+ try:
+ self.pmkdir(filename)
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to create directories: %s' % str(err))
+ return
+
+ try:
+ success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
+ except (OSError, IOError), err:
+ raise UnavailableVideoError
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.trouble('ERROR: unable to download video data: %s' % str(err))
+ return
+ except (ContentTooShortError, ), err:
+ self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ return
+
+ if success:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble('ERROR: postprocessing: %s' % str(err))
+ return
+
+ def download(self, url_list):
+ """Download a given list of URLs."""
+ if len(url_list) > 1 and self.fixed_template():
+ raise SameFileError(self.params['outtmpl'])
+
+ for url in url_list:
+ suitable_found = False
+ for ie in self._ies:
+ # Go to next InfoExtractor if not suitable
+ if not ie.suitable(url):
+ continue
+
+ # Suitable InfoExtractor found
+ suitable_found = True
+
+ # Extract information from URL and process it
+ ie.extract(url)
+
+ # Suitable InfoExtractor had been found; go to next URL
+ break
+
+ if not suitable_found:
+ self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+
+ return self._download_retcode
+
+ def post_process(self, filename, ie_info):
+ """Run the postprocessing chain on the given file."""
+ info = dict(ie_info)
+ info['filepath'] = filename
+ for pp in self._pps:
+ info = pp.run(info)
+ if info is None:
+ break
+
+ def _download_with_rtmpdump(self, filename, url, player_url):
+ self.report_destination(filename)
+
+ # Check for rtmpdump first
+ try:
+ subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ except (OSError, IOError):
+ self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+ return False
+
+ # Download using rtmpdump. rtmpdump returns exit code 2 when
+ # the connection was interrumpted and resuming appears to be
+ # possible. This is part of rtmpdump's normal usage, AFAIK.
+ basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename]
+ retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+ while retval == 2 or retval == 1:
+ prevsize = os.path.getsize(filename)
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+ time.sleep(5.0) # This seems to be needed
+ retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+ cursize = os.path.getsize(filename)
+ if prevsize == cursize and retval == 1:
+ break
+ if retval == 0:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ return True
+ else:
+ self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+ return False
+
+ def _do_download(self, filename, url, player_url):
+ # Attempt to download using rtmpdump
+ if url.startswith('rtmp'):
+ return self._download_with_rtmpdump(filename, url, player_url)
+
+ stream = None
+ open_mode = 'wb'
+ basic_request = urllib2.Request(url, None, std_headers)
+ request = urllib2.Request(url, None, std_headers)
+
+ # Establish possible resume length
+ if os.path.isfile(filename):
+ resume_len = os.path.getsize(filename)
+ else:
+ resume_len = 0
+
+ # Request parameters in case of being able to resume
+ if self.params.get('continuedl', False) and resume_len != 0:
+ self.report_resuming_byte(resume_len)
+ request.add_header('Range','bytes=%d-' % resume_len)
+ open_mode = 'ab'
+
+ count = 0
+ retries = self.params.get('retries', 0)
+ while True:
+ # Establish connection
+ try:
+ data = urllib2.urlopen(request)
+ break
+ except (urllib2.HTTPError, ), err:
+ if err.code == 503:
+ # Retry in case of HTTP error 503
+ count += 1
+ if count <= retries:
+ self.report_retry(count, retries)
+ continue
+ if err.code != 416: # 416 is 'Requested range not satisfiable'
+ raise
+ # Unable to resume
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+
+ if content_length is not None and long(content_length) == resume_len:
+ # Because the file had already been fully downloaded
+ self.report_file_already_downloaded(filename)
+ return True
+ else:
+ # Because the server didn't let us
+ self.report_unable_to_resume()
+ open_mode = 'wb'
+
+ data_len = data.info().get('Content-length', None)
+ data_len_str = self.format_bytes(data_len)
+ byte_counter = 0
+ block_size = 1024
+ start = time.time()
+ while True:
+ # Download and write
+ before = time.time()
+ data_block = data.read(block_size)
+ after = time.time()
+ data_block_len = len(data_block)
+ if data_block_len == 0:
+ break
+ byte_counter += data_block_len
+
+ # Open file just in time
+ if stream is None:
+ try:
+ (stream, filename) = sanitize_open(filename, open_mode)
+ self.report_destination(filename)
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ return False
+ try:
+ stream.write(data_block)
+ except (IOError, OSError), err:
+ self.trouble('\nERROR: unable to write data: %s' % str(err))
+ block_size = self.best_block_size(after - before, data_block_len)
+
+ # Progress message
+ percent_str = self.calc_percent(byte_counter, data_len)
+ eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
+ speed_str = self.calc_speed(start, time.time(), byte_counter)
+ self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+
+ # Apply rate limit
+ self.slow_down(start, byte_counter)
+
+ self.report_finish()
+ if data_len is not None and str(byte_counter) != data_len:
+ raise ContentTooShortError(byte_counter, long(data_len))
+ return True
+
+class InfoExtractor(object):
+ """Information Extractor class.
