2008-07-21 21:12:31 +00:00
|
|
|
#!/usr/bin/env python
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# Author: Ricardo Garcia Gonzalez
|
2009-02-02 19:34:20 +00:00
|
|
|
# Author: Danny Colligan
|
2008-07-21 21:12:31 +00:00
|
|
|
# License: Public domain code
|
|
|
|
import htmlentitydefs
|
|
|
|
import httplib
|
2008-09-13 11:23:24 +00:00
|
|
|
import locale
|
2008-07-21 21:12:31 +00:00
|
|
|
import math
|
|
|
|
import netrc
|
|
|
|
import os
|
|
|
|
import os.path
|
|
|
|
import re
|
|
|
|
import socket
|
|
|
|
import string
|
|
|
|
import sys
|
|
|
|
import time
|
|
|
|
import urllib
|
|
|
|
import urllib2
|
|
|
|
|
2009-04-02 18:23:13 +00:00
|
|
|
std_headers = {
|
2009-04-15 18:17:16 +00:00
|
|
|
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
|
2008-07-21 21:12:31 +00:00
|
|
|
'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',
|
|
|
|
}
|
|
|
|
|
|
|
|
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
|
|
|
|
|
2008-07-22 13:52:56 +00:00
|
|
|
class DownloadError(Exception):
|
|
|
|
"""Download Error exception.
|
|
|
|
|
|
|
|
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
|
|
|
|
|
2008-07-27 10:13:49 +00:00
|
|
|
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
|
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
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
|
2009-04-23 20:34:58 +00:00
|
|
|
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.
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
File downloaders accept a lot of parameters. In order not to saturate
|
|
|
|
the object constructor with arguments, it receives a dictionary of
|
2009-03-04 21:12:33 +00:00
|
|
|
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".
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
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.
|
2008-07-22 08:00:43 +00:00
|
|
|
forceurl: Force printing final URL.
|
|
|
|
forcetitle: Force printing title.
|
2008-07-21 21:58:16 +00:00
|
|
|
simulate: Do not download the video files.
|
2008-07-21 21:12:31 +00:00
|
|
|
format: Video format code.
|
|
|
|
outtmpl: Template for output names.
|
2008-07-22 09:33:41 +00:00
|
|
|
ignoreerrors: Do not stop on download errors.
|
2008-07-24 07:47:07 +00:00
|
|
|
ratelimit: Download speed limit, in bytes/sec.
|
2009-02-04 20:38:31 +00:00
|
|
|
nooverwrites: Prevent overwriting files.
|
2008-07-21 21:12:31 +00:00
|
|
|
"""
|
|
|
|
|
2009-03-04 21:12:33 +00:00
|
|
|
params = None
|
2008-07-21 21:12:31 +00:00
|
|
|
_ies = []
|
2008-07-27 10:13:49 +00:00
|
|
|
_pps = []
|
2009-04-23 19:43:04 +00:00
|
|
|
_download_retcode = None
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
def __init__(self, params):
|
2008-07-22 09:41:25 +00:00
|
|
|
"""Create a FileDownloader object with the given options."""
|
2008-07-21 21:12:31 +00:00
|
|
|
self._ies = []
|
2008-07-27 10:13:49 +00:00
|
|
|
self._pps = []
|
2009-04-23 19:43:04 +00:00
|
|
|
self._download_retcode = 0
|
2009-03-04 21:12:33 +00:00
|
|
|
self.params = params
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
@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))]
|
2008-07-24 08:07:46 +00:00
|
|
|
aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
|
2008-07-21 21:12:31 +00:00
|
|
|
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 bytes == 0:
|
|
|
|
exponent = 0
|
|
|
|
else:
|
|
|
|
exponent = long(math.log(float(bytes), 1024.0))
|
|
|
|
suffix = 'bkMGTPEZY'[exponent]
|
|
|
|
converted = float(bytes) / float(1024**exponent)
|
|
|
|
return '%.2f%s' % (converted, suffix)
|
|
|
|
|
|
|
|
@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)
|
|
|
|
|
2009-02-28 23:00:04 +00:00
|
|
|
@staticmethod
|
2008-07-21 21:12:31 +00:00
|
|
|
def calc_speed(start, now, bytes):
|
|
|
|
dif = now - start
|
|
|
|
if bytes == 0 or dif < 0.001: # One millisecond
|
2008-07-21 21:53:06 +00:00
|
|
|
return '%10s' % '---b/s'
|
2008-07-21 21:12:31 +00:00
|
|
|
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 int(new_max)
|
|
|
|
rate = bytes / elapsed_time
|
|
|
|
if rate > new_max:
|
|
|
|
return int(new_max)
|
|
|
|
if rate < new_min:
|
|
|
|
return int(new_min)
|
|
|
|
return int(rate)
|
|
|
|
|
2008-07-24 07:47:07 +00:00
|
|
|
@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))
|
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
def add_info_extractor(self, ie):
|
|
|
|
"""Add an InfoExtractor object to the end of the list."""
