#!/usr/bin/env python
# -*- coding: utf-8 -*-
__authors__ = (
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
'Vasyl\' Vavrychuk',
'Witold Baryluk',
'Paweł Paprota',
'Gergely Imreh',
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
'Kevin Ngo',
'Ori Avtalion',
'shizeeg',
'Filippo Valsorda',
)
__license__ = 'Public Domain'
__version__ = '2012.02.27'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
import cookielib
import datetime
import getpass
import gzip
import htmlentitydefs
import HTMLParser
import httplib
import locale
import math
import netrc
import optparse
import os
import os.path
import re
import shlex
import socket
import string
import subprocess
import sys
import time
import urllib
import urllib2
import warnings
import zlib
if os.name == 'nt':
import ctypes
try:
import email.utils
except ImportError: # Python 2.4
import email.Utils
try:
import cStringIO as StringIO
except ImportError:
import StringIO
# parse_qs was moved from the cgi module to the urlparse module recently.
try:
from urlparse import parse_qs
except ImportError:
from cgi import parse_qs
try:
import xml.etree.ElementTree
except ImportError: # Python<2.5: Not officially supported, but let it slip
warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
try:
import json
except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
import re
class json(object):
@staticmethod
def loads(s):
s = s.decode('UTF-8')
def raiseError(msg, i):
raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
def skipSpace(i, expectMore=True):
while i < len(s) and s[i] in ' \t\r\n':
i += 1
if expectMore:
if i >= len(s):
raiseError('Premature end', i)
return i
def decodeEscape(match):
esc = match.group(1)
_STATIC = {
'"': '"',
'\\': '\\',
'/': '/',
'b': unichr(0x8),
'f': unichr(0xc),
'n': '\n',
'r': '\r',
't': '\t',
}
if esc in _STATIC:
return _STATIC[esc]
if esc[0] == 'u':
if len(esc) == 1+4:
return unichr(int(esc[1:5], 16))
if len(esc) == 5+6 and esc[5:7] == '\\u':
hi = int(esc[1:5], 16)
low = int(esc[7:11], 16)
return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
raise ValueError('Unknown escape ' + str(esc))
def parseString(i):
i += 1
e = i
while True:
e = s.index('"', e)
bslashes = 0
while s[e-bslashes-1] == '\\':
bslashes += 1
if bslashes % 2 == 1:
e += 1
continue
break
rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
stri = rexp.sub(decodeEscape, s[i:e])
return (e+1,stri)
def parseObj(i):
i += 1
res = {}
i = skipSpace(i)
if s[i] == '}': # Empty dictionary
return (i+1,res)
while True:
if s[i] != '"':
raiseError('Expected a string object key', i)
i,key = parseString(i)
i = skipSpace(i)
if i >= len(s) or s[i] != ':':
raiseError('Expected a colon', i)
i,val = parse(i+1)
res[key] = val
i = skipSpace(i)
if s[i] == '}':
return (i+1, res)
if s[i] != ',':
raiseError('Expected comma or closing curly brace', i)
i = skipSpace(i+1)
def parseArray(i):
res = []
i = skipSpace(i+1)
if s[i] == ']': # Empty array
return (i+1,res)
while True:
i,val = parse(i)
res.append(val)
i = skipSpace(i) # Raise exception if premature end
if s[i] == ']':
return (i+1, res)
if s[i] != ',':
raiseError('Expected a comma or closing bracket', i)
i = skipSpace(i+1)
def parseDiscrete(i):
for k,v in {'true': True, 'false': False, 'null': None}.items():
if s.startswith(k, i):
return (i+len(k), v)
raiseError('Not a boolean (or null)', i)
def parseNumber(i):
mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
if mobj is None:
raiseError('Not a number', i)
nums = mobj.group(1)
if '.' in nums or 'e' in nums or 'E' in nums:
return (i+len(nums), float(nums))
return (i+len(nums), int(nums))
CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
def parse(i):
i = skipSpace(i)
i,res = CHARMAP.get(s[i], parseNumber)(i)
i = skipSpace(i, False)
return (i,res)
i,res = parse(0)
if i < len(s):
raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
return res
class IDParser(HTMLParser.HTMLParser):
"""Modified HTMLParser that isolates a tag with the specified id"""
def __init__(self, id):
self.id = id
self.result = None
self.started = False
self.depth = {}
self.html = None
self.watch_startpos = False
HTMLParser.HTMLParser.__init__(self)
def loads(self, html):
self.html = html
