+ @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_screen(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(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_screen(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(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_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(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_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(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_screen(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_screen(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_screen(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
+ 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_yahoo_results:
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ n = self._max_yahoo_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._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
+ _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+ _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."""
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ 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:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # 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:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ break
+ pagenum = pagenum + 1
+
+ playliststart = self._downloader.params.get('playliststart', 1)
+ playliststart -= 1 #our arrays are zero-based but the playlist is 1-based
+ if playliststart > 0:
+ video_ids = video_ids[playliststart:]
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+class YoutubeUserIE(InfoExtractor):
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+ _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(YoutubeUserIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, username):
+ """Report attempt to download user page."""
+ self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Download user page
+ username = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ self.report_download_page(username)
+ request = urllib2.Request(self._TEMPLATE_URL % (username), 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
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ playliststart = self._downloader.params.get('playliststart', 1)
+ playliststart = playliststart-1 #our arrays are zero-based but the playlist is 1-based
+ if playliststart > 0:
+ video_ids = video_ids[playliststart:]
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+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
+ composed 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 ###
+if __name__ == '__main__':
+ try:
+ # Modules needed only when running the main program
+ import getpass
+ import optparse
+
+ # Function to update the program file with the latest version from bitbucket.org
+ def update_self(downloader, filename):
+ # Note: downloader only used for options
+ if not os.access (filename, os.W_OK):
+ sys.exit('ERROR: no write permissions on %s' % filename)
+
+ downloader.to_screen('Updating to latest stable version...')
+ latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+ latest_version = urllib.urlopen(latest_url).read().strip()
+ prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+ newcontent = urllib.urlopen(prog_url).read()
+ stream = open(filename, 'w')
+ stream.write(newcontent)
+ stream.close()
+ downloader.to_screen('Updated to version %s' % latest_version)
+
+ # Parse command line
+ parser = optparse.OptionParser(
+ usage='Usage: %prog [options] url...',
+ version='2010.10.24',
+ 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', '--update',
+ action='store_true', dest='update_self', help='update this program to latest stable version')
+ parser.add_option('-i', '--ignore-errors',
+ action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+ parser.add_option('-r', '--rate-limit',
+ dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+ parser.add_option('-R', '--retries',
+ dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
+ parser.add_option('--playlist-start',
+ dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+
+ authentication = optparse.OptionGroup(parser, 'Authentication Options')
+ authentication.add_option('-u', '--username',
+ dest='username', metavar='USERNAME', help='account username')
+ authentication.add_option('-p', '--password',
+ dest='password', metavar='PASSWORD', help='account password')
+ authentication.add_option('-n', '--netrc',
+ action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+ parser.add_option_group(authentication)
+
+ video_format = optparse.OptionGroup(parser, 'Video Format Options')
+ video_format.add_option('-f', '--format',
+ action='store', dest='format', metavar='FORMAT', help='video format code')
+ video_format.add_option('-m', '--mobile-version',
+ action='store_const', dest='format', help='alias for -f 17', const='17')
+ video_format.add_option('--all-formats',
+ action='store_const', dest='format', help='download all available video formats', const='-1')
+ video_format.add_option('--max-quality',
+ action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+ video_format.add_option('-b', '--best-quality',
+ action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')
+ parser.add_option_group(video_format)
+
+ verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+ verbosity.add_option('-q', '--quiet',
+ action='store_true', dest='quiet', help='activates quiet mode', default=False)
+ verbosity.add_option('-s', '--simulate',
+ action='store_true', dest='simulate', help='do not download video', default=False)
+ verbosity.add_option('-g', '--get-url',
+ action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+ verbosity.add_option('-e', '--get-title',
+ action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+ verbosity.add_option('--get-thumbnail',
