From 0a3f3e67f98ab8168fc7b80abf00ba5f04302532 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Rog=C3=A9rio=20Brito?= Date: Sat, 18 Jun 2011 02:16:49 -0300 Subject: [PATCH] Imported Upstream version 2009.09.13 --- .hg_archival.txt | 2 + .hgtags | 23 + LATEST_VERSION | 1 + youtube-dl | 1597 +++++++++++++++++++++++++++++++++++----------- 4 files changed, 1233 insertions(+), 390 deletions(-) create mode 100644 .hg_archival.txt create mode 100644 .hgtags create mode 100644 LATEST_VERSION diff --git a/.hg_archival.txt b/.hg_archival.txt new file mode 100644 index 0000000..6f101fa --- /dev/null +++ b/.hg_archival.txt @@ -0,0 +1,2 @@ +repo: f87cf8f2527c4adda57b14bd79a354f815164a41 +node: 6947c04fb1b4e94cd9422efe6854f8abe80568d2 diff --git a/.hgtags b/.hgtags new file mode 100644 index 0000000..01a12a3 --- /dev/null +++ b/.hgtags @@ -0,0 +1,23 @@ +afa03d33275e27c5ef7de0256053894a3c938901 2008.07.22 +385afd90ca13840be83bd736985817e9002775ad 2008.08.09 +9636c1843c6fb35cd2a934d5447210be9a8f9793 2008.09.20 +846c13fabe7837ef578d00e3d492cfae6c832a33 2008.10.16 +c72929f1680dc42e6fa1183be295a83427a290b4 2008.11.01 +ee7b97092712edf401fa237a7cd9b74925409a54 2009.01.31 +ef03a5f5f3337cd07b6d230226e199d4d9bb50ce 2009.02.07 +8dc1b312077f4c5eea95581c62ae256089e0eb50 2009.03.03 +1dd3c78e417e1ac30d03ddd350eca58e7d224066 2009.03.28 +468b207ea6eef08c713c27facc131e6e0dcacc85 2009.04.06 +c42582904adf7184e0e1909cfc80e64359d8294c 2009.04.25 +95b216d50f8ae9e78b16769c237e18fa05c6ac1b 2009.05.11 +31198e942e00619effa7ed3cef92771002eb0e48 2009.05.13 +63a16cc3d504cfce9e6db067c673c3ddcf2402c6 2009.05.23 +63a16cc3d504cfce9e6db067c673c3ddcf2402c6 2009.05.23 +0000000000000000000000000000000000000000 2009.05.23 +0000000000000000000000000000000000000000 2009.05.23 +3f498fb562912768a2ce8e2552747f27f525faa5 2009.05.23 +4bc5ac772e8a5b5dfa4ca88898daec8dd5502c2b 2009.05.25 +cfc3202eb7b61d4a7fd837cb5e3e35535d835f46 2009.05.30 +2793d3270ff9f7ea6e8f00effd6fb1b07e86d4d1 2009.06.29 +df8b882d8b39952a6be64ab8d742044a5d41fb18 2009.08.08 +4597eb63af5c26d07bfbef476a74963d72a78ba4 2009.09.08 diff --git a/LATEST_VERSION b/LATEST_VERSION new file mode 100644 index 0000000..70456bc --- /dev/null +++ b/LATEST_VERSION @@ -0,0 +1 @@ +2009.09.13 diff --git a/youtube-dl b/youtube-dl index ba27e75..5afff4e 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1,411 +1,1228 @@ #!/usr/bin/env python -# -# Copyright (c) 2006-2008 Ricardo Garcia Gonzalez -# -# Permission is hereby granted, free of charge, to any person obtaining a -# copy of this software and associated documentation files (the "Software"), -# to deal in the Software without restriction, including without limitation -# the rights to use, copy, modify, merge, publish, distribute, sublicense, -# and/or sell copies of the Software, and to permit persons to whom the -# Software is furnished to do so, subject to the following conditions: -# -# The above copyright notice and this permission notice shall be included -# in all copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL -# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR -# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, -# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR -# OTHER DEALINGS IN THE SOFTWARE. -# -# Except as contained in this notice, the name(s) of the above copyright -# holders shall not be used in advertising or otherwise to promote the -# sale, use or other dealings in this Software without prior written -# authorization. -# -import getpass +# -*- coding: utf-8 -*- +# Author: Ricardo Garcia Gonzalez +# Author: Danny Colligan +# License: Public domain code +import htmlentitydefs import httplib +import locale import math import netrc -import optparse import os +import os.path import re import socket import string import sys import time +import urllib import urllib2 -# Global constants -const_1k = 1024 -const_initial_block_size = 10 * const_1k -const_epsilon = 0.0001 -const_timeout = 120 - -const_video_url_str = 'http://www.youtube.com/watch?v=%s' -const_video_url_re = re.compile(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:v/|(?:watch(?:\.php)?)?\?(?:.+&)?v=))?([0-9A-Za-z_-]+)(?(1)[&/].*)?$') -const_video_url_format_suffix = '&fmt=%s' -const_best_quality_format = 18 -const_login_url_str = 'http://www.youtube.com/login?next=/watch%%3Fv%%3D%s' -const_login_post_str = 'current_form=loginForm&next=%%2Fwatch%%3Fv%%3D%s&username=%s&password=%s&action_login=Log+In' -const_age_url_str = 'http://www.youtube.com/verify_age?next_url=/watch%%3Fv%%3D%s' -const_age_post_str = 'next_url=%%2Fwatch%%3Fv%%3D%s&action_confirm=Confirm' -const_url_t_param_re = re.compile(r', "t": "([^"]+)"') -const_video_url_real_str = 'http://www.youtube.com/get_video?video_id=%s&t=%s' -const_video_title_re = re.compile(r'YouTube - ([^<]*)', re.M | re.I) - -# Print error message, followed by standard advice information, and then exit -def error_advice_exit(error_text): - sys.stderr.write('Error: %s.