|
|
|
|
self._ies.append(ie)
|
|
|
|
ie.set_downloader(self)
|
|
|
|
|
2008-07-27 10:13:49 +00:00
|
|
|
def add_post_processor(self, pp):
|
|
|
|
"""Add a PostProcessor object to the end of the chain."""
|
|
|
|
self._pps.append(pp)
|
|
|
|
pp.set_downloader(self)
|
|
|
|
|
2008-07-21 21:53:06 +00:00
|
|
|
def to_stdout(self, message, skip_eol=False):
|
|
|
|
"""Print message to stdout if not in quiet mode."""
|
2009-03-04 21:12:33 +00:00
|
|
|
if not self.params.get('quiet', False):
|
2009-04-25 09:11:11 +00:00
|
|
|
print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()),
|
2008-07-21 21:53:06 +00:00
|
|
|
sys.stdout.flush()
|
2008-07-21 22:07:07 +00:00
|
|
|
|
|
|
|
def to_stderr(self, message):
|
|
|
|
"""Print message to stderr."""
|
2008-07-25 11:28:41 +00:00
|
|
|
print >>sys.stderr, message
|
2008-07-22 07:45:49 +00:00
|
|
|
|
|
|
|
def fixed_template(self):
|
|
|
|
"""Checks if the output template is fixed."""
|
2009-03-04 21:12:33 +00:00
|
|
|
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
|
2008-07-21 21:53:06 +00:00
|
|
|
|
2008-07-22 09:33:41 +00:00
|
|
|
def trouble(self, message=None):
|
|
|
|
"""Determine action to take when a download problem appears.
|
|
|
|
|
|
|
|
Depending on if the downloader has been configured to ignore
|
2008-07-22 13:52:56 +00:00
|
|
|
download errors or not, this method may throw an exception or
|
2009-04-23 19:43:04 +00:00
|
|
|
not when errors are found, after printing the message.
|
2008-07-22 09:33:41 +00:00
|
|
|
"""
|
|
|
|
if message is not None:
|
|
|
|
self.to_stderr(message)
|
2009-03-04 21:12:33 +00:00
|
|
|
if not self.params.get('ignoreerrors', False):
|
2008-07-22 13:52:56 +00:00
|
|
|
raise DownloadError(message)
|
2009-04-23 19:43:04 +00:00
|
|
|
self._download_retcode = 1
|
2008-07-22 09:33:41 +00:00
|
|
|
|
2008-07-24 07:47:07 +00:00
|
|
|
def slow_down(self, start_time, byte_counter):
|
|
|
|
"""Sleep if the download speed is over the rate limit."""
|
2009-03-04 21:12:33 +00:00
|
|
|
rate_limit = self.params.get('ratelimit', None)
|
2008-07-24 07:47:07 +00:00
|
|
|
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)
|
|
|
|
|
2008-07-22 20:40:50 +00:00
|
|
|
def report_destination(self, filename):
|
|
|
|
"""Report destination filename."""
|
2008-07-25 11:28:41 +00:00
|
|
|
self.to_stdout(u'[download] Destination: %s' % filename)
|
2008-07-22 20:40:50 +00:00
|
|
|
|
|
|
|
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
|
|
|
"""Report download progress."""
|
2008-07-25 11:28:41 +00:00
|
|
|
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
|
2008-07-22 20:40:50 +00:00
|
|
|
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
|
|
|
|
|
|
|
def report_finish(self):
|
|
|
|
"""Report download finished."""
|
2008-07-25 11:28:41 +00:00
|
|
|
self.to_stdout(u'')
|
2008-07-22 20:40:50 +00:00
|
|
|
|
2009-04-09 22:59:59 +00:00
|
|
|
def process_info(self, info_dict):
|
|
|
|
"""Process a single dictionary returned by an InfoExtractor."""
