import urllib2
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
'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',
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
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 it
- doesn't raise, it returns an error code suitable to be returned
- later as a program exit code to indicate error.
+ 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)
- return 1
+ self._download_retcode = 1
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- return 0
+ return
try:
filename = self.params['outtmpl'] % info_dict
self.report_destination(filename)
except (ValueError, KeyError), err:
- return self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
+ self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
if self.params['nooverwrites'] and os.path.exists(filename):
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
- return 0
+ return
try:
self.pmkdir(filename)
except (OSError, IOError), err:
- return self.trouble('ERROR: unable to create directories: %s' % str(err))
+ self.trouble('ERROR: unable to create directories: %s' % str(err))
+ return
try:
outstream = open(filename, 'wb')
except (OSError, IOError), err:
- return self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ return
try:
self._do_download(outstream, info_dict['url'])
outstream.close()
except (OSError, IOError), err:
- return self.trouble('ERROR: unable to write video data: %s' % str(err))
+ self.trouble('ERROR: unable to write video data: %s' % str(err))
+ return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- return self.trouble('ERROR: unable to download video data: %s' % str(err))
+ self.trouble('ERROR: unable to download video data: %s' % str(err))
+ return
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
- return self.trouble('ERROR: postprocessing: %s' % str(err))
+ self.trouble('ERROR: postprocessing: %s' % str(err))
+ return
- return 0
+ return
def download(self, url_list):
"""Download a given list of URLs."""
- retcode = 0
if len(url_list) > 1 and self.fixed_template():
raise SameFileError(self.params['outtmpl'])
# See if there were problems extracting any information
if len(results) != len(all_results):
- retcode = self.trouble()
+ self.trouble()
# Two results could go to the same file
if len(results) > 1 and self.fixed_template():
# Process each result
for result in results:
- result = self.process_info(result)
-
- # Do not overwrite an error code with a success code
- if result != 0:
- retcode = result
+ self.process_info(result)
# Suitable InfoExtractor had been found; go to next URL
break
if not suitable_found:
- retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+ self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
- return retcode
+ return self._download_retcode
def post_process(self, filename, ie_info):
"""Run the postprocessing chain on the given file."""
"""Sets the downloader for this IE."""
self._downloader = downloader
- def to_stdout(self, message):
- """Print message to stdout if downloader is not in quiet mode."""
- if self._downloader is None or not self._downloader.params.get('quiet', False):
- print message
-
- def to_stderr(self, message):
- """Print message to stderr."""
- print >>sys.stderr, message
-
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
pass
def report_lang(self):
"""Report attempt to set language."""
- self.to_stdout(u'[youtube] Setting language')
+ self._downloader.to_stdout(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
- self.to_stdout(u'[youtube] Logging in')
+ self._downloader.to_stdout(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self.to_stdout(u'[youtube] Confirming age')
+ self._downloader.to_stdout(u'[youtube] Confirming age')
def report_webpage_download(self, video_id):
"""Report attempt to download webpage."""
- self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+ self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
def report_video_url(self, video_id, video_real_url):
"""Report extracted video URL."""
- self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
+ self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
def _real_initialize(self):
if self._downloader is None:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
- self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ self._downloader.trouble(u'WARNING: parsing .netrc: %s' % str(err))
return
# Set language
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+ self._downloader.trouble(u'WARNING: unable to set language: %s' % str(err))
return
# No authentication to be performed
self.report_login()
login_results = urllib2.urlopen(request).read()
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self.to_stderr(u'WARNING: unable to log in: bad username or password')
+ self._downloader.trouble(u'WARNING: unable to log in: bad username or password')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ self._downloader.trouble(u'WARNING: unable to log in: %s' % str(err))
return
# Confirm age
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to confirm age: %s' % str(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.to_stderr(u'ERROR: invalid URL: %s' % url)
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return [None]
video_id = mobj.group(2)
self.report_webpage_download(video_id)
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to download video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return [None]
self.report_information_extraction(video_id)
# "t" param
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract "t" parameter')
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
return [None]
- 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&el=detailpage&ps=' % (video_id, mobj.group(1))
if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
self.report_video_url(video_id, video_real_url)
# uploader
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract uploader nickname')
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return [None]
video_uploader = mobj.group(1)
# title
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract video title')
+ self._downloader.trouble(u'ERROR: unable to extract video title')
return [None]
video_title = mobj.group(1).decode('utf-8')
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
- # Return information
+ # Process video information
return [{
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
def report_disclaimer(self):
"""Report disclaimer retrieval."""
- self.to_stdout(u'[metacafe] Retrieving disclaimer')
+ self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self.to_stdout(u'[metacafe] Confirming age')
+ self._downloader.to_stdout(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+ self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+ self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
return
# Confirm age
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to confirm age: %s' % str(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.to_stderr(u'ERROR: invalid URL: %s' % url)
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return [None]
video_id = mobj.group(1)
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
return [None]
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract media URL')
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
return [None]
mediaURL = mobj.group(1).replace('\\', '')
mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract gdaKey')
+ self._downloader.trouble(u'ERROR: unable to extract gdaKey')
return [None]
gdaKey = mobj.group(1)
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract title')
+ self._downloader.trouble(u'ERROR: unable to extract title')
return [None]
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract uploader nickname')
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return [None]
video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
- self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+ 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.to_stderr(u'ERROR: invalid search query "%s"' % query)
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return [None]
prefix, query = query.split(':')
try:
n = int(prefix)
if n <= 0:
- self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return [None]
elif n > self._max_youtube_results:
- self.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ self._downloader.trouble(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
return self._download_n_results(query, n)
except ValueError: # parsing prefix as int fails
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return [None]
# Extract video identifiers
def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number."""
- self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+ self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
def _real_initialize(self):
self._youtube_ie.initialize()
# Extract playlist id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self.to_stderr(u'ERROR: invalid url: %s' % url)
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return [None]
# Download playlist pages
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return [None]
# Extract video identifiers
def __init__(self, downloader=None):
self._downloader = downloader
- def to_stdout(self, message):
- """Print message to stdout if downloader is not in quiet mode."""
- if self._downloader is None or not self._downloader.params.get('quiet', False):
- print message
-
- def to_stderr(self, message):
- """Print message to stderr."""
- print >>sys.stderr, message
-
def set_downloader(self, downloader):
"""Sets the downloader for this PP."""
self._downloader = downloader
youtube_search_ie = YoutubeSearchIE(youtube_ie)
# File downloader
- charset = locale.getdefaultlocale()[1]
+ charset = locale.getpreferredencoding()
if charset is None:
charset = 'ascii'
fd = FileDownloader({