+ action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
+ verbosity.add_option('--get-description',
+ action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
+ verbosity.add_option('--no-progress',
+ action='store_true', dest='noprogress', help='do not print progress bar', default=False)
+ parser.add_option_group(verbosity)
+
+ filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
+ filesystem.add_option('-t', '--title',
+ action='store_true', dest='usetitle', help='use title in file name', default=False)
+ filesystem.add_option('-l', '--literal',
+ action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+ filesystem.add_option('-o', '--output',
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template')
+ filesystem.add_option('-a', '--batch-file',
+ dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+ filesystem.add_option('-w', '--no-overwrites',
+ action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+ filesystem.add_option('-c', '--continue',
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+ filesystem.add_option('--cookies',
+ dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+ parser.add_option_group(filesystem)
+
+ (opts, args) = parser.parse_args()
+
+ # Open appropriate CookieJar
+ if opts.cookiefile is None:
+ jar = cookielib.CookieJar()
+ else:
+ try:
+ jar = cookielib.MozillaCookieJar(opts.cookiefile)
+ if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+ jar.load()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to open cookie file')
+
+ # General configuration
+ cookie_processor = urllib2.HTTPCookieProcessor(jar)
+ urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
+ urllib2.install_opener(urllib2.build_opener(cookie_processor))
+ socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+ # Batch file verification
+ batchurls = []
+ if opts.batchfile is not None:
+ try:
+ if opts.batchfile == '-':
+ batchfd = sys.stdin
+ else:
+ batchfd = open(opts.batchfile, 'r')
+ batchurls = batchfd.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
+
+ # Conflicting, missing and erroneous options
+ if opts.bestquality:
+ print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'
+ if opts.usenetrc and (opts.username is not None or opts.password is not None):
+ parser.error(u'using .netrc conflicts with giving username/password')
+ if opts.password is not None and opts.username is None:
+ parser.error(u'account username missing')
+ if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
+ parser.error(u'using output template conflicts with using title or literal title')
+ if opts.usetitle and opts.useliteral:
+ parser.error(u'using title conflicts with using literal title')
+ if opts.username is not None and opts.password is None:
+ opts.password = getpass.getpass(u'Type account password and press return:')
+ if opts.ratelimit is not None:
+ numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
+ if numeric_limit is None:
+ parser.error(u'invalid rate limit specified')
+ opts.ratelimit = numeric_limit
+ if opts.retries is not None:
+ try:
+ opts.retries = long(opts.retries)
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid retry count specified')
+ if opts.playliststart is not None:
+ try:
+ opts.playliststart = long(opts.playliststart)
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid playlist page specified')
+
+ # Information extractors
+ youtube_ie = YoutubeIE()
+ metacafe_ie = MetacafeIE(youtube_ie)
+ dailymotion_ie = DailymotionIE()
+ youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_user_ie = YoutubeUserIE(youtube_ie)
+ youtube_search_ie = YoutubeSearchIE(youtube_ie)
+ google_ie = GoogleIE()
+ google_search_ie = GoogleSearchIE(google_ie)
+ photobucket_ie = PhotobucketIE()
+ yahoo_ie = YahooIE()
+ yahoo_search_ie = YahooSearchIE(yahoo_ie)
+ generic_ie = GenericIE()
+
+ # File downloader
+ fd = FileDownloader({
+ 'usenetrc': opts.usenetrc,
+ 'username': opts.username,
+ 'password': opts.password,
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
+ 'forceurl': opts.geturl,
+ 'forcetitle': opts.gettitle,
+ 'forcethumbnail': opts.getthumbnail,
+ 'forcedescription': opts.getdescription,
+ 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
+ 'format': opts.format,
+ 'format_limit': opts.format_limit,
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+ or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+ 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'),
+ 'ignoreerrors': opts.ignoreerrors,
+ 'ratelimit': opts.ratelimit,
+ 'nooverwrites': opts.nooverwrites,
+ 'retries': opts.retries,
+ 'continuedl': opts.continue_dl,
+ 'noprogress': opts.noprogress,
+ 'playliststart': opts.playliststart,
+ 'logtostderr': opts.outtmpl == '-',
+ })
+ fd.add_info_extractor(youtube_search_ie)
+ fd.add_info_extractor(youtube_pl_ie)
+ fd.add_info_extractor(youtube_user_ie)
+ fd.add_info_extractor(metacafe_ie)
+ fd.add_info_extractor(dailymotion_ie)
+ fd.add_info_extractor(youtube_ie)
+ fd.add_info_extractor(google_ie)
+ fd.add_info_extractor(google_search_ie)
+ fd.add_info_extractor(photobucket_ie)
+ fd.add_info_extractor(yahoo_ie)
+ fd.add_info_extractor(yahoo_search_ie)
+
+ # This must come last since it's the
+ # fallback if none of the others work
+ fd.add_info_extractor(generic_ie)
+
+ # Update version
+ if opts.update_self:
+ update_self(fd, sys.argv[0])
+
+ # Maybe do nothing
+ if len(all_urls) < 1:
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
+ retcode = fd.download(all_urls)
+
+ # Dump cookie jar if requested
+ if opts.cookiefile is not None:
+ try:
+ jar.save()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to save cookie jar')
+
+ sys.exit(retcode)
+
+ except DownloadError:
+ sys.exit(1)
+ except SameFileError:
+ sys.exit(u'ERROR: fixed output name but more than one file to download')
+ except KeyboardInterrupt:
+ sys.exit(u'\nERROR: Interrupted by user')
Rapsys Git / youtubedl / blobdiff