# -*- coding: utf-8 -*-
# Author: Ricardo Garcia Gonzalez
# Author: Danny Colligan
+# Author: Benjamin Johnson
# License: Public domain code
import htmlentitydefs
import httplib
import re
import socket
import string
+import subprocess
import sys
import time
import urllib
import urllib2
+# parse_qs was moved from the cgi module to the urlparse module recently.
+try:
+ from urlparse import parse_qs
+except ImportError:
+ from cgi import parse_qs
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
'Accept-Language': 'en-us,en;q=0.5',
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
+def preferredencoding():
+ """Get preferred encoding.
+
+ Returns the best encoding scheme for the system, based on
+ locale.getpreferredencoding() and some further tweaks.
+ """
+ def yield_preferredencoding():
+ try:
+ pref = locale.getpreferredencoding()
+ u'TEST'.encode(pref)
+ except:
+ pref = 'UTF-8'
+ while True:
+ yield pref
+ return yield_preferredencoding().next()
+
+def htmlentity_transform(matchobj):
+ """Transforms an HTML entity to a Unicode character.
+
+ This function receives a match object and is intended to be used with
+ the re.sub() function.
+ """
+ entity = matchobj.group(1)
+
+ # Known non-numeric HTML entity
+ if entity in htmlentitydefs.name2codepoint:
+ return unichr(htmlentitydefs.name2codepoint[entity])
+
+ # Unicode character
+ mobj = re.match(ur'(?u)#(x?\d+)', entity)
+ if mobj is not None:
+ numstr = mobj.group(1)
+ if numstr.startswith(u'x'):
+ base = 16
+ numstr = u'0%s' % numstr
+ else:
+ base = 10
+ return unichr(long(numstr, base))
+
+ # Unknown entity in name, return its literal representation
+ return (u'&%s;' % entity)
+
+def sanitize_title(utitle):
+ """Sanitizes a video title so it could be used as part of a filename."""
+ utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
+ return utitle.replace(unicode(os.sep), u'%')
+
+def sanitize_open(filename, open_mode):
+ """Try to open the given filename, and slightly tweak it if this fails.
+
+ Attempts to open the given filename. If this fails, it tries to change
+ the filename slightly, step by step, until it's either able to open it
+ or it fails and raises a final exception, like the standard open()
+ function.
+
+ It returns the tuple (stream, definitive_file_name).
+ """
+ try:
+ if filename == u'-':
+ return (sys.stdout, filename)
+ stream = open(filename, open_mode)
+ return (stream, filename)
+ except (IOError, OSError), err:
+ # In case of error, try to remove win32 forbidden chars
+ filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename)
+
+ # An exception here should be caught in the caller
+ stream = open(filename, open_mode)
+ return (stream, filename)
+
+
class DownloadError(Exception):
"""Download Error exception.
"""
pass
+class UnavailableFormatError(Exception):
+ """Unavailable Format exception.
+
+ This exception will be thrown when a video is requested
+ in a format that is not available for that video.
+ """
+ pass
+
+class ContentTooShortError(Exception):
+ """Content Too Short exception.
+
+ This exception may be raised by FileDownloader objects when a file they
+ download is too small for what the server announced first, indicating
+ the connection was probably interrupted.
+ """
+ # Both in bytes
+ downloaded = None
+ expected = None
+
+ def __init__(self, downloaded, expected):
+ self.downloaded = downloaded
+ self.expected = expected
+
class FileDownloader(object):
"""File Downloader class.
For this, file downloader objects have a method that allows
InfoExtractors to be registered in a given order. When it is passed
a URL, the file downloader handles it to the first InfoExtractor it
- finds that reports being able to handle it. The InfoExtractor returns
- all the information to the FileDownloader and the latter downloads the
- file or does whatever it's instructed to do.
+ finds that reports being able to handle it. The InfoExtractor extracts
+ all the information about the video or videos the URL refers to, and
+ asks the FileDownloader to process the video information, possibly
+ downloading the video.