self.feed(html)
self.close()
def handle_starttag(self, tag, attrs):
attrs = dict(attrs)
if self.started:
self.find_startpos(None)
if 'id' in attrs and attrs['id'] == self.id:
self.result = [tag]
self.started = True
self.watch_startpos = True
if self.started:
if not tag in self.depth: self.depth[tag] = 0
self.depth[tag] += 1
def handle_endtag(self, tag):
if self.started:
if tag in self.depth: self.depth[tag] -= 1
if self.depth[self.result[0]] == 0:
self.started = False
self.result.append(self.getpos())
def find_startpos(self, x):
"""Needed to put the start position of the result (self.result[1])
after the opening tag with the requested id"""
if self.watch_startpos:
self.watch_startpos = False
self.result.append(self.getpos())
handle_entityref = handle_charref = handle_data = handle_comment = \
handle_decl = handle_pi = unknown_decl = find_startpos
def get_result(self):
if self.result == None: return None
if len(self.result) != 3: return None
lines = self.html.split('\n')
lines = lines[self.result[1][0]-1:self.result[2][0]]
lines[0] = lines[0][self.result[1][1]:]
if len(lines) == 1:
lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
lines[-1] = lines[-1][:self.result[2][1]]
return '\n'.join(lines).strip()
def get_element_by_id(id, html):
"""Return the content of the tag with the specified id in the passed HTML document"""
parser = IDParser(id)
parser.loads(html)
return parser.get_result()
def preferredencoding():
"""Get preferred encoding.
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
def yield_preferredencoding():
try:
pref = locale.getpreferredencoding()
u'TEST'.encode(pref)
except:
pref = 'UTF-8'
while True:
yield pref
return yield_preferredencoding().next()
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a Unicode character.
This function receives a match object and is intended to be used with
the re.sub() function.
"""
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 clean_html(html):
"""Clean an HTML snippet into a readable string"""
# Newline vs
html = html.replace('\n', ' ')
html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
html = re.sub(ur'(?u)&(.+?);', htmlentity_transform, html)
return html
def sanitize_title(utitle):
"""Sanitizes a video title so it could be used as part of a filename."""
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
return utitle.replace(unicode(os.sep), u'%')
def sanitize_open(filename, open_mode):
"""Try to open the given filename, and slightly tweak it if this fails.
Attempts to open the given filename. If this fails, it tries to change
the filename slightly, step by step, until it's either able to open it
or it fails and raises a final exception, like the standard open()
function.
It returns the tuple (stream, definitive_file_name).
"""
try:
if filename == u'-':
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout, filename)
stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError), err:
# In case of error, try to remove win32 forbidden chars
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
# An exception here should be caught in the caller
stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
def timeconvert(timestr):
"""Convert RFC 2822 defined time string into system timestamp"""
timestamp = None
timetuple = email.utils.parsedate_tz(timestr)
if timetuple is not None:
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
def _simplify_title(title):
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
return expr.sub(u'_', title).strip(u'_')
def _orderedSet(iterable):
""" Remove all duplicates from the input iterable """
res = []
for el in iterable:
if el not in res:
res.append(el)
return res
def _unescapeHTML(s):
"""
@param s a string (of type unicode)
"""
assert type(s) == type(u'')
htmlParser = HTMLParser.HTMLParser()
return htmlParser.unescape(s)
def _encodeFilename(s):
"""
@param s The name of the file (of type unicode)
"""
assert type(s) == type(u'')
if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
# Pass u'' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
return s
else:
return s.encode(sys.getfilesystemencoding(), 'ignore')
class DownloadError(Exception):
"""Download Error exception.