|
|
|
|
# Forced printings
|
|
|
|
if self.params.get('forcetitle', False):
|
2009-04-25 09:11:11 +00:00
|
|
|
print info_dict['title'].encode(locale.getpreferredencoding())
|
2009-04-09 22:59:59 +00:00
|
|
|
if self.params.get('forceurl', False):
|
2009-04-25 09:11:11 +00:00
|
|
|
print info_dict['url'].encode(locale.getpreferredencoding())
|
2009-04-09 22:59:59 +00:00
|
|
|
|
|
|
|
# Do nothing else if in simulate mode
|
|
|
|
if self.params.get('simulate', False):
|
2009-04-23 19:43:04 +00:00
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
|
|
|
|
try:
|
|
|
|
filename = self.params['outtmpl'] % info_dict
|
|
|
|
self.report_destination(filename)
|
|
|
|
except (ValueError, KeyError), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
|
2009-04-09 22:59:59 +00:00
|
|
|
if self.params['nooverwrites'] and os.path.exists(filename):
|
|
|
|
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
|
2009-04-23 19:43:04 +00:00
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
try:
|
|
|
|
self.pmkdir(filename)
|
|
|
|
except (OSError, IOError), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: unable to create directories: %s' % str(err))
|
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
try:
|
|
|
|
outstream = open(filename, 'wb')
|
|
|
|
except (OSError, IOError), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
try:
|
|
|
|
self._do_download(outstream, info_dict['url'])
|
|
|
|
outstream.close()
|
|
|
|
except (OSError, IOError), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: unable to write video data: %s' % str(err))
|
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: unable to download video data: %s' % str(err))
|
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
try:
|
|
|
|
self.post_process(filename, info_dict)
|
|
|
|
except (PostProcessingError), err:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: postprocessing: %s' % str(err))
|
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
|
2009-04-23 19:43:04 +00:00
|
|
|
return
|
2009-04-09 22:59:59 +00:00
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
def download(self, url_list):
|
|
|
|
"""Download a given list of URLs."""
|
2008-07-22 07:45:49 +00:00
|
|
|
if len(url_list) > 1 and self.fixed_template():
|
2009-03-04 21:12:33 +00:00
|
|
|
raise SameFileError(self.params['outtmpl'])
|
2008-07-22 07:45:49 +00:00
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
for url in url_list:
|
|
|
|
suitable_found = False
|
|
|
|
for ie in self._ies:
|
2009-04-09 22:59:59 +00:00
|
|
|
# Go to next InfoExtractor if not suitable
|
2008-07-21 21:12:31 +00:00
|
|
|
if not ie.suitable(url):
|
|
|
|
continue
|
2009-04-09 22:59:59 +00:00
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
# Suitable InfoExtractor found
|
|
|
|
suitable_found = True
|
2009-04-09 22:59:59 +00:00
|
|
|
|
2009-04-23 20:20:06 +00:00
|
|
|
# Extract information from URL and process it
|
|
|
|
ie.extract(url)
|
2008-07-27 10:13:49 +00:00
|
|
|
|
2009-04-09 22:59:59 +00:00
|
|
|
# Suitable InfoExtractor had been found; go to next URL
|
2008-07-21 21:12:31 +00:00
|
|
|
break
|
2009-04-09 22:59:59 +00:00
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
if not suitable_found:
|
2009-04-23 19:43:04 +00:00
|
|
|
self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
|
2008-07-22 09:16:32 +00:00
|
|
|
|
2009-04-23 19:43:04 +00:00
|
|
|
return self._download_retcode
|
2008-07-27 10:13:49 +00:00
|
|
|
|
|
|
|
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
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
def _do_download(self, stream, url):
|
|
|
|
request = urllib2.Request(url, None, std_headers)
|
|
|
|
data = urllib2.urlopen(request)
|
|
|
|
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:
|
2008-07-22 20:40:50 +00:00
|
|
|
# Progress message
|
2008-07-21 21:12:31 +00:00
|
|
|
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)
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
2008-07-21 21:12:31 +00:00
|
|
|
|
2008-07-22 20:40:50 +00:00
|
|
|
# Download and write
|
2008-07-21 21:12:31 +00:00
|
|
|
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
|
|
|
|
stream.write(data_block)
|
|
|
|
block_size = self.best_block_size(after - before, data_block_len)
|
|
|
|
|
2008-07-24 07:47:07 +00:00
|
|
|
# Apply rate limit
|
|
|
|
self.slow_down(start, byte_counter)
|
|
|
|
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_finish()
|
2008-07-21 21:12:31 +00:00
|
|
|
if data_len is not None and str(byte_counter) != data_len:
|
|
|
|
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
|
|
|
|
|
|
|
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
|
2009-04-23 20:34:58 +00:00
|
|
|
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
|
2008-07-21 21:12:31 +00:00
|
|
|
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."""
|
2008-07-24 13:53:24 +00:00
|
|
|
return False
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
def initialize(self):
|
2008-07-22 09:41:25 +00:00
|
|
|
"""Initializes an instance (authentication, etc)."""
|
2008-07-21 21:12:31 +00:00
|
|
|
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."""