\n' % error_text) - sys.stderr.write('Try again several times. It may be a temporary problem.\n') - sys.stderr.write('Other typical problems:\n\n') - sys.stderr.write('* Video no longer exists.\n') - sys.stderr.write('* Video requires age confirmation but you did not provide an account.\n') - sys.stderr.write('* You provided the account data, but it is not valid.\n') - sys.stderr.write('* The connection was cut suddenly for some reason.\n') - sys.stderr.write('* YouTube changed their system, and the program no longer works.\n') - sys.stderr.write('\nTry to confirm you are able to view the video using a web browser.\n') - sys.stderr.write('Use the same video URL and account information, if needed, with this program.\n') - sys.stderr.write('When using a proxy, make sure http_proxy has http://host:port format.\n') - sys.stderr.write('Try again several times and contact me if the problem persists.\n') - sys.exit('\n') - -# Wrapper to create custom requests with typical headers -def request_create(url, extra_headers, post_data): - retval = urllib2.Request(url) - if post_data is not None: - retval.add_data(post_data) - # Try to mimic Firefox, at least a little bit - retval.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11') - retval.add_header('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7') - retval.add_header('Accept', 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5') - retval.add_header('Accept-Language', 'en-us,en;q=0.5') - if extra_headers is not None: - for header in extra_headers: - retval.add_header(header[0], header[1]) - return retval - -# Perform a request, process headers and return response -def perform_request(url, headers=None, data=None): - request = request_create(url, headers, data) - response = urllib2.urlopen(request) - return response - -# Conditional print -def cond_print(str): - global cmdl_opts - if not (cmdl_opts.quiet or cmdl_opts.get_url): - sys.stdout.write(str) - sys.stdout.flush() - -# Title string normalization -def title_string_norm(title): - title = ''.join((x in string.ascii_letters or x in string.digits) and x or ' ' for x in title) - title = '_'.join(title.split()) - title = title.lower() - return title - -# Generic download step -def download_step(return_data_flag, step_title, step_error, url, post_data=None): - try: - cond_print('%s... ' % step_title) - data = perform_request(url, data=post_data).read() - cond_print('done.\n') - if return_data_flag: - return data - return None +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', + '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', +} - except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error): - cond_print('failed.\n') - error_advice_exit(step_error) +simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') - except KeyboardInterrupt: - sys.exit('\n') +def preferredencoding(): + """Get preferred encoding. -# Generic extract step -def extract_step(step_title, step_error, regexp, data): + Returns the best encoding scheme for the system, based on + locale.getpreferredencoding() and some further tweaks. + """ try: - cond_print('%s... ' % step_title) - match = regexp.search(data) - - if match is None: - cond_print('failed.\n') - error_advice_exit(step_error) - - extracted_data = match.group(1) - cond_print('done.\n') - return extracted_data + 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. - except KeyboardInterrupt: - sys.exit('\n') - -# Calculate new block size based on previous block size -def new_block_size(before, after, bytes): - new_min = max(bytes / 2.0, 1.0) - new_max = max(bytes * 2.0, 1.0) - dif = after - before - if dif < const_epsilon: - return int(new_max) - rate = bytes / dif - if rate > new_max: - return int(new_max) - if rate < new_min: - return int(new_min) - return int(rate) - -# Get optimum 1k exponent to represent a number of bytes -def optimum_k_exp(num_bytes): - global const_1k - if num_bytes == 0: - return 0 - return long(math.log(num_bytes, const_1k)) - -# Get optimum representation of number of bytes -def format_bytes(num_bytes): - global const_1k - try: - exp = optimum_k_exp(num_bytes) - suffix = 'bkMGTPEZY'[exp] - if exp == 0: - return '%s%s' % (num_bytes, suffix) - converted = float(num_bytes) / float(const_1k**exp) + This exception may be thrown by FileDownloader objects if they are not + configured to continue on errors. They will contain the appropriate + error message. + """ + pass + +class SameFileError(Exception): + """Same File exception. + + This exception will be thrown by FileDownloader objects if they detect + multiple files would have to be downloaded to the same file on disk. + """ + pass + +class PostProcessingError(Exception): + """Post Processing exception. + + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + 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. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, file downloader objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the file downloader handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + simulate: Do not download the video files. + format: Video format code. + outtmpl: Template for output names. + 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 + _ies = [] + _pps = [] + _download_retcode = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._download_retcode = 0 + self.params = params + + @staticmethod + def pmkdir(filename): + """Create directory components in filename. Similar to Unix "mkdir -p".""" + components = filename.split(os.sep) + aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] + aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator + for dir in aggregate: + if not os.path.exists(dir): + os.mkdir(dir) + + @staticmethod + def format_bytes(bytes): + if bytes is None: + return 'N/A' + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: + exponent = 0 + else: + exponent = long(math.log(bytes, 1024.0)) + suffix = 'bkMGTPEZY'[exponent] + converted = float(bytes) / float(1024**exponent) return '%.2f%s' % (converted, suffix) - except IndexError: - sys.exit('Error: internal error formatting number of bytes.') - -# Calculate ETA and return it in string format as MM:SS -def calc_eta(start, now, total, current): - dif = now - start - if current == 0 or dif < const_epsilon: - return '--:--' - rate = float(current) / dif - eta = long((total - current) / rate) - (eta_mins, eta_secs) = divmod(eta, 60) - if eta_mins > 99: - return '--:--' - return '%02d:%02d' % (eta_mins, eta_secs) - -# Calculate speed and return it in string format -def calc_speed(start, now, bytes): - dif = now - start - if bytes == 0 or dif < const_epsilon: - return 'N/A b' - return format_bytes(float(bytes) / dif) - - -# Title string minimal transformation -def title_string_touch(title): - return title.replace(os.sep, '%') - -# Create the command line options parser and parse command line -cmdl_usage = 'usage: %prog [options] video_url' -cmdl_version = '2008.03.22' -cmdl_parser = optparse.OptionParser(usage=cmdl_usage, version=cmdl_version, conflict_handler='resolve') -cmdl_parser.add_option('-h', '--help', action='help', help='print this help text and exit') -cmdl_parser.add_option('-v', '--version', action='version', help='print program version and exit') -cmdl_parser.add_option('-u', '--username', dest='username', metavar='USERNAME', help='account username') -cmdl_parser.add_option('-p', '--password', dest='password', metavar='PASSWORD', help='account password') -cmdl_parser.add_option('-o', '--output', dest='outfile', metavar='FILE', help='output video file name') -cmdl_parser.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode') -cmdl_parser.add_option('-s', '--simulate', action='store_true', dest='simulate', help='do not download video') -cmdl_parser.add_option('-t', '--title', action='store_true', dest='use_title', help='use title in file name') -cmdl_parser.add_option('-l', '--literal', action='store_true', dest='use_literal', help='use literal title in file name') -cmdl_parser.add_option('-n', '--netrc', action='store_true', dest='use_netrc', help='use .netrc authentication data') -cmdl_parser.add_option('-g', '--get-url', action='store_true', dest='get_url', help='print final video URL only') -cmdl_parser.add_option('-2', '--title-too', action='store_true', dest='get_title', help='used with -g, print title too') -cmdl_parser.add_option('-f', '--format', dest='video_format', metavar='FORMAT', help='append &fmt=FORMAT to the URL') -cmdl_parser.add_option('-b', '--best-quality', action='store_true', dest='best_quality', help='alias for -f 18') -(cmdl_opts, cmdl_args) = cmdl_parser.parse_args() - -# Set socket timeout -socket.setdefaulttimeout(const_timeout) - -# Get video URL -if len(cmdl_args) != 1: - cmdl_parser.print_help() - sys.exit('\n') -video_url_cmdl = cmdl_args[0] - -# Verify video URL format and convert to "standard" format -video_url_mo = const_video_url_re.match(video_url_cmdl) -if video_url_mo is None: - sys.exit('Error: URL does not seem to be a youtube video URL. If it is, report a bug.') -video_url_id = video_url_mo.group(2) -video_url = const_video_url_str % video_url_id - -video_format = None -if cmdl_opts.best_quality: - video_format = const_best_quality_format - video_extension = '.mp4' -else: - video_extension = '.flv' - -if cmdl_opts.video_format is not None: - if video_format is not None and video_format != cmdl_opts.video_format: - sys.exit('Error: conflicting video formats specified\n') - video_format = cmdl_opts.video_format - -if video_format is not None: - video_url = '%s%s' % (video_url, const_video_url_format_suffix % video_format) - -# Check conflicting options -if cmdl_opts.outfile is not None and (cmdl_opts.simulate or cmdl_opts.get_url): - sys.stderr.write('Warning: video file name given but will not be used.