#!/usr/bin/env python
# -*- coding: utf-8 -*-
-__author__ = (
+__authors__ = (
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
+ 'Kevin Ngo',
+ 'Ori Avtalion',
+ 'shizeeg',
)
__license__ = 'Public Domain'
-__version__ = '2011.09.13'
+__version__ = '2012.02.27'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
-UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
import cookielib
import datetime
+import getpass
import gzip
import htmlentitydefs
+import HTMLParser
import httplib
import locale
import math
import netrc
+import optparse
import os
import os.path
import re
+import shlex
import socket
import string
import subprocess
try:
import xml.etree.ElementTree
-except ImportError: # Python<2.5
- pass # Not officially supported, but let it slip
+except ImportError: # Python<2.5: Not officially supported, but let it slip
+ warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
'Accept-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 msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout, filename)
- stream = open(filename, open_mode)
+ stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError), err:
# In case of error, try to remove win32 forbidden chars
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
# An exception here should be caught in the caller
- stream = open(filename, open_mode)
+ stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
+def _simplify_title(title):
+ expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+ return expr.sub(u'_', title).strip(u'_')
+
+def _orderedSet(iterable):
+ """ Remove all duplicates from the input iterable """
+ res = []
+ for el in iterable:
+ if el not in res:
+ res.append(el)
+ return res
+
+def _unescapeHTML(s):
+ """
+ @param s a string (of type unicode)
+ """
+ assert type(s) == type(u'')
+
+ htmlParser = HTMLParser.HTMLParser()
+ return htmlParser.unescape(s)
+
+def _encodeFilename(s):
+ """
+ @param s The name of the file (of type unicode)
+ """
+
+ assert type(s) == type(u'')
+
+ if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
+ # Pass u'' directly to use Unicode APIs on Windows 2000 and up
+ # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+ # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+ return s
+ else:
+ return s.encode(sys.getfilesystemencoding(), 'ignore')
class DownloadError(Exception):
"""Download Error exception.
"""
pass
+class MaxDownloadsReached(Exception):
+ """ --max-downloads limit has been reached. """
+ pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
noprogress: Do not print the progress bar.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
+ matchtitle: Download only matching titles.
+ rejecttitle: Reject downloads for matching titles.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
+ writesubtitles: Write the video subtitles to a .srt file
+ subtitleslang: Language of the subtitles to download
"""
params = None
self._pps.append(pp)
pp.set_downloader(self)
- def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
+ def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
- try:
- if not self.params.get('quiet', False):
- terminator = [u'\n', u''][skip_eol]
- print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+ assert type(message) == type(u'')
+ if not self.params.get('quiet', False):
+ terminator = [u'\n', u''][skip_eol]
+ output = message + terminator
+
+ if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
+ output = output.encode(preferredencoding(), 'ignore')
+ self._screen_file.write(output)
self._screen_file.flush()
- except (UnicodeEncodeError), err:
- if not ignore_encoding_errors:
- raise
def to_stderr(self, message):
"""Print message to stderr."""
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)):
+ (os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))):
return filename
return filename + u'.part'
try:
if old_filename == new_filename:
return
- os.rename(old_filename, new_filename)
+ os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename))
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
- if not os.path.isfile(filename):
+ if not os.path.isfile(_encodeFilename(filename)):
return
timestr = last_modified_hdr
if timestr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
- return
+ return filetime
try:
os.utime(filename, (time.time(), filetime))
except:
pass
+ return filetime
def report_writedescription(self, descfn):
""" Report that the description file is being written """
- self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+ self.to_screen(u'[info] Writing video description to: ' + descfn)
+
+ def report_writesubtitles(self, srtfn):
+ """ Report that the subtitles file is being written """
+ self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
def report_writeinfojson(self, infofn):
""" Report that the metadata file has been written """
- self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
+ self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
def report_destination(self, filename):
"""Report destination filename."""
- self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+ self.to_screen(u'[download] Destination: ' + filename)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
+ def _match_entry(self, info_dict):
+ """ Returns None iff the file should be downloaded """
+
+ title = info_dict['title']
+ matchtitle = self.params.get('matchtitle', False)
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+ rejecttitle = self.params.get('rejecttitle', False)
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ return None
+
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+
+ reason = self._match_entry(info_dict)
+ if reason is not None:
+ self.to_screen(u'[download] ' + reason)
+ return
+
+ max_downloads = self.params.get('max_downloads')
+ if max_downloads is not None:
+ if self._num_downloads > int(max_downloads):
+ raise MaxDownloadsReached()
+
filename = self.prepare_filename(info_dict)
+
+ # Forced printings
+ if self.params.get('forcetitle', False):
+ print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forceurl', False):
+ print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+ print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcedescription', False) and 'description' in info_dict:
+ print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcefilename', False) and filename is not None:
+ print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forceformat', False):
+ print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- # Forced printings
- if self.params.get('forcetitle', False):
- print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
- if self.params.get('forceurl', False):
- print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
- if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
- print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
- if self.params.get('forcedescription', False) and 'description' in info_dict:
- print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
- if self.params.get('forcefilename', False) and filename is not None:
- print filename.encode(preferredencoding(), 'xmlcharrefreplace')
-
return
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:
- dn = os.path.dirname(filename)
- if dn != '' and not os.path.exists(dn):
+ dn = os.path.dirname(_encodeFilename(filename))
+ if dn != '' and not os.path.exists(dn): # dn is already encoded
os.makedirs(dn)
except (OSError, IOError), err:
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
if self.params.get('writedescription', False):
try:
- descfn = filename + '.description'
+ descfn = filename + u'.description'
self.report_writedescription(descfn)
- descfile = open(descfn, 'wb')
+ descfile = open(_encodeFilename(descfn), 'wb')
try:
descfile.write(info_dict['description'].encode('utf-8'))
finally:
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write description file ' + descfn)
return
+
+ if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
+ # subtitles download errors are already managed as troubles in relevant IE
+ # that way it will silently go on when used with unsupporting IE
+ try:
+ srtfn = filename.rsplit('.', 1)[0] + u'.srt'
+ self.report_writesubtitles(srtfn)
+ srtfile = open(_encodeFilename(srtfn), 'wb')
+ try:
+ srtfile.write(info_dict['subtitles'].encode('utf-8'))
+ finally:
+ srtfile.close()
+ except (OSError, IOError):
+ self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
+ return
if self.params.get('writeinfojson', False):
- infofn = filename + '.info.json'
+ infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)
try:
json.dump
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')
+ infof = open(_encodeFilename(infofn), 'wb')
try:
- json.dump(info_dict, infof)
+ json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+ json.dump(json_info_dict, infof)
finally:
infof.close()
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
return
- try:
- success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
- except (OSError, IOError), err:
- raise UnavailableVideoError
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.trouble(u'ERROR: unable to download video data: %s' % str(err))
- return
- except (ContentTooShortError, ), err:
- self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
- return
-
- if success:
- try:
- self.post_process(filename, info_dict)
- except (PostProcessingError), err:
- self.trouble(u'ERROR: postprocessing: %s' % str(err))
- return
+ if not self.params.get('skip_download', False):
+ if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)):
+ success = True
+ else:
+ try:
+ success = self._do_download(filename, info_dict)
+ except (OSError, IOError), err:
+ raise UnavailableVideoError
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+ return
+ except (ContentTooShortError, ), err:
+ self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ return
+
+ if success:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble(u'ERROR: postprocessing: %s' % str(err))
+ return
def download(self, url_list):
"""Download a given list of URLs."""