+
+ Information extractors are the classes that, given a URL, extract
+ information from the video (or videos) the URL refers to. This
+ information includes the real video URL, the video title and simplified
+ title, author and others. The information is stored in a dictionary
+ which is then passed to the FileDownloader. The FileDownloader
+ processes this information possibly downloading the video to the file
+ system, among other possible outcomes. The dictionaries must include
+ the following fields:
+
+ id: Video identifier.
+ url: Final video URL.
+ uploader: Nickname of the video uploader.
+ title: Literal title.
+ stitle: Simplified title.
+ ext: Video filename extension.
+ format: Video format.
+ player_url: SWF Player URL (may be None).
+
+ The following fields are optional. Their primary purpose is to allow
+ youtube-dl to serve as the backend for a video search function, such
+ as the one in youtube2mp3. They are only used when their respective
+ forced printing functions are called:
+
+ thumbnail: Full URL to a video thumbnail image.
+ description: One-line video description.
+
+ Subclasses of this one should re-define the _real_initialize() and
+ _real_extract() methods, as well as the suitable() static method.
+ Probably, they should also be instantiated and added to the main
+ downloader.
+ """
+
+ _ready = False
+ _downloader = None
+
+ def __init__(self, downloader=None):
+ """Constructor. Receives an optional downloader."""
+ self._ready = False
+ self.set_downloader(downloader)
+
+ @staticmethod
+ def suitable(url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return False
+
+ def initialize(self):
+ """Initializes an instance (authentication, etc)."""
+ if not self._ready:
+ self._real_initialize()
+ self._ready = True
+
+ def extract(self, url):
+ """Extracts URL information and returns it in list of dicts."""
+ self.initialize()
+ return self._real_extract(url)
+
+ def set_downloader(self, downloader):
+ """Sets the downloader for this IE."""
+ self._downloader = downloader
+
+ def _real_initialize(self):
+ """Real initialization process. Redefine in subclasses."""
+ pass
+
+ def _real_extract(self, url):
+ """Real extraction process. Redefine in subclasses."""
+ pass
+
+class YoutubeIE(InfoExtractor):
+ """Information extractor for youtube.com."""
+
+ _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
+ _NETRC_MACHINE = 'youtube'
+ # Listed in order of quality
+ _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
+ _video_extensions = {
+ '13': '3gp',
+ '17': 'mp4',
+ '18': 'mp4',
+ '22': 'mp4',
+ '37': 'mp4',
+ '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
+ '43': 'webm',
+ '45': 'webm',
+ }
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeIE._VALID_URL, url) is not None)
+
+ def report_lang(self):
+ """Report attempt to set language."""
+ self._downloader.to_stdout(u'[youtube] Setting language')
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._downloader.to_stdout(u'[youtube] Logging in')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self._downloader.to_stdout(u'[youtube] Confirming age')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+
+ def report_video_info_webpage_download(self, video_id):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+
+ def report_unavailable_format(self, video_id, format):
+ """Report extracted video URL."""
+ self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+
+ def report_rtmp_download(self):
+ """Indicate the download will use the RTMP protocol."""