|
|
|
|
|
2008-07-24 13:53:24 +00:00
|
|
|
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
|
2009-01-31 09:12:22 +00:00
|
|
|
_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'
|
2008-07-21 21:12:31 +00:00
|
|
|
_NETRC_MACHINE = 'youtube'
|
|
|
|
|
2008-07-24 13:53:24 +00:00
|
|
|
@staticmethod
|
|
|
|
def suitable(url):
|
|
|
|
return (re.match(YoutubeIE._VALID_URL, url) is not None)
|
|
|
|
|
2009-04-05 09:01:02 +00:00
|
|
|
@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)
|
|
|
|
|
2009-01-31 09:12:22 +00:00
|
|
|
def report_lang(self):
|
|
|
|
"""Report attempt to set language."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] Setting language')
|
2009-01-31 09:12:22 +00:00
|
|
|
|
2008-07-22 20:40:50 +00:00
|
|
|
def report_login(self):
|
|
|
|
"""Report attempt to log in."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] Logging in')
|
2008-07-22 20:40:50 +00:00
|
|
|
|
|
|
|
def report_age_confirmation(self):
|
|
|
|
"""Report attempt to confirm age."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] Confirming age')
|
2008-07-22 20:40:50 +00:00
|
|
|
|
|
|
|
def report_webpage_download(self, video_id):
|
|
|
|
"""Report attempt to download webpage."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
|
2008-07-22 20:40:50 +00:00
|
|
|
|
|
|
|
def report_information_extraction(self, video_id):
|
|
|
|
"""Report attempt to extract video information."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
|
2008-07-22 20:40:50 +00:00
|
|
|
|
|
|
|
def report_video_url(self, video_id, video_real_url):
|
|
|
|
"""Report extracted video URL."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
2009-04-05 09:01:02 +00:00
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
def _real_initialize(self):
|
|
|
|
if self._downloader is None:
|
|
|
|
return
|
|
|
|
|
|
|
|
username = None
|
|
|
|
password = None
|
2009-03-04 21:12:33 +00:00
|
|
|
downloader_params = self._downloader.params
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# 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:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
|
2008-07-21 21:12:31 +00:00
|
|
|
return
|
|
|
|
|
2009-01-31 09:12:22 +00:00
|
|
|
# Set language
|
2009-03-01 23:02:56 +00:00
|
|
|
request = urllib2.Request(self._LANG_URL, None, std_headers)
|
2009-01-31 09:12:22 +00:00
|
|
|
try:
|
|
|
|
self.report_lang()
|
|
|
|
urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
|
2009-01-31 09:12:22 +00:00
|
|
|
return
|
|
|
|
|
2009-03-01 23:02:56 +00:00
|
|
|
# No authentication to be performed
|
|
|
|
if username is None:
|
|
|
|
return
|
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
# Log in
|
2008-07-21 21:53:06 +00:00
|
|
|
login_form = {
|
|
|
|
'current_form': 'loginForm',
|
2008-07-21 21:12:31 +00:00
|
|
|
'next': '/',
|
|
|
|
'action_login': 'Log In',
|
|
|
|
'username': username,
|
2008-07-21 21:53:06 +00:00
|
|
|
'password': password,
|
|
|
|
}
|
2008-07-21 21:12:31 +00:00
|
|
|
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
|
|
|
|
try:
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_login()
|
2008-07-21 21:12:31 +00:00
|
|
|
login_results = urllib2.urlopen(request).read()
|
|
|
|
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
|
2008-07-21 21:12:31 +00:00
|
|
|
return
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
|
2008-07-21 21:12:31 +00:00
|
|
|
return
|
|
|
|
|
|
|
|
# Confirm age
|
2008-07-21 21:53:06 +00:00
|
|
|
age_form = {
|
|
|
|
'next_url': '/',
|
|
|
|
'action_confirm': 'Confirm',
|
|
|
|
}
|
2008-07-21 21:12:31 +00:00
|
|
|
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
|
|
|
|
try:
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_age_confirmation()
|
2008-07-21 21:12:31 +00:00
|
|
|
age_results = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
|
2008-07-22 13:52:56 +00:00
|
|
|
return
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
# Extract video id from URL
|
2008-07-24 13:53:24 +00:00
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2008-07-21 21:12:31 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-21 21:12:31 +00:00
|
|
|
video_id = mobj.group(2)
|
|
|
|
|
|
|
|
# Downloader parameters
|
|
|
|
format_param = None
|
|
|
|
if self._downloader is not None:
|
2009-03-04 21:12:33 +00:00
|
|
|
params = self._downloader.params
|
2008-07-21 21:12:31 +00:00
|
|
|
format_param = params.get('format', None)
|
|
|
|
|
|
|
|
# Extension
|
2009-03-28 09:26:41 +00:00
|
|
|
video_extension = {
|
|
|
|
'17': '3gp',
|
|
|
|
'18': 'mp4',
|
|
|
|
'22': 'mp4',
|
|
|
|
}.get(format_param, 'flv')
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# Normalize URL, including format
