Compare commits

..

54 Commits

Author SHA1 Message Date
Ricardo Garcia
ad0525b3e6 Bump version number 2010-10-31 11:24:52 +01:00
Ricardo Garcia
30edbf89e4 Report final URL with -g and do not print URLs normally (fixes issue #49) 2010-10-31 11:24:52 +01:00
Ricardo Garcia
eae2666cb4 Handle weird OSX locale settings gracefully (fixes issue #43) 2010-10-31 11:24:52 +01:00
Ricardo Garcia
2a04438c7c Restore INTERNAL version number 2010-10-31 11:24:52 +01:00
Ricardo Garcia
dd24ff44ab Bump version number 2010-10-31 11:24:48 +01:00
Ricardo Garcia
304a4d85ea Modify _MORE_PAGES_INDICATOR for searches (fixes issue #41) 2010-10-31 11:24:48 +01:00
Ricardo Garcia
d899774377 Accept my_playlists syntax for playlists 2010-10-31 11:24:48 +01:00
Ricardo Garcia
fade05990c Do not specify any format as a last option for the -b flag 2010-10-31 11:24:48 +01:00
Ricardo Garcia
e5b1604882 Set INTERNAL version number 2010-10-31 11:24:48 +01:00
Ricardo Garcia
0c8beb43f2 Bump version number 2010-10-31 11:24:44 +01:00
Ricardo Garcia
71b7300e63 Use get_video_info to work around captcha problems (fixes issue #31) 2010-10-31 11:24:44 +01:00
Ricardo Garcia
8497c36d5a Fix minor problem with size formatting method 2010-10-31 11:24:44 +01:00
Ricardo Garcia
110cd3462e Update User-agent string 2010-10-31 11:24:43 +01:00
Ricardo Garcia
18963a36b0 Fix metacafe.com code due to recent changes in the site 2010-10-31 11:24:43 +01:00
Ricardo Garcia
df1ceb1fd9 Include format 5 in best quality list 2010-10-31 11:24:43 +01:00
Ricardo Garcia
7eb0e89742 Properly encode messages sent to stderr (fixes issue #34) 2010-10-31 11:24:43 +01:00
Ricardo Garcia
8b07dec5f6 Bump version number 2010-10-31 11:24:40 +01:00
Ricardo Garcia
113e5266cc Modify "more pages" check in YouTube playlist (fixes issue #29) 2010-10-31 11:24:40 +01:00
Ricardo Garcia
55e7c75e12 Delay opening file until there is data to write
Fixes issue #19.
2010-10-31 11:24:40 +01:00
Ricardo Garcia
ff21a710ae Restore INTERNAL version number 2010-10-31 11:24:36 +01:00
Ricardo Garcia
7374795552 Bump version number 2010-10-31 11:24:36 +01:00
Ricardo Garcia
0cd61126fc Document new "continuedl" FileDownloader option 2010-10-31 11:24:36 +01:00
Ricardo Garcia
e1f18b8a84 Remove integer casts and replace them with long integer casts 2010-10-31 11:24:36 +01:00
Ricardo Garcia
6a0015a7e0 Fix missing cast preventing detection of already downloaded file 2010-10-31 11:24:36 +01:00
Ricardo Garcia
7db85b2c70 Tweaks to ivanov's code 2010-10-31 11:24:36 +01:00
Paul Ivanov
f76c2df64e Added -c option (--continue)
interrupted downloads will properly resume and append to the previously downloaded data, instead of overwriting the file.

There's some error checking - if the length of the file to be download matches the length of the previously downloaded data, we report that this file has already been downloaded and do nothing.

If there is some other HTTP 416 'Requested range not satisfiable' error, we simply re-download the whole file (reverting to the original functionality)

All other HTTP errors are simply raised.

Resuming does not override -w (--nooverwrite), since it is not clear what should happen if file on disk is larger than file to be downloaded.