# 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'] + [[], ['-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)])
+ basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
+ args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
+ if self.params.get('verbose', False):
+ try:
+ import pipes
+ shell_quote = lambda args: ' '.join(map(pipes.quote, args))
+ except ImportError:
+ shell_quote = repr
+ self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
+ retval = subprocess.call(args)
while retval == 2 or retval == 1:
- prevsize = os.path.getsize(tmpfilename)
+ prevsize = os.path.getsize(_encodeFilename(tmpfilename))
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
- cursize = os.path.getsize(tmpfilename)
+ cursize = os.path.getsize(_encodeFilename(tmpfilename))
if prevsize == cursize and retval == 1:
break
+ # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+ if prevsize == cursize and retval == 2 and cursize > 1024:
+ self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+ retval = 0
+ break
if retval == 0:
- self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
+ self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename)))
self.try_rename(tmpfilename, filename)
return True
else:
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False
- def _do_download(self, filename, url, player_url):
+ def _do_download(self, filename, info_dict):
+ url = info_dict['url']
+ player_url = info_dict.get('player_url', None)
+
# Check file already present
- if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
+ if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
return True
tmpfilename = self.temp_name(filename)
stream = None
- open_mode = 'wb'
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
request = urllib2.Request(url, None, headers)
# Establish possible resume length
- if os.path.isfile(tmpfilename):
- resume_len = os.path.getsize(tmpfilename)
+ if os.path.isfile(_encodeFilename(tmpfilename)):
+ resume_len = os.path.getsize(_encodeFilename(tmpfilename))
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'
+ open_mode = 'wb'
+ if resume_len != 0:
+ if self.params.get('continuedl', False):
+ self.report_resuming_byte(resume_len)
+ request.add_header('Range','bytes=%d-' % resume_len)
+ open_mode = 'ab'
+ else:
+ resume_len = 0
count = 0
retries = self.params.get('retries', 0)
while count <= retries:
# Establish connection
try:
+ if count == 0 and 'urlhandle' in info_dict:
+ data = info_dict['urlhandle']
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), err:
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 - 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)
+ if data_len is None:
+ self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+ else:
+ percent_str = self.calc_percent(byte_counter, data_len)
+ eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+ self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
# Update file modification time
if self.params.get('updatetime', True):
- self.try_utime(filename, data.info().get('last-modified', None))
+ info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
return True
description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods, as well as the suitable() static method.
- Probably, they should also be instantiated and added to the main
- downloader.
+ _real_extract() methods and define a _VALID_URL regexp.
+ Probably, they should also be added to the list of extractors.
"""
_ready = False
self._ready = False
self.set_downloader(downloader)
- @staticmethod
- def suitable(url):
+ def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
- return False
+ return re.match(self._VALID_URL, url) is not None
def initialize(self):
"""Initializes an instance (authentication, etc)."""
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
- _available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13']
+ _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
+ _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
+ '44': 'webm',
'45': 'webm',
}
-
- @staticmethod
- def suitable(url):
- return (re.match(YoutubeIE._VALID_URL, url) is not None)
+ _video_dimensions = {
+ '5': '240x400',
+ '6': '???',
+ '13': '???',
+ '17': '144x176',
+ '18': '360x640',
+ '22': '720x1280',
+ '34': '360x640',
+ '35': '480x854',
+ '37': '1080x1920',
+ '38': '3072x4096',
+ '43': '360x640',
+ '44': '480x854',
+ '45': '720x1280',
+ }
+ IE_NAME = u'youtube'
def report_lang(self):
"""Report attempt to set language."""
"""Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+ def report_video_subtitles_download(self, video_id):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
+
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected')
+ def _closed_captions_xml_to_srt(self, xml_string):
+ srt = ''
+ texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
+ # TODO parse xml instead of regex
+ for n, (start, dur_tag, dur, caption) in enumerate(texts):
+ if not dur: dur = '4'
+ start = float(start)
+ end = start + float(dur)
+ start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
+ end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
+ caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption)
+ caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional
+ srt += str(n) + '\n'
+ srt += start + ' --> ' + end + '\n'
+ srt += caption + '\n\n'
+ return srt
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for x in formats:
+ print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+
def _real_initialize(self):
if self._downloader is None:
return
# 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)
+ 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:
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'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail_url' not in video_info:
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')
+ mobj = re.search(r'<meta name="description" content="(.*?)">', 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
+
+ # closed captions
+ video_subtitles = None
+ if self._downloader.params.get('writesubtitles', False):
+ self.report_video_subtitles_download(video_id)
+ request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
+ try:
+ srt_list = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+ else:
+ srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
+ if srt_lang_list:
+ if self._downloader.params.get('subtitleslang', False):
+ srt_lang = self._downloader.params.get('subtitleslang')
+ elif 'en' in srt_lang_list:
+ srt_lang = 'en'
+ else:
+ srt_lang = srt_lang_list[0]
+ if not srt_lang in srt_lang_list:
+ self._downloader.trouble(u'WARNING: no closed captions found in the specified language')
+ else:
+ request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
+ try:
+ srt_xml = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+ else:
+ video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
+ else:
+ self._downloader.trouble(u'WARNING: video has no closed captions')
# token
video_token = urllib.unquote_plus(video_info['token'][0])
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):]
+ available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
+ if format_limit is not None and format_limit in available_formats:
+ format_list = available_formats[available_formats.index(format_limit):]
else:
- format_list = self._available_formats
+ format_list = 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:
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(existing_formats)
+ return
+ if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == '-1':
+ elif req_format == 'worst':
+ video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+ elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
- # Specific format
- if req_format not in url_map:
+ # Specific formats. We pick the first in a slash-delimeted sequence.
+ # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
+ req_formats = req_format.split('/')
+ video_url_list = None
+ for rf in req_formats:
+ if rf in url_map:
+ video_url_list = [(rf, url_map[rf])]
+ break
+ if video_url_list is None:
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 conn or url_encoded_fmt_stream_map information found in video info')
return
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'player_url': player_url,
+ 'subtitles': video_subtitles
})
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
+ IE_NAME = u'metacafe'
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
- @staticmethod
- def suitable(url):
- return (re.match(MetacafeIE._VALID_URL, url) is not None)
-
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return (re.match(DailymotionIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
self._downloader.increment_downloads()
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# 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'<meta property="og:title" content="(?P<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 = _unescapeHTML(mobj.group('title').decode('utf-8'))
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
- mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', 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
"""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=([^\&]+).*'
+ IE_NAME = u'video.google'
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_screen(u'[video.google] %s: Downloading webpage' % video_id)
"""Report information extraction."""
self._downloader.to_screen(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)
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)
+ simple_title = _simplify_title(video_title)
# Extract video description
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
"""Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ IE_NAME = u'photobucket'
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_screen(u'[photobucket] %s: Downloading webpage' % video_id)
"""Report information extraction."""
self._downloader.to_screen(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)
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)
+ simple_title = _simplify_title(vide_title)
video_uploader = mobj.group(2).decode('utf-8')
# _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]+)(?:[#\?].*)?'
+ IE_NAME = u'video.yahoo'
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_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
"""Report information extraction."""
self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, 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)
+ simple_title = _simplify_title(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:
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+ IE_NAME = u'vimeo'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- 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'[vimeo] %s: Downloading webpage' % video_id)
"""Report information extraction."""
self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
# Retrieve video webpage to extract further information
- request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
+ request = urllib2.Request(url, None, std_headers)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
- # Extract title
- mobj = re.search(r'<caption>(.*?)</caption>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
+ # Extract the config JSON
+ config = webpage.split(' = {config:')[1].split(',assets:')[0]
+ try:
+ config = json.loads(config)
+ except:
+ self._downloader.trouble(u'ERROR: unable to extract info section')
return
- video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Extract title
+ video_title = config["video"]["title"]
+ simple_title = _simplify_title(video_title)
# 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_uploader = config["video"]["owner"]["name"]
# 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')
+ video_thumbnail = config["video"]["thumbnail"]
- # # 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 request signature')
- return
- sig = mobj.group(1).decode('utf-8')
+ # Extract video description
+ try:
+ lxml.etree
+ except NameError:
+ video_description = u'No description available.'
+ mobj = re.search(r'<meta name="description" content="(.*?)" />', webpage, re.MULTILINE)
+ if mobj is not None:
+ video_description = mobj.group(1)
+ else:
+ html_parser = lxml.etree.HTMLParser()
+ vwebpage_doc = lxml.etree.parse(StringIO.StringIO(webpage), html_parser)
+ video_description = u''.join(vwebpage_doc.xpath('id("description")//text()')).strip()
+ # TODO use another parser
- # 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 request signature expiration')
+ # Extract upload date
+ video_upload_date = u'NA'
+ mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
+ if mobj is not None:
+ video_upload_date = mobj.group(1)
+
+ # Vimeo specific: extract request signature and timestamp
+ sig = config['request']['signature']
+ timestamp = config['request']['timestamp']
+
+ # Vimeo specific: extract video codec and quality information
+ # TODO bind to format param
+ codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
+ for codec in codecs:
+ if codec[0] in config["video"]["files"]:
+ video_codec = codec[0]
+ video_extension = codec[1]
+ if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
+ else: quality = 'sd'
+ break
+ else:
+ self._downloader.trouble(u'ERROR: no known codec found')
return
- sig_exp = mobj.group(1).decode('utf-8')
- video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
+ video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
+ %(video_id, sig, timestamp, quality, video_codec.upper())
try:
# Process video information
self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
+ 'id': video_id,
'url': video_url,
'uploader': video_uploader,
- 'upload_date': u'NA',
+ 'upload_date': video_upload_date,
'title': video_title,
'stitle': simple_title,
- 'ext': u'mp4',
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
+ 'ext': video_extension,
'thumbnail': video_thumbnail,
'description': video_description,
'player_url': None,
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
+ _VALID_URL = r'.*'
+ IE_NAME = u'generic'
+
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.')
"""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()
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)
+ simple_title = _simplify_title(video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
class YoutubeSearchIE(InfoExtractor):
"""Information Extractor for YouTube search queries."""
- _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'(?m)>\s*Next\s*</a>'
+ _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
+ _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
_youtube_ie = None
_max_youtube_results = 1000
+ IE_NAME = u'youtube:search'
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 report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._youtube_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
"""Downloads a specified number of results for a query"""
video_ids = []
- already_seen = set()
- pagenum = 1
+ pagenum = 0
+ limit = n
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ while (50 * pagenum) < limit:
+ self.report_download_page(query, pagenum+1)
+ result_url = self._API_URL % (urllib.quote_plus(query), (50*pagenum)+1)
request = urllib2.Request(result_url)
try:
- page = urllib2.urlopen(request).read()
+ data = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err))
return
+ api_response = json.loads(data)['data']
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ new_ids = list(video['id'] for video in api_response['items'])
+ video_ids += new_ids
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ limit = min(n, api_response['totalItems'])
+ pagenum += 1
- pagenum = pagenum + 1
+ if len(video_ids) > n:
+ video_ids = video_ids[:n]
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
class GoogleSearchIE(InfoExtractor):
"""Information Extractor for Google Video search queries."""