|
2009-01-31 09:12:22 +00:00
|
|
|
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
|
2008-07-21 21:12:31 +00:00
|
|
|
if format_param is not None:
|
|
|
|
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
|
|
request = urllib2.Request(normalized_url, None, std_headers)
|
|
|
|
try:
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_webpage_download(video_id)
|
2008-07-21 21:12:31 +00:00
|
|
|
video_webpage = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_information_extraction(video_id)
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# "t" param
|
|
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-04-15 18:01:06 +00:00
|
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
|
2008-07-21 21:12:31 +00:00
|
|
|
if format_param is not None:
|
|
|
|
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
2008-07-22 20:40:50 +00:00
|
|
|
self.report_video_url(video_id, video_real_url)
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# uploader
|
2008-07-26 00:07:03 +00:00
|
|
|
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
|
2008-07-21 21:12:31 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-21 21:12:31 +00:00
|
|
|
video_uploader = mobj.group(1)
|
|
|
|
|
|
|
|
# title
|
|
|
|
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video title')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-21 21:12:31 +00:00
|
|
|
video_title = mobj.group(1).decode('utf-8')
|
2009-04-05 09:01:02 +00:00
|
|
|
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
|
2008-07-22 09:05:22 +00:00
|
|
|
video_title = video_title.replace(os.sep, u'%')
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# simplified title
|
2008-07-22 07:53:05 +00:00
|
|
|
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
|
|
|
simple_title = simple_title.strip(ur'_')
|
2008-07-21 21:12:31 +00:00
|
|
|
|
2009-04-23 19:58:03 +00:00
|
|
|
# Process video information
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.process_info({
|
2008-07-25 11:28:41 +00:00
|
|
|
'id': video_id.decode('utf-8'),
|
|
|
|
'url': video_real_url.decode('utf-8'),
|
|
|
|
'uploader': video_uploader.decode('utf-8'),
|
2008-07-21 21:53:06 +00:00
|
|
|
'title': video_title,
|
|
|
|
'stitle': simple_title,
|
2008-07-25 11:28:41 +00:00
|
|
|
'ext': video_extension.decode('utf-8'),
|
2009-04-23 20:20:06 +00:00
|
|
|
})
|
2008-07-21 21:12:31 +00:00
|
|
|
|
2008-07-24 13:53:24 +00:00
|
|
|
class MetacafeIE(InfoExtractor):
|
|
|
|
"""Information Extractor for metacafe.com."""
|
|
|
|
|
|
|
|
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
|
2008-09-13 11:23:24 +00:00
|
|
|
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
|
2009-04-25 09:52:33 +00:00
|
|
|
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
|
2008-07-24 13:53:24 +00:00
|
|
|
_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."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
def report_age_confirmation(self):
|
|
|
|
"""Report attempt to confirm age."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[metacafe] Confirming age')
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
def report_download_webpage(self, video_id):
|
|
|
|
"""Report webpage download."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
def report_extraction(self, video_id):
|
|
|
|
"""Report information extraction."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
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:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
|
2008-07-24 13:53:24 +00:00
|
|
|
return
|
|
|
|
|
|
|
|
# Confirm age
|
|
|
|
disclaimer_form = {
|
2008-09-13 11:23:24 +00:00
|
|
|
'filters': '0',
|
2008-07-24 13:53:24 +00:00
|
|
|
'submit': "Continue - I'm over 18",
|
|
|
|
}
|
2009-04-25 09:52:33 +00:00
|
|
|
request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
|
2008-07-24 13:53:24 +00:00
|
|
|
try:
|
|
|
|
self.report_age_confirmation()
|
|
|
|
disclaimer = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
|
2008-07-24 13:53:24 +00:00
|
|
|
return
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
# Extract id and simplified title from URL
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
video_id = mobj.group(1)
|
|
|
|
|
|
|
|
# Check if video comes from YouTube
|
|
|
|
mobj2 = re.match(r'^yt-(.*)$', video_id)
|
|
|
|
if mobj2 is not None:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
|
|
|
|
return
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
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:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-24 13:53:24 +00:00
|
|
|
|
|
|
|
# Extract URL, uploader and title from webpage
|