+ self._downloader.to_stdout(u'[youtube] RTMP download detected')
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ username = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ username = downloader_params['username']
+ password = downloader_params['password']
+ elif downloader_params.get('usenetrc', False):
+ try:
+ info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+ if info is not None:
+ username = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError), err:
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ return
+
+ # Set language
+ request = urllib2.Request(self._LANG_URL, None, std_headers)
+ try:
+ self.report_lang()
+ urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+ return
+
+ # No authentication to be performed
+ if username is None:
+ return
+
+ # Log in
+ login_form = {
+ 'current_form': 'loginForm',
+ 'next': '/',
+ 'action_login': 'Log In',
+ 'username': username,
+ 'password': password,
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ return
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ return
+
+ # Confirm age
+ age_form = {
+ 'next_url': '/',
+ 'action_confirm': 'Confirm',
+ }
+ request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
+ try:
+ self.report_age_confirmation()
+ age_results = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ # Extract video id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group(2)
+
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+ try:
+ video_webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ # Attempt to extract SWF player URL
+ mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
+ if mobj is not None:
+ player_url = mobj.group(1)
+ else:
+ player_url = None
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url, None, std_headers)
+ try:
+ video_info_webpage = urllib2.urlopen(request).read()
+ video_info = parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
+ self.report_information_extraction(video_id)
+
+ # uploader
+ if 'author' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote_plus(video_info['author'][0])
+
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote_plus(video_info['title'][0])
+ video_title = video_title.decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ # thumbnail image
+ if 'thumbnail_url' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else: # don't panic if we can't find it
+ video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+
+ # description
+ video_description = 'No description available.'
+ if self._downloader.params.get('forcedescription', False):
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+ if mobj is not None:
+ video_description = mobj.group(1)
+
+ # Decide which formats to download
+ if 'fmt_url_map' in video_info:
+ url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
+ format_limit = self._downloader.params.get('format_limit', None)
+ if format_limit is not None and format_limit in self._available_formats:
+ format_list = self._available_formats[self._available_formats.index(format_limit):]
+ else:
+ format_list = self._available_formats
+ existing_formats = [x for x in format_list if x in url_map]
+ if len(existing_formats) == 0:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ requested_format = self._downloader.params.get('format', None)
+ if requested_format is None:
+ video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif requested_format == '-1':
+ video_url_list = url_map.items() # All formats
+ else:
+ if requested_format not in existing_formats:
+ self._downloader.trouble(u'ERROR: format not available for video')
+ return
+ video_url_list = [(requested_format, url_map[requested_format])] # Specific format
+ elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_url_list = [(None, video_info['conn'][0])]
+ else:
+ self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+ return
+
+ for format_param, video_real_url in video_url_list:
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Find the video URL in fmt_url_map or conn paramters
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_real_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description.decode('utf-8'),
+ 'player_url': player_url,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class MetacafeIE(InfoExtractor):
+ """Information Extractor for metacafe.com."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+ _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+ _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(MetacafeIE._VALID_URL, url) is not None)
+
+ def report_disclaimer(self):
+ """Report disclaimer retrieval."""
+ self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self._downloader.to_stdout(u'[metacafe] Confirming age')
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ # Retrieve disclaimer
+ request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+ try:
+ self.report_disclaimer()
+ disclaimer = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+ return
+
+ # Confirm age
+ disclaimer_form = {
+ 'filters': '0',
+ 'submit': "Continue - I'm over 18",
+ }
+ request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
+ try:
+ self.report_age_confirmation()
+ disclaimer = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ # Extract id and simplified title from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+
+ # Check if video comes from YouTube
+ mobj2 = re.match(r'^yt-(.*)$', video_id)
+ if mobj2 is not None:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ simple_title = mobj.group(2).decode('utf-8')
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ #if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ # return
+ #gdaKey = mobj.group(1)
+ #
+ #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+
+ video_url = mediaURL
+
+ mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class DailymotionIE(InfoExtractor):
+ """Information Extractor for Dailymotion"""
+
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(DailymotionIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id and simplified title from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ simple_title = mobj.group(2).decode('utf-8')
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ # if needed add http://www.dailymotion.com/ if relative URL
+
+ video_url = mediaURL
+
+ # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
+ mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+class GoogleIE(InfoExtractor):
+ """Information extractor for video.google.com."""
