#!/usr/bin/env python
# -*- coding: utf-8 -*-
-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# Author: Vasyl' Vavrychuk
-# License: Public domain code
+
+__author__ = (
+ 'Ricardo Garcia Gonzalez',
+ 'Danny Colligan',
+ 'Benjamin Johnson',
+ 'Vasyl\' Vavrychuk',
+ 'Witold Baryluk',
+ 'Paweł Paprota',
+ 'Gergely Imreh',
+ 'Rogério Brito',
+ 'Philipp Hagemeister',
+ 'Sören Schulze',
+ )
+
+__license__ = 'Public Domain'
+__version__ = '2011.09.14'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
+
import cookielib
import datetime
+import gzip
import htmlentitydefs
import httplib
import locale
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:
except ImportError:
from cgi import parse_qs
+try:
+ import lxml.etree
+except ImportError:
+ pass # Handled below
+
+try:
+ import xml.etree.ElementTree
+except ImportError: # Python<2.5
+ pass # Not officially supported, but let it slip
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',
+ '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',
}
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
+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
+
def preferredencoding():
"""Get preferred encoding.
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.
"""
# Unknown entity in name, return its literal representation
return (u'&%s;' % entity)
+
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.
stream = open(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
+
+
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.
"""
pass
+
class PostProcessingError(Exception):
"""Post Processing exception.
"""
pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
"""
pass
+
class ContentTooShortError(Exception):
"""Content Too Short exception.
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.
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.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
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
"""
params = None
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.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))]
- aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
- for dir in aggregate:
- if not os.path.exists(dir):
- os.mkdir(dir)
-
- @staticmethod
- def temp_name(filename):
- """Returns a temporary filename for the given filename."""
- if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)):
- return filename
- return filename + u'.part'
-
+
@staticmethod
def format_bytes(bytes):
if bytes is None:
else:
exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
- converted = float(bytes) / float(1024**exponent)
+ converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
@staticmethod
"""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, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
try:
except (UnicodeEncodeError), err:
if not ignore_encoding_errors:
raise
-
+
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)
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(filename) and not os.path.isfile(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:
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(filename):
+ return
+ timestr = last_modified_hdr
+ if timestr is None:
+ return
+ filetime = timeconvert(timestr)
+ if filetime is None:
+ return
+ try:
+ os.utime(filename, (time.time(), filetime))
+ except:
+ pass
+
+ def report_writedescription(self, descfn):
+ """ Report that the description file is being written """
+ self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+
+ def report_writeinfojson(self, infofn):
+ """ Report that the metadata file has been written """
+ self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
+
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
-
+
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 process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+ filename = self.prepare_filename(info_dict)
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
# Forced printings
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')
return
-
- 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
- except (ValueError, KeyError), err:
- self.trouble(u'ERROR: invalid system charset or erroneous output template')
+
+ if filename is None:
return
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists and will be skipped')
return
try:
- self.pmkdir(filename)
+ dn = os.path.dirname(filename)
+ if dn != '' and not os.path.exists(dn):
+ os.makedirs(dn)
except (OSError, IOError), err:
- self.trouble(u'ERROR: unable to create directories: %s' % str(err))
+ self.trouble(u'ERROR: unable to create directory ' + unicode(err))
return
+ if self.params.get('writedescription', False):
+ try:
+ descfn = filename + '.description'
+ self.report_writedescription(descfn)
+ descfile = open(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('writeinfojson', False):
+ infofn = filename + '.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(infofn, 'wb')
+ try:
+ json.dump(info_dict, infof)
+ finally:
+ infof.close()
+ except (OSError, IOError):
+ self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+ return
+
try:
success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
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)
# 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]
+ basic_args = ['rtmpdump'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
prevsize = os.path.getsize(tmpfilename)
def _do_download(self, filename, url, player_url):
# Check file already present
- if self.params.get('continuedl', False) and os.path.isfile(filename):
+ if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
return True
tmpfilename = self.temp_name(filename)
stream = None
open_mode = 'wb'
- basic_request = urllib2.Request(url, None, std_headers)
- request = urllib2.Request(url, None, std_headers)
+
+ # 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(tmpfilename):
# Request parameters in case of being able to resume
if self.params.get('continuedl', False) and resume_len != 0:
self.report_resuming_byte(resume_len)
- request.add_header('Range','bytes=%d-' % resume_len)
+ request.add_header('Range', 'bytes=%d-' % resume_len)
open_mode = 'ab'
count = 0
else:
# Examine the reported length
if (content_length is not None and
- (resume_len - 100 < long(content_length) < resume_len + 100)):
+ (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,
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
+ byte_counter = 0 + resume_len
block_size = 1024
start = time.time()
while True:
before = time.time()
data_block = data.read(block_size)
after = time.time()
- data_block_len = len(data_block)
- if data_block_len == 0:
+ if len(data_block) == 0:
break
- byte_counter += data_block_len
+ 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))
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, data_block_len)
+ block_size = self.best_block_size(after - before, len(data_block))
# Progress message
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)
+ eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+ speed_str = self.calc_speed(start, time.time(), 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)
+ 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 str(byte_counter) != data_len:
+ 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):
+ self.try_utime(filename, data.info().get('last-modified', None))
+
return True
+
class InfoExtractor(object):
"""Information Extractor class.
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
"""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/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_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', '34', '43', '18', '6', '5', '17', '13']
+ _available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
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_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 _real_initialize(self):
if self._downloader is None:
return
return
# Set language
- request = urllib2.Request(self._LANG_URL, None, std_headers)
+ request = urllib2.Request(self._LANG_URL)
try:
self.report_lang()
urllib2.urlopen(request).read()
'username': username,
'password': password,
}
- request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
try:
self.report_login()
login_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'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)
+ request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
try:
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
# Get video webpage
self.report_video_webpage_download(video_id)
- request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = urllib2.Request(video_info_url, None, std_headers)
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url)
try:
video_info_webpage = urllib2.urlopen(request).read()
video_info = parse_qs(video_info_webpage)
# upload date
upload_date = u'NA'
- mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
+ mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y']
+ format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
pass
# description
- video_description = 'No description available.'