Thus, -c does nothing if -w is present.
2010-10-31 11:24:36 +01:00
Ricardo Garcia
daa88ccc2e Fix TypeError when using the -f option (fixes issue #24) 2010-10-31 11:24:36 +01:00
Ricardo Garcia
eb5d184157 Restore INTERNAL version number 2010-10-31 11:24:36 +01:00
Ricardo Garcia
5745bfdcdc Bump version number 2010-10-31 11:24:32 +01:00
Ricardo Garcia
320becd692 Remove trails from the "append_const" change (fixes issue #23) 2010-10-31 11:24:32 +01:00
Ricardo Garcia
968aa88438 Only catch UnavailableFormatError in call to process_info 2010-10-31 11:24:32 +01:00
Ricardo Garcia
cbfff4db63 Verify URLs in simulate mode (fixes issue #22) 2010-10-31 11:24:32 +01:00
Ricardo Garcia
781daeabdb Restore "INTERNAL" version number 2010-10-31 11:24:32 +01:00
Ricardo Garcia
705804f5d1 Update version number in LATEST_VERSION 2010-10-31 11:24:24 +01:00
Ricardo Garcia
1d50e3d153 Bump version number 2010-10-31 11:24:19 +01:00
Ricardo Garcia
d69a1c9189 Handle "content too short" errors properly 2010-10-31 11:24:19 +01:00
Ricardo Garcia
488f619471 Close video file before removing it. 2010-10-31 11:24:19 +01:00
Ricardo Garcia
097ba9472b Remove .hgignore from version tracking 2010-10-31 11:24:19 +01:00
Ricardo Garcia
554f3e284c Add LATEST_VERSION to further ease checking which is the latest stable version 2010-10-31 11:24:19 +01:00
Ricardo Garcia
cab60d710a Put back INTERNAL version 2010-10-31 11:24:19 +01:00
Ricardo Garcia
152edc0d4c Set version number 2010-10-31 11:24:16 +01:00
Ricardo Garcia
b74c859d0f Use store_const instead of append_const as the latter requires Python 2.5 2010-10-31 11:24:16 +01:00
Ricardo Garcia
0e54320009 Restore INTERNAL version number 2010-10-31 11:24:16 +01:00
Ricardo Garcia
43f35682e9 Put version number in place 2010-10-31 11:24:12 +01:00
Ricardo Garcia
ad274509aa Add an "epoch" keyword to the output template 2010-10-31 11:24:12 +01:00
Ricardo Garcia
d09744d055 Add format 35 (flv) as second best in quality 2010-10-31 11:24:12 +01:00
Ricardo Garcia
1c76e23e0f Move the -t and -l options to the filesystem group 2010-10-31 11:24:12 +01:00
dannycolligan
42bcd27d3b Some consistency changes and ghost-file bugfix after discussion with rg3 2010-10-31 11:24:12 +01:00
dannycolligan
2740c509b3 Fixed ambiguity of multiple video option specifiers by dissalowing it; changed some sys.ext calls to parser.error 2010-10-31 11:24:12 +01:00
dannycolligan
7b7759f5a4 Added -b option and created option groups for help prompt 2010-10-31 11:24:12 +01:00
Ricardo Garcia
8d2c83eda5 Update and correct (format,extension) table for YouTube 2010-10-31 11:24:12 +01:00
Ricardo Garcia
2f11508ada Minor documentation change 2010-10-31 11:24:12 +01:00
Ricardo Garcia
b65740e474 Skip blank lines in batch file -- fixes issue #9 2010-10-31 11:24:12 +01:00
Ricardo Garcia
a825f0ca83 Revert version number to INTERNAL 2010-10-31 11:24:12 +01:00
3 changed files with 333 additions and 166 deletions