This exception may be thrown by FileDownloader objects if they are not
configured to continue on errors. They will contain the appropriate
error message.
"""
pass
class SameFileError(Exception):
"""Same File exception.
This exception will be thrown by FileDownloader objects if they detect
multiple files would have to be downloaded to the same file on disk.
"""
pass
class PostProcessingError(Exception):
"""Post Processing exception.
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
pass
class MaxDownloadsReached(Exception):
""" --max-downloads limit has been reached. """
pass
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
in a format that is not available for that video.
"""
pass
class ContentTooShortError(Exception):
"""Content Too Short exception.
This exception may be raised by FileDownloader objects when a file they
download is too small for what the server announced first, indicating
the connection was probably interrupted.
"""
# Both in bytes
downloaded = None
expected = None
def __init__(self, downloaded, expected):
self.downloaded = downloaded
self.expected = expected
class YoutubeDLHandler(urllib2.HTTPHandler):
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
to include the HTTP header "Youtubedl-No-Compression", which will be
removed before making the real request.
Part of this code was copied from:
http://techknack.net/python-urllib2-handlers/
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
@staticmethod
def deflate(data):
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
@staticmethod
def addinfourl_wrapper(stream, headers, url, code):
if hasattr(urllib2.addinfourl, 'getcode'):
return urllib2.addinfourl(stream, headers, url, code)
ret = urllib2.addinfourl(stream, headers, url)
ret.code = code
return ret
def http_request(self, req):
for h in std_headers:
if h in req.headers:
del req.headers[h]
req.add_header(h, std_headers[h])
if 'Youtubedl-no-compression' in req.headers:
if 'Accept-encoding' in req.headers:
del req.headers['Accept-encoding']
del req.headers['Youtubedl-no-compression']
return req
def http_response(self, req, resp):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = StringIO.StringIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
return resp
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 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 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:
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.
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
forcefilename: Force printing final filename.
simulate: Do not download the video files.
format: Video format code.
format_limit: Highest quality format to try.
outtmpl: Template for output names.
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
retries: Number of times to retry for HTTP error 5xx
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
writesubtitles: Write the video subtitles to a .srt file
subtitleslang: Language of the subtitles to download
"""
params = None
_ies = []
_pps = []
_download_retcode = None
_num_downloads = None
_screen_file = None
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._pps = []
self._download_retcode = 0
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params
@staticmethod
def format_bytes(bytes):
if bytes is None:
return 'N/A'
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = long(math.log(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 long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return long(new_max)
if rate < new_min:
return long(new_min)
return long(rate)
@staticmethod
def parse_bytes(bytestr):
"""Parse a string indicating a byte quantity into a long integer."""
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
if matchobj is None:
return None
number = float(matchobj.group(1))
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
ie.set_downloader(self)
def add_post_processor(self, pp):
"""Add a PostProcessor object to the end of the chain."""
self._pps.append(pp)
pp.set_downloader(self)
def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
assert type(message) == type(u'')
if not self.params.get('quiet', False):
terminator = [u'\n', u''][skip_eol]
output = message + terminator
if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
output = output.encode(preferredencoding(), 'ignore')
self._screen_file.write(output)
self._screen_file.flush()
def to_stderr(self, message):
"""Print message to stderr."""
print >>sys.stderr, message.encode(preferredencoding())
def to_cons_title(self, message):
"""Set console/terminal window title to message."""
