# -*- coding: utf-8 -*-
# Author: Ricardo Garcia Gonzalez
# Author: Danny Colligan
+# Author: Benjamin Johnson
# License: Public domain code
import htmlentitydefs
import httplib
import time
import urllib
import urllib2
-import urlparse
+
+# 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',
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:
+ 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.
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."""
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."""
"""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'].encode('utf-8')).decode('utf-8')
- 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:
+ info_dict['url'] = 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')
return
# 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.
- retval = subprocess.call(['rtmpdump', '-q', '-r', url, '-o', filename] + [[], ['-e']][self.params.get('continuedl', False)])
- while retval == 2:
+ basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename]
+ retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+ while retval == 2 or retval == 1:
self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True)
time.sleep(2.0) # This seems to be needed
- retval = subprocess.call(['rtmpdump', '-q', '-e', '-r', url, '-o', filename])
+ retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
if retval == 0:
self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
return True
# 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)
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
- _available_formats = ['37', '22', '35', '18', '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',
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')
try:
self.report_video_info_webpage_download(video_id)
video_info_webpage = urllib2.urlopen(request).read()
- video_info = urlparse.parse_qs(video_info_webpage)
+ video_info = parse_qs(video_info_webpage)
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
return
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)
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)By:\s*<a .*?>(.+?)<', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: format not available for video')
+class GoogleIE(InfoExtractor):
+ """Information extractor for video.google.com."""
+
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r"download_url:'([^']+)'", webpage)
+ if mobj is None:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+ mediaURL = mediaURL.replace('\\x3d', '\x3d')
+ mediaURL = mediaURL.replace('\\x26', '\x26')
+
+ video_url = mediaURL
+
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Google Video doesn't show uploader nicknames?
+ video_uploader = 'NA'
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class PhotobucketIE(InfoExtractor):
+ """Information extractor for photobucket.com."""
+
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(PhotobucketIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ video_url = mediaURL
+
+ mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ video_uploader = mobj.group(2).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ })
+ 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'),
+ })
+ 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]+'
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):
prefix, query = query.split(':')
prefix = prefix[8:]
+ query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2009.12.26',
+ version='2010.02.13',
conflict_handler='resolve',
)
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
youtube_user_ie = YoutubeUserIE(youtube_ie)
youtube_search_ie = YoutubeSearchIE(youtube_ie)
+ google_ie = GoogleIE()
+ photobucket_ie = PhotobucketIE()
+ generic_ie = GenericIE()
# File downloader
fd = FileDownloader({
fd.add_info_extractor(youtube_user_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
+ fd.add_info_extractor(google_ie)
+ fd.add_info_extractor(photobucket_ie)
+
+ # 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:
projects / youtube-dl / blobdiff