Merge branch 'master' into prefer-webm

This commit is contained in:
Rogério Brito 2011-01-29 03:45:21 -02:00
commit 9e1ee3364a
2 changed files with 395 additions and 147 deletions

View File

@ -1 +1 @@
2010.11.19
2010.12.09

View File

@ -3,8 +3,14 @@
# Author: Ricardo Garcia Gonzalez
# Author: Danny Colligan
# Author: Benjamin Johnson
# Author: Vasyl' Vavrychuk
# Author: Witold Baryluk
# License: Public domain code
import cookielib
import ctypes
import datetime
import email.utils
import gzip
import htmlentitydefs
import httplib
import locale
@ -15,11 +21,13 @@ import os.path
import re
import socket
import string
import StringIO
import subprocess
import sys
import time
import urllib
import urllib2
import zlib
# parse_qs was moved from the cgi module to the urlparse module recently.
try:
@ -31,26 +39,12 @@ std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
month_name_to_number = {
'January': '01',
'February': '02',
'March': '03',
'April': '04',
'May': '05',
'June': '06',
'July': '07',
'August': '08',
'September': '09',
'October': '10',
'November': '11',
'December': '12',
}
def preferredencoding():
"""Get preferred encoding.
@ -124,6 +118,13 @@ def sanitize_open(filename, open_mode):
stream = open(filename, open_mode)
return (stream, filename)
def timeconvert(timestr):
"""Convert RFC 2822 defined time string into system timestamp"""
timestamp = None
timetuple = email.utils.parsedate_tz(timestr)
if timetuple is not None:
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
class DownloadError(Exception):
"""Download Error exception.
@ -173,6 +174,64 @@ class ContentTooShortError(Exception):
self.downloaded = downloaded
self.expected = expected
class YoutubeDLHandler(urllib2.HTTPHandler):
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
to include the HTTP header "Youtubedl-No-Compression", which will be
removed before making the real request.
Part of this code was copied from:
http://techknack.net/python-urllib2-handlers/
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
@staticmethod
def deflate(data):
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
@staticmethod
def addinfourl_wrapper(stream, headers, url, code):
if hasattr(urllib2.addinfourl, 'getcode'):
return urllib2.addinfourl(stream, headers, url, code)
ret = urllib2.addinfourl(stream, headers, url)
ret.code = code
return ret
def http_request(self, req):
for h in std_headers:
if h in req.headers:
del req.headers[h]
req.add_header(h, std_headers[h])
if 'Youtubedl-no-compression' in req.headers:
if 'Accept-encoding' in req.headers:
del req.headers['Accept-encoding']
del req.headers['Youtubedl-no-compression']
return req
def http_response(self, req, resp):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = StringIO.StringIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
return resp
class FileDownloader(object):
"""File Downloader class.
@ -208,6 +267,7 @@ class FileDownloader(object):
forcetitle: Force printing title.
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
forcefilename: Force printing final filename.
simulate: Do not download the video files.
format: Video format code.
format_limit: Highest quality format to try.
@ -221,6 +281,9 @@ class FileDownloader(object):
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
"""
params = None
@ -338,6 +401,17 @@ class FileDownloader(object):
"""Print message to stderr."""
print >>sys.stderr, message.encode(preferredencoding())
def to_cons_title(self, message):
"""Set console/terminal window title to message."""
if not self.params.get('consoletitle', False):
return
if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ:
sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
@ -368,6 +442,43 @@ class FileDownloader(object):
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == u'-' or \
(os.path.exists(filename) and not os.path.isfile(filename)):
return filename
return filename + u'.part'
def undo_temp_name(self, filename):
if filename.endswith(u'.part'):
return filename[:-len(u'.part')]
return filename
def try_rename(self, old_filename, new_filename):
try:
if old_filename == new_filename:
return
os.rename(old_filename, new_filename)
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
if not os.path.isfile(filename):
return
timestr = last_modified_hdr
if timestr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
return
try:
os.utime(filename,(time.time(), filetime))
except:
pass
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
@ -378,6 +489,8 @@ class FileDownloader(object):
return
self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
@ -409,8 +522,21 @@ class FileDownloader(object):
"""Increment the ordinal that assigns a number to each file."""
self._num_downloads += 1
def prepare_filename(self, info_dict):
"""Generate the output filename."""