- if self._downloader.params.get('forcedescription', False):
- mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
- if mobj is not None:
- video_description = mobj.group(1)
+ try:
+ lxml.etree
+ except NameError:
+ video_description = u'No description available.'
+ if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+ else:
+ html_parser = lxml.etree.HTMLParser(encoding='utf-8')
+ vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
+ video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
+ # TODO use another parser
# token
video_token = urllib.unquote_plus(video_info['token'][0])
# Decide which formats to download
req_format = self._downloader.params.get('format', None)
- get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
- if 'fmt_url_map' in video_info:
- url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_url_list = [(None, video_info['conn'][0])]
+ elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+ url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
+ url_data = [parse_qs(uds) for uds in url_data_strs]
+ url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
+ url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+
format_limit = self._downloader.params.get('format_limit', None)
if format_limit is not None and format_limit in self._available_formats:
format_list = self._available_formats[self._available_formats.index(format_limit):]
elif req_format == '-1':
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
- if req_format in url_map:
- video_url_list = [(req_format, url_map[req_format])] # Specific format
- else:
- video_url_list = [(req_format, get_video_template % req_format)] # Specific format
-
- elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_url_list = [(None, video_info['conn'][0])]
-
+ # Specific format
+ if req_format not in url_map:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ video_url_list = [(req_format, url_map[req_format])] # Specific format
else:
- self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+ self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
return
for format_param, video_real_url in video_url_list:
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
- # Find the video URL in fmt_url_map or conn paramters
try:
# Process video information
self._downloader.process_info({
'ext': video_extension.decode('utf-8'),
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description.decode('utf-8'),
+ 'description': video_description,
'player_url': player_url,
})
except UnavailableVideoError, err:
- self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
+ self._downloader.trouble(u'\nERROR: unable to download video')
class MetacafeIE(InfoExtractor):
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_screen(u'[metacafe] Confirming age')
-
+
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
+
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
- request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+ request = urllib2.Request(self._DISCLAIMER)
try:
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
+ request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), 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 not None:
mediaURL = urllib.unquote(mobj.group(1))
video_extension = mediaURL[-3:]
-
+
# Extract gdaKey if available
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
'player_url': None,
})
except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download video')
class DailymotionIE(InfoExtractor):
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
+
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = urllib.unquote(mobj.group(1))
+ sequence = urllib.unquote(mobj.group(1))
+ mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
# if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL
- # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
- mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+ mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
+ mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
'player_url': None,
})
except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com."""
else: # we need something to pass to process_info
video_thumbnail = ''
-
try:
# Process video information
self._downloader.process_info({
'player_url': None,
})
except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download video')
class PhotobucketIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download video')
class YahooIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to extract video description')
return
video_description = mobj.group(1).decode('utf-8')
- if not video_description: video_description = 'No description available.'
+ if not video_description:
+ video_description = 'No description available.'
# Extract video height and width
mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
yv_bitrate = '700' # according to Wikipedia this is hard-coded
request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+ '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+ '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
- 'description': video_description,
'player_url': None,
})
except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ self._downloader.trouble(u'\nERROR: unable to download video')
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
+class VimeoIE(InfoExtractor):
+ """Information extractor for vimeo.com."""
+
+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
- return True
+ return (re.match(VimeoIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
def _real_initialize(self):
return
- def _real_extract(self, url):
+ def _real_extract(self, url, new_video=True):
+ # Extract ID from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
# At this point we have a new video
self._downloader.increment_downloads()
+ video_id = mobj.group(1)
- video_id = url.split('/')[-1]
- request = urllib2.Request(url)
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
- except ValueError, err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+
+ # Extract title
+ mobj = re.search(r'<caption>(.*?)</caption>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ self._downloader.trouble(u'ERROR: unable to extract video title')
return
+ video_title = mobj.group(1).decode('utf-8')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ # Extract uploader
+ mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
return
+ video_uploader = mobj.group(1).decode('utf-8')
- video_url = urllib.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
+ # Extract video thumbnail
+ mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- mobj = re.search(r'<title>(.*)</title>', webpage)
+ # # Extract video description
+ # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
+ # if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract video description')
+ # return
+ # video_description = mobj.group(1).decode('utf-8')
+ # if not video_description: video_description = 'No description available.'
+ video_description = 'Foo.'
+
+ # Vimeo specific: extract request signature
+ mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.trouble(u'ERROR: unable to extract request signature')
return
- video_title = mobj.group(1).decode('utf-8')
- video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ sig = mobj.group(1).decode('utf-8')
- # video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ # Vimeo specific: Extract request signature expiration
+ mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
+ self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
return
- video_uploader = mobj.group(1).decode('utf-8')
+ sig_exp = mobj.group(1).decode('utf-8')
+
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
+ 'url': video_url,
'uploader': video_uploader,
'upload_date': u'NA',
'title': video_title,
'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
+ 'ext': u'mp4',
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
'player_url': None,
})
- except UnavailableVideoError, err:
+ except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
+class GenericIE(InfoExtractor):
+ """Generic last-resort information extractor."""
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return True
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ video_id = url.split('/')[-1]
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ except ValueError, err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ self.report_extraction(video_id)
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = urllib.unquote(mobj.group(1))
+ video_id = os.path.basename(video_url)
+
+ # here's a fun little line of code for you:
+ video_extension = os.path.splitext(video_id)[1][1:]
+ video_id = os.path.splitext(video_id)[0]
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # video uploader is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
class YoutubeSearchIE(InfoExtractor):
"""Information Extractor for YouTube search queries."""
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
-
+
@staticmethod
def suitable(url):
return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
def _real_initialize(self):
self._youtube_ie.initialize()
-
+
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
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))
+ 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
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url, None, std_headers)
+ request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
pagenum = pagenum + 1
+
class GoogleSearchIE(InfoExtractor):
"""Information Extractor for Google Video search queries."""
_VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
def __init__(self, google_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._google_ie = google_ie
-
+
@staticmethod
def suitable(url):
return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
def _real_initialize(self):
self._google_ie.initialize()
-
+
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
n = self._max_google_results
self._download_n_results(query, n)
return
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url, None, std_headers)
+ request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
pagenum = pagenum + 1
+
class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
_VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
def __init__(self, yahoo_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._yahoo_ie = yahoo_ie
-
+
@staticmethod
def suitable(url):
return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
def _real_initialize(self):
self._yahoo_ie.initialize()
-
+
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
prefix, query = query.split(':')
prefix = prefix[8:]
- query = query.encode('utf-8')
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
n = self._max_yahoo_results
self._download_n_results(query, n)
return
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url, None, std_headers)
+ request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
pagenum = pagenum + 1
+
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
-
+
@staticmethod
def suitable(url):
return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
def _real_initialize(self):
self._youtube_ie.initialize()
-
+
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url)
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
+ # Single video case
+ if mobj.group(3) is not None:
+ self._youtube_ie.extract(mobj.group(3))
+ return
+
# Download playlist pages
- playlist_id = mobj.group(1)
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_prefix = 'p'
+ playlist_access = 'view_play_list'
+ playlist_id = mobj.group(2)
video_ids = []
pagenum = 1
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
+
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+ _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+ _GDATA_PAGE_SIZE = 50
+ _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
-
+
@staticmethod
def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
- def report_download_page(self, username):
+ def report_download_page(self, username, start_index):
"""Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
+ self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
+ (username, start_index, start_index + self._GDATA_PAGE_SIZE))
def _real_initialize(self):
self._youtube_ie.initialize()
-
+
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
- # Download user page
username = mobj.group(1)
+
+ # Download video ids using YouTube Data API. Result size per
+ # query is limited (currently to 50 videos) so we need to query
+ # page by page until there are no video ids - it means we got
+ # all of them.
+
video_ids = []
- pagenum = 1
+ pagenum = 0
- self.report_download_page(username)
- request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
+ while True:
+ start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+ self.report_download_page(username, start_index)
+
+ request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+
+ video_ids.extend(ids_in_page)
+
+ # A little optimization - if current page is not
+ # "full", ie. does not contain PAGE_SIZE video ids then
+ # we can assume that this page is the last one - there
+ # are no more ids on further pages - no need to query
+ # again.
- # Extract video identifiers
- ids_in_page = []
+ if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+ break
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ pagenum += 1
+ all_ids_count = len(video_ids)
playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1)
- video_ids = video_ids[playliststart:playlistend]
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ (username, all_ids_count, len(video_ids)))
+
+ for video_id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+
class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com"""
# Retrieve file webpage with 'Free download' button pressed
free_download_indication = { 'gateway_result' : '1' }
- request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers)
+ request = urllib2.Request(url, urllib.urlencode(free_download_indication))
try:
self.report_download_webpage(file_id)
webpage = urllib2.urlopen(request).read()
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download file')
+
+class FacebookIE(InfoExtractor):
+ """Information Extractor for Facebook"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+ _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
+ _NETRC_MACHINE = 'facebook'
+ _available_formats = ['highqual', 'lowqual']
+ _video_extensions = {
+ 'highqual': 'mp4',
+ 'lowqual': 'mp4',
+ }
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(FacebookIE._VALID_URL, url) is not None)
+
+ def _reporter(self, message):
+ """Add header and report message."""
+ self._downloader.to_screen(u'[facebook] %s' % message)
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._reporter(u'Logging in')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._reporter(u'%s: Downloading video webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._reporter(u'%s: Extracting video information' % video_id)
+
+ def _parse_page(self, video_webpage):
+ """Extract video information from page"""
+ # General data
+ data = {'title': r'class="video_title datawrap">(.*?)</',
+ 'description': r'<div class="datawrap">(.*?)</div>',
+ 'owner': r'\("video_owner_name", "(.*?)"\)',
+ 'upload_date': r'data-date="(.*?)"',
+ 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
+ }
+ video_info = {}
+ for piece in data.keys():
+ mobj = re.search(data[piece], video_webpage)
+ if mobj is not None:
+ video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+
+ # Video urls
+ video_urls = {}
+ for fmt in self._available_formats:
+ mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
+ if mobj is not None:
+ # URL is in a Javascript segment inside an escaped Unicode format within
+ # the generally utf-8 page
+ video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+ video_info['video_urls'] = video_urls
+
+ return video_info
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ useremail = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ useremail = 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:
+ useremail = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError), err:
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ return
+
+ if useremail is None:
+ return
+
+ # Log in
+ login_form = {
+ 'email': useremail,
+ 'pass': password,
+ 'login': 'Log+In'
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+ return
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group('ID')
+
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
+ try:
+ page = urllib2.urlopen(request)
+ video_webpage = page.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ # Start extracting information
+ self.report_information_extraction(video_id)
+
+ # Extract information
+ video_info = self._parse_page(video_webpage)
+
+ # uploader
+ if 'owner' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = video_info['owner']
+
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = video_info['title']
+ video_title = video_title.decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ # thumbnail image
+ if 'thumbnail' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else:
+ video_thumbnail = video_info['thumbnail']
+
+ # upload date
+ upload_date = u'NA'
+ if 'upload_date' in video_info:
+ upload_time = video_info['upload_date']
+ timetuple = email.utils.parsedate_tz(upload_time)
+ if timetuple is not None:
+ try:
+ upload_date = time.strftime('%Y%m%d', timetuple[0:9])
+ except:
+ pass
+
+ # description
+ video_description = video_info.get('description', 'No description available.')
