# -*- coding: utf-8 -*-
# Author: Ricardo Garcia Gonzalez
# Author: Danny Colligan
+# Author: Benjamin Johnson
# License: Public domain code
import htmlentitydefs
import httplib
import re
import socket
import string
+import subprocess
import sys
import time
import urllib
import urllib2
+# parse_qs was moved from the cgi module to the urlparse module recently.
+try:
+ from urlparse import parse_qs
+except ImportError:
+ from cgi import parse_qs
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
'Accept-Language': 'en-us,en;q=0.5',
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
+ def yield_preferredencoding():
+ try:
+ pref = locale.getpreferredencoding()
+ u'TEST'.encode(pref)
+ except:
+ pref = 'UTF-8'
+ while True:
+ yield pref
+ return yield_preferredencoding().next()
+
+def htmlentity_transform(matchobj):
+ """Transforms an HTML entity to a Unicode character.
+
+ This function receives a match object and is intended to be used with
+ the re.sub() function.
+ """
+ entity = matchobj.group(1)
+
+ # Known non-numeric HTML entity
+ if entity in htmlentitydefs.name2codepoint:
+ return unichr(htmlentitydefs.name2codepoint[entity])
+
+ # Unicode character
+ mobj = re.match(ur'(?u)#(x?\d+)', entity)
+ if mobj is not None:
+ numstr = mobj.group(1)
+ if numstr.startswith(u'x'):
+ base = 16
+ numstr = u'0%s' % numstr
+ else:
+ base = 10
+ return unichr(long(numstr, base))
+
+ # Unknown entity in name, return its literal representation
+ return (u'&%s;' % entity)
+
+def sanitize_title(utitle):
+ """Sanitizes a video title so it could be used as part of a filename."""
+ utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
+ return utitle.replace(unicode(os.sep), u'%')
+
+def sanitize_open(filename, open_mode):
+ """Try to open the given filename, and slightly tweak it if this fails.
+
+ Attempts to open the given filename. If this fails, it tries to change
+ the filename slightly, step by step, until it's either able to open it
+ or it fails and raises a final exception, like the standard open()
+ function.
+
+ It returns the tuple (stream, definitive_file_name).
+ """
try:
- pref = locale.getpreferredencoding()
- # Mac OSX systems have this problem sometimes
- if pref == '':
- return 'UTF-8'
- return pref
- except:
- sys.stderr.write('WARNING: problem obtaining preferred encoding. Falling back to UTF-8.\n')
- return 'UTF-8'
+ if filename == u'-':
+ return (sys.stdout, filename)
+ stream = open(filename, open_mode)
+ return (stream, filename)
+ except (IOError, OSError), err:
+ # In case of error, try to remove win32 forbidden chars
+ filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename)
+
+ # An exception here should be caught in the caller
+ stream = open(filename, open_mode)
+ return (stream, filename)
+
class DownloadError(Exception):
"""Download Error exception.
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
+ retries: Number of times to retry for HTTP error 503
continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
"""
params = None
_ies = []
_pps = []
_download_retcode = None
+ _num_downloads = None
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._pps = []
self._download_retcode = 0
+ self._num_downloads = 0
self.params = params
@staticmethod
self._pps.append(pp)
pp.set_downloader(self)
- def to_stdout(self, message, skip_eol=False):
+ def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
- if not self.params.get('quiet', False):
- print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
+ try:
+ if not self.params.get('quiet', False):
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
sys.stdout.flush()
+ except (UnicodeEncodeError), err:
+ if not ignore_encoding_errors:
+ raise
def to_stderr(self, message):
"""Print message to stderr."""
def report_destination(self, filename):
"""Report destination filename."""
- self.to_stdout(u'[download] Destination: %s' % filename)
+ self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
+ if self.params.get('noprogress', False):
+ return
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
"""Report attemtp to resume at given byte."""
self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+ def report_retry(self, count, retries):
+ """Report retry in case of HTTP error 503"""
+ self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries))
+
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
- self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+ try:
+ self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+ except (UnicodeEncodeError), err:
+ self.to_stdout(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
def report_finish(self):
"""Report download finished."""