\n') - -if cmdl_opts.outfile is not None and (cmdl_opts.use_title or cmdl_opts.use_literal): - sys.exit('Error: using the video title conflicts with using a given file name.') - -if cmdl_opts.use_title and cmdl_opts.use_literal: - sys.exit('Error: cannot use title and literal title at the same time.') - -if cmdl_opts.quiet and cmdl_opts.get_url: - sys.exit('Error: cannot be quiet and print final URL at the same time.') - -# Incorrect option formatting -if cmdl_opts.username is None and cmdl_opts.password is not None: - sys.exit('Error: password give but username is missing.') - -if cmdl_opts.use_netrc and (cmdl_opts.username is not None or cmdl_opts.password is not None): - sys.exit('Error: cannot use netrc and username/password at the same time.') - -if cmdl_opts.get_url is None and cmdl_opts.get_title is not None: - sys.exit('Error: getting title requires getting URL.') - -# Get account information if any -account_username = None -account_password = None - -if cmdl_opts.use_netrc: - try: - info = netrc.netrc().authenticators('youtube') - if info is None: - sys.exit('Error: no authenticators for machine youtube.') - account_username = info[0] - account_password = info[2] - except IOError: - sys.exit('Error: unable to read .netrc file.') - except netrc.NetrcParseError: - sys.exit('Error: unable to parse .netrc file.') -else: - account_username = cmdl_opts.username - if account_username is not None: - if cmdl_opts.password is None: - account_password = getpass.getpass('Type YouTube password and press return: ') + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return '--:--' + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return '--:--' + rate = float(current) / dif + eta = long((float(total) - float(current)) / rate) + (eta_mins, eta_secs) = divmod(eta, 60) + if eta_mins > 99: + return '--:--' + return '%02d:%02d' % (eta_mins, eta_secs) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + 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 long(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return long(new_max) + if rate < new_min: + return long(new_min) + return long(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into a long integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + 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) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + 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(preferredencoding()), + sys.stdout.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + print >>sys.stderr, 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) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + """ + if message is not None: + self.to_stderr(message) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_stdout(u'[download] Destination: %s' % filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """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.""" + 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 + + # 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: + 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(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: + success = self._do_download(filename, info_dict['url']) + except (OSError, IOError), err: + raise UnavailableFormatError + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.trouble('ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ), err: + self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return + + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError), err: + self.trouble('ERROR: postprocessing: %s' % str(err)) + return + + def download(self, url_list): + """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for url in url_list: + suitable_found = False + for ie in self._ies: + # Go to next InfoExtractor if not suitable + if not ie.suitable(url): + continue + + # Suitable InfoExtractor found + suitable_found = True + + # Extract information from URL and process it + ie.extract(url) + + # Suitable InfoExtractor had been found; go to next URL + break + + if not suitable_found: + self.trouble('ERROR: no suitable InfoExtractor: %s' % url) + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break + + 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) + + # Attempt to resume download with "continuedl" option + if os.path.isfile(filename): + resume_len = os.path.getsize(filename) else: - account_password = cmdl_opts.password - -# Get output file name -if cmdl_opts.outfile is None: - video_filename = '%s%s' % (video_url_id, video_extension) -else: - video_filename = cmdl_opts.outfile - -# Install cookie and proxy handlers -urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) -urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor())) - -# Log in and confirm age if