View File

@@ -1,2 +0,0 @@
syntax: glob
.*.swp

1
LATEST_VERSION Normal file
View File

@@ -0,0 +1 @@
2009.09.13

View File

@@ -19,7 +19,7 @@ import urllib
import urllib2
std_headers = {
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
'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',
@@ -27,6 +27,22 @@ std_headers = {
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
def preferredencoding():
"""Get preferred encoding.
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
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'
class DownloadError(Exception):
"""Download Error exception.
@@ -52,6 +68,29 @@ class PostProcessingError(Exception):
"""
pass
class UnavailableFormatError(Exception):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
in a format that is not available for that video.
"""
pass
class ContentTooShortError(Exception):
"""Content Too Short exception.
This exception may be raised by FileDownloader objects when a file they
download is too small for what the server announced first, indicating
the connection was probably interrupted.
"""
# Both in bytes
downloaded = None
expected = None
def __init__(self, downloaded, expected):
self.downloaded = downloaded
self.expected = expected
class FileDownloader(object):
"""File Downloader class.
@@ -91,6 +130,7 @@ class FileDownloader(object):
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
continuedl: Try to continue downloads if possible.
"""
params = None
@@ -119,10 +159,12 @@ class FileDownloader(object):
def format_bytes(bytes):
if bytes is None:
return 'N/A'
if bytes == 0:
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = long(math.log(float(bytes), 1024.0))
exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
@@ -159,13 +201,13 @@ class FileDownloader(object):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return int(new_max)
return long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return int(new_max)
return long(new_max)
if rate < new_min:
return int(new_min)
return int(rate)
return long(new_min)
return long(rate)
@staticmethod
def parse_bytes(bytestr):
@@ -177,6 +219,16 @@ class FileDownloader(object):
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
@staticmethod
def verify_url(url):
"""Verify a URL is valid and data could be downloaded. Return real data URL."""
request = urllib2.Request(url, None, std_headers)
data = urllib2.urlopen(request)
data.read(1)
url = data.geturl()
data.close()
return url
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
@@ -190,12 +242,12 @@ class FileDownloader(object):
def to_stdout(self, message, skip_eol=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(locale.getpreferredencoding()),
print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
sys.stdout.flush()
def to_stderr(self, message):
"""Print message to stderr."""
print >>sys.stderr, message
print >>sys.stderr, message.encode(preferredencoding())
def fixed_template(self):
"""Checks if the output template is fixed."""
@@ -235,6 +287,18 @@ class FileDownloader(object):
"""Report download progress."""
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
def report_resuming_byte(self, resume_len):
"""Report attemtp to resume at given byte."""
self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
self.to_stdout(u'[download] %s has already been downloaded' % file_name)
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_stdout(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
@@ -242,50 +306,54 @@ class FileDownloader(object):
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
# Forced printings
if self.params.get('forcetitle', False):
print info_dict['title'].encode(locale.getpreferredencoding())
if self.params.get('forceurl', False):
print info_dict['url'].encode(locale.getpreferredencoding())
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
return
try:
info_dict['url'] = self.verify_url(info_dict['url'])
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())
if self.params.get('forceurl', False):
print info_dict['url'].encode(preferredencoding())
return
try:
filename = self.params['outtmpl'] % info_dict
self.report_destination(filename)
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
if self.params['nooverwrites'] and os.path.exists(filename):
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
return
try:
self.pmkdir(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to create directories: %s' % str(err))
return
try:
outstream = open(filename, 'wb')
success = self._do_download(filename, info_dict['url'])
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return
try:
self._do_download(outstream, info_dict['url'])
outstream.close()
except (OSError, IOError), err:
self.trouble('ERROR: unable to write video data: %s' % str(err))
return
raise UnavailableFormatError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
return
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
except (ContentTooShortError, ), err:
self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list):
"""Download a given list of URLs."""
@@ -322,21 +390,43 @@ class FileDownloader(object):
if info is None:
break
def _do_download(self, stream, url):
def _do_download(self, filename, url):
stream = None
open_mode = 'ab'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
data = urllib2.urlopen(request)
# Attempt to resume download with "continuedl" option
if os.path.isfile(filename):
resume_len = os.path.getsize(filename)
else:
resume_len = 0
if self.params['continuedl'] and resume_len != 0:
self.report_resuming_byte(resume_len)
request.add_header('Range','bytes=%d-' % resume_len)
# 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'
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
# Progress message
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
speed_str = self.calc_speed(start, time.time(), byte_counter)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Download and write
before = time.time()
data_block = data.read(block_size)
@@ -345,15 +435,31 @@ class FileDownloader(object):
if data_block_len == 0:
break
byte_counter += data_block_len
# Open file just in time
if stream is None:
try:
stream = open(filename, open_mode)
self.report_destination(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return False
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
# Progress message
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
speed_str = self.calc_speed(start, time.time(), byte_counter)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter)
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
raise ContentTooShortError(byte_counter, long(data_len))
return True
class InfoExtractor(object):
"""Information Extractor class.
@@ -424,6 +530,13 @@ class YoutubeIE(InfoExtractor):
_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
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
}
@staticmethod
def suitable(url):
@@ -464,17 +577,17 @@ class YoutubeIE(InfoExtractor):
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[youtube] Confirming age')
def report_webpage_download(self, video_id):
"""Report attempt to download webpage."""
self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
def report_video_url(self, video_id, video_real_url):
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
def _real_initialize(self):
if self._downloader is None:
@@ -554,70 +667,99 @@ class YoutubeIE(InfoExtractor):
video_id = mobj.group(2)
# Downloader parameters
best_quality = False
format_param = None
quality_index = 0
if self._downloader is not None:
params = self._downloader.params
format_param = params.get('format', None)
if format_param == '0':
format_param = self._available_formats[quality_index]
best_quality = True
# Extension
video_extension = {
'17': '3gp',
'18': 'mp4',
'22': 'mp4',
}.get(format_param, 'flv')
while True:
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
# Normalize URL, including format
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
if format_param is not None:
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
request = urllib2.Request(normalized_url, None, std_headers)
try:
self.report_webpage_download(video_id)
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return
self.report_information_extraction(video_id)