- self.to_stdout(u'')
+ if self.params.get('noprogress', False):
+ self.to_stdout(u'[download] Download completed')
+ else:
+ self.to_stdout(u'')
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- try:
- info_dict['url'] = self.verify_url(info_dict['url'])
- except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise UnavailableFormatError
+ # Verify URL if it's an HTTP one
+ if info_dict['url'].startswith('http'):
+ try:
+ self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+ except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+ raise UnavailableFormatError
# Forced printings
if self.params.get('forcetitle', False):
- print info_dict['title'].encode(preferredencoding())
+ print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceurl', False):
- print info_dict['url'].encode(preferredencoding())
+ 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')
return
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
+ template_dict['ord'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
- if self.params['nooverwrites'] and os.path.exists(filename):
+ if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
return
return
try:
- success = self._do_download(filename, info_dict['url'])
+ success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
raise UnavailableFormatError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
if info is None:
break
- def _do_download(self, filename, url):
- stream = None
- open_mode = 'ab'
+ def _download_with_rtmpdump(self, filename, url, player_url):
+ self.report_destination(filename)
+ # Check for rtmpdump first
+ try:
+ subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ except (OSError, IOError):
+ self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+ return False
+
+ # Download using rtmpdump. rtmpdump returns exit code 2 when
+ # the connection was interrumpted and resuming appears to be
+ # possible. This is part of rtmpdump's normal usage, AFAIK.
+ basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename]
+ retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+ while retval == 2 or retval == 1:
+ prevsize = os.path.getsize(filename)
+ self.to_stdout(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(filename)
+ if prevsize == cursize and retval == 1:
+ break
+ if retval == 0:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ return True
+ else:
+ self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+ return False
+
+ def _do_download(self, filename, url, player_url):
+ # Attempt to download using rtmpdump
+ if url.startswith('rtmp'):
+ return self._download_with_rtmpdump(filename, url, player_url)
+
+ stream = None
+ open_mode = 'wb'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
- # Attempt to resume download with "continuedl" option
+ # Establish possible resume length
if os.path.isfile(filename):
resume_len = os.path.getsize(filename)
else:
resume_len = 0
- if self.params['continuedl'] and resume_len != 0:
+
+ # Request parameters in case of being able to resume
+ if self.params.get('continuedl', False) and resume_len != 0:
self.report_resuming_byte(resume_len)
request.add_header('Range','bytes=%d-' % resume_len)
+ open_mode = 'ab'
- # Establish connection
- try:
- data = urllib2.urlopen(request)
- except (urllib2.HTTPError, ), err:
- if err.code != 416: # 416 is 'Requested range not satisfiable'
- raise
- data = urllib2.urlopen(basic_request)
- content_length = data.info()['Content-Length']
- if content_length is not None and long(content_length) == resume_len:
- self.report_file_already_downloaded(filename)
- return True
- else:
- self.report_unable_to_resume()
- open_mode = 'wb'
+ count = 0
+ retries = self.params.get('retries', 0)
+ while True:
+ # Establish connection
+ try:
+ data = urllib2.urlopen(request)
+ break
+ except (urllib2.HTTPError, ), err:
+ if err.code == 503:
+ # Retry in case of HTTP error 503
+ count += 1
+ if count <= retries:
+ self.report_retry(count, retries)
+ continue
+ if err.code != 416: # 416 is 'Requested range not satisfiable'
+ raise
+ # Unable to resume
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+
+ if content_length is not None and long(content_length) == resume_len:
+ # Because the file had already been fully downloaded
+ self.report_file_already_downloaded(filename)
+ self._num_downloads += 1
+ return True
+ else:
+ # Because the server didn't let us
+ self.report_unable_to_resume()
+ open_mode = 'wb'
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
# Open file just in time
if stream is None:
try:
- stream = open(filename, open_mode)
+ (stream, filename) = sanitize_open(filename, open_mode)
self.report_destination(filename)
+ self._num_downloads += 1
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return False
- stream.write(data_block)
+ try:
+ stream.write(data_block)
+ except (IOError, OSError), err:
+ self.trouble('\nERROR: unable to write data: %s' % str(err))
block_size = self.best_block_size(after - before, data_block_len)
# Progress message
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
+ format: Video format.
+ player_url: SWF Player URL (may be None).
+
+ The following fields are optional. Their primary purpose is to allow
+ youtube-dl to serve as the backend for a video search function, such
+ as the one in youtube2mp3. They are only used when their respective
+ forced printing functions are called:
+
+ thumbnail: Full URL to a video thumbnail image.
+ description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods, as well as the suitable() static method.
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
- _available_formats = ['22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag
+ _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
+ '37': 'mp4',
+ '43': 'webm',
+ '45': 'webm',
}
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
- @staticmethod
- def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a Unicode character."""