- _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+ _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
- _MORE_PAGES_INDICATOR = r'<span>Next</span>'
+ _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
+ _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
_google_ie = None
_max_google_results = 1000
+ IE_NAME = u'video.google:search'
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 report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._google_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
"""Downloads a specified number of results for a query"""
video_ids = []
- already_seen = set()
- pagenum = 1
+ pagenum = 0
while True:
self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum*10)
request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
# Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
video_id = mobj.group(1)
- if video_id not in already_seen:
+ if video_id not in video_ids:
video_ids.append(video_id)
- already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
for id in video_ids:
class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
- _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+ _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
_VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
_MORE_PAGES_INDICATOR = r'\s*Next'
_yahoo_ie = None
_max_yahoo_results = 1000
+ IE_NAME = u'video.yahoo:search'
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 report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._yahoo_ie.initialize()
def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ mobj = re.match(self._VALID_URL, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _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_-]+))?.*'
+ _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([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=(.+?)&'
+ _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
+ IE_NAME = u'youtube:playlist'
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 report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number."""
self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+ url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+ request = urllib2.Request(url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
# Extract video identifiers
ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1)
- video_ids = video_ids[playliststart:playlistend]
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
- _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+ _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_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=(.+?)&'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
_youtube_ie = None
+ IE_NAME = u'youtube:user'
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, start_index):
"""Report attempt to download user page."""
self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
else:
video_ids = video_ids[playliststart:playlistend]
- self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
(username, all_ids_count, len(video_ids)))
for video_id in video_ids:
class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com"""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
+ IE_NAME = u'DepositFiles'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- @staticmethod
- def suitable(url):
- return (re.match(DepositFilesIE._VALID_URL, url) is not None)
-
def report_download_webpage(self, file_id):
"""Report webpage download."""
self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
"""Report information extraction."""
self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
- def _real_initialize(self):
- return
-
def _real_extract(self, url):
# At this point we have a new file
self._downloader.increment_downloads()
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.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']
+ _available_formats = ['video', 'highqual', 'lowqual']
_video_extensions = {
+ 'video': 'mp4',
'highqual': 'mp4',
'lowqual': 'mp4',
}
+ IE_NAME = u'facebook'
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 _parse_page(self, video_webpage):
"""Extract video information from page"""
# General data
- data = {'title': r'class="video_title datawrap">(.*?)</',
+ data = {'title': r'\("video_title", "(.*?)"\)',
'description': r'<div class="datawrap">(.*?)</div>',
'owner': r'\("video_owner_name", "(.*?)"\)',
- 'upload_date': r'data-date="(.*?)"',
'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
}
video_info = {}
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'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail' not in video_info:
return
if req_format is None:
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif req_format == 'worst':
+ video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
elif req_format == '-1':
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
_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)
+ IE_NAME = u'blip.tv'
def report_extraction(self, file_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, 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 report_direct_download(self, title):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
request = urllib2.Request(json_url)
self.report_extraction(mobj.group(1))
+ info = None
try:
- json_code = urllib2.urlopen(request).read()
+ urlh = urllib2.urlopen(request)
+ if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+ basename = url.split('/')[-1]
+ title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
+ ext = ext.replace('.', '')
+ self.report_direct_download(title)
+ info = {
+ 'id': title,
+ 'url': url,
+ 'title': title,
+ 'stitle': _simplify_title(title),
+ 'ext': ext,
+ 'urlhandle': urlh
+ }
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)
+ if info is None: # Regular URL
+ try:
+ json_code = urlh.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
+ return
- self._downloader.increment_downloads()
+ 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)
+
+ info = {
+ 'id': data['item_id'],
+ 'url': video_url,
+ 'uploader': data['display_name'],
+ 'upload_date': upload_date,
+ 'title': data['title'],
+ 'stitle': _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
- 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
+ self._downloader.increment_downloads()
try:
self._downloader.process_info(info)
"""Information Extractor for myvideo.de."""
_VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+ IE_NAME = u'myvideo'
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)
"""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:
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)
video_title = mobj.group(1)
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
+
try:
- print(video_url)
self._downloader.process_info({
'id': video_id,
'url': video_url,
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>.*)$'
-
- @staticmethod
- def suitable(url):
- return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+ _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+ IE_NAME = u'comedycentral'
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_index_download(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % 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:
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = u'http://www.thedailyshow.com/full-episodes/'
else:
- url = 'http://www.colbertnation.com/full-episodes/'
+ url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
return
epTitle = mobj.group('episode')
- mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
+ mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(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)
+
+ playerUrl_raw = mMovieParams[0][0]
self.report_player_url(epTitle)
try:
- playerResponse = urllib2.urlopen(playerReq)
+ urlHandle = urllib2.urlopen(playerUrl_raw)
+ playerUrl = urlHandle.geturl()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+ return
+
+ uri = mMovieParams[0][1]
+ indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri})
+ self.report_index_download(epTitle)
+ try:
+ indexXml = urllib2.urlopen(indexUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
+ self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
return
- player_url = playerResponse.geturl()
- for actNum in range(ACT_COUNT):
- mediaNum = startMediaNum + actNum
- mediaId = movieId + str(mediaNum)
+ idoc = xml.etree.ElementTree.fromstring(indexXml)
+ itemEls = idoc.findall('.//item')
+ for itemEl in itemEls:
+ mediaId = itemEl.findall('./guid')[0].text
+ shortMediaId = mediaId.split(':')[-1]
+ showId = mediaId.split(':')[-2].replace('.com', '')
+ officialTitle = itemEl.findall('./title')[0].text
+ officialDate = itemEl.findall('./pubDate')[0].text
+
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
urllib.urlencode({'uri': mediaId}))
configReq = urllib2.Request(configUrl)
turls.append(finfo)
if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
continue
# For now, just pick the highest bitrate
self._downloader.increment_downloads()
- effTitle = show_id.replace('.com', '') + '-' + epTitle
+ effTitle = showId + u'-' + epTitle
info = {
- 'id': str(mediaNum),
+ 'id': shortMediaId,
'url': video_url,
- 'uploader': show_id,
- 'upload_date': 'NA',
+ 'uploader': showId,
+ 'upload_date': officialDate,
'title': effTitle,
- 'stitle': self._simplify_title(effTitle),
+ 'stitle': _simplify_title(effTitle),
'ext': 'mp4',
'format': format,
'thumbnail': None,
- 'description': 'TODO: Not yet supported',
- 'player_url': player_url
+ 'description': officialTitle,
+ 'player_url': playerUrl
}
try:
self._downloader.process_info(info)
except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+ self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
continue
-class PostProcessor(object):
- """Post Processor class.