needed -if account_username is not None: - url = const_login_url_str % video_url_id - post = const_login_post_str % (video_url_id, account_username, account_password) - download_step(False, 'Logging in', 'unable to log in', url, post) - - url = const_age_url_str % video_url_id - post = const_age_post_str % video_url_id - download_step(False, 'Confirming age', 'unable to confirm age', url, post) - -# Retrieve video webpage -video_webpage = download_step(True, 'Retrieving video webpage', 'unable to retrieve video webpage', video_url) - -# Extract video title if needed -if cmdl_opts.use_title or cmdl_opts.use_literal or cmdl_opts.get_title: - video_title = extract_step('Extracting video title', 'unable to extract video title', const_video_title_re, video_webpage) - -# Extract needed video URL parameters -video_url_t_param = extract_step('Extracting URL "t" parameter', 'unable to extract URL "t" parameter', const_url_t_param_re, video_webpage) -video_url_real = const_video_url_real_str % (video_url_id, video_url_t_param) -if video_format is not None: - video_url_real = '%s%s' % (video_url_real, const_video_url_format_suffix % video_format) - -# Rebuild filename if needed -if cmdl_opts.use_title or cmdl_opts.use_literal: - if cmdl_opts.use_title: - prefix = title_string_norm(video_title) - else: - prefix = title_string_touch(video_title) - video_filename = '%s-%s%s' % (prefix, video_url_id, video_extension) - -# Check name -if not video_filename.lower().endswith(video_extension): - sys.stderr.write('Warning: video file name does not end in %s\n' % video_extension) - -# Retrieve video data -try: - cond_print('Requesting video file... ') - video_data = perform_request(video_url_real) - cond_print('done.\n') - cond_print('Video data found at %s\n' % video_data.geturl()) - - if cmdl_opts.get_title: - print video_title - - if cmdl_opts.get_url: - print video_data.geturl() - - if cmdl_opts.simulate or cmdl_opts.get_url: - sys.exit() + 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) - try: - video_file = open(video_filename, 'wb') - except (IOError, OSError): - sys.exit('Error: unable to open "%s" for writing.' % video_filename) - try: - video_len = long(video_data.info()['Content-length']) - video_len_str = format_bytes(video_len) - except KeyError: - video_len = None - video_len_str = 'N/A' - - byte_counter = 0 - block_size = const_initial_block_size - start_time = time.time() - while True: - if video_len is not None: - percent = float(byte_counter) / float(video_len) * 100.0 - percent_str = '%.1f' % percent - eta_str = calc_eta(start_time, time.time(), video_len, byte_counter) + # 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: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + data_block_len = len(data_block) + 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 ContentTooShortError(byte_counter, long(data_len)) + return True + +class InfoExtractor(object): + """Information Extractor class. + + Information extractors are the classes that, given a URL, extract + information from the video (or videos) the URL refers to. This + information includes the real video URL, the video title and simplified + title, author and others. The information is stored in a dictionary + which is then passed to the FileDownloader. The FileDownloader + processes this information possibly downloading the video to the file + system, among other possible outcomes. The dictionaries must include + the following fields: + + id: Video identifier. + url: Final video URL. + uploader: Nickname of the video uploader. + title: Literal title. + stitle: Simplified title. + ext: Video filename extension. + + Subclasses of this one should re-define the _real_initialize() and + _real_extract() methods, as well as the suitable() static method. + Probably, they should also be instantiated and added to the main + downloader. + """ + + _ready = False + _downloader = None + + def __init__(self, downloader=None): + """Constructor. Receives an optional downloader.""" + self._ready = False + self.set_downloader(downloader) + + @staticmethod + def suitable(url): + """Receives a URL and returns True if suitable for this IE.""" + return False + + def initialize(self): + """Initializes an instance (authentication, etc).""" + if not self._ready: + self._real_initialize() + self._ready = True + + def extract(self, url): + """Extracts URL information and returns it in list of dicts.""" + self.initialize() + return self._real_extract(url) + + def set_downloader(self, downloader): + """Sets the downloader for this IE.""" + self._downloader = downloader + + def _real_initialize(self): + """Real initialization process. Redefine in subclasses.""" + pass + + def _real_extract(self, url): + """Real extraction process. Redefine in subclasses.""" + pass + +class YoutubeIE(InfoExtractor): + """Information extractor for