File downloaders accept a lot of parameters. In order not to saturate
the object constructor with arguments, it receives a dictionary of
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
"""
params = None
def format_bytes(bytes):
if bytes is None:
return 'N/A'
- if bytes == 0:
+ if type(bytes) is str:
+ bytes = float(bytes)
+ if bytes == 0.0:
exponent = 0
else:
- exponent = long(math.log(float(bytes), 1024.0))
+ exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
- return int(new_max)
+ return long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
- return int(new_max)
+ return long(new_max)
if rate < new_min:
- return int(new_min)
- return int(rate)
+ return long(new_min)
+ return long(rate)
@staticmethod
def parse_bytes(bytestr):
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
+ @staticmethod
+ def verify_url(url):
+ """Verify a URL is valid and data could be downloaded. Return real data URL."""
+ request = urllib2.Request(url, None, std_headers)
+ data = urllib2.urlopen(request)
+ data.read(1)
+ url = data.geturl()
+ data.close()
+ return url
+
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
self._pps.append(pp)
pp.set_downloader(self)
- def to_stdout(self, message, skip_eol=False):
+ def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
- if not self.params.get('quiet', False):
- print u'%s%s' % (message, [u'\n', u''][skip_eol]),
+ try:
+ if not self.params.get('quiet', False):
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
sys.stdout.flush()
+ except (UnicodeEncodeError), err:
+ if not ignore_encoding_errors:
+ raise
def to_stderr(self, message):
"""Print message to stderr."""
- print >>sys.stderr, message
+ print >>sys.stderr, message.encode(preferredencoding())
def fixed_template(self):
"""Checks if the output template is fixed."""
def report_destination(self, filename):
"""Report destination filename."""
- self.to_stdout(u'[download] Destination: %s' % filename)
+ self.to_stdout(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_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+
+ def report_resuming_byte(self, resume_len):
+ """Report attemtp to resume at given byte."""
+ self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+
+ def report_file_already_downloaded(self, file_name):
+ """Report file has already been fully downloaded."""
+ try:
+ self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+ except (UnicodeEncodeError), err:
+ self.to_stdout(u'[download] The file has already been downloaded')
+
+ def report_unable_to_resume(self):
+ """Report it was impossible to resume download."""
+ self.to_stdout(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
- self.to_stdout(u'')
+ if self.params.get('noprogress', False):
+ self.to_stdout(u'[download] Download completed')
+ else:
+ self.to_stdout(u'')
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
- # Forced printings
- if self.params.get('forcetitle', False):
- print info_dict['title']
- if self.params.get('forceurl', False):
- print info_dict['url']
-
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- return
+ # Verify URL if it's an HTTP one
+ if info_dict['url'].startswith('http'):
+ try:
+ self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+ except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+ raise UnavailableFormatError
+
+ # Forced printings
+ if self.params.get('forcetitle', False):
+ print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forceurl', False):
+ print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+ return
+
try:
- filename = self.params['outtmpl'] % info_dict
- self.report_destination(filename)
+ template_dict = dict(info_dict)
+ template_dict['epoch'] = unicode(long(time.time()))
+ filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
- if self.params['nooverwrites'] and os.path.exists(filename):
- self.to_stderr('WARNING: file exists: %s; skipping' % filename)
+ if self.params.get('nooverwrites', False) and os.path.exists(filename):
+ self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
return
+
try:
self.pmkdir(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to create directories: %s' % str(err))
return
+
try:
- outstream = open(filename, 'wb')
- except (OSError, IOError), err:
- self.trouble('ERROR: unable to open for writing: %s' % str(err))
- return
- try:
- self._do_download(outstream, info_dict['url'])
- outstream.close()
+ success = self._do_download(filename, info_dict['url'].encode('utf-8'))
except (OSError, IOError), err:
- self.trouble('ERROR: unable to write video data: %s' % str(err))
- return
+ raise UnavailableFormatError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
return
- try:
- self.post_process(filename, info_dict)
- except (PostProcessingError), err:
- self.trouble('ERROR: postprocessing: %s' % str(err))
+ except (ContentTooShortError, ), err:
+ self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
- return
+ if success:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble('ERROR: postprocessing: %s' % str(err))
+ return
def download(self, url_list):
"""Download a given list of URLs."""