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
return filename
except (ValueError, KeyError), err:
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
filename = self.prepare_filename(info_dict)
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
# Forced printings
@ -422,16 +548,12 @@ class FileDownloader(object):
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcefilename', False) and filename is not None:
print filename.encode(preferredencoding(), 'xmlcharrefreplace')
return
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble(u'ERROR: invalid system charset or erroneous output template')
if filename is None:
return
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists and will be skipped')
@ -498,6 +620,7 @@ class FileDownloader(object):
def _download_with_rtmpdump(self, filename, url, player_url):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
# Check for rtmpdump first
try:
@ -509,36 +632,46 @@ class FileDownloader(object):
# 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]
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
prevsize = os.path.getsize(filename)
prevsize = os.path.getsize(tmpfilename)
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
cursize = os.path.getsize(filename)
cursize = os.path.getsize(tmpfilename)
if prevsize == cursize and retval == 1:
break
if retval == 0:
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
self.try_rename(tmpfilename, filename)
return True
else:
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False
def _do_download(self, filename, url, player_url):
# Check file already present
if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
return True
# Attempt to download using rtmpdump
if url.startswith('rtmp'):
return self._download_with_rtmpdump(filename, url, player_url)
tmpfilename = self.temp_name(filename)
stream = None
open_mode = 'wb'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
basic_request = urllib2.Request(url, None, headers)
request = urllib2.Request(url, None, headers)
# Establish possible resume length
if os.path.isfile(filename):
resume_len = os.path.getsize(filename)
if os.path.isfile(tmpfilename):
resume_len = os.path.getsize(tmpfilename)
else:
resume_len = 0
@ -580,6 +713,7 @@ class FileDownloader(object):
# completely downloaded if the file size differs less than 100 bytes from
# the one in the hard drive.
self.report_file_already_downloaded(filename)
self.try_rename(tmpfilename, filename)
return True
else:
# The length does not match, we start the download over
@ -596,8 +730,10 @@ class FileDownloader(object):
return False
data_len = data.info().get('Content-length', None)
if data_len is not None:
data_len = long(data_len) + resume_len
data_len_str = self.format_bytes(data_len)
byte_counter = 0
byte_counter = 0 + resume_len
block_size = 1024
start = time.time()
while True:
@ -605,15 +741,15 @@ class FileDownloader(object):
before = time.time()
data_block = data.read(block_size)
after = time.time()
data_block_len = len(data_block)
if data_block_len == 0:
if len(data_block) == 0:
break
byte_counter += data_block_len
byte_counter += len(data_block)
# Open file just in time
if stream is None:
try:
(stream, filename) = sanitize_open(filename, open_mode)
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError), err:
self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
@ -623,20 +759,27 @@ class FileDownloader(object):
except (IOError, OSError), err:
self.trouble(u'\nERROR: unable to write data: %s' % str(err))
return False
block_size = self.best_block_size(after - before, data_block_len)
block_size = self.best_block_size(after - before, len(data_block))
# Progress message
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
speed_str = self.calc_speed(start, time.time(), byte_counter)
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter)
self.slow_down(start, byte_counter - resume_len)
stream.close()
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
self.try_rename(tmpfilename, filename)
# Update file modification time
if self.params.get('updatetime', True):
self.try_utime(filename, data.info().get('last-modified', None))
return True
class InfoExtractor(object):
@ -713,7 +856,7 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@ -792,7 +935,7 @@ class YoutubeIE(InfoExtractor):
return
# Set language
request = urllib2.Request(self._LANG_URL, None, std_headers)
request = urllib2.Request(self._LANG_URL)
try:
self.report_lang()
urllib2.urlopen(request).read()
@ -812,7 +955,7 @@ class YoutubeIE(InfoExtractor):
'username': username,
'password': password,
}
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
try:
self.report_login()
login_results = urllib2.urlopen(request).read()
@ -828,7 +971,7 @@ class YoutubeIE(InfoExtractor):
'next_url': '/',
'action_confirm': 'Confirm',
}
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
try:
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
@ -846,7 +989,7 @@ class YoutubeIE(InfoExtractor):
# Get video webpage
self.report_video_webpage_download(video_id)
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers)
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -865,7 +1008,7 @@ class YoutubeIE(InfoExtractor):
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)
request = urllib2.Request(video_info_url)
try:
video_info_webpage = urllib2.urlopen(request).read()
video_info = parse_qs(video_info_webpage)
@ -913,18 +1056,13 @@ class YoutubeIE(InfoExtractor):
upload_date = u'NA'
mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
try:
if ',' in mobj.group(1):
# Month Day, Year
m, d, y = mobj.group(1).replace(',', '').split()
else:
# Day Month Year, we'll suppose
d, m, y = mobj.group(1).split()
m = month_name_to_number[m]
d = '%02d' % (long(d))
upload_date = '%s%s%s' % (y, m, d)
except:
upload_date = u'NA'
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
format_expressions = ['%d %B %Y', '%B %d %Y']
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
except:
pass
# description
video_description = 'No description available.'
