing it to disk if the user has requested
it, among some other tasks. In most cases there should be one per
program. As, given a video URL, the downloader doesn't know how to
extract all the needed information, task that InfoExtractors do, it
has to pass the URL to one of them.
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.
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".
Available options:
username: Username for authentication purposes.
password: Password for authentication purposes.
usenetrc: Use netrc for authentication instead.
quiet: Do not print messages to stdout.
forceurl: Force printing final URL.
forcetitle: Force printing title.
2008-07-21 21:58:16 +00:00
simulate: Do not download the video files.
format: Video format code.
outtmpl: Template for output names.
ignoreerrors: Do not stop on download errors.
"""
_params = None
_ies = []
def __init__(self, params):
2008-07-22 09:41:25 +00:00
"""Create a FileDownloader object with the given options."""
self._ies = []
self.set_params(params)
@staticmethod
def pmkdir(filename):
"""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))]
for dir in aggregate:
if not os.path.exists(dir):
os.mkdir(dir)
@staticmethod
def format_bytes(bytes):
if bytes is None:
return 'N/A'
if bytes == 0:
exponent = 0
else:
exponent = long(math.log(float(bytes), 1024.0))
suffix = 'bkMGTPEZY'[exponent]
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
@staticmethod
def calc_percent(byte_counter, data_len):
if data_len is None:
return '---.-%'
return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
@staticmethod
def calc_eta(start, now, total, current):
if total is None:
return '--:--'
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return '--:--'
rate = float(current) / dif
eta = long((float(total) - float(current)) / rate)
(eta_mins, eta_secs) = divmod(eta, 60)
if eta_mins > 99:
return '--:--'
return '%02d:%02d' % (eta_mins, eta_secs)
@staticmethod
def calc_speed(start, now, bytes):
dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond
return '%10s' % '---b/s'
return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return int(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return int(new_max)
if rate < new_min:
return int(new_min)
return int(rate)
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)
ie.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]))
sys.stdout.flush()
2008-07-21 22:07:07 +00:00
def to_stderr(self, message):
"""Print message to stderr."""
sys.stderr.write('%s\n' % message)
2008-07-22 07:45:49 +00:00
def fixed_template(self):
"""Checks if the output template is fixed."""
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 exit the program or
not when errors are found, after printing the message. If it
doesn't exit, it returns an error code suitable to be returned
later as a program exit code to indicate error.
"""
if message is not None:
self.to_stderr(message)
if not self._params.get('ignoreerrors', False):
sys.exit(1)
return 1
def download(self, url_list):
"""Download a given list of URLs."""
retcode = 0
2008-07-22 07:45:49 +00:00
if len(url_list) > 1 and self.fixed_template():
sys.exit('ERROR: fixed output name but more than one file to download')
for url in url_list:
suitable_found = False
for ie in self._ies:
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()
2008-07-22 07:45:49 +00:00
if len(results) > 1 and self.fixed_template():
sys.exit('ERROR: fixed output name but more than one file to download')
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
2008-07-22 07:21:43 +00:00
except (ValueError, KeyError), err:
retcode = self.trouble('ERROR: invalid output template: %s' % str(err))
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
break
if not suitable_found:
retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
return retcode
def _do_download(self, stream, url):
request = urllib2.Request(url, None, std_headers)
data = urllib2.urlopen(request)
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
speed_str = self.calc_speed(start, time.time(), byte_counter)
self.to_stdout('\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
before = time.time()
data_block = data.read(block_size)
after = time.time()
data_block_len = len(data_block)
if data_block_len == 0:
break
byte_counter += data_block_len
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
self.to_stdout('')
if data_len is not None and str(byte_counter) != data_len:
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
class InfoExtractor(object):
"""Information Extractor class.
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
the following fields:
id: Video identifier.
url: Final video URL.
uploader: Nickname of the video uploader.
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods, as well as the suitable() static method.
Probably, they should also be instantiated and added to the main
downloader.