# Suitable InfoExtractor found
suitable_found = True
- # Extract information from URL
- all_results = ie.extract(url)
- results = [x for x in all_results if x is not None]
-
- # See if there were problems extracting any information
- if len(results) != len(all_results):
- self.trouble()
-
- # Two results could go to the same file
- if len(results) > 1 and self.fixed_template():
- raise SameFileError(self.params['outtmpl'])
-
- # Process each result
- for result in results:
- self.process_info(result)
+ # Extract information from URL and process it
+ ie.extract(url)
# Suitable InfoExtractor had been found; go to next URL
break
if info is None:
break
- def _do_download(self, stream, url):
+ def _download_with_rtmpdump(self, filename, url):
+ self.report_destination(filename)
+
+ # Check for rtmpdump first
+ try:
+ subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ except (OSError, IOError):
+ self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+ return False
+
+ # Download using rtmpdump. rtmpdump returns exit code 2 when
+ # the connection was interrumpted and resuming appears to be
+ # possible. This is part of rtmpdump's normal usage, AFAIK.
+ basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename]
+ retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+ while retval == 2 or retval == 1:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True)
+ time.sleep(2.0) # This seems to be needed
+ retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+ if retval == 0:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ return True
+ else:
+ self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+ return False
+
+ def _do_download(self, filename, url):
+ # Attempt to download using rtmpdump
+ if url.startswith('rtmp'):
+ return self._download_with_rtmpdump(filename, url)
+
+ stream = None
+ open_mode = 'wb'
+ basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
- data = urllib2.urlopen(request)
+
+ # Establish possible resume length
+ if os.path.isfile(filename):
+ resume_len = os.path.getsize(filename)
+ else:
+ resume_len = 0
+
+ # 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)
+ open_mode = 'ab'
+
+ # Establish connection
+ try:
+ data = urllib2.urlopen(request)
+ except (urllib2.HTTPError, ), err:
+ if err.code != 416: # 416 is 'Requested range not satisfiable'
+ raise
+ # Unable to resume
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+
+ if content_length is not None and long(content_length) == resume_len:
+ # Because the file had already been fully downloaded
+ self.report_file_already_downloaded(filename)
+ return True
+ else:
+ # Because the server didn't let us
+ self.report_unable_to_resume()
+ open_mode = 'wb'
+
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
- # 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)
- self.report_progress(percent_str, data_len_str, speed_str, eta_str)
-
# Download and write
before = time.time()
data_block = data.read(block_size)
if data_block_len == 0:
break
byte_counter += data_block_len
+
+ # Open file just in time
+ if stream is None:
+ try:
+ (stream, filename) = sanitize_open(filename, open_mode)
+ self.report_destination(filename)
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ return False
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
+ # 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)
+ self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+
# Apply rate limit
self.slow_down(start, byte_counter)
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
- raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
+ raise ContentTooShortError(byte_counter, long(data_len))
+ return True
class InfoExtractor(object):
"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
information from the video (or videos) the URL refers to. This
information includes the real video URL, the video title and simplified
- title, author and others. It is returned in a list of dictionaries when
- calling its extract() method. It is a list because a URL can refer to
- more than one video (think of playlists). The dictionaries must include
+ title, author and others. The information is stored in a dictionary
+ which is then passed to the FileDownloader. The FileDownloader
+ processes this information possibly downloading the video to the file
+ system, among other possible outcomes. The dictionaries must include
the following fields:
id: Video identifier.
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
+ format: Video format.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods, as well as the suitable() static method.
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
+ _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag
+ _video_extensions = {
+ '13': '3gp',
+ '17': 'mp4',
+ '18': 'mp4',
+ '22': 'mp4',
+ '37': 'mp4',
+ }
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
- @staticmethod
- def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a Unicode character."""
- entity = matchobj.group(1)
-
- # Known non-numeric HTML entity
- if entity in htmlentitydefs.name2codepoint:
- return unichr(htmlentitydefs.name2codepoint[entity])
-
- # Unicode character
- mobj = re.match(ur'(?u)#(x?\d+)', entity)
- if mobj is not None:
- numstr = mobj.group(1)
- if numstr.startswith(u'x'):
- base = 16
- numstr = u'0%s' % numstr
- else:
- base = 10
- return unichr(long(numstr, base))
-
- # Unknown entity in name, return its literal representation
- return (u'&%s;' % entity)
-
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_stdout(u'[youtube] Setting language')
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[youtube] Confirming age')
- def report_webpage_download(self, video_id):
- """Report attempt to download webpage."""