@ -937,8 +1075,7 @@ class YoutubeIE(InfoExtractor):
video_token = urllib.unquote_plus(video_info['token'][0])
# Decide which formats to download
requested_format = self._downloader.params.get('format', None)
get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
req_format = self._downloader.params.get('format', None)
if 'fmt_url_map' in video_info:
url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
@ -951,12 +1088,16 @@ class YoutubeIE(InfoExtractor):
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
return
if requested_format is None:
video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality
elif requested_format == '-1':
video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats
if req_format is None:
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == '-1':
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format
# Specific format
if req_format not in url_map:
self._downloader.trouble(u'ERROR: requested format not available')
return
video_url_list = [(req_format, url_map[req_format])] # Specific format
elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
@ -990,7 +1131,7 @@ class YoutubeIE(InfoExtractor):
'player_url': player_url,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
self._downloader.trouble(u'\nERROR: unable to download video')
class MetacafeIE(InfoExtractor):
@ -1027,7 +1168,7 @@ class MetacafeIE(InfoExtractor):
def _real_initialize(self):
# Retrieve disclaimer
request = urllib2.Request(self._DISCLAIMER, None, std_headers)
request = urllib2.Request(self._DISCLAIMER)
try:
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
@ -1040,7 +1181,7 @@ class MetacafeIE(InfoExtractor):
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
@ -1135,7 +1276,7 @@ class MetacafeIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class DailymotionIE(InfoExtractor):
@ -1204,7 +1345,7 @@ class DailymotionIE(InfoExtractor):
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
@ -1224,7 +1365,7 @@ class DailymotionIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com."""
@ -1334,7 +1475,7 @@ class GoogleIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class PhotobucketIE(InfoExtractor):
@ -1416,7 +1557,7 @@ class PhotobucketIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class YahooIE(InfoExtractor):
@ -1574,7 +1715,7 @@ class YahooIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class GenericIE(InfoExtractor):
@ -1617,6 +1758,7 @@ class GenericIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
self.report_extraction(video_id)
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None:
@ -1674,7 +1816,7 @@ class GenericIE(InfoExtractor):
'player_url': None,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video')
self._downloader.trouble(u'\nERROR: unable to download video')
class YoutubeSearchIE(InfoExtractor):
@ -1742,7 +1884,7 @@ class YoutubeSearchIE(InfoExtractor):
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)
request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1833,7 +1975,7 @@ class GoogleSearchIE(InfoExtractor):
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)
request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1924,7 +2066,7 @@ class YahooSearchIE(InfoExtractor):
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)
request = urllib2.Request(result_url)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1953,7 +2095,7 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|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'(?m)>\s*Next\s*</a>'
@ -1988,7 +2130,7 @@ class YoutubePlaylistIE(InfoExtractor):
while True:
self.report_download_page(playlist_id, pagenum)
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -2050,7 +2192,7 @@ class YoutubeUserIE(InfoExtractor):
pagenum = 1
self.report_download_page(username)
request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
request = urllib2.Request(self._TEMPLATE_URL % (username))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -2073,6 +2215,85 @@ class YoutubeUserIE(InfoExtractor):
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com"""
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(DepositFilesIE._VALID_URL, url) is not None)
def report_download_webpage(self, file_id):
"""Report webpage download."""
self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
def report_extraction(self, file_id):
"""Report information extraction."""
self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
def _real_initialize(self):
return
def _real_extract(self, url):
# At this point we have a new file
self._downloader.increment_downloads()
file_id = url.split('/')[-1]
# Rebuild url in english locale
url = 'http://depositfiles.com/en/files/' + file_id
# Retrieve file webpage with 'Free download' button pressed
free_download_indication = { 'gateway_result' : '1' }
request = urllib2.Request(url, urllib.urlencode(free_download_indication))
try:
self.report_download_webpage(file_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
return
# Search for the real file URL
mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
if (mobj is None) or (mobj.group(1) is None):
# Try to figure out reason of the error.
mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
if (mobj is not None) and (mobj.group(1) is not None):
restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
self._downloader.trouble(u'ERROR: %s' % restriction_message)
else:
self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
return
file_url = mobj.group(1)
file_extension = os.path.splitext(file_url)[1][1:]
# Search for file title
mobj = re.search(r'<b title="(.*?)">', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
file_title = mobj.group(1).decode('utf-8')
try:
# Process file information
self._downloader.process_info({
'id': file_id.decode('utf-8'),
'url': file_url.decode('utf-8'),
'uploader': u'NA',
'upload_date': u'NA',
'title': file_title,
'stitle': file_title,
'ext': file_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download file')
class PostProcessor(object):
"""Post Processor class.