|
|
|
self.report_extraction(video_id)
|
2009-04-25 09:52:33 +00:00
|
|
|
mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
|
2008-07-24 13:53:24 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-04-25 09:52:33 +00:00
|
|
|
mediaURL = urllib.unquote(mobj.group(1))
|
2008-07-24 13:53:24 +00:00
|
|
|
|
2009-04-25 09:52:33 +00:00
|
|
|
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
|
2008-07-24 13:53:24 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract gdaKey')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-24 13:53:24 +00:00
|
|
|
gdaKey = mobj.group(1)
|
|
|
|
|
|
|
|
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
|
|
|
|
|
2008-09-13 11:23:24 +00:00
|
|
|
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
|
2008-07-24 13:53:24 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract title')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-24 13:53:24 +00:00
|
|
|
video_title = mobj.group(1).decode('utf-8')
|
|
|
|
|
2009-04-25 09:52:33 +00:00
|
|
|
mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
|
2008-07-24 13:53:24 +00:00
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-04-25 09:52:33 +00:00
|
|
|
video_uploader = mobj.group(1)
|
2008-07-24 13:53:24 +00:00
|
|
|
|
2009-04-23 20:20:06 +00:00
|
|
|
# Process video information
|
|
|
|
self._downloader.process_info({
|
2008-07-25 11:28:41 +00:00
|
|
|
'id': video_id.decode('utf-8'),
|
|
|
|
'url': video_url.decode('utf-8'),
|
|
|
|
'uploader': video_uploader.decode('utf-8'),
|
2008-07-24 13:53:24 +00:00
|
|
|
'title': video_title,
|
|
|
|
'stitle': simple_title,
|
2008-07-25 11:28:41 +00:00
|
|
|
'ext': video_extension.decode('utf-8'),
|
2009-04-23 20:20:06 +00:00
|
|
|
})
|
2008-07-24 13:53:24 +00:00
|
|
|
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
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'>Next</a>'
|
|
|
|
_youtube_ie = None
|
2009-04-07 00:39:16 +00:00
|
|
|
_max_youtube_results = 1000
|
2009-02-02 18:59:48 +00:00
|
|
|
|
2009-04-02 18:23:13 +00:00
|
|
|
def __init__(self, youtube_ie, downloader=None):
|
2009-02-02 18:59:48 +00:00
|
|
|
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."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
self._youtube_ie.initialize()
|
|
|
|
|
|
|
|
def _real_extract(self, query):
|
|
|
|
mobj = re.match(self._VALID_QUERY, query)
|
|
|
|
if mobj is None:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
prefix, query = query.split(':')
|
|
|
|
prefix = prefix[8:]
|
2009-04-02 18:23:13 +00:00
|
|
|
if prefix == '':
|
2009-04-23 20:20:06 +00:00
|
|
|
self._download_n_results(query, 1)
|
|
|
|
return
|
2009-04-02 18:23:13 +00:00
|
|
|
elif prefix == 'all':
|
2009-04-23 20:20:06 +00:00
|
|
|
self._download_n_results(query, self._max_youtube_results)
|
|
|
|
return
|
2009-04-02 18:23:13 +00:00
|
|
|
else:
|
2009-02-02 18:59:48 +00:00
|
|
|
try:
|
|
|
|
n = int(prefix)
|
|
|
|
if n <= 0:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-04-07 15:21:27 +00:00
|
|
|
elif n > self._max_youtube_results:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
|
2009-04-07 15:21:27 +00:00
|
|
|
n = self._max_youtube_results
|
2009-04-23 20:20:06 +00:00
|
|
|
self._download_n_results(query, n)
|
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
except ValueError: # parsing prefix as int fails
|
2009-04-23 20:20:06 +00:00
|
|
|
self._download_n_results(query, 1)
|
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
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)
|
2009-02-02 19:29:44 +00:00
|
|
|
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
|
2009-02-02 18:59:48 +00:00
|
|
|
request = urllib2.Request(result_url, None, std_headers)
|
|
|
|
try:
|
|
|
|
page = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
# 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:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
if self._MORE_PAGES_INDICATOR not in page:
|
|
|
|
for id in video_ids:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
|
|
|
return
|
2009-02-02 18:59:48 +00:00
|
|
|
|
|
|
|
pagenum = pagenum + 1
|
|
|
|
|
2008-07-25 10:55:01 +00:00
|
|
|
class YoutubePlaylistIE(InfoExtractor):
|
|
|
|
"""Information Extractor for YouTube playlists."""
|
|
|
|
|
|
|
|
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
|
2009-01-31 09:12:22 +00:00
|
|
|
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
|
2008-07-25 10:55:01 +00:00
|
|
|
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
2008-07-26 00:07:03 +00:00
|
|
|
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
|
2008-07-25 10:55:01 +00:00
|
|
|
_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."""