- self._downloader.to_stdout(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_stdout(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_stdout(u'[youtube] %s: Extracting video information' % video_id)
- def report_video_url(self, video_id, video_real_url):
+ def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
+ self._downloader.to_stdout(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_stdout(u'[youtube] RTMP download detected')
def _real_initialize(self):
if self._downloader is None:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
- self._downloader.trouble(u'WARNING: parsing .netrc: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
return
# Set language
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'WARNING: unable to set language: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
return
# No authentication to be performed
self.report_login()
login_results = urllib2.urlopen(request).read()
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self._downloader.trouble(u'WARNING: unable to log in: bad username or password')
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'WARNING: unable to log in: %s' % str(err))
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return
# Confirm age
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return [None]
+ return
video_id = mobj.group(2)
# Downloader parameters
+ best_quality = False
+ all_formats = False
format_param = None
+ quality_index = 0
if self._downloader is not None:
params = self._downloader.params
format_param = params.get('format', None)
+ if format_param == '0':
+ format_param = self._available_formats[quality_index]
+ best_quality = True
+ elif format_param == '-1':
+ format_param = self._available_formats[quality_index]
+ all_formats = True
- # Extension
- video_extension = {
- '17': '3gp',
- '18': 'mp4',
- '22': 'mp4',
- }.get(format_param, 'flv')
-
- # Normalize URL, including format
- normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
- if format_param is not None:
- normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
- request = urllib2.Request(normalized_url, None, std_headers)
- try:
- self.report_webpage_download(video_id)
- video_webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
- return [None]
- self.report_information_extraction(video_id)
-
- # "t" param
- mobj = re.search(r', "t": "([^"]+)"', video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
- return [None]
- video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
- if format_param is not None:
- video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
- self.report_video_url(video_id, video_real_url)
-
- # uploader
- mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return [None]
- video_uploader = mobj.group(1)
+ while True:
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['embedded', 'detailpage']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s&el=%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url, None, std_headers)
+ try:
+ video_info_webpage = urllib2.urlopen(request).read()
+ video_info = parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
+ self.report_information_extraction(video_id)
+
+ # "t" param
+ if 'token' not in video_info:
+ # Attempt to see if YouTube has issued an error message
+ if 'reason' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
+ stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
+ stream.write(video_info_webpage)
+ stream.close()
+ else:
+ reason = urllib.unquote_plus(video_info['reason'][0])
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
+ return
+ token = urllib.unquote_plus(video_info['token'][0])
+ video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
+ if format_param is not None:
+ video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+
+ # Check possible RTMP download
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_real_url = video_info['conn'][0]
+
+ # uploader
+ if 'author' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote_plus(video_info['author'][0])
- # title
- mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return [None]
- video_title = mobj.group(1).decode('utf-8')
- video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
- video_title = video_title.replace(os.sep, u'%')
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote_plus(video_info['title'][0])
+ 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'_')
+
+ 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'),
+ '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')),
+ })
+
+ if all_formats:
+ if quality_index == len(self._available_formats) - 1:
+ # None left to get
+ return
+ else:
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ if format_param == None:
+ return
+ continue
+
+ return
+
+ except UnavailableFormatError, err:
+ if best_quality or all_formats:
+ if quality_index == len(self._available_formats) - 1:
+ # I don't ever expect this to happen
+ if not all_formats:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ else:
+ self.report_unavailable_format(video_id, format_param)
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ if format_param == None:
+ return
+ continue
+ else:
+ self._downloader.trouble('ERROR: format not available for video')
+ return
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
-
- # Process video information
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- }]
class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com."""
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+ _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+ request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return [None]
+ return
video_id = mobj.group(1)
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
- return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ return
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
- return [None]
+ return
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
+ mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
- return [None]
- mediaURL = mobj.group(1).replace('\\', '')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
- mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract gdaKey')
- return [None]
- gdaKey = mobj.group(1)
+ #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ #if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ # return
+ #gdaKey = mobj.group(1)
+ #
+ #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+ video_url = mediaURL
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
- return [None]
+ return
video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
- mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+ mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return [None]
- video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class GoogleIE(InfoExtractor):
+ """Information extractor for video.google.com."""