youtube.com.""" + + _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 + _video_extensions = { + '13': '3gp', + '17': 'mp4', + '18': 'mp4', + '22': 'mp4', + } + + @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') + + def report_login(self): + """Report attempt to log in.""" + self._downloader.to_stdout(u'[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_stdout(u'[youtube] Confirming age') + + 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_unavailable_format(self, video_id, format): + """Report extracted video URL.""" + self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format)) + + def _real_initialize(self): + if self._downloader is None: + return + + username = None + password = None + downloader_params = self._downloader.params + + # Attempt to use provided username and password or .netrc data + if downloader_params.get('username', None) is not None: + username = downloader_params['username'] + password = downloader_params['password'] + elif downloader_params.get('usenetrc', False): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + username = info[0] + password = info[2] + else: + raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) + except (IOError, netrc.NetrcParseError), err: + self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) + return + + # Set language + request = urllib2.Request(self._LANG_URL, None, std_headers) + try: + self.report_lang() + urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + return + + # No authentication to be performed + if username is None: + return + + # Log in + login_form = { + 'current_form': 'loginForm', + 'next': '/', + 'action_login': 'Log In', + 'username': username, + 'password': password, + } + request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) + try: + self.report_login() + login_results = urllib2.urlopen(request).read() + if re.search(r'(?i)]* name="loginForm"', login_results) is not None: + self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') + return + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) + return + + # Confirm age + age_form = { + 'next_url': '/', + 'action_confirm': 'Confirm', + } + request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) + try: + self.report_age_confirmation() + age_results = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + return + + def _real_extract(self, url): + # Extract video 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) + + # 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 + + 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) + 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) + + # "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=([^&]+)(?:&|$)', video_info_webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason') + stream = open('reportme-ydl-%s.dat' % time.time(), 'wb') + stream.write(video_info_webpage) + stream.close() + else: + reason = urllib.unquote_plus(mobj.group(1)) + self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8')) + return + token = urllib.unquote(mobj.group(1)) + video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token) + if format_param is not None: + video_real_url = '%s&fmt=%s' % (video_real_url, format_param) + + # uploader + mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', 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)) + + # 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 + + +class MetacafeIE(InfoExtractor): + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' + _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(MetacafeIE._VALID_URL, url) is not None) + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self._downloader.to_stdout(u'[metacafe] Confirming age') + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id) + + def _real_initialize(self): + # Retrieve disclaimer + request = urllib2.Request(self._DISCLAIMER, None, std_headers) + try: + self.report_disclaimer() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) + return + + # Confirm age + disclaimer_form = { + 'filters': '0', + 'submit': "Continue - I'm over 18", + } + request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) + try: + self.report_age_confirmation() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) + return + + def _real_extract(self, url): + # Extract id and simplified title 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) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + return + + simple_title = mobj.group(2).decode('utf-8') + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request('http://www.metacafe.com/watch/%s/' % 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 retrieve video webpage: %s' % str(err)) + return + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + 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) + # + #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + + video_url = mediaURL + + mobj = re.search(r'(?im)(.*) - Video', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'(?ms)