+class EscapistIE(InfoExtractor):
+ """Information extractor for The Escapist """
- PostProcessor objects can be added to downloaders with their
- add_post_processor() method. When the downloader has finished a
- successful download, it will take its internal chain of PostProcessors
+ _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+ IE_NAME = u'escapist'
+
+ def report_extraction(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
+
+ def report_config_download(self, showName):
+ self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ showName = mobj.group('showname')
+ videoId = mobj.group('episode')
+
+ self.report_extraction(showName)
+ try:
+ webPage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+ return
+
+ descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
+ description = htmlParser.unescape(descMatch.group(1))
+ imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
+ imgUrl = htmlParser.unescape(imgMatch.group(1))
+ playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
+ playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+ configUrlMatch = re.search('config=(.*)$', playerUrl)
+ configUrl = urllib2.unquote(configUrlMatch.group(1))
+
+ self.report_config_download(showName)
+ try:
+ configJSON = urllib2.urlopen(configUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+ return
+
+ # Technically, it's JavaScript, not JSON
+ configJSON = configJSON.replace("'", '"')
+
+ try:
+ config = json.loads(configJSON)
+ except (ValueError,), err:
+ self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+ return
+
+ playlist = config['playlist']
+ videoUrl = playlist[1]['url']
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': videoId,
+ 'url': videoUrl,
+ 'uploader': showName,
+ 'upload_date': None,
+ 'title': showName,
+ 'stitle': _simplify_title(showName),
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': imgUrl,
+ 'description': description,
+ 'player_url': playerUrl,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+
+
+class CollegeHumorIE(InfoExtractor):
+ """Information extractor for collegehumor.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+ IE_NAME = u'collegehumor'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ 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('videoid')
+
+ self.report_webpage(video_id)
+ 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 download video webpage: %s' % str(err))
+ return
+
+ m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
+ if m is None:
+ self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+ return
+ internal_video_id = m.group('internalvideoid')
+
+ info = {
+ 'id': video_id,
+ 'internal_id': internal_video_id,
+ }
+
+ self.report_extraction(video_id)
+ xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+ try:
+ metaXml = urllib2.urlopen(xmlUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+ return
+
+ mdoc = xml.etree.ElementTree.fromstring(metaXml)
+ try:
+ videoNode = mdoc.findall('./video')[0]
+ info['description'] = videoNode.findall('./description')[0].text
+ info['title'] = videoNode.findall('./caption')[0].text
+ info['stitle'] = _simplify_title(info['title'])
+ info['url'] = videoNode.findall('./file')[0].text
+ info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+ info['ext'] = info['url'].rpartition('.')[2]
+ info['format'] = info['ext']
+ except IndexError:
+ self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ return
+
+ self._downloader.increment_downloads()
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+ """Information extractor for xvideos.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+ IE_NAME = u'xvideos'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ 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).decode('utf-8')
+
+ self.report_webpage(video_id)
+
+ request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+ try:
+ 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
+
+ self.report_extraction(video_id)
+
+
+ # Extract video URL
+ mobj = re.search(r'flv_url=(.+?)&', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+ # Extract title
+ mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+
+ # Extract video thumbnail
+ mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': video_thumbnail,
+ 'description': None,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class SoundcloudIE(InfoExtractor):
+ """Information extractor for soundcloud.com
+ To access the media, the uid of the song and a stream token
+ must be extracted from the page source and the script must make
+ a request to media.soundcloud.com/crossdomain.xml. Then
+ the media can be grabbed by requesting from an url composed
+ of the stream token and uid
+ """
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'soundcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # extract uploader (which is in the url)
+ uploader = mobj.group(1).decode('utf-8')
+ # extract simple title (uploader + slug of song title)
+ slug_title = mobj.group(2).decode('utf-8')
+ simple_title = uploader + '-' + slug_title
+
+ self.report_webpage('%s/%s' % (uploader, slug_title))
+
+ request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+ try:
+ 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
+
+ self.report_extraction('%s/%s' % (uploader, slug_title))
+
+ # extract uid and stream token that soundcloud hands out for access
+ mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
+ if mobj:
+ video_id = mobj.group(1)
+ stream_token = mobj.group(2)
+
+ # extract unsimplified title
+ mobj = re.search('"title":"(.*?)",', webpage)
+ if mobj:
+ title = mobj.group(1)
+
+ # construct media url (with uid/token)
+ mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
+ mediaURL = mediaURL % (video_id, stream_token)
+
+ # description
+ description = u'No description available'
+ mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
+ if mobj:
+ description = mobj.group(1)
+
+ # upload date
+ upload_date = None
+ mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
+ if mobj:
+ try:
+ upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+ except Exception, e:
+ print str(e)
+
+ # for soundcloud, a request to a cross domain is required for cookies
+ request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+
+ try:
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': mediaURL,
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': upload_date,
+ 'title': simple_title.decode('utf-8'),
+ 'stitle': simple_title.decode('utf-8'),
+ 'ext': u'mp3',
+ 'format': u'NA',
+ 'player_url': None,
+ 'description': description.decode('utf-8')
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class InfoQIE(InfoExtractor):
+ """Information extractor for infoq.com"""
+
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+ IE_NAME = u'infoq'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ def _real_extract(self, url):
+ htmlParser = HTMLParser.HTMLParser()
+
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ self.report_webpage(url)
+
+ 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 download video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(url)
+
+
+ # Extract video URL
+ mobj = re.search(r"jsclassref='([^']*)'", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+ # Extract title
+ mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+ # Extract description
+ video_description = u'No description available.'
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+
+ video_filename = video_url.split('/')[-1]
+ video_id, extension = video_filename.split('.')