- entity = matchobj.group(1)
-
- # Known non-numeric HTML entity
- if entity in htmlentitydefs.name2codepoint:
- return unichr(htmlentitydefs.name2codepoint[entity])
-
- # Unicode character
- mobj = re.match(ur'(?u)#(x?\d+)', entity)
- if mobj is not None:
- numstr = mobj.group(1)
- if numstr.startswith(u'x'):
- base = 16
- numstr = u'0%s' % numstr
- else:
- base = 10
- return unichr(long(numstr, base))
-
- # Unknown entity in name, return its literal representation
- return (u'&%s;' % entity)
-
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_stdout(u'[youtube] Setting language')
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[youtube] Confirming age')
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
"""Report extracted video URL."""
self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+ def report_rtmp_download(self):
+ """Indicate the download will use the RTMP protocol."""
+ self._downloader.to_stdout(u'[youtube] RTMP download detected')
+
def _real_initialize(self):
if self._downloader is None:
return
# Downloader parameters
best_quality = False
+ all_formats = False
format_param = None
quality_index = 0
if self._downloader is not None:
if format_param == '0':
format_param = self._available_formats[quality_index]
best_quality = True
+ elif format_param == '-1':
+ format_param = self._available_formats[quality_index]
+ all_formats = True
while True:
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
- # Get video info
- video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id
- request = urllib2.Request(video_info_url, None, std_headers)
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
try:
- self.report_video_info_webpage_download(video_id)
- video_info_webpage = urllib2.urlopen(request).read()
+ video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return
+
+ # Attempt to extract SWF player URL
+ mobj = re.search(r'swfConfig.*"(http://.*?watch-.*?\.swf)"', video_webpage)
+ if mobj is not None:
+ player_url = mobj.group(1)
+ else:
+ player_url = None
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url, None, std_headers)
+ try:
+ video_info_webpage = urllib2.urlopen(request).read()
+ video_info = parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
self.report_information_extraction(video_id)
# "t" param
- mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
- if mobj is None:
+ if 'token' not in video_info:
# Attempt to see if YouTube has issued an error message
- mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
- if mobj is None:
+ if 'reason' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
stream.write(video_info_webpage)
stream.close()
else:
- reason = urllib.unquote_plus(mobj.group(1))
+ reason = urllib.unquote_plus(video_info['reason'][0])
self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
return
- token = urllib.unquote(mobj.group(1))
+ token = urllib.unquote_plus(video_info['token'][0])
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+ # Check possible RTMP download
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_real_url = video_info['conn'][0]
+
# uploader
- mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
- if mobj is None:
+ if 'author' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
- video_uploader = urllib.unquote(mobj.group(1))
+ video_uploader = urllib.unquote_plus(video_info['author'][0])
# title
- mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage)
- if mobj is None:
+ if 'title' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
- video_title = urllib.unquote(mobj.group(1))
+ video_title = urllib.unquote_plus(video_info['title'][0])
video_title = video_title.decode('utf-8')
- video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
- video_title = video_title.replace(os.sep, u'%')
+ video_title = sanitize_title(video_title)
# simplified title
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
+ # thumbnail image
+ if 'thumbnail_url' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else: # don't panic if we can't find it
+ video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+
+ # description
+ video_description = 'No description available.'
+ if self._downloader.params.get('forcedescription', False):
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+ if mobj is not None:
+ video_description = mobj.group(1)
+
try:
# Process video information
self._downloader.process_info({
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description.decode('utf-8'),
+ 'player_url': player_url,
})
+ if all_formats:
+ quality_index += 1
+ if quality_index == len(self._available_formats):
+ # None left to get
+ return
+ else:
+ format_param = self._available_formats[quality_index]
+ continue
return
except UnavailableFormatError, err:
- if best_quality:
- if quality_index == len(self._available_formats) - 1:
+ if best_quality or all_formats:
+ quality_index += 1
+ if quality_index == len(self._available_formats):
# I don't ever expect this to happen
- self._downloader.trouble(u'ERROR: no known formats available for video')
+ if not all_formats:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
return
else:
self.report_unavailable_format(video_id, format_param)
- quality_index += 1
format_param = self._available_formats[quality_index]
continue
else:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
- mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
+ mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
})
except UnavailableFormatError:
self._downloader.trouble(u'ERROR: format not available for video')
-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>'
- _youtube_ie = None
- _max_youtube_results = 1000
+class GoogleIE(InfoExtractor):
+ """Information extractor for video.google.com."""