# "t" param
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
return
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
self.report_video_url(video_id, video_real_url)
# 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)
try:
self.report_video_info_webpage_download(video_id)
video_info_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))
return
self.report_information_extraction(video_id)
# uploader
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = mobj.group(1)
# "t" param
mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
if mobj is None:
# Attempt to see if YouTube has issued an error message
mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
if mobj is None:
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))
self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
return
token = urllib.unquote(mobj.group(1))
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)
# title
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
video_title = video_title.replace(os.sep, u'%')
# uploader
mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = urllib.unquote(mobj.group(1))
# simplified title
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
# title
mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = urllib.unquote(mobj.group(1))
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'%')
# simplified title
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
})
return
except UnavailableFormatError, err:
if best_quality:
if quality_index == len(self._available_formats) - 1:
# I don't ever expect this to happen
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('ERROR: format not available for video')
return
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
})
class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com."""
@@ -703,19 +845,21 @@ class MetacafeIE(InfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract gdaKey')
return
gdaKey = mobj.group(1)
#mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
#if mobj is None:
# self._downloader.trouble(u'ERROR: unable to extract gdaKey')
# return
#gdaKey = mobj.group(1)
#
#video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
video_url = mediaURL
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
@@ -729,15 +873,18 @@ class MetacafeIE(InfoExtractor):
return
video_uploader = mobj.group(1)
# 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'),
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 YoutubeSearchIE(InfoExtractor):
@@ -745,7 +892,7 @@ class YoutubeSearchIE(InfoExtractor):
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
_MORE_PAGES_INDICATOR = r'>Next</a>'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
_max_youtube_results = 1000
@@ -780,7 +927,7 @@ class YoutubeSearchIE(InfoExtractor):
return
else:
try:
n = int(prefix)
n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
@@ -789,7 +936,7 @@ class YoutubeSearchIE(InfoExtractor):
n = self._max_youtube_results
self._download_n_results(query, n)
return
except ValueError: # parsing prefix as int fails
except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
@@ -822,7 +969,7 @@ class YoutubeSearchIE(InfoExtractor):
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
if self._MORE_PAGES_INDICATOR not in page:
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
@@ -832,10 +979,10 @@ class YoutubeSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&amp;page=%s'
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
@@ -881,7 +1028,7 @@ class YoutubePlaylistIE(InfoExtractor):
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
break
pagenum = pagenum + 1
@@ -919,7 +1066,7 @@ class PostProcessor(object):
"""Run the PostProcessor.
The "information" argument is a dictionary like the ones
returned by InfoExtractors. The only difference is that this
composed by InfoExtractors. The only difference is that this
one has an extra field called "filepath" that points to the
downloaded file.
@@ -949,76 +1096,96 @@ if __name__ == '__main__':
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='2009.04.25',
conflict_handler='resolve',
)
usage='Usage: %prog [options] url...',
version='2009.09.13',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
parser.add_option('-u', '--username',
dest='username', metavar='UN', help='account username')
parser.add_option('-p', '--password',
dest='password', metavar='PW', help='account password')
parser.add_option('-o', '--output',
dest='outtmpl', metavar='TPL', help='output filename template')
parser.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
parser.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
parser.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name', default=False)
parser.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
parser.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
parser.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
parser.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
parser.add_option('-f', '--format',
dest='format', metavar='FMT', help='video format code')
parser.add_option('-m', '--mobile-version',
action='store_const', dest='format', help='alias for -f 17', const='17')
parser.add_option('-d', '--high-def',
action='store_const', dest='format', help='alias for -f 22', const='22')
parser.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
parser.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
parser.add_option('-a', '--batch-file',
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
dest='username', metavar='UN', help='account username')
authentication.add_option('-p', '--password',
dest='password', metavar='PW', help='account password')
authentication.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
parser.add_option_group(authentication)
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FMT', help='video format code')
video_format.add_option('-b', '--best-quality',
action='store_const', dest='format', help='download the best quality video possible', const='0')
video_format.add_option('-m', '--mobile-version',
action='store_const', dest='format', help='alias for -f 17', const='17')
video_format.add_option('-d', '--high-def',
action='store_const', dest='format', help='alias for -f 22', const='22')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
parser.add_option_group(verbosity)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
filesystem.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TPL', help='output filename template')
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='F', help='file containing URLs to download')
parser.add_option('-w', '--no-overwrites',
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
# Batch file verification
batchurls = []
if opts.batchfile is not None:
try:
batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
batchurls = open(opts.batchfile, 'r').readlines()
batchurls = [x.strip() for x in batchurls]
batchurls = [x for x in batchurls if len(x) > 0]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
# Conflicting, missing and erroneous options
if len(all_urls) < 1:
sys.exit(u'ERROR: you must provide at least one URL')
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):
sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
sys.exit(u'ERROR: account username missing')
parser.error(u'account username missing')
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
sys.exit(u'ERROR: using output template conflicts with using title or literal title')
parser.error(u'using output template conflicts with using title or literal title')
if opts.usetitle and opts.useliteral:
sys.exit(u'ERROR: using title conflicts with using literal title')
parser.error(u'using title conflicts with using literal title')
if opts.username is not None and opts.password is None:
opts.password = getpass.getpass(u'Type account password and press return:')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
sys.exit(u'ERROR: invalid rate limit specified')
parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
# Information extractors
@@ -1037,13 +1204,14 @@ if __name__ == '__main__':
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
'format': opts.format,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'continuedl': opts.continue_dl,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)