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 returns
- all the information to the FileDownloader and the latter downloads the
- file or does whatever it's instructed to do.
+ 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
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]),
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()),
sys.stdout.flush()
def to_stderr(self, message):
"""Process a single dictionary returned by an InfoExtractor."""
# Forced printings
if self.params.get('forcetitle', False):
- print info_dict['title']
+ print info_dict['title'].encode(locale.getpreferredencoding())
if self.params.get('forceurl', False):
- print info_dict['url']
+ print info_dict['url'].encode(locale.getpreferredencoding())
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
# Suitable InfoExtractor found
suitable_found = True
- # Extract information from URL
- all_results = ie.extract(url)
- results = [x for x in all_results if x is not None]
-
- # See if there were problems extracting any information
- if len(results) != len(all_results):
- self.trouble()
-
- # Two results could go to the same file
- if len(results) > 1 and self.fixed_template():
- raise SameFileError(self.params['outtmpl'])
-
- # Process each result
- for result in results:
- self.process_info(result)
+ # Extract information from URL and process it
+ ie.extract(url)
# Suitable InfoExtractor had been found; go to next URL
break
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. It is returned in a list of dictionaries when
- calling its extract() method. It is a list because a URL can refer to
- more than one video (think of playlists). The dictionaries must include
+ 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.
"""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.to_stderr(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.to_stderr(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.to_stderr(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.to_stderr(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)
- return [None]
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
video_id = mobj.group(2)
# Downloader parameters
if self._downloader is not None:
params = self._downloader.params
format_param = params.get('format', None)
- if format_param is None:
- format_param = '34'
# Extension
video_extension = {
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))
- return [None]
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
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')
- return [None]
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
+ return
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)
# uploader
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract uploader nickname')
- return [None]
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
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')
- return [None]
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
video_title = mobj.group(1).decode('utf-8')
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
video_title = video_title.replace(os.sep, u'%')
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
- # Return information
- return [{
+ # 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'),
- }]
+ })
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):
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
'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+ 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.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)
- return [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:
- return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ 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'
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))
- return [None]
+ 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":"(http.*?\.flv)"', webpage)
+ mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract media URL')
- return [None]
- mediaURL = mobj.group(1).replace('\\', '')
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
- mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
+ mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract gdaKey')
- return [None]
+ self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ return
gdaKey = mobj.group(1)
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract title')
- return [None]
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
video_title = mobj.group(1).decode('utf-8')
- mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+ mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
if mobj is None:
- self.to_stderr(u'ERROR: unable to extract uploader nickname')
- return [None]
- video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
- # Return information
- return [{
+ # 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'),
- }]
+ })
class YoutubeSearchIE(InfoExtractor):
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)
- return [None]
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
prefix, query = query.split(':')
prefix = prefix[8:]
if prefix == '':
- return self._download_n_results(query, 1)
+ self._download_n_results(query, 1)
+ return
elif prefix == 'all':
- return self._download_n_results(query, self._max_youtube_results)
+ self._download_n_results(query, self._max_youtube_results)
+ return
else:
try:
n = int(prefix)
if n <= 0:
- self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return [None]
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
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.to_stderr(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)
+ self._download_n_results(query, n)
+ return
except ValueError: # parsing prefix as int fails
- return self._download_n_results(query, 1)
+ self._download_n_results(query, 1)
+ return
def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query"""
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))
- return [None]
+ 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):
already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
- information = []
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
if self._MORE_PAGES_INDICATOR not in page:
- information = []
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
pagenum = pagenum + 1
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)
- return [None]
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
# Download playlist pages
playlist_id = mobj.group(1)
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))
- return [None]
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
# Extract video identifiers
ids_in_page = []
break
pagenum = pagenum + 1
- information = []
for id in video_ids:
- information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
- return information
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
class PostProcessor(object):
"""Post Processor class.
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
batchurls = []
if opts.batchfile is not None:
try:
- batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+ 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
youtube_search_ie = YoutubeSearchIE(youtube_ie)
# File downloader
- charset = locale.getpreferredencoding()
- if charset is None:
- charset = 'ascii'
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'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(charset))
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
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'),