|
2009-04-23 19:58:03 +00:00
|
|
|
self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
|
2008-07-25 10:55:01 +00:00
|
|
|
|
|
|
|
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:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-25 10:55:01 +00:00
|
|
|
|
|
|
|
# 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:
|
2009-04-23 20:01:28 +00:00
|
|
|
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
2009-04-23 20:20:06 +00:00
|
|
|
return
|
2008-07-25 10:55:01 +00:00
|
|
|
|
|
|
|
# Extract video identifiers
|
2008-11-01 14:52:51 +00:00
|
|
|
ids_in_page = []
|
2008-07-25 10:55:01 +00:00
|
|
|
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
|
2008-11-01 14:52:51 +00:00
|
|
|
if mobj.group(1) not in ids_in_page:
|
|
|
|
ids_in_page.append(mobj.group(1))
|
|
|
|
video_ids.extend(ids_in_page)
|
2008-07-25 10:55:01 +00:00
|
|
|
|
2008-07-26 00:07:03 +00:00
|
|
|
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
|
2008-07-25 10:55:01 +00:00
|
|
|
break
|
|
|
|
pagenum = pagenum + 1
|
|
|
|
|
|
|
|
for id in video_ids:
|
2009-04-23 20:20:06 +00:00
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
|
|
|
|
return
|
2008-07-25 10:55:01 +00:00
|
|
|
|
2008-07-27 10:13:49 +00:00
|
|
|
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
|
|
|
|
returned 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 ###
|
2008-07-21 21:12:31 +00:00
|
|
|
if __name__ == '__main__':
|
|
|
|
try:
|
2008-07-22 08:14:13 +00:00
|
|
|
# Modules needed only when running the main program
|
2008-07-22 08:56:54 +00:00
|
|
|
import getpass
|
2008-07-22 08:14:13 +00:00
|
|
|
import optparse
|
|
|
|
|
2008-07-21 21:12:31 +00:00
|
|
|
# General configuration
|
|
|
|
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
|
|
|
|
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
|
2008-07-22 08:14:13 +00:00
|
|
|
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
|
|
|
|
|
|
|
|
# Parse command line
|
2008-07-22 08:56:54 +00:00
|
|
|
parser = optparse.OptionParser(
|
|
|
|
usage='Usage: %prog [options] url...',
|
2009-04-06 15:16:40 +00:00
|
|
|
version='INTERNAL',
|
2008-07-22 08:56:54 +00:00
|
|
|
conflict_handler='resolve',
|
|
|
|
)
|
|
|
|
parser.add_option('-h', '--help',
|
|
|
|
action='help', help='print this help text and exit')
|
|
|
|
parser.add_option('-v', '--version',
|
|
|
|
action='version', help='print program version and exit')
|
|
|
|
parser.add_option('-u', '--username',
|
|
|
|
dest='username', metavar='UN', help='account username')
|
|
|
|
parser.add_option('-p', '--password',
|
|
|
|
dest='password', metavar='PW', help='account password')
|
|
|
|
parser.add_option('-o', '--output',
|
|
|
|
dest='outtmpl', metavar='TPL', help='output filename template')
|
|
|
|
parser.add_option('-q', '--quiet',
|
|
|
|
action='store_true', dest='quiet', help='activates quiet mode', default=False)
|
|
|
|
parser.add_option('-s', '--simulate',
|
|
|
|
action='store_true', dest='simulate', help='do not download video', default=False)
|
|
|
|
parser.add_option('-t', '--title',
|
|
|
|
action='store_true', dest='usetitle', help='use title in file name', default=False)
|
|
|
|
parser.add_option('-l', '--literal',
|
|
|
|
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
|
|
|
parser.add_option('-n', '--netrc',
|
|
|
|
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
|
|
|
|
parser.add_option('-g', '--get-url',
|
|
|
|
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
|
|
|
|
parser.add_option('-e', '--get-title',
|
|
|
|
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
|
|
|
parser.add_option('-f', '--format',
|
|
|
|
dest='format', metavar='FMT', help='video format code')
|
2008-07-22 20:18:51 +00:00
|
|
|
parser.add_option('-m', '--mobile-version',
|
2008-07-22 20:47:36 +00:00
|
|
|
action='store_const', dest='format', help='alias for -f 17', const='17')
|
2009-03-28 09:26:41 +00:00
|
|
|
parser.add_option('-d', '--high-def',
|
|
|
|
action='store_const', dest='format', help='alias for -f 22', const='22')
|
2008-07-22 09:33:41 +00:00
|
|
|
parser.add_option('-i', '--ignore-errors',