  • .*?Submitter:.*?(.*?)<', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = mobj.group(1) + + 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): + """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*' + _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.""" + 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:] + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_youtube_results) + return else: - percent_str = '---.-' - eta_str = '--:--' - counter = format_bytes(byte_counter) - speed_str = calc_speed(start_time, time.time(), byte_counter) - cond_print('\rRetrieving video data: %5s%% (%8s of %s) at %8s/s ETA %s ' % (percent_str, counter, video_len_str, speed_str, eta_str)) - - before = time.time() - video_block = video_data.read(block_size) - after = time.time() - dl_bytes = len(video_block) - if dl_bytes == 0: - break - byte_counter += dl_bytes - video_file.write(video_block) - block_size = new_block_size(before, after, dl_bytes) - - if video_len is not None and byte_counter != video_len: - error_advice_exit('server did not send the expected ammount of data') - - video_file.close() - cond_print('done.\n') - cond_print('Video data saved to %s\n' % video_filename) - -except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error): - cond_print('failed.\n') - error_advice_exit('unable to download video data') - -except KeyboardInterrupt: - sys.exit('\n') - -# Finish -sys.exit() + 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 YoutubePlaylistIE(InfoExtractor): + """Information Extractor for YouTube playlists.""" + + _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 + + 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 (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page: + break + pagenum = pagenum + 1 + + 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. + """ + + _downloader = None + + def __init__(self, downloader=None): + self._downloader = downloader + + def set_downloader(self, downloader): + """Sets the downloader for this PP.""" + self._downloader = downloader + + def run(self, information): + """Run the PostProcessor. + + The "information" argument is a dictionary like the ones + composed by InfoExtractors. The only difference is that this + one has an extra field called "filepath" that points to the + downloaded file. + + When this method returns None, the postprocessing chain is + stopped. However, this method may return an information + dictionary that will be passed to the next postprocessing + object in the chain. It can be the one it received after + changing some fields. + + In addition, this method may raise a PostProcessingError + exception that will be taken into account by the downloader + it was called from. + """ + return information # by default, do nothing + +### MAIN PROGRAM ### +if __name__ == '__main__': + try: + # Modules needed only when running the main program + import getpass + import optparse + + # General configuration + urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) + urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor())) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + + # Parse command line + parser = optparse.OptionParser( + 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('-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)') + + 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') + 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 = 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: + 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: + parser.error(u'account username missing') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle): + parser.error(u'using output template conflicts with using title or literal title') + if opts.usetitle and opts.useliteral: + 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: + parser.error(u'invalid rate limit specified') + opts.ratelimit = numeric_limit + + # Information extractors + youtube_ie = YoutubeIE() + metacafe_ie = MetacafeIE(youtube_ie) + youtube_pl_ie = YoutubePlaylistIE(youtube_ie) + youtube_search_ie = YoutubeSearchIE(youtube_ie) + + # File downloader + fd = FileDownloader({ + 'usenetrc': opts.usenetrc, + 'username': opts.username, + 'password': opts.password, + 'quiet': (opts.quiet or opts.geturl or opts.gettitle), + 'forceurl': opts.geturl, + '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(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) + fd.add_info_extractor(metacafe_ie) + fd.add_info_extractor(youtube_ie) + retcode = fd.download(all_urls) + sys.exit(retcode) + + except DownloadError: + sys.exit(1) + except SameFileError: + sys.exit(u'ERROR: fixed output name but more than one file to download') + except KeyboardInterrupt: + sys.exit(u'\nERROR: Interrupted by user') -- 2.41.1