+
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # 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
+
+ video_id = mobj.group(1)
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % 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
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r"download_url:'([^']+)'", webpage)
+ if mobj is None:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+ mediaURL = mediaURL.replace('\\x3d', '\x3d')
+ mediaURL = mediaURL.replace('\\x26', '\x26')
+
+ video_url = mediaURL
+
+ 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)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
- # Return information
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- }]
+
+class PhotobucketIE(InfoExtractor):
+ """Information extractor for photobucket.com."""
+
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(PhotobucketIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # 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
+
+ video_id = mobj.group(1)
+
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ 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
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ video_url = mediaURL
+
+ mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</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 = mobj.group(2).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,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class YahooIE(InfoExtractor):
+ """Information extractor for video.yahoo.com."""
+
+ # _VALID_URL matches all Yahoo! Video URLs
+ # _VPAGE_URL matches only the extractable '/watch/' URLs
+ _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
+ _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YahooIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # 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
+
+ video_id = mobj.group(2)
+ video_extension = 'flv'
+
+ # Rewrite valid but non-extractable URLs as
+ # extractable English language /watch/ URLs
+ if re.match(self._VPAGE_URL, url) is None:
+ request = urllib2.Request(url)
+ try:
+ 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
+
+ mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract id field')
+ return
+ yahoo_id = mobj.group(1)
+
+ mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract vid field')
+ return
+ yahoo_vid = mobj.group(1)
+
+ url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
+ return self._real_extract(url)
+
+ # Retrieve video webpage to extract further information
+ 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
+
+ # Extract uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
+ if mobj is None:
+ 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)
+
+ mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ # Extract video height and width
+ mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video height')
+ return
+ yv_video_height = mobj.group(1)
+
+ mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video width')
+ return
+ yv_video_width = mobj.group(1)
+
+ # Retrieve video playlist to extract media URL
+ # I'm not completely sure what all these options are, but we
+ # seem to need most of them, otherwise the server sends a 401.
+ 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')
+ 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
+
+ # Extract media URL from playlist XML
+ mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract media URL')
+ return
+ video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
+ video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for 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_stdout(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ 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
+
+ # 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,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
class YoutubeSearchIE(InfoExtractor):
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
- _MORE_PAGES_INDICATOR = r'>Next</a>'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
_max_youtube_results = 1000
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return [None]
+ return
prefix, query = query.split(':')
prefix = prefix[8:]
+ query = query.encode('utf-8')
if prefix == '':
- return self._download_n_results(query, 1)
+ self._download_n_results(query, 1)
+ return
elif prefix == 'all':
- return self._download_n_results(query, self._max_youtube_results)
+ self._download_n_results(query, self._max_youtube_results)
+ return
else:
try:
- n = int(prefix)
+ n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return [None]
+ return
elif n > self._max_youtube_results:
- self._downloader.trouble(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
- return self._download_n_results(query, n)
- except ValueError: # parsing prefix as int fails
- return self._download_n_results(query, 1)
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query"""
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 [None]
+ return
# Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
- information = []
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
- if self._MORE_PAGES_INDICATOR not in page:
- information = []
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
pagenum = pagenum + 1
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
+ _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return [None]
+ return
# Download playlist pages
playlist_id = mobj.group(1)
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 [None]
+ return
# Extract video identifiers
ids_in_page = []
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
- if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
+ if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
break
pagenum = pagenum + 1
- information = []
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+class YoutubeUserIE(InfoExtractor):
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+ _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):
+ """Report attempt to download user page."""
+ self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Download user page
+ username = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ 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
+
+ # 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)
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
class PostProcessor(object):
"""Post Processor class.
"""Run the PostProcessor.
The "information" argument is a dictionary like the ones
- returned by InfoExtractors. The only difference is that this
+ composed by InfoExtractors. The only difference is that this
one has an extra field called "filepath" that points to the
downloaded file.
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_stdout('Updating to latest stable version...')
+ latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+ latest_version = urllib.urlopen(latest_url).read().strip()
+ prog_url = 'http://bitbucket.org/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_stdout('Updated to version %s' % latest_version)
+
# General configuration
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
# Parse command line
parser = optparse.OptionParser(
- usage='Usage: %prog [options] url...',
- version='INTERNAL',
- conflict_handler='resolve',
- )
+ usage='Usage: %prog [options] url...',
+ version='2010.04.02',
+ conflict_handler='resolve',
+ )
+
parser.add_option('-h', '--help',
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
- parser.add_option('-u', '--username',
+ 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='L', help='download rate limit (e.g. 50k or 44.6m)')
+
+ authentication = optparse.OptionGroup(parser, 'Authentication Options')
+ authentication.add_option('-u', '--username',
dest='username', metavar='UN', help='account username')
- parser.add_option('-p', '--password',
+ authentication.add_option('-p', '--password',
dest='password', metavar='PW', help='account password')
- parser.add_option('-o', '--output',
- dest='outtmpl', metavar='TPL', help='output filename template')
- parser.add_option('-q', '--quiet',
+ 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='FMT', help='video format code')
+ video_format.add_option('-b', '--best-quality',
+ action='store_const', dest='format', help='download the best quality video possible', const='0')
+ video_format.add_option('-m', '--mobile-version',
+ action='store_const', dest='format', help='alias for -f 17', const='17')
+ video_format.add_option('-d', '--high-def',
+ action='store_const', dest='format', help='alias for -f 22', const='22')
+ video_format.add_option('--all-formats',
+ action='store_const', dest='format', help='download all available video formats', const='-1')
+ 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)
- parser.add_option('-s', '--simulate',
+ verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
- parser.add_option('-t', '--title',
- action='store_true', dest='usetitle', help='use title in file name', default=False)
- parser.add_option('-l', '--literal',
- action='store_true', dest='useliteral', help='use literal title in file name', default=False)
- parser.add_option('-n', '--netrc',
- action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
- parser.add_option('-g', '--get-url',
+ verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
- parser.add_option('-e', '--get-title',
+ verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
- parser.add_option('-f', '--format',
- dest='format', metavar='FMT', help='video format code')
- parser.add_option('-m', '--mobile-version',
- action='store_const', dest='format', help='alias for -f 17', const='17')
- parser.add_option('-d', '--high-def',
- action='store_const', dest='format', help='alias for -f 22', const='22')
- parser.add_option('-i', '--ignore-errors',
- action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
- parser.add_option('-r', '--rate-limit',
- dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
- parser.add_option('-a', '--batch-file',
+ 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('-o', '--output',
+ dest='outtmpl', metavar='TPL', help='output filename template')
+ filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='F', help='file containing URLs to download')
- parser.add_option('-w', '--no-overwrites',
+ filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
- (opts, args) = parser.parse_args()
+ filesystem.add_option('-c', '--continue',
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+ parser.add_option_group(filesystem)
+ (opts, args) = parser.parse_args()
+
# Batch file verification
batchurls = []
if opts.batchfile is not None:
try:
- batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+ batchurls = open(opts.batchfile, 'r').readlines()
+ batchurls = [x.strip() for x in batchurls]
+ batchurls = [x for x in batchurls if len(x) > 0]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
# Conflicting, missing and erroneous options
- if len(all_urls) < 1:
- sys.exit(u'ERROR: you must provide at least one URL')
if opts.usenetrc and (opts.username is not None or opts.password is not None):
- sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
+ parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
- sys.exit(u'ERROR: account username missing')
+ parser.error(u'account username missing')
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
- sys.exit(u'ERROR: using output template conflicts with using title or literal title')
+ parser.error(u'using output template conflicts with using title or literal title')
if opts.usetitle and opts.useliteral:
- sys.exit(u'ERROR: using title conflicts with using literal title')
+ 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:
- sys.exit(u'ERROR: invalid rate limit specified')
+ parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
# Information extractors
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_user_ie = YoutubeUserIE(youtube_ie)
youtube_search_ie = YoutubeSearchIE(youtube_ie)
+ google_ie = GoogleIE()
+ photobucket_ie = PhotobucketIE()
+ yahoo_ie = YahooIE()
+ generic_ie = GenericIE()
# File downloader
- charset = locale.getpreferredencoding()
- if charset is None:
- charset = 'ascii'
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
'format': opts.format,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(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 u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
+ 'continuedl': opts.continue_dl,
+ 'noprogress': opts.noprogress,
})
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(youtube_ie)
+ fd.add_info_extractor(google_ie)
+ fd.add_info_extractor(photobucket_ie)
+ fd.add_info_extractor(yahoo_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')
+ else:
+ sys.exit()
retcode = fd.download(all_urls)
sys.exit(retcode)