|
|
|
|
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
2008-07-24 07:47:07 +00:00
|
|
|
parser.add_option('-r', '--rate-limit',
|
|
|
|
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
2009-01-31 09:25:59 +00:00
|
|
|
parser.add_option('-a', '--batch-file',
|
|
|
|
dest='batchfile', metavar='F', help='file containing URLs to download')
|
2009-02-04 20:38:31 +00:00
|
|
|
parser.add_option('-w', '--no-overwrites',
|
|
|
|
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
2008-07-22 08:56:54 +00:00
|
|
|
(opts, args) = parser.parse_args()
|
|
|
|
|
2009-01-31 09:25:59 +00:00
|
|
|
# Batch file verification
|
2009-01-31 11:07:37 +00:00
|
|
|
batchurls = []
|
2009-01-31 09:25:59 +00:00
|
|
|
if opts.batchfile is not None:
|
|
|
|
try:
|
|
|
|
batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
|
|
|
|
except IOError:
|
|
|
|
sys.exit(u'ERROR: batch file could not be read')
|
|
|
|
all_urls = batchurls + args
|
|
|
|
|
2008-07-22 08:56:54 +00:00
|
|
|
# Conflicting, missing and erroneous options
|
2009-01-31 09:25:59 +00:00
|
|
|
if len(all_urls) < 1:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: you must provide at least one URL')
|
2008-07-22 08:56:54 +00:00
|
|
|
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
|
2008-07-22 08:56:54 +00:00
|
|
|
if opts.password is not None and opts.username is None:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: account username missing')
|
2008-07-22 08:56:54 +00:00
|
|
|
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: using output template conflicts with using title or literal title')
|
2008-07-22 08:56:54 +00:00
|
|
|
if opts.usetitle and opts.useliteral:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: using title conflicts with using literal title')
|
2008-07-22 08:56:54 +00:00
|
|
|
if opts.username is not None and opts.password is None:
|
2008-07-25 11:28:41 +00:00
|
|
|
opts.password = getpass.getpass(u'Type account password and press return:')
|
2008-07-24 07:47:07 +00:00
|
|
|
if opts.ratelimit is not None:
|
|
|
|
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
|
|
|
|
if numeric_limit is None:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: invalid rate limit specified')
|
2008-07-24 07:47:07 +00:00
|
|
|
opts.ratelimit = numeric_limit
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# Information extractors
|
|
|
|
youtube_ie = YoutubeIE()
|
2008-07-24 13:53:24 +00:00
|
|
|
metacafe_ie = MetacafeIE(youtube_ie)
|
2008-07-25 10:55:01 +00:00
|
|
|
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
|
2009-02-02 18:59:48 +00:00
|
|
|
youtube_search_ie = YoutubeSearchIE(youtube_ie)
|
2008-07-21 21:12:31 +00:00
|
|
|
|
|
|
|
# File downloader
|
2008-07-21 21:53:06 +00:00
|
|
|
fd = FileDownloader({
|
2008-07-22 08:56:54 +00:00
|
|
|
'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,
|
2009-04-25 09:11:11 +00:00
|
|
|
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
|
2008-07-25 11:28:41 +00:00
|
|
|
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'),
|
2008-07-22 09:33:41 +00:00
|
|
|
'ignoreerrors': opts.ignoreerrors,
|
2008-07-24 07:47:07 +00:00
|
|
|
'ratelimit': opts.ratelimit,
|
2009-02-04 20:38:31 +00:00
|
|
|
'nooverwrites': opts.nooverwrites,
|
2008-07-21 21:53:06 +00:00
|
|
|
})
|
2009-02-02 18:59:48 +00:00
|
|
|
fd.add_info_extractor(youtube_search_ie)
|
2008-07-25 10:55:01 +00:00
|
|
|
fd.add_info_extractor(youtube_pl_ie)
|
2008-07-24 13:53:24 +00:00
|
|
|
fd.add_info_extractor(metacafe_ie)
|
2008-07-21 21:12:31 +00:00
|
|
|
fd.add_info_extractor(youtube_ie)
|
2009-01-31 09:25:59 +00:00
|
|
|
retcode = fd.download(all_urls)
|
2008-07-22 09:16:32 +00:00
|
|
|
sys.exit(retcode)
|
2008-07-21 21:12:31 +00:00
|
|
|
|
2008-07-22 13:52:56 +00:00
|
|
|
except DownloadError:
|
|
|
|
sys.exit(1)
|
|
|
|
except SameFileError:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'ERROR: fixed output name but more than one file to download')
|
2008-07-21 21:12:31 +00:00
|
|
|
except KeyboardInterrupt:
|
2008-07-25 11:28:41 +00:00
|
|
|
sys.exit(u'\nERROR: Interrupted by user')
|