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': extension,
+ 'format': extension, # Extension is always(?) mp4, but seems to be flv
+ 'thumbnail': None,
+ 'description': video_description,
+ 'player_url': None,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+class MixcloudIE(InfoExtractor):
+ """Information extractor for www.mixcloud.com"""
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'mixcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_json(self, file_id):
+ """Report JSON download."""
+ self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+ def get_urls(self, jsonData, fmt, bitrate='best'):
+ """Get urls from 'audio_formats' section in json"""
+ file_url = None
+ try:
+ bitrate_list = jsonData[fmt]
+ if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+ bitrate = max(bitrate_list) # select highest
+
+ url_list = jsonData[fmt][bitrate]
+ except TypeError: # we have no bitrate info.
+ url_list = jsonData[fmt]
+
+ return url_list
+
+ def check_urls(self, url_list):
+ """Returns 1st active url from list"""
+ for url in url_list:
+ try:
+ urllib2.urlopen(url)
+ return url
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ url = None
+
+ return None
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for fmt in formats.keys():
+ for b in formats[fmt]:
+ try:
+ ext = formats[fmt][b][0]
+ print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+ except TypeError: # we have no bitrate info
+ ext = formats[fmt][0]
+ print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+ break
+
+ 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
+ # extract uploader & filename from url
+ uploader = mobj.group(1).decode('utf-8')
+ file_id = uploader + "-" + mobj.group(2).decode('utf-8')
+
+ # construct API request
+ file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+ # retrieve .json file with links to files
+ request = urllib2.Request(file_url)
+ try:
+ self.report_download_json(file_url)
+ jsonData = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+ return
+
+ # parse JSON
+ json_data = json.loads(jsonData)
+ player_url = json_data['player_swf_url']
+ formats = dict(json_data['audio_formats'])
+
+ req_format = self._downloader.params.get('format', None)
+ bitrate = None
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ if req_format is None or req_format == 'best':
+ for format_param in formats.keys():
+ url_list = self.get_urls(formats, format_param)
+ # check urls
+ file_url = self.check_urls(url_list)
+ if file_url is not None:
+ break # got it!
+ else:
+ if req_format not in formats.keys():
+ self._downloader.trouble(u'ERROR: format is not available')
+ return
+
+ url_list = self.get_urls(formats, req_format)
+ file_url = self.check_urls(url_list)
+ format_param = req_format
+
+ # We have audio
+ self._downloader.increment_downloads()
+ try:
+ # Process file information
+ self._downloader.process_info({
+ 'id': file_id.decode('utf-8'),
+ 'url': file_url.decode('utf-8'),
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': u'NA',
+ 'title': json_data['name'],
+ 'stitle': _simplify_title(json_data['name']),
+ 'ext': file_url.split('.')[-1].decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': json_data['thumbnail_url'],
+ 'description': json_data['description'],
+ 'player_url': player_url.decode('utf-8'),
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download file')
+
+class StanfordOpenClassroomIE(InfoExtractor):
+ """Information extractor for Stanford's Open ClassRoom"""
+
+ _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+ IE_NAME = u'stanfordoc'
+
+ def report_download_webpage(self, objid):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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('course') and mobj.group('video'): # A specific video
+ course = mobj.group('course')
+ video = mobj.group('video')
+ info = {
+ 'id': _simplify_title(course + '_' + video),
+ }
+
+ self.report_extraction(info['id'])
+ baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
+ xmlUrl = baseUrl + video + '.xml'
+ try:
+ metaXml = urllib2.urlopen(xmlUrl).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err))
+ return
+ mdoc = xml.etree.ElementTree.fromstring(metaXml)
+ try:
+ info['title'] = mdoc.findall('./title')[0].text
+ info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
+ except IndexError:
+ self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+ return
+ info['stitle'] = _simplify_title(info['title'])
+ info['ext'] = info['url'].rpartition('.')[2]
+ info['format'] = info['ext']
+ self._downloader.increment_downloads()
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+ elif mobj.group('course'): # A course page
+ unescapeHTML = HTMLParser.HTMLParser().unescape
+
+ course = mobj.group('course')
+ info = {
+ 'id': _simplify_title(course),
+ 'type': 'playlist',
+ }
+
+ self.report_download_webpage(info['id'])
+ try:
+ coursepage = urllib2.urlopen(url).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+ return
+
+ m = re.search('<h1>([^<]+)</h1>', coursepage)
+ if m:
+ info['title'] = unescapeHTML(m.group(1))
+ else:
+ info['title'] = info['id']
+ info['stitle'] = _simplify_title(info['title'])
+
+ m = re.search('<description>([^<]+)</description>', coursepage)
+ if m:
+ info['description'] = unescapeHTML(m.group(1))
+
+ links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
+ info['list'] = [
+ {
+ 'type': 'reference',
+ 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
+ }
+ for vpage in links]
+
+ for entry in info['list']:
+ assert entry['type'] == 'reference'
+ self.extract(entry['url'])
+ else: # Root page
+ unescapeHTML = HTMLParser.HTMLParser().unescape
+
+ info = {
+ 'id': 'Stanford OpenClassroom',
+ 'type': 'playlist',
+ }
+
+ self.report_download_webpage(info['id'])
+ rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
+ try:
+ rootpage = urllib2.urlopen(rootURL).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+ return
+
+ info['title'] = info['id']
+ info['stitle'] = _simplify_title(info['title'])
+
+ links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
+ info['list'] = [
+ {
+ 'type': 'reference',
+ 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
+ }
+ for cpage in links]
+
+ for entry in info['list']:
+ assert entry['type'] == 'reference'
+ self.extract(entry['url'])
+
+class MTVIE(InfoExtractor):
+ """Information extractor for MTV.com"""
+
+ _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
+ IE_NAME = u'mtv'
+
+ def report_webpage(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+ 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 not mobj.group('proto'):
+ url = 'http://' + url
+ video_id = mobj.group('videoid')
+ self.report_webpage(video_id)
+
+ 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 download video webpage: %s' % str(err))
+ return
+
+ mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract song name')
+ return
+ song_name = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
+ mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract performer')
+ return
+ performer = _unescapeHTML(mobj.group(1).decode('iso-8859-1'))
+ video_title = performer + ' - ' + song_name
+
+ mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to mtvn_uri')
+ return
+ mtvn_uri = mobj.group(1)
+
+ mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract content id')
+ return
+ content_id = mobj.group(1)
+
+ videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
+ self.report_extraction(video_id)
+ request = urllib2.Request(videogen_url)
+ try:
+ metadataXml = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err))
+ return
+
+ mdoc = xml.etree.ElementTree.fromstring(metadataXml)
+ renditions = mdoc.findall('.//rendition')
+
+ # For now, always pick the highest quality.
