|
|
@ -193,6 +193,19 @@ class FileDownloader(object):
|
|
|
|
raise DownloadError(message)
|
|
|
|
raise DownloadError(message)
|
|
|
|
return 1
|
|
|
|
return 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_destination(self, filename):
|
|
|
|
|
|
|
|
"""Report destination filename."""
|
|
|
|
|
|
|
|
self.to_stdout('[download] Destination: %s' % filename)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
|
|
|
|
|
|
|
"""Report download progress."""
|
|
|
|
|
|
|
|
self.to_stdout('\r[download] %s of %s at %s ETA %s' %
|
|
|
|
|
|
|
|
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_finish(self):
|
|
|
|
|
|
|
|
"""Report download finished."""
|
|
|
|
|
|
|
|
self.to_stdout('')
|
|
|
|
|
|
|
|
|
|
|
|
def download(self, url_list):
|
|
|
|
def download(self, url_list):
|
|
|
|
"""Download a given list of URLs."""
|
|
|
|
"""Download a given list of URLs."""
|
|
|
|
retcode = 0
|
|
|
|
retcode = 0
|
|
|
@ -228,7 +241,7 @@ class FileDownloader(object):
|
|
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
filename = self._params['outtmpl'] % result
|
|
|
|
filename = self._params['outtmpl'] % result
|
|
|
|
self.to_stdout('[download] Destination: %s' % filename)
|
|
|
|
self.report_destination(filename)
|
|
|
|
except (ValueError, KeyError), err:
|
|
|
|
except (ValueError, KeyError), err:
|
|
|
|
retcode = self.trouble('ERROR: invalid output template: %s' % str(err))
|
|
|
|
retcode = self.trouble('ERROR: invalid output template: %s' % str(err))
|
|
|
|
continue
|
|
|
|
continue
|
|
|
@ -266,12 +279,13 @@ class FileDownloader(object):
|
|
|
|
block_size = 1024
|
|
|
|
block_size = 1024
|
|
|
|
start = time.time()
|
|
|
|
start = time.time()
|
|
|
|
while True:
|
|
|
|
while True:
|
|
|
|
|
|
|
|
# Progress message
|
|
|
|
percent_str = self.calc_percent(byte_counter, data_len)
|
|
|
|
percent_str = self.calc_percent(byte_counter, data_len)
|
|
|
|
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
|
|
|
|
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
|
|
|
|
speed_str = self.calc_speed(start, time.time(), byte_counter)
|
|
|
|
speed_str = self.calc_speed(start, time.time(), byte_counter)
|
|
|
|
self.to_stdout('\r[download] %s of %s at %s ETA %s' %
|
|
|
|
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
|
|
|
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Download and write
|
|
|
|
before = time.time()
|
|
|
|
before = time.time()
|
|
|
|
data_block = data.read(block_size)
|
|
|
|
data_block = data.read(block_size)
|
|
|
|
after = time.time()
|
|
|
|
after = time.time()
|
|
|
@ -282,7 +296,7 @@ class FileDownloader(object):
|
|
|
|
stream.write(data_block)
|
|
|
|
stream.write(data_block)
|
|
|
|
block_size = self.best_block_size(after - before, data_block_len)
|
|
|
|
block_size = self.best_block_size(after - before, data_block_len)
|
|
|
|
|
|
|
|
|
|
|
|
self.to_stdout('')
|
|
|
|
self.report_finish()
|
|
|
|
if data_len is not None and str(byte_counter) != data_len:
|
|
|
|
if data_len is not None and str(byte_counter) != data_len:
|
|
|
|
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
|
|
|
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
|
|
|
|
|
|
|
|
|
|
@ -362,6 +376,26 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
|
|
|
|
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
|
|
|
|
_NETRC_MACHINE = 'youtube'
|
|
|
|
_NETRC_MACHINE = 'youtube'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_login(self):
|
|
|
|
|
|
|
|
"""Report attempt to log in."""
|
|
|
|
|
|
|
|
self.to_stdout('[youtube] Logging in')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_age_confirmation(self):
|
|
|
|
|
|
|
|
"""Report attempt to confirm age."""
|
|
|
|
|
|
|
|
self.to_stdout('[youtube] Confirming age')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_webpage_download(self, video_id):
|
|
|
|
|
|
|
|
"""Report attempt to download webpage."""
|
|
|
|
|
|
|
|
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_information_extraction(self, video_id):
|
|
|
|
|
|
|
|
"""Report attempt to extract video information."""
|
|
|
|
|
|
|
|
self.to_stdout('[youtube] %s: Extracting video information' % video_id)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def report_video_url(self, video_id, video_real_url):
|
|
|
|
|
|
|
|
"""Report extracted video URL."""
|
|
|
|
|
|
|
|
self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
|
|
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
def _real_initialize(self):
|
|
|
|
if self._downloader is None:
|
|
|
|
if self._downloader is None:
|
|
|
|
return
|
|
|
|
return
|
|
|
@ -400,7 +434,7 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
}
|
|
|
|
}
|
|
|
|
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
|
|
|
|
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
self.to_stdout('[youtube] Logging in')
|
|
|
|
self.report_login()
|
|
|
|
login_results = urllib2.urlopen(request).read()
|
|
|
|
login_results = urllib2.urlopen(request).read()
|
|
|
|
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
|
|
|
|
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
|
|
|
|
self.to_stderr('WARNING: unable to log in: bad username or password')
|
|
|
|
self.to_stderr('WARNING: unable to log in: bad username or password')
|
|
|
@ -416,7 +450,7 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
}
|
|
|
|
}
|
|
|
|
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
|
|
|
|
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
self.to_stdout('[youtube] Confirming age')
|
|
|
|
self.report_age_confirmation()
|
|
|
|
age_results = urllib2.urlopen(request).read()
|
|
|
|
age_results = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
|
|
|
|
self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
|
|
|
@ -445,12 +479,12 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
|
|
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
|
|
request = urllib2.Request(normalized_url, None, std_headers)
|
|
|
|
request = urllib2.Request(normalized_url, None, std_headers)
|
|
|
|
try:
|
|
|
|
try:
|
|
|
|
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
|
|
|
|
self.report_webpage_download(video_id)
|
|
|
|
video_webpage = urllib2.urlopen(request).read()
|
|
|
|
video_webpage = urllib2.urlopen(request).read()
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
self.to_stderr('ERROR: unable to download video webpage: %s' % str(err))
|
|
|
|
self.to_stderr('ERROR: unable to download video webpage: %s' % str(err))
|
|
|
|
return [None]
|
|
|
|
return [None]
|
|
|
|
self.to_stdout('[youtube] %s: Extracting video information' % video_id)
|
|
|
|
self.report_information_extraction(video_id)
|
|
|
|
|
|
|
|
|
|
|
|
# "t" param
|
|
|
|
# "t" param
|
|
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
|
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
|
|
@ -460,7 +494,7 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
|
|
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
|
|
|
|
if format_param is not None:
|
|
|
|
if format_param is not None:
|
|
|
|
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
|
|
|
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
|
|
|
self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
|
|
|
|
self.report_video_url(video_id, video_real_url)
|
|
|
|
|
|
|
|
|
|
|
|
# uploader
|
|
|
|
# uploader
|
|
|
|
mobj = re.search(r'More From: ([^<]*)<', video_webpage)
|
|
|
|
mobj = re.search(r'More From: ([^<]*)<', video_webpage)
|
|
|
|