+
+ url_map = video_info['video_urls']
+ if len(url_map.keys()) > 0:
+ # Decide which formats to download
+ req_format = self._downloader.params.get('format', None)
+ format_limit = self._downloader.params.get('format_limit', None)
+
+ if format_limit is not None and format_limit in self._available_formats:
+ format_list = self._available_formats[self._available_formats.index(format_limit):]
+ else:
+ format_list = self._available_formats
+ existing_formats = [x for x in format_list if x in url_map]
+ if len(existing_formats) == 0:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ if req_format is None:
+ video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif req_format == '-1':
+ video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
+ else:
+ # Specific format
+ if req_format not in url_map:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ video_url_list = [(req_format, url_map[req_format])] # Specific format
+
+ for format_param, video_real_url in video_url_list:
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'mp4')
+
+ try:
+ # 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'),
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description.decode('utf-8'),
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+class BlipTVIE(InfoExtractor):
+ """Information extractor for blip.tv"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
+ _URL_EXT = r'^.*\.([a-z0-9]+)$'
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(BlipTVIE._VALID_URL, url) is not None)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ if '?' in url:
+ cchar = '&'
+ else:
+ cchar = '?'
+ json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
+ request = urllib2.Request(json_url)
+ self.report_extraction(mobj.group(1))
+ try:
+ json_code = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
+ try:
+ json_data = json.loads(json_code)
+ if 'Post' in json_data:
+ data = json_data['Post']
+ else:
+ data = json_data
+
+ upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+ video_url = data['media']['url']
+ umobj = re.match(self._URL_EXT, video_url)
+ if umobj is None:
+ raise ValueError('Can not determine filename extension')
+ ext = umobj.group(1)
+
+ self._downloader.increment_downloads()
+
+ info = {
+ 'id': data['item_id'],
+ 'url': video_url,
+ 'uploader': data['display_name'],
+ 'upload_date': upload_date,
+ 'title': data['title'],
+ 'stitle': self._simplify_title(data['title']),
+ 'ext': ext,
+ 'format': data['media']['mimeType'],
+ 'thumbnail': data['thumbnailUrl'],
+ 'description': data['description'],
+ 'player_url': data['embedUrl']
+ }
+ except (ValueError,KeyError), err:
+ self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+ return
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class MyVideoIE(InfoExtractor):
+ """Information Extractor for myvideo.de."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(MyVideoIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._download.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+ simple_title = mobj.group(2).decode('utf-8')
+ # should actually not be necessary
+ simple_title = sanitize_title(simple_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
+
+ # Get video webpage
+ request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+ webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+ mobj = re.search('<title>([^<]+)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+
+ video_title = mobj.group(1)
+ video_title = sanitize_title(video_title)
+
+ try:
+ print(video_url)
+ self._downloader.process_info({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': u'NA',
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'flv',
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: Unable to download video')
+
+class ComedyCentralIE(InfoExtractor):
+ """Information extractor for The Daily Show and Colbert Report """
+
+ _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+
+ def report_extraction(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
+
+ def report_config_download(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+
+ def report_player_url(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ if mobj.group('shortname'):
+ if mobj.group('shortname') in ('tds', 'thedailyshow'):
+ url = 'http://www.thedailyshow.com/full-episodes/'
+ else:
+ url = 'http://www.colbertnation.com/full-episodes/'
+ mobj = re.match(self._VALID_URL, url)
+ assert mobj is not None
+
+ dlNewest = not mobj.group('episode')
+ if dlNewest:
+ epTitle = mobj.group('showname')
+ else:
+ epTitle = mobj.group('episode')
+
+ req = urllib2.Request(url)
+ self.report_extraction(epTitle)
+ try:
+ htmlHandle = urllib2.urlopen(req)
+ html = htmlHandle.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+ if dlNewest:
+ url = htmlHandle.geturl()
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+ return
+ if mobj.group('episode') == '':
+ self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+ return
+ epTitle = mobj.group('episode')
+
+ mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
+ if len(mMovieParams) == 0:
+ self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ return
+ show_id = mMovieParams[0][2]
+ ACT_COUNT = { # TODO: Detect this dynamically
+ 'thedailyshow.com': 4,
+ 'colbertnation.com': 3,
+ }.get(show_id, 4)
+ OFFSET = {
+ 'thedailyshow.com': 1,
+ 'colbertnation.com': 1,
+ }.get(show_id, 1)
+
+ first_player_url = mMovieParams[0][0]
+ startMediaNum = int(mMovieParams[0][3]) + OFFSET
+ movieId = mMovieParams[0][1]
+
+ playerReq = urllib2.Request(first_player_url)
+ self.report_player_url(epTitle)
+ try:
+ playerResponse = urllib2.urlopen(playerReq)
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
+ return
+ player_url = playerResponse.geturl()
+
+ for actNum in range(ACT_COUNT):
+ mediaNum = startMediaNum + actNum
+ mediaId = movieId + str(mediaNum)
+ configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+ urllib.urlencode({'uri': mediaId}))
+ configReq = urllib2.Request(configUrl)
+ self.report_config_download(epTitle)
+ try:
+ configXml = urllib2.urlopen(configReq).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+
+ cdoc = xml.etree.ElementTree.fromstring(configXml)
+ turls = []
+ for rendition in cdoc.findall('.//rendition'):
+ finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+ turls.append(finfo)
+
+ if len(turls) == 0:
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+ continue
+
+ # For now, just pick the highest bitrate
+ format,video_url = turls[-1]
+
+ self._downloader.increment_downloads()
+
+ effTitle = show_id.replace('.com', '') + '-' + epTitle
+ info = {
+ 'id': str(mediaNum),
+ 'url': video_url,
+ 'uploader': show_id,
+ 'upload_date': 'NA',
+ 'title': effTitle,
+ 'stitle': self._simplify_title(effTitle),
+ 'ext': 'mp4',
+ 'format': format,
+ 'thumbnail': None,
+ 'description': 'TODO: Not yet supported',
+ 'player_url': player_url
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+ continue
+
+
class PostProcessor(object):
"""Post Processor class.
def set_downloader(self, downloader):
"""Sets the downloader for this PP."""
self._downloader = downloader
-
+
def run(self, information):
"""Run the PostProcessor.
it was called from.