"""
_ready = False
_downloader = None
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
self._ready = False
self.set_downloader(downloader)
@staticmethod
def suitable(url):
"""Receives a URL and returns True if suitable for this IE."""
return True
def initialize(self):
2008-07-22 09:41:25 +00:00
"""Initializes an instance (authentication, etc)."""
if not self._ready:
self._real_initialize()
self._ready = True
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
self.initialize()
return self._real_extract(url)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
self._downloader = downloader
def to_stdout(self, message):
2008-07-22 09:41:25 +00:00
"""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):
2008-07-22 09:41:25 +00:00
"""Print message to stderr."""
sys.stderr.write('%s\n' % message)
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
pass
def _real_extract(self, url):
"""Real extraction process. Redefine in subclasses."""
pass
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=/'
_NETRC_MACHINE = 'youtube'
def _real_initialize(self):
if self._downloader is None:
return
username = None
password = None
downloader_params = self._downloader.get_params()
# Attempt to use provided username and password or .netrc data
if downloader_params.get('username', None) is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
username = info[0]
password = info[2]
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))
return
2008-07-22 13:26:32 +00:00
# No authentication to be performed
if username is None:
return
# Log in
login_form = {
'current_form': 'loginForm',
'next': '/',
'action_login': 'Log In',
'username': username,
'password': password,
}
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
try:
self.to_stdout('[youtube] Logging in')
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')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.to_stderr('WARNING: unable to log in: %s' % str(err))
return
# Confirm age
age_form = {
'next_url': '/',
'action_confirm': 'Confirm',
}
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
try:
self.to_stdout('[youtube] Confirming age')
age_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
sys.exit('ERROR: unable to confirm age: %s' % str(err))
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)
if mobj is None:
self.to_stderr('ERROR: invalid URL: %s' % url)
return [None]
video_id = mobj.group(2)
# Downloader parameters
format_param = None
if self._downloader is not None:
params = self._downloader.get_params()
format_param = params.get('format', None)
# Extension
2008-07-22 08:14:13 +00:00
video_extension = {'18': 'mp4'}.get(format_param, 'flv')
# Normalize URL, including format
normalized_url = 'http://www.youtube.com/watch?v=%s' % 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)
try:
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
sys.exit('ERROR: unable to download video: %s' % str(err))
self.to_stdout('[youtube] %s: Extracting video information' % video_id)
# "t" param
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
if mobj is None:
self.to_stderr('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:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
# uploader
mobj = re.search(r'More From: ([^<]*)<', video_webpage)
if mobj is None:
self.to_stderr('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')
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)
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 [{
'id': video_id,
'url': video_real_url,
'uploader': video_uploader,
'title': video_title,
'stitle': simple_title,
'ext': video_extension,
}]
if __name__ == '__main__':
try:
2008-07-22 08:14:13 +00:00
# Modules needed only when running the main program
2008-07-22 08:56:54 +00:00
import getpass
2008-07-22 08:14:13 +00:00
import optparse
# General configuration
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
2008-07-22 08:14:13 +00:00
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
# Parse command line
2008-07-22 08:56:54 +00:00
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='INTERNAL',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
parser.add_option('-u', '--username',
dest='username', metavar='UN', help='account username')
parser.add_option('-p', '--password',
dest='password', metavar='PW', help='account password')
parser.add_option('-o', '--output',
dest='outtmpl', metavar='TPL', help='output filename template')
parser.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
parser.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
parser.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name', default=False)
parser.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
parser.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
parser.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
parser.add_option('-e', '--get-title',
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='video_format', help='alias for -f 18', const='18')
parser.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
2008-07-22 08:56:54 +00:00
(opts, args) = parser.parse_args()
# Conflicting, missing and erroneous options
if len(args) < 1:
sys.exit('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')
if opts.password is not None and opts.username is None:
sys.exit('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')
if opts.usetitle and opts.useliteral:
sys.exit('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:')
# Information extractors
youtube_ie = YoutubeIE()
# File downloader
fd = FileDownloader({
2008-07-22 08:56:54 +00:00
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'quiet': (opts.quiet or opts.geturl or opts.gettitle),
'forceurl': opts.geturl,
'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')
2008-07-22 08:56:54 +00:00
or (opts.useliteral and '%(title)s-%(id)s.%(ext)s')
or '%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
})
fd.add_info_extractor(youtube_ie)
retcode = fd.download(args)
sys.exit(retcode)
except KeyboardInterrupt:
sys.exit('\nERROR: Interrupted by user')