- def __init__(self, youtube_ie, downloader=None):
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+
+ def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
+
@staticmethod
def suitable(url):
- return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+ return (re.match(GoogleIE._VALID_URL, url) is not None)
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_QUERY, query)
+ return
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
- prefix, query = query.split(':')
- prefix = prefix[8:]
- if prefix == '':
- self._download_n_results(query, 1)
+ video_id = mobj.group(1)
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r"download_url:'([^']+)'", webpage)
+ if mobj is None:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
+ mediaURL = urllib.unquote(mobj.group(1))
+ mediaURL = mediaURL.replace('\\x3d', '\x3d')
+ mediaURL = mediaURL.replace('\\x26', '\x26')
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
+ video_url = mediaURL
- video_ids = []
- already_seen = set()
- pagenum = 1
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url, None, std_headers)
+ # Extract video description
+ mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', 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.'
+
+ # Extract video thumbnail
+ if self._downloader.params.get('forcethumbnail', False):
+ request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
try:
- page = urllib2.urlopen(request).read()
+ webpage = 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 retrieve video webpage: %s' % str(err))
+ return
+ mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
return
+ video_thumbnail = mobj.group(1)
+ else: # we need something to pass to process_info
+ video_thumbnail = ''
- # 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
- 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
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
- pagenum = pagenum + 1
-class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
+class PhotobucketIE(InfoExtractor):
+ """Information extractor for photobucket.com."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
- _youtube_ie = None
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- def __init__(self, youtube_ie, downloader=None):
+ def __init__(self, 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)
+ return (re.match(PhotobucketIE._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_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
def _real_initialize(self):
- self._youtube_ie.initialize()
-
+ return
+
def _real_extract(self, url):
- # Extract playlist id
+ # Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
- # Download playlist pages
- playlist_id = mobj.group(1)
- video_ids = []
- pagenum = 1
+ video_id = mobj.group(1)
- while True:
- self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
+ video_extension = 'flv'
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
- if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
- break
- pagenum = pagenum + 1
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ video_url = mediaURL
-class PostProcessor(object):
- """Post Processor class.
+ mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- 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.
+ video_uploader = mobj.group(2).decode('utf-8')
- The chain will be stopped if one of them ever returns None or the end
- of the chain is reached.
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class YahooIE(InfoExtractor):
+ """Information extractor for video.yahoo.com."""
+
+ # _VALID_URL matches all Yahoo! Video URLs
+ # _VPAGE_URL matches only the extractable '/watch/' URLs
+ _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
+ _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YahooIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract ID from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(2)
+ video_extension = 'flv'
+
+ # Rewrite valid but non-extractable URLs as
+ # extractable English language /watch/ URLs
+ if re.match(self._VPAGE_URL, url) is None:
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract id field')
+ return
+ yahoo_id = mobj.group(1)
+
+ mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract vid field')
+ return
+ yahoo_vid = mobj.group(1)
+
+ url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
+ return self._real_extract(url)
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ # Extract video thumbnail
+ mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+ # Extract video description
+ mobj = re.search(r'<meta name="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.'
+
+ # Extract video height and width
+ mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video height')
+ return
+ yv_video_height = mobj.group(1)
+
+ mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video width')
+ return
+ yv_video_width = mobj.group(1)
+
+ # Retrieve video playlist to extract media URL
+ # I'm not completely sure what all these options are, but we
+ # seem to need most of them, otherwise the server sends a 401.
+ yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
+ yv_bitrate = '700' # according to Wikipedia this is hard-coded
+ request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
+ '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+ '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract media URL from playlist XML
+ mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract media URL')
+ return
+ video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
+ video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'player_url': None,
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class GenericIE(InfoExtractor):
+ """Generic last-resort information extractor."""
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return True
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ video_id = url.split('/')[-1]
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ except ValueError, err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = urllib.unquote(mobj.group(1))
+ video_id = os.path.basename(video_url)
+
+ # here's a fun little line of code for you:
+ video_extension = os.path.splitext(video_id)[1][1:]
+ video_id = os.path.splitext(video_id)[0]
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # video uploader is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+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>'
+ _youtube_ie = None
+ _max_youtube_results = 1000
+
+ 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._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_youtube_results:
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ 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
+
+ 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
+
+ pagenum = pagenum + 1
+
+class GoogleSearchIE(InfoExtractor):
+ """Information Extractor for Google Video search queries."""
+ _VALID_QUERY = 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>'
+ _google_ie = None
+ _max_google_results = 1000
+
+ 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._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._google_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_google_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_google_results:
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ n = self._max_google_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(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._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class YahooSearchIE(InfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
+ _VALID_QUERY = 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
+
+ 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._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._yahoo_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_yahoo_results:
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ n = self._max_yahoo_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(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._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
+ _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Download playlist pages
+ playlist_id = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(playlist_id, pagenum)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ break
+ pagenum = pagenum + 1
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+class YoutubeUserIE(InfoExtractor):
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, username):
+ """Report attempt to download user page."""