+ rendition = renditions[-1]
+
+ try:
+ _,_,ext = rendition.attrib['type'].partition('/')
+ format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
+ video_url = rendition.find('./src').text
+ except KeyError:
+ self._downloader.trouble('Invalid rendition field.')
+ return
+
+ self._downloader.increment_downloads()
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': performer,
+ 'title': video_title,
+ 'stitle': _simplify_title(video_title),
+ 'ext': ext,
+ 'format': format,
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class PostProcessor(object):
+ """Post Processor class.
+
+ PostProcessor objects can be added to downloaders with their
+ add_post_processor() method. When the downloader has finished a
+ successful download, it will take its internal chain of PostProcessors
and start calling the run() method on each one of them, first with
an initial argument and then with the returned value of the previous
PostProcessor.
"""
return information # by default, do nothing
+class AudioConversionError(BaseException):
+ def __init__(self, message):
+ self.message = message
class FFmpegExtractAudioPP(PostProcessor):
- def __init__(self, downloader=None, preferredcodec=None):
+ def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
PostProcessor.__init__(self, downloader)
if preferredcodec is None:
preferredcodec = 'best'
self._preferredcodec = preferredcodec
+ self._preferredquality = preferredquality
+ self._keepvideo = keepvideo
@staticmethod
def get_audio_codec(path):
try:
- cmd = ['ffprobe', '-show_streams', '--', path]
+ cmd = ['ffprobe', '-show_streams', '--', _encodeFilename(path)]
handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
output = handle.communicate()[0]
if handle.wait() != 0:
@staticmethod
def run_ffmpeg(path, out_path, codec, more_opts):
+ if codec is None:
+ acodec_opts = []
+ else:
+ acodec_opts = ['-acodec', codec]
+ cmd = ['ffmpeg', '-y', '-i', _encodeFilename(path), '-vn'] + acodec_opts + more_opts + ['--', _encodeFilename(out_path)]
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)
+ p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ stdout,stderr = p.communicate()
except (IOError, OSError):
- return False
+ e = sys.exc_info()[1]
+ if isinstance(e, OSError) and e.errno == 2:
+ raise AudioConversionError('ffmpeg not found. Please install ffmpeg.')
+ else:
+ raise e
+ if p.returncode != 0:
+ msg = stderr.strip().split('\n')[-1]
+ raise AudioConversionError(msg)
def run(self, information):
path = information['filepath']
return None
more_opts = []
- if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
- if filecodec == 'aac' or filecodec == 'mp3':
+ if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
+ if self._preferredcodec == 'm4a' and filecodec == 'aac':
+ # Lossless, but in another container
+ acodec = 'copy'
+ extension = self._preferredcodec
+ more_opts = ['-absf', 'aac_adtstoasc']
+ elif filecodec in ['aac', 'mp3', 'vorbis']:
# Lossless if possible
acodec = 'copy'
extension = filecodec
if filecodec == 'aac':
more_opts = ['-f', 'adts']
+ if filecodec == 'vorbis':
+ extension = 'ogg'
else:
# MP3 otherwise.
acodec = 'libmp3lame'
extension = 'mp3'
- more_opts = ['-ab', '128k']
+ more_opts = []
+ if self._preferredquality is not None:
+ more_opts += ['-ab', self._preferredquality]
else:
# We convert the audio (lossy)
- acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+ acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
extension = self._preferredcodec
- more_opts = ['-ab', '128k']
+ more_opts = []
+ if self._preferredquality is not None:
+ more_opts += ['-ab', self._preferredquality]
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
-
+ if self._preferredcodec == 'm4a':
+ more_opts += ['-absf', 'aac_adtstoasc']
+ if self._preferredcodec == 'vorbis':
+ extension = 'ogg'
+ if self._preferredcodec == 'wav':
+ extension = 'wav'
+ more_opts += ['-f', 'wav']
+
+ prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
+ new_path = prefix + sep + extension
+ self._downloader.to_screen(u'[ffmpeg] Destination: ' + new_path)
try:
- os.remove(path)
- except (IOError, OSError):
- self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+ self.run_ffmpeg(path, new_path, acodec, more_opts)
+ except:
+ etype,e,tb = sys.exc_info()
+ if isinstance(e, AudioConversionError):
+ self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
+ else:
+ self._downloader.to_stderr(u'ERROR: error running ffmpeg')
return None
+ # Try to update the date time for extracted audio file.
+ if information.get('filetime') is not None:
+ try:
+ os.utime(_encodeFilename(new_path), (time.time(), information['filetime']))
+ except:
+ self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+ if not self._keepvideo:
+ try:
+ os.remove(_encodeFilename(path))
+ except (IOError, OSError):
+ self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+ return None
+
information['filepath'] = new_path
return information
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
- downloader.to_screen('Updating to latest version...')
+ downloader.to_screen(u'Updating to latest version...')
try:
try:
urlh = urllib.urlopen(UPDATE_URL)
newcontent = urlh.read()
+
+ vmatch = re.search("__version__ = '([^']+)'", newcontent)
+ if vmatch is not None and vmatch.group(1) == __version__:
+ downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
+ return
finally:
urlh.close()
except (IOError, OSError), err:
except (IOError, OSError), err:
sys.exit('ERROR: unable to overwrite current version')
- downloader.to_screen('Updated youtube-dl. Restart to use the new version.')
+ downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
def parseOpts():
- # Deferred imports
- import getpass
- import optparse
+ def _readOptions(filename_bytes):
+ try:
+ optionf = open(filename_bytes)
+ except IOError:
+ return [] # silently skip if file is not present
+ try:
+ res = []
+ for l in optionf:
+ res += shlex.split(l, comments=True)
+ finally:
+ optionf.close()
+ return res
def _format_option_string(option):
''' ('-o', '--option') -> -o, --format METAVAR'''
kw = {
'version' : __version__,
'formatter' : fmt,
- 'usage' : '%prog [options] url...',
+ 'usage' : '%prog [options] url [url...]',
'conflict_handler' : 'resolve',
}
# option groups
general = optparse.OptionGroup(parser, 'General Options')
+ selection = optparse.OptionGroup(parser, 'Video Selection')
authentication = optparse.OptionGroup(parser, 'Authentication Options')
video_format = optparse.OptionGroup(parser, 'Video Format Options')
postproc = optparse.OptionGroup(parser, 'Post-processing Options')
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)
+ general.add_option('--list-extractors',
+ action='store_true', dest='list_extractors',
+ help='List all supported extractors and the URLs they would handle', default=False)
+
+ selection.add_option('--playlist-start',
+ dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+ selection.add_option('--playlist-end',
+ dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+ selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
+ selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
+ selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
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')
+ action='store_const', dest='format', help='download all available video formats', const='all')
+ video_format.add_option('--prefer-free-formats',
+ action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+ video_format.add_option('-F', '--list-formats',
+ action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
+ video_format.add_option('--write-srt',
+ action='store_true', dest='writesubtitles',
+ help='write video closed captions to a .srt file (currently youtube only)', default=False)
+ video_format.add_option('--srt-lang',
+ action='store', dest='subtitleslang', metavar='LANG',
+ help='language of the closed captions to download (optional) use IETF language tags like \'en\'')
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)
+ action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
+ verbosity.add_option('--skip-download',
+ action='store_true', dest='skip_download', help='do not download the 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',
verbosity.add_option('--get-filename',
action='store_true', dest='getfilename',
help='simulate, quiet but print output filename', default=False)
+ verbosity.add_option('--get-format',
+ action='store_true', dest='getformat',
+ help='simulate, quiet but print output format', 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)
+ verbosity.add_option('-v', '--verbose',
+ action='store_true', dest='verbose', help='print various debugging information', default=False)
filesystem.add_option('-t', '--title',
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')
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.')
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)
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True)
+ filesystem.add_option('--no-continue',
+ action='store_false', dest='continue_dl',
+ help='do not resume partially downloaded files (restart from beginning)')
filesystem.add_option('--cookies',
- dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+ dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
filesystem.add_option('--no-part',
action='store_true', dest='nopart', help='do not use .part files', default=False)
filesystem.add_option('--no-mtime',
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')
+ help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
+ postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
+ help='ffmpeg audio bitrate specification, 128k by default')
+ postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
+ help='keeps the video file on disk after the post-processing; the video is erased by default')
parser.add_option_group(general)
+ parser.add_option_group(selection)
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()
+ xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+ if xdg_config_home:
+ userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
+ else:
+ userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+ argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
+ opts, args = parser.parse_args(argv)
return parser, opts, args
-def main():
+def gen_extractors():
+ """ Return a list of an instance of every supported extractor.
+ The order does matter; the first extractor matched is the one handling the URL.
+ """
+ youtube_ie = YoutubeIE()
+ google_ie = GoogleIE()
+ yahoo_ie = YahooIE()
+ return [
+ YoutubePlaylistIE(youtube_ie),
+ YoutubeUserIE(youtube_ie),
+ YoutubeSearchIE(youtube_ie),
+ youtube_ie,
+ MetacafeIE(youtube_ie),
+ DailymotionIE(),
+ google_ie,
+ GoogleSearchIE(google_ie),
+ PhotobucketIE(),
+ yahoo_ie,
+ YahooSearchIE(yahoo_ie),
+ DepositFilesIE(),
+ FacebookIE(),
+ BlipTVIE(),
+ VimeoIE(),
+ MyVideoIE(),
+ ComedyCentralIE(),
+ EscapistIE(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+ MixcloudIE(),
+ StanfordOpenClassroomIE(),
+ MTVIE(),
+
+ GenericIE()
+ ]
+
+def _real_main():
parser, opts, args = parseOpts()
# Open appropriate CookieJar
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:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
+ # General configuration
+ cookie_processor = urllib2.HTTPCookieProcessor(jar)
+ proxy_handler = urllib2.ProxyHandler()
+ opener = urllib2.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+ urllib2.install_opener(opener)
+ socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+ if opts.verbose:
+ print(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
+
+ extractors = gen_extractors()
+
+ if opts.list_extractors:
+ for ie in extractors:
+ print(ie.IE_NAME)
+ matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
+ all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+ for mu in matchedUrls:
+ print(u' ' + mu)
+ sys.exit(0)
+
# 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')
except (TypeError, ValueError), err:
parser.error(u'invalid playlist end number specified')
if opts.extractaudio:
- if opts.audioformat not in ['best', 'aac', 'mp3']:
+ if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
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),
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'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),
+ 'forceformat': opts.getformat,
+ 'simulate': opts.simulate,
+ 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'format': opts.format,
'format_limit': opts.format_limit,
+ 'listformats': opts.listformats,
'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')
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson,
+ 'writesubtitles': opts.writesubtitles,
+ 'subtitleslang': opts.subtitleslang,
+ 'matchtitle': opts.matchtitle,
+ 'rejecttitle': opts.rejecttitle,
+ 'max_downloads': opts.max_downloads,
+ 'prefer_free_formats': opts.prefer_free_formats,
+ 'verbose': opts.verbose,
})
- 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)
+ for extractor in extractors:
+ fd.add_info_extractor(extractor)
# PostProcessors
if opts.extractaudio:
- fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
+ fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
# Update version
if opts.update_self:
parser.error(u'you must provide at least one URL')
else:
sys.exit()
- retcode = fd.download(all_urls)
+
+ try:
+ retcode = fd.download(all_urls)
+ except MaxDownloadsReached:
+ fd.to_screen(u'--max-download limit reached, aborting.')
+ retcode = 101
# Dump cookie jar if requested
if opts.cookiefile is not None:
sys.exit(retcode)
-
-if __name__ == '__main__':
+def main():
try:
- main()
+ _real_main()
except DownloadError:
sys.exit(1)
except SameFileError:
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
+if __name__ == '__main__':
+ main()
+
# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python:
git://git.jankratochvil.net / youtube-dl.git / blobdiff