"""
return information # by default, do nothing
-
-### MAIN PROGRAM ###
-if __name__ == '__main__':
- try:
- # Modules needed only when running the main program
- import getpass
- import optparse
-
- # Function to update the program file with the latest version from bitbucket.org
- def update_self(downloader, filename):
- # Note: downloader only used for options
- if not os.access (filename, os.W_OK):
- sys.exit('ERROR: no write permissions on %s' % filename)
-
- downloader.to_screen('Updating to latest stable version...')
- latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
- latest_version = urllib.urlopen(latest_url).read().strip()
- prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
- newcontent = urllib.urlopen(prog_url).read()
- stream = open(filename, 'w')
- stream.write(newcontent)
- stream.close()
- downloader.to_screen('Updated to version %s' % latest_version)
-
- # Parse command line
- parser = optparse.OptionParser(
- usage='Usage: %prog [options] url...',
- version='2010.12.09',
- 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', '--update',
- action='store_true', dest='update_self', help='update this program to latest stable version')
- parser.add_option('-i', '--ignore-errors',
- action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
- parser.add_option('-r', '--rate-limit',
- dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
- parser.add_option('-R', '--retries',
- dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
- parser.add_option('--playlist-start',
- dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
- parser.add_option('--playlist-end',
- dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
-
- authentication = optparse.OptionGroup(parser, 'Authentication Options')
- authentication.add_option('-u', '--username',
- dest='username', metavar='USERNAME', help='account username')
- authentication.add_option('-p', '--password',
- dest='password', metavar='PASSWORD', help='account password')
- authentication.add_option('-n', '--netrc',
- action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
- parser.add_option_group(authentication)
-
- video_format = optparse.OptionGroup(parser, 'Video Format Options')
- video_format.add_option('-f', '--format',
- action='store', dest='format', metavar='FORMAT', help='video format code')
- video_format.add_option('-m', '--mobile-version',
- action='store_const', dest='format', help='alias for -f 17', const='17')
- video_format.add_option('--all-formats',
- action='store_const', dest='format', help='download all available video formats', const='-1')
- video_format.add_option('--max-quality',
- action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
- video_format.add_option('-b', '--best-quality',
- action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')
- parser.add_option_group(video_format)
-
- verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
- verbosity.add_option('-q', '--quiet',
- action='store_true', dest='quiet', help='activates quiet mode', default=False)
- verbosity.add_option('-s', '--simulate',
- action='store_true', dest='simulate', help='do not download video', default=False)
- verbosity.add_option('-g', '--get-url',
- action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
- verbosity.add_option('-e', '--get-title',
- action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
- verbosity.add_option('--get-thumbnail',
- action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
- verbosity.add_option('--get-description',
- action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
- verbosity.add_option('--no-progress',
- action='store_true', dest='noprogress', help='do not print progress bar', default=False)
- parser.add_option_group(verbosity)
-
- filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
- filesystem.add_option('-t', '--title',
- action='store_true', dest='usetitle', help='use title in file name', default=False)
- filesystem.add_option('-l', '--literal',
- action='store_true', dest='useliteral', help='use literal title in file name', default=False)
- filesystem.add_option('-A', '--auto-number',
- action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False)
- filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template')
- filesystem.add_option('-a', '--batch-file',
- dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
- filesystem.add_option('-w', '--no-overwrites',
- action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
- filesystem.add_option('-c', '--continue',
- action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
- filesystem.add_option('--cookies',
- dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
- parser.add_option_group(filesystem)
-
- (opts, args) = parser.parse_args()
-
- # Open appropriate CookieJar
- if opts.cookiefile is None:
- jar = cookielib.CookieJar()
+
+
+class FFmpegExtractAudioPP(PostProcessor):
+
+ def __init__(self, downloader=None, preferredcodec=None):
+ PostProcessor.__init__(self, downloader)
+ if preferredcodec is None:
+ preferredcodec = 'best'
+ self._preferredcodec = preferredcodec
+
+ @staticmethod
+ def get_audio_codec(path):
+ try:
+ cmd = ['ffprobe', '-show_streams', '--', path]
+ handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
+ output = handle.communicate()[0]
+ if handle.wait() != 0:
+ return None
+ except (IOError, OSError):
+ return None
+ audio_codec = None
+ for line in output.split('\n'):
+ if line.startswith('codec_name='):
+ audio_codec = line.split('=')[1].strip()
+ elif line.strip() == 'codec_type=audio' and audio_codec is not None:
+ return audio_codec
+ return None
+
+ @staticmethod
+ def run_ffmpeg(path, out_path, codec, more_opts):
+ try:
+ cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
+ ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
+ return (ret == 0)
+ except (IOError, OSError):
+ return False
+
+ def run(self, information):
+ path = information['filepath']
+
+ filecodec = self.get_audio_codec(path)
+ if filecodec is None:
+ self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
+ return None
+
+ more_opts = []
+ if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
+ if filecodec == 'aac' or filecodec == 'mp3':
+ # Lossless if possible
+ acodec = 'copy'
+ extension = filecodec
+ if filecodec == 'aac':
+ more_opts = ['-f', 'adts']
+ else:
+ # MP3 otherwise.