@ -2126,26 +2347,32 @@ if __name__ == '__main__':
import getpass
import optparse
# Function to update the program file with the latest version from bitbucket.org
# Function to update the program file with the latest version from the repository.
def update_self(downloader, filename):
# Note: downloader only used for options
if not os.access (filename, os.W_OK):
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
downloader.to_screen('Updating to latest stable version...')
latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
latest_version = urllib.urlopen(latest_url).read().strip()
prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
newcontent = urllib.urlopen(prog_url).read()
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
try:
latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
latest_version = urllib.urlopen(latest_url).read().strip()
prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
newcontent = urllib.urlopen(prog_url).read()
except (IOError, OSError), err:
sys.exit('ERROR: unable to download latest version')
try:
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
except (IOError, OSError), err:
sys.exit('ERROR: unable to overwrite current version')
downloader.to_screen('Updated to version %s' % latest_version)
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='2010.11.19',
version='2010.12.09',
conflict_handler='resolve',
)
@ -2165,6 +2392,9 @@ if __name__ == '__main__':
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
parser.add_option('--playlist-end',
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
parser.add_option('--dump-user-agent',
action='store_true', dest='dump_user_agent',
help='display the current browser identification', default=False)
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
@ -2178,14 +2408,10 @@ if __name__ == '__main__':
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', help='video format code')
video_format.add_option('-m', '--mobile-version',
action='store_const', dest='format', help='alias for -f 17', const='17')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='-1')
video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-b', '--best-quality',
action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
@ -2198,11 +2424,19 @@ if __name__ == '__main__':
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)
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)
action='store_true', dest='getdescription',
help='simulate, quiet but print video description', default=False)
verbosity.add_option('--get-filename',
action='store_true', dest='getfilename',
help='simulate, quiet but print output filename', default=False)
verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title',
action='store_true', dest='consoletitle',
help='display progress in console titlebar', default=False)
parser.add_option_group(verbosity)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
@ -2211,7 +2445,8 @@ if __name__ == '__main__':
filesystem.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
filesystem.add_option('-A', '--auto-number',
action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False)
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TEMPLATE', help='output filename template')
filesystem.add_option('-a', '--batch-file',
@ -2222,6 +2457,11 @@ if __name__ == '__main__':
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
filesystem.add_option('--cookies',
dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
filesystem.add_option('--no-part',
action='store_true', dest='nopart', help='do not use .part files', default=False)
filesystem.add_option('--no-mtime',
action='store_false', dest='updatetime',
help='do not use the Last-modified header to set the file modification time', default=True)
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
@ -2237,10 +2477,14 @@ if __name__ == '__main__':
except (IOError, OSError), err:
sys.exit(u'ERROR: unable to open cookie file')
# Dump user agent
if opts.dump_user_agent:
print std_headers['User-Agent']
sys.exit(0)
# General configuration
cookie_processor = urllib2.HTTPCookieProcessor(jar)
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(cookie_processor))
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
# Batch file verification
@ -2259,8 +2503,6 @@ if __name__ == '__main__':
all_urls = batchurls + args
# Conflicting, missing and erroneous options
if opts.bestquality:
print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'
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:
@ -2306,6 +2548,7 @@ if __name__ == '__main__':
photobucket_ie = PhotobucketIE()
yahoo_ie = YahooIE()
yahoo_search_ie = YahooSearchIE(yahoo_ie)
deposit_files_ie = DepositFilesIE()
generic_ie = GenericIE()
# File downloader
@ -2313,12 +2556,13 @@ if __name__ == '__main__':
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'forcefilename': opts.getfilename,
'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
'format': opts.format,
'format_limit': opts.format_limit,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
@ -2340,6 +2584,9 @@ if __name__ == '__main__':
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
'updatetime': opts.updatetime,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
@ -2352,6 +2599,7 @@ if __name__ == '__main__':
fd.add_info_extractor(photobucket_ie)
fd.add_info_extractor(yahoo_ie)
fd.add_info_extractor(yahoo_search_ie)
fd.add_info_extractor(deposit_files_ie)
# This must come last since it's the
# fallback if none of the others work