+
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r"download_url:'([^']+)'", webpage)
+ if mobj is None:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+ mediaURL = mediaURL.replace('\\x3d', '\x3d')
+ mediaURL = mediaURL.replace('\\x26', '\x26')
+
+ video_url = mediaURL
+
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Extract video description
+ mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video description')
+ return
+ video_description = mobj.group(1).decode('utf-8')
+ if not video_description:
+ video_description = 'No description available.'
+
+ # Extract video thumbnail
+ if self._downloader.params.get('forcethumbnail', False):
+ request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1)
+ else: # we need something to pass to process_info
+ video_thumbnail = ''
+
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class PhotobucketIE(InfoExtractor):
+ """Information extractor for photobucket.com."""
+
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(PhotobucketIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ video_url = mediaURL
+
+ mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ video_uploader = mobj.group(2).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class YahooIE(InfoExtractor):
+ """Information extractor for video.yahoo.com."""
+
+ # _VALID_URL matches all Yahoo! Video URLs
+ # _VPAGE_URL matches only the extractable '/watch/' URLs
+ _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
+ _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YahooIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url, new_video=True):
+ # Extract ID from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(2)
+ video_extension = 'flv'
+
+ # Rewrite valid but non-extractable URLs as
+ # extractable English language /watch/ URLs
+ if re.match(self._VPAGE_URL, url) is None:
+ request = urllib2.Request(url)
+ try:
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract id field')
+ return
+ yahoo_id = mobj.group(1)
+
+ mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract vid field')
+ return
+ yahoo_vid = mobj.group(1)
+
+ url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
+ return self._real_extract(url, new_video=False)
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ # Extract video thumbnail
+ mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+ # Extract video description
+ mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video description')
+ return
+ video_description = mobj.group(1).decode('utf-8')
+ if not video_description: video_description = 'No description available.'
+
+ # Extract video height and width
+ mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video height')
+ return
+ yv_video_height = mobj.group(1)
+
+ mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video width')
+ return
+ yv_video_width = mobj.group(1)
+
+ # Retrieve video playlist to extract media URL
+ # I'm not completely sure what all these options are, but we
+ # seem to need most of them, otherwise the server sends a 401.
+ yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
+ yv_bitrate = '700' # according to Wikipedia this is hard-coded
+ request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
+ '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+ '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract media URL from playlist XML
+ mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Unable to extract media URL')
+ return
+ video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
+ video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class GenericIE(InfoExtractor):
+ """Generic last-resort information extractor."""
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return True
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ video_id = url.split('/')[-1]
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ except ValueError, err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = urllib.unquote(mobj.group(1))
+ video_id = os.path.basename(video_url)
+
+ # here's a fun little line of code for you:
+ video_extension = os.path.splitext(video_id)[1][1:]
+ video_id = os.path.splitext(video_id)[0]
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # video uploader is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class YoutubeSearchIE(InfoExtractor):
+ """Information Extractor for YouTube search queries."""
+ _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+ _youtube_ie = None
+ _max_youtube_results = 1000
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_youtube_results:
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class GoogleSearchIE(InfoExtractor):
+ """Information Extractor for Google Video search queries."""
+ _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
+ _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
+ _MORE_PAGES_INDICATOR = r'<span>Next</span>'
+ _google_ie = None
+ _max_google_results = 1000
+
+ def __init__(self, google_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._google_ie = google_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._google_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_google_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_google_results:
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ n = self._max_google_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class YahooSearchIE(InfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
+ _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
+ _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
+ _MORE_PAGES_INDICATOR = r'\s*Next'
+ _yahoo_ie = None
+ _max_yahoo_results = 1000
+
+ def __init__(self, yahoo_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._yahoo_ie = yahoo_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._yahoo_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
Rapsys Git / youtubedl / blobdiff