+ acodec = 'libmp3lame'
+ extension = 'mp3'
+ more_opts = ['-ab', '128k']
else:
- try:
- jar = cookielib.MozillaCookieJar(opts.cookiefile)
- if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
- jar.load()
- except (IOError, OSError), err:
- sys.exit(u'ERROR: unable to open cookie file')
+ # We convert the audio (lossy)
+ acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+ extension = self._preferredcodec
+ more_opts = ['-ab', '128k']
+ if self._preferredcodec == 'aac':
+ more_opts += ['-f', 'adts']
+
+ (prefix, ext) = os.path.splitext(path)
+ new_path = prefix + '.' + extension
+ self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
+ status = self.run_ffmpeg(path, new_path, acodec, more_opts)
+
+ if not status:
+ self._downloader.to_stderr(u'WARNING: error running ffmpeg')
+ return None
- # General configuration
- cookie_processor = urllib2.HTTPCookieProcessor(jar)
- urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
- urllib2.install_opener(urllib2.build_opener(cookie_processor))
- socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+ try:
+ os.remove(path)
+ except (IOError, OSError):
+ self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+ return None
- # Batch file verification
- batchurls = []
- if opts.batchfile is not None:
- try:
- if opts.batchfile == '-':
- batchfd = sys.stdin
- else:
- batchfd = open(opts.batchfile, 'r')
- batchurls = batchfd.readlines()
- batchurls = [x.strip() for x in batchurls]
- batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
- except IOError:
- sys.exit(u'ERROR: batch file could not be read')
- all_urls = batchurls + args
-
- # Conflicting, missing and erroneous options
- if opts.bestquality:
- print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'
- if opts.usenetrc and (opts.username is not None or opts.password is not None):
- parser.error(u'using .netrc conflicts with giving username/password')
- if opts.password is not None and opts.username is None:
- parser.error(u'account username missing')
- if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
- parser.error(u'using output template conflicts with using title, literal title or auto number')
- if opts.usetitle and opts.useliteral:
- parser.error(u'using title conflicts with using literal title')
- if opts.username is not None and opts.password is None:
- opts.password = getpass.getpass(u'Type account password and press return:')
- if opts.ratelimit is not None:
- numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
- if numeric_limit is None:
- parser.error(u'invalid rate limit specified')
- opts.ratelimit = numeric_limit
- if opts.retries is not None:
- try:
- opts.retries = long(opts.retries)
- except (TypeError, ValueError), err:
- parser.error(u'invalid retry count specified')
+ information['filepath'] = new_path
+ return information
+
+
+def updateSelf(downloader, filename):
+ ''' Update the program file with the latest version from the repository '''
+ # Note: downloader only used for options
+ if not os.access(filename, os.W_OK):
+ sys.exit('ERROR: no write permissions on %s' % filename)
+
+ downloader.to_screen('Updating to latest version...')
+
+ try:
try:
- opts.playliststart = long(opts.playliststart)
- if opts.playliststart <= 0:
- raise ValueError
- except (TypeError, ValueError), err:
- parser.error(u'invalid playlist start number specified')
+ urlh = urllib.urlopen(UPDATE_URL)
+ newcontent = urlh.read()
+ finally:
+ urlh.close()
+ except (IOError, OSError), err:
+ sys.exit('ERROR: unable to download latest version')
+
+ try:
+ outf = open(filename, 'wb')
try:
- opts.playlistend = long(opts.playlistend)
- if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
- raise ValueError
- except (TypeError, ValueError), err:
- parser.error(u'invalid playlist end number specified')
-
- # Information extractors
- youtube_ie = YoutubeIE()
- metacafe_ie = MetacafeIE(youtube_ie)
- dailymotion_ie = DailymotionIE()
- youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
- youtube_user_ie = YoutubeUserIE(youtube_ie)
- youtube_search_ie = YoutubeSearchIE(youtube_ie)
- google_ie = GoogleIE()
- google_search_ie = GoogleSearchIE(google_ie)
- photobucket_ie = PhotobucketIE()
- yahoo_ie = YahooIE()
- yahoo_search_ie = YahooSearchIE(yahoo_ie)
- deposit_files_ie = DepositFilesIE()
- generic_ie = GenericIE()
-
- # File downloader
- fd = FileDownloader({
- 'usenetrc': opts.usenetrc,
- 'username': opts.username,
- 'password': opts.password,
- 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
- 'forceurl': opts.geturl,
- 'forcetitle': opts.gettitle,
- 'forcethumbnail': opts.getthumbnail,
- 'forcedescription': opts.getdescription,
- 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
- 'format': opts.format,
- 'format_limit': opts.format_limit,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
- or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
- or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
- or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
- or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
- or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
- or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
- or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
- or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
- or u'%(id)s.%(ext)s'),
- 'ignoreerrors': opts.ignoreerrors,
- 'ratelimit': opts.ratelimit,
- 'nooverwrites': opts.nooverwrites,
- 'retries': opts.retries,
- 'continuedl': opts.continue_dl,
- 'noprogress': opts.noprogress,
- 'playliststart': opts.playliststart,
- 'playlistend': opts.playlistend,
- 'logtostderr': opts.outtmpl == '-',
- })
- fd.add_info_extractor(youtube_search_ie)
- fd.add_info_extractor(youtube_pl_ie)
- fd.add_info_extractor(youtube_user_ie)
- fd.add_info_extractor(metacafe_ie)
- fd.add_info_extractor(dailymotion_ie)
- fd.add_info_extractor(youtube_ie)
- fd.add_info_extractor(google_ie)
- fd.add_info_extractor(google_search_ie)
- fd.add_info_extractor(photobucket_ie)
- fd.add_info_extractor(yahoo_ie)
- fd.add_info_extractor(yahoo_search_ie)
- fd.add_info_extractor(deposit_files_ie)
-
- # This must come last since it's the
- # fallback if none of the others work
- fd.add_info_extractor(generic_ie)
-
- # Update version
- if opts.update_self:
- update_self(fd, sys.argv[0])
-
- # Maybe do nothing
- if len(all_urls) < 1:
- if not opts.update_self:
- parser.error(u'you must provide at least one URL')
+ outf.write(newcontent)
+ finally:
+ outf.close()
+ except (IOError, OSError), err:
+ sys.exit('ERROR: unable to overwrite current version')
+
+ downloader.to_screen('Updated youtube-dl. Restart to use the new version.')