if not self.params.get('consoletitle', False):
return
if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ:
sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
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 throw an exception or
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):
raise DownloadError(message)
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)
if rate_limit is None or byte_counter == 0:
return
now = time.time()
elapsed = now - start_time
if elapsed <= 0.0:
return
speed = float(byte_counter) / elapsed
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == u'-' or \
(os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))):
return filename
return filename + u'.part'
def undo_temp_name(self, filename):
if filename.endswith(u'.part'):
return filename[:-len(u'.part')]
return filename
def try_rename(self, old_filename, new_filename):
try:
if old_filename == new_filename:
return
os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename))
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
if not os.path.isfile(_encodeFilename(filename)):
return
timestr = last_modified_hdr
if timestr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
return filetime
try:
os.utime(filename, (time.time(), filetime))
except:
pass
return filetime
def report_writedescription(self, descfn):
""" Report that the description file is being written """
self.to_screen(u'[info] Writing video description to: ' + descfn)
def report_writesubtitles(self, srtfn):
""" Report that the subtitles file is being written """
self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
def report_writeinfojson(self, infofn):
""" Report that the metadata file has been written """
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: ' + filename)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
if self.params.get('noprogress', False):
return
self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
except (UnicodeEncodeError), err:
self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed')
else:
self.to_screen(u'')
def increment_downloads(self):
"""Increment the ordinal that assigns a number to each file."""
self._num_downloads += 1
def prepare_filename(self, info_dict):
"""Generate the output filename."""
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
return filename
except (ValueError, KeyError), err:
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
def _match_entry(self, info_dict):
""" Returns None iff the file should be downloaded """
title = info_dict['title']
matchtitle = self.params.get('matchtitle', False)
if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
rejecttitle = self.params.get('rejecttitle', False)
if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
return None
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
reason = self._match_entry(info_dict)
if reason is not None:
self.to_screen(u'[download] ' + reason)
return
max_downloads = self.params.get('max_downloads')
if max_downloads is not None:
if self._num_downloads > int(max_downloads):
raise MaxDownloadsReached()
filename = self.prepare_filename(info_dict)
# Forced printings
if self.params.get('forcetitle', False):
print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceurl', False):
print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcefilename', False) and filename is not None:
print filename.encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceformat', False):
print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
return
if filename is None:
return
try:
dn = os.path.dirname(_encodeFilename(filename))
if dn != '' and not os.path.exists(dn): # dn is already encoded
os.makedirs(dn)
except (OSError, IOError), err:
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
return
if self.params.get('writedescription', False):
try:
descfn = filename + u'.description'
self.report_writedescription(descfn)
descfile = open(_encodeFilename(descfn), 'wb')
try:
descfile.write(info_dict['description'].encode('utf-8'))
finally:
descfile.close()
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write description file ' + descfn)
return
if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
try:
srtfn = filename.rsplit('.', 1)[0] + u'.srt'
self.report_writesubtitles(srtfn)
srtfile = open(_encodeFilename(srtfn), 'wb')
try:
srtfile.write(info_dict['subtitles'].encode('utf-8'))
finally:
srtfile.close()
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
return
if self.params.get('writeinfojson', False):
infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)
try:
json.dump
except (NameError,AttributeError):
self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
return
try:
infof = open(_encodeFilename(infofn), 'wb')
try:
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
json.dump(json_info_dict, infof)
finally:
infof.close()
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
return
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)):
success = True
else:
try:
success = self._do_download(filename, info_dict)
except (OSError, IOError), err:
raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble(u'ERROR: unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ), err:
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble(u'ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
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
# Extract information from URL and process it
ie.extract(url)
# Suitable InfoExtractor had been found; go to next URL
break
if not suitable_found:
self.trouble(u'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."""