+ self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Download user page
+ username = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ self.report_download_page(username)
+ request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+class PostProcessor(object):
+ """Post Processor class.
+
+ 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.
+
+ The chain will be stopped if one of them ever returns None or the end
+ of the chain is reached.
PostProcessor objects follow a "mutual registration" process similar
to InfoExtractor objects.
import getpass
import optparse
+ # Function to update the program file with the latest version from bitbucket.org
+ def update_self(downloader, filename):
+ # Note: downloader only used for options
+ if not os.access (filename, os.W_OK):
+ sys.exit('ERROR: no write permissions on %s' % filename)
+
+ downloader.to_stdout('Updating to latest stable version...')
+ latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+ latest_version = urllib.urlopen(latest_url).read().strip()
+ prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+ newcontent = urllib.urlopen(prog_url).read()
+ stream = open(filename, 'w')
+ stream.write(newcontent)
+ stream.close()
+ downloader.to_stdout('Updated to version %s' % latest_version)
+
# General configuration
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2009.09.13',
+ version='2010.06.06',
conflict_handler='resolve',
)
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
+ parser.add_option('-U', '--update',
+ action='store_true', dest='update_self', help='update this program to latest stable version')
parser.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
parser.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
+ parser.add_option('-R', '--retries',
+ dest='retries', metavar='T', help='number of retries (default is 10)', default=10)
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
action='store_const', dest='format', help='alias for -f 17', const='17')
video_format.add_option('-d', '--high-def',
action='store_const', dest='format', help='alias for -f 22', const='22')
+ video_format.add_option('--all-formats',
+ action='store_const', dest='format', help='download all available video formats', const='-1')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+ verbosity.add_option('--get-thumbnail',
+ action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
+ verbosity.add_option('--get-description',
+ action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
+ verbosity.add_option('--no-progress',
+ action='store_true', dest='noprogress', help='do not print progress bar', default=False)
parser.add_option_group(verbosity)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TPL', help='output filename template')
filesystem.add_option('-a', '--batch-file',
- dest='batchfile', metavar='F', help='file containing URLs to download')
+ dest='batchfile', metavar='F', 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',
batchurls = []
if opts.batchfile is not None:
try:
- batchurls = open(opts.batchfile, 'r').readlines()
+ if opts.batchfile == '-':
+ batchfd = sys.stdin
+ else:
+ batchfd = open(opts.batchfile, 'r')
+ batchurls = batchfd.readlines()
batchurls = [x.strip() for x in batchurls]
batchurls = [x for x in batchurls if len(x) > 0]
except IOError:
all_urls = batchurls + args
# Conflicting, missing and erroneous options
- if len(all_urls) < 1:
- parser.error(u'you must provide at least one URL')
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
if numeric_limit is None:
parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
+ if opts.retries is not None:
+ try:
+ opts.retries = long(opts.retries)
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid retry count specified')
# Information extractors
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_user_ie = YoutubeUserIE(youtube_ie)
youtube_search_ie = YoutubeSearchIE(youtube_ie)
+ google_ie = GoogleIE()
+ google_search_ie = GoogleSearchIE(google_ie)
+ photobucket_ie = PhotobucketIE()
+ yahoo_ie = YahooIE()
+ yahoo_search_ie = YahooSearchIE(yahoo_ie)
+ 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),
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
- 'simulate': (opts.simulate or opts.geturl or opts.gettitle),
+ 'forcethumbnail': opts.getthumbnail,
+ 'forcedescription': opts.getdescription,
+ 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'format': opts.format,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+ or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
+ 'retries': opts.retries,
'continuedl': opts.continue_dl,
+ 'noprogress': opts.noprogress,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
+ fd.add_info_extractor(youtube_user_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
+ fd.add_info_extractor(google_ie)
+ fd.add_info_extractor(google_search_ie)
+ fd.add_info_extractor(photobucket_ie)
+ fd.add_info_extractor(yahoo_ie)
+ fd.add_info_extractor(yahoo_search_ie)
+
+ # This must come last since it's the
+ # fallback if none of the others work
+ fd.add_info_extractor(generic_ie)
+
+ # Update version
+ if opts.update_self:
+ update_self(fd, sys.argv[0])
+
+ # Maybe do nothing
+ if len(all_urls) < 1:
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
retcode = fd.download(all_urls)
sys.exit(retcode)