+
+def parseOpts():
+ # Deferred imports
+ import getpass
+ import optparse
+
+ def _format_option_string(option):
+ ''' ('-o', '--option') -> -o, --format METAVAR'''
+
+ opts = []
+
+ if option._short_opts: opts.append(option._short_opts[0])
+ if option._long_opts: opts.append(option._long_opts[0])
+ if len(opts) > 1: opts.insert(1, ', ')
+
+ if option.takes_value(): opts.append(' %s' % option.metavar)
+
+ return "".join(opts)
+
+ def _find_term_columns():
+ columns = os.environ.get('COLUMNS', None)
+ if columns:
+ return int(columns)
+
+ try:
+ sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out,err = sp.communicate()
+ return int(out.split()[1])
+ except:
+ pass
+ return None
+
+ max_width = 80
+ max_help_position = 80
+
+ # No need to wrap help messages if we're on a wide console
+ columns = _find_term_columns()
+ if columns: max_width = columns
+
+ fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
+ fmt.format_option_strings = _format_option_string
+
+ kw = {
+ 'version' : __version__,
+ 'formatter' : fmt,
+ 'usage' : '%prog [options] url...',
+ 'conflict_handler' : 'resolve',
+ }
+
+ parser = optparse.OptionParser(**kw)
+
+ # option groups
+ general = optparse.OptionGroup(parser, 'General Options')
+ authentication = optparse.OptionGroup(parser, 'Authentication Options')
+ video_format = optparse.OptionGroup(parser, 'Video Format Options')
+ postproc = optparse.OptionGroup(parser, 'Post-processing Options')
+ filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
+ verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+
+ general.add_option('-h', '--help',
+ action='help', help='print this help text and exit')
+ general.add_option('-v', '--version',
+ action='version', help='print program version and exit')
+ general.add_option('-U', '--update',
+ action='store_true', dest='update_self', help='update this program to latest version')
+ general.add_option('-i', '--ignore-errors',
+ action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+ general.add_option('-r', '--rate-limit',
+ dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+ general.add_option('-R', '--retries',
+ dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
+ general.add_option('--playlist-start',
+ dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+ general.add_option('--playlist-end',
+ dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+ general.add_option('--dump-user-agent',
+ action='store_true', dest='dump_user_agent',
+ help='display the current browser identification', default=False)
+
+ authentication.add_option('-u', '--username',
+ dest='username', metavar='USERNAME', help='account username')
+ authentication.add_option('-p', '--password',
+ dest='password', metavar='PASSWORD', help='account password')
+ authentication.add_option('-n', '--netrc',
+ action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+
+
+ video_format.add_option('-f', '--format',
+ action='store', dest='format', metavar='FORMAT', help='video format code')
+ video_format.add_option('--all-formats',
+ action='store_const', dest='format', help='download all available video formats', const='-1')
+ video_format.add_option('--max-quality',
+ action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+
+
+ verbosity.add_option('-q', '--quiet',
+ action='store_true', dest='quiet', help='activates quiet mode', default=False)
+ verbosity.add_option('-s', '--simulate',
+ action='store_true', dest='simulate', help='do not download video', default=False)
+ verbosity.add_option('-g', '--get-url',
+ action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+ verbosity.add_option('-e', '--get-title',
+ action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+ verbosity.add_option('--get-thumbnail',
+ action='store_true', dest='getthumbnail',
+ help='simulate, quiet but print thumbnail URL', default=False)
+ verbosity.add_option('--get-description',
+ action='store_true', dest='getdescription',
+ help='simulate, quiet but print video description', default=False)
+ verbosity.add_option('--get-filename',
+ action='store_true', dest='getfilename',
+ help='simulate, quiet but print output filename', default=False)
+ verbosity.add_option('--no-progress',
+ action='store_true', dest='noprogress', help='do not print progress bar', default=False)
+ verbosity.add_option('--console-title',
+ action='store_true', dest='consoletitle',
+ help='display progress in console titlebar', default=False)
+
+
+ filesystem.add_option('-t', '--title',
+ action='store_true', dest='usetitle', help='use title in file name', default=False)
+ filesystem.add_option('-l', '--literal',
+ action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+ filesystem.add_option('-A', '--auto-number',
+ action='store_true', dest='autonumber',
+ help='number downloaded files starting from 00000', default=False)
+ filesystem.add_option('-o', '--output',
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template')
+ filesystem.add_option('-a', '--batch-file',
+ dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+ filesystem.add_option('-w', '--no-overwrites',
+ action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+ filesystem.add_option('-c', '--continue',
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+ filesystem.add_option('--cookies',
+ dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+ filesystem.add_option('--no-part',
+ action='store_true', dest='nopart', help='do not use .part files', default=False)
+ filesystem.add_option('--no-mtime',
+ action='store_false', dest='updatetime',
+ help='do not use the Last-modified header to set the file modification time', default=True)
+ filesystem.add_option('--write-description',
+ action='store_true', dest='writedescription',
+ help='write video description to a .description file', default=False)
+ filesystem.add_option('--write-info-json',
+ action='store_true', dest='writeinfojson',
+ help='write video metadata to a .info.json file', default=False)
+
+
+ postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
+ help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
+ postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
+ help='"best", "aac" or "mp3"; best by default')
+
+
+ parser.add_option_group(general)
+ parser.add_option_group(filesystem)
+ parser.add_option_group(verbosity)
+ parser.add_option_group(video_format)
+ parser.add_option_group(authentication)
+ parser.add_option_group(postproc)
+
+ opts, args = parser.parse_args()
+
+ return parser, opts, args
+
+def main():
+ parser, opts, args = parseOpts()
+