info = dict(ie_info)
info['filepath'] = filename
for pp in self._pps:
info = pp.run(info)
if info is None:
break
def _download_with_rtmpdump(self, filename, url, player_url):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
# Check for rtmpdump first
try:
subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
if self.params.get('verbose', False):
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, args))
except ImportError:
shell_quote = repr
self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
retval = subprocess.call(args)
while retval == 2 or retval == 1:
prevsize = os.path.getsize(_encodeFilename(tmpfilename))
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
cursize = os.path.getsize(_encodeFilename(tmpfilename))
if prevsize == cursize and retval == 1:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == 2 and cursize > 1024:
self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = 0
break
if retval == 0:
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename)))
self.try_rename(tmpfilename, filename)
return True
else:
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False
def _do_download(self, filename, info_dict):
url = info_dict['url']
player_url = info_dict.get('player_url', None)
# Check file already present
if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
return True
# Attempt to download using rtmpdump
if url.startswith('rtmp'):
return self._download_with_rtmpdump(filename, url, player_url)
tmpfilename = self.temp_name(filename)
stream = None
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
basic_request = urllib2.Request(url, None, headers)
request = urllib2.Request(url, None, headers)
# Establish possible resume length
if os.path.isfile(_encodeFilename(tmpfilename)):
resume_len = os.path.getsize(_encodeFilename(tmpfilename))
else:
resume_len = 0
open_mode = 'wb'
if resume_len != 0:
if self.params.get('continuedl', False):
self.report_resuming_byte(resume_len)
request.add_header('Range','bytes=%d-' % resume_len)
open_mode = 'ab'
else:
resume_len = 0
count = 0
retries = self.params.get('retries', 0)
while count <= retries:
# Establish connection
try:
if count == 0 and 'urlhandle' in info_dict:
data = info_dict['urlhandle']
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), err:
if (err.code < 500 or err.code >= 600) and err.code != 416:
# Unexpected HTTP error
raise
elif err.code == 416:
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
data = urllib2.urlopen(basic_request)
content_length = data.info()['Content-Length']
except (urllib2.HTTPError, ), err:
if err.code < 500 or err.code >= 600:
raise
else:
# Examine the reported length
if (content_length is not None and
(resume_len - 100 < long(content_length) < resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
# changing the file size slightly and causing problems for some users. So
# I decided to implement a suggested change and consider the file
# completely downloaded if the file size differs less than 100 bytes from
# the one in the hard drive.
self.report_file_already_downloaded(filename)
self.try_rename(tmpfilename, filename)
return True
else:
# The length does not match, we start the download over
self.report_unable_to_resume()
open_mode = 'wb'
break
# Retry
count += 1
if count <= retries:
self.report_retry(count, retries)
if count > retries:
self.trouble(u'ERROR: giving up after %s retries' % retries)
return False
data_len = data.info().get('Content-length', None)
if data_len is not None:
data_len = long(data_len) + resume_len
data_len_str = self.format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = 1024
start = time.time()
while True:
# Download and write
before = time.time()
data_block = data.read(block_size)
after = time.time()
if len(data_block) == 0:
break
byte_counter += len(data_block)
# Open file just in time
if stream is None:
try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
assert stream is not None
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError), err:
self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError), err:
self.trouble(u'\nERROR: unable to write data: %s' % str(err))
return False
block_size = self.best_block_size(after - before, len(data_block))
# Progress message
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
if data_len is None:
self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
else:
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
if stream is None:
self.trouble(u'\nERROR: Did not get any data blocks')
return False
stream.close()
self.report_finish()
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
self.try_rename(tmpfilename, filename)
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
return True
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. 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.
url: Final video URL.
uploader: Nickname of the video uploader.
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
format: Video format.
player_url: SWF Player URL (may be None).
The following fields are optional. Their primary purpose is to allow
youtube-dl to serve as the backend for a video search function, such
as the one in youtube2mp3. They are only used when their respective
forced printing functions are called:
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
"""
_ready = False
_downloader = None
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
self._ready = False
self.set_downloader(downloader)
def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url) is not None
def initialize(self):
"""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 _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."""
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://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'
# Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
'37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
'44': 'webm',
'45': 'webm',
}
_video_dimensions = {
'5': '240x400',
'6': '???',
'13': '???',
'17': '144x176',
'18': '360x640',
'22': '720x1280',
'34': '360x640',
'35': '480x854',
'37': '1080x1920',
'38': '3072x4096',
'43': '360x640',
'44': '480x854',
'45': '720x1280',
}
IE_NAME = u'youtube'
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
self._downloader.to_screen(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_screen(u'[youtube] Confirming age')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected')
def _closed_captions_xml_to_srt(self, xml_string):
srt = ''
texts = re.findall(r'