+ # Open appropriate CookieJar
+ if opts.cookiefile is None:
+ jar = cookielib.CookieJar()
+ else:
+ try:
+ jar = cookielib.MozillaCookieJar(opts.cookiefile)
+ if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+ jar.load()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to open cookie file')
+
+ # Dump user agent
+ if opts.dump_user_agent:
+ print std_headers['User-Agent']
+ sys.exit(0)
+
+ # General configuration
+ cookie_processor = urllib2.HTTPCookieProcessor(jar)
+ opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
+ urllib2.install_opener(opener)
+ socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+ # Batch file verification
+ batchurls = []
+ if opts.batchfile is not None:
+ try:
+ if opts.batchfile == '-':
+ batchfd = sys.stdin
else:
- sys.exit()
- retcode = fd.download(all_urls)
+ batchfd = open(opts.batchfile, 'r')
+ batchurls = batchfd.readlines()
+ batchurls = [x.strip() for x in batchurls]
+ batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+ except IOError:
+ sys.exit(u'ERROR: batch file could not be read')
+ all_urls = batchurls + args
+
+ # Conflicting, missing and erroneous options
+ if opts.usenetrc and (opts.username is not None or opts.password is not None):
+ parser.error(u'using .netrc conflicts with giving username/password')
+ if opts.password is not None and opts.username is None:
+ parser.error(u'account username missing')
+ if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
+ parser.error(u'using output template conflicts with using title, literal title or auto number')
+ if opts.usetitle and opts.useliteral:
+ parser.error(u'using title conflicts with using literal title')
+ if opts.username is not None and opts.password is None:
+ opts.password = getpass.getpass(u'Type account password and press return:')
+ if opts.ratelimit is not None:
+ numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
+ if numeric_limit is None:
+ parser.error(u'invalid rate limit specified')
+ opts.ratelimit = numeric_limit
+ if opts.retries is not None:
+ try:
+ opts.retries = long(opts.retries)
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid retry count specified')
+ try:
+ opts.playliststart = int(opts.playliststart)
+ if opts.playliststart <= 0:
+ raise ValueError(u'Playlist start must be positive')
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid playlist start number specified')
+ try:
+ opts.playlistend = int(opts.playlistend)
+ if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+ raise ValueError(u'Playlist end must be greater than playlist start')
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid playlist end number specified')
+ if opts.extractaudio:
+ if opts.audioformat not in ['best', 'aac', 'mp3']:
+ parser.error(u'invalid audio format specified')
+
+ # Information extractors
+ youtube_ie = YoutubeIE()
+ metacafe_ie = MetacafeIE(youtube_ie)
+ dailymotion_ie = DailymotionIE()
+ youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_user_ie = YoutubeUserIE(youtube_ie)
+ youtube_search_ie = YoutubeSearchIE(youtube_ie)
+ google_ie = GoogleIE()
+ google_search_ie = GoogleSearchIE(google_ie)
+ photobucket_ie = PhotobucketIE()
+ yahoo_ie = YahooIE()
+ yahoo_search_ie = YahooSearchIE(yahoo_ie)
+ deposit_files_ie = DepositFilesIE()
+ facebook_ie = FacebookIE()
+ bliptv_ie = BlipTVIE()
+ vimeo_ie = VimeoIE()
+ myvideo_ie = MyVideoIE()
+ comedycentral_ie = ComedyCentralIE()
+
+ generic_ie = GenericIE()
+
+ # File downloader
+ fd = FileDownloader({
+ 'usenetrc': opts.usenetrc,
+ 'username': opts.username,
+ 'password': opts.password,
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
+ 'forceurl': opts.geturl,
+ 'forcetitle': opts.gettitle,
+ 'forcethumbnail': opts.getthumbnail,
+ 'forcedescription': opts.getdescription,
+ 'forcefilename': opts.getfilename,
+ 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
+ 'format': opts.format,
+ 'format_limit': opts.format_limit,
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+ or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+ or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
+ or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+ or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
+ or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
+ or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
+ or u'%(id)s.%(ext)s'),
+ 'ignoreerrors': opts.ignoreerrors,
+ 'ratelimit': opts.ratelimit,
+ 'nooverwrites': opts.nooverwrites,
+ 'retries': opts.retries,
+ 'continuedl': opts.continue_dl,
+ 'noprogress': opts.noprogress,
+ 'playliststart': opts.playliststart,
+ 'playlistend': opts.playlistend,
+ 'logtostderr': opts.outtmpl == '-',
+ 'consoletitle': opts.consoletitle,
+ 'nopart': opts.nopart,
+ 'updatetime': opts.updatetime,
+ 'writedescription': opts.writedescription,
+ 'writeinfojson': opts.writeinfojson,
+ })
+ fd.add_info_extractor(youtube_search_ie)
+ fd.add_info_extractor(youtube_pl_ie)
+ fd.add_info_extractor(youtube_user_ie)
+ fd.add_info_extractor(metacafe_ie)
+ fd.add_info_extractor(dailymotion_ie)
+ fd.add_info_extractor(youtube_ie)
+ fd.add_info_extractor(google_ie)
+ fd.add_info_extractor(google_search_ie)
+ fd.add_info_extractor(photobucket_ie)
+ fd.add_info_extractor(yahoo_ie)
+ fd.add_info_extractor(yahoo_search_ie)
+ fd.add_info_extractor(deposit_files_ie)
+ fd.add_info_extractor(facebook_ie)
+ fd.add_info_extractor(bliptv_ie)
+ fd.add_info_extractor(vimeo_ie)
+ fd.add_info_extractor(myvideo_ie)
+ fd.add_info_extractor(comedycentral_ie)
+
+ # This must come last since it's the
+ # fallback if none of the others work
+ fd.add_info_extractor(generic_ie)
+
+ # PostProcessors
+ if opts.extractaudio:
+ fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
+
+ # Update version
+ if opts.update_self:
+ updateSelf(fd, sys.argv[0])
+
+ # Maybe do nothing
+ if len(all_urls) < 1:
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
+ retcode = fd.download(all_urls)
- # Dump cookie jar if requested
- if opts.cookiefile is not None:
- try:
- jar.save()
- except (IOError, OSError), err:
- sys.exit(u'ERROR: unable to save cookie jar')
+ # Dump cookie jar if requested
+ if opts.cookiefile is not None:
+ try:
+ jar.save()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to save cookie jar')
+
+ sys.exit(retcode)
- sys.exit(retcode)
+if __name__ == '__main__':
+ try:
+ main()
except DownloadError:
sys.exit(1)
except SameFileError:
sys.exit(u'ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
+
+# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python:
Rapsys Git / youtubedl / blobdiff