X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube-dl;h=5aff9c08c1aab97a14909e76a0cb042f78345d6a;hb=8c5dc3ad4024eab1d167fb62a92eeabf7d895e59;hp=1ae68b2b5d017c3d530eb986cb48f50c3b368234;hpb=2c8d32de33dd6618659cd1fe98dcdf09fde1ecaf;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 1ae68b2b5..5aff9c08c 100755 --- a/youtube-dl +++ b/youtube-dl @@ -9,10 +9,15 @@ __author__ = ( 'Witold Baryluk', 'Paweł Paprota', 'Gergely Imreh', + 'Rogério Brito', + 'Philipp Hagemeister', + 'Sören Schulze', ) __license__ = 'Public Domain' -__version__ = '2011.08.24-phihag' +__version__ = '2011.09.14' + +UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' import cookielib import datetime @@ -58,6 +63,11 @@ try: except ImportError: pass # Handled below +try: + import xml.etree.ElementTree +except ImportError: # Python<2.5 + pass # Not officially supported, but let it slip + std_headers = { 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', @@ -197,6 +207,7 @@ def preferredencoding(): yield pref return yield_preferredencoding().next() + def htmlentity_transform(matchobj): """Transforms an HTML entity to a Unicode character. @@ -223,11 +234,13 @@ def htmlentity_transform(matchobj): # Unknown entity in name, return its literal representation return (u'&%s;' % entity) + def sanitize_title(utitle): """Sanitizes a video title so it could be used as part of a filename.""" utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) return utitle.replace(unicode(os.sep), u'%') + def sanitize_open(filename, open_mode): """Try to open the given filename, and slightly tweak it if this fails. @@ -254,13 +267,15 @@ def sanitize_open(filename, open_mode): stream = open(filename, open_mode) return (stream, filename) + def timeconvert(timestr): - """Convert RFC 2822 defined time string into system timestamp""" - timestamp = None - timetuple = email.utils.parsedate_tz(timestr) - if timetuple is not None: - timestamp = email.utils.mktime_tz(timetuple) - return timestamp + """Convert RFC 2822 defined time string into system timestamp""" + timestamp = None + timetuple = email.utils.parsedate_tz(timestr) + if timetuple is not None: + timestamp = email.utils.mktime_tz(timetuple) + return timestamp + class DownloadError(Exception): """Download Error exception. @@ -271,6 +286,7 @@ class DownloadError(Exception): """ pass + class SameFileError(Exception): """Same File exception. @@ -279,6 +295,7 @@ class SameFileError(Exception): """ pass + class PostProcessingError(Exception): """Post Processing exception. @@ -287,6 +304,7 @@ class PostProcessingError(Exception): """ pass + class UnavailableVideoError(Exception): """Unavailable Format exception. @@ -295,6 +313,7 @@ class UnavailableVideoError(Exception): """ pass + class ContentTooShortError(Exception): """Content Too Short exception. @@ -310,6 +329,7 @@ class ContentTooShortError(Exception): self.downloaded = downloaded self.expected = expected + class YoutubeDLHandler(urllib2.HTTPHandler): """Handler for HTTP requests and responses. @@ -319,11 +339,11 @@ class YoutubeDLHandler(urllib2.HTTPHandler): a particular request, the original request in the program code only has to include the HTTP header "Youtubedl-No-Compression", which will be removed before making the real request. - + Part of this code was copied from: - http://techknack.net/python-urllib2-handlers/ - + http://techknack.net/python-urllib2-handlers/ + Andrew Rowls, the author of that code, agreed to release it to the public domain. """ @@ -334,7 +354,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): return zlib.decompress(data, -zlib.MAX_WBITS) except zlib.error: return zlib.decompress(data) - + @staticmethod def addinfourl_wrapper(stream, headers, url, code): if hasattr(urllib2.addinfourl, 'getcode'): @@ -342,7 +362,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): ret = urllib2.addinfourl(stream, headers, url) ret.code = code return ret - + def http_request(self, req): for h in std_headers: if h in req.headers: @@ -368,6 +388,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): resp.msg = old_resp.msg return resp + class FileDownloader(object): """File Downloader class. @@ -440,16 +461,6 @@ class FileDownloader(object): self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self.params = params - @staticmethod - def pmkdir(filename): - """Create directory components in filename. Similar to Unix "mkdir -p".""" - components = filename.split(os.sep) - aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] - aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator - for dir in aggregate: - if not os.path.exists(dir): - os.mkdir(dir) - @staticmethod def format_bytes(bytes): if bytes is None: @@ -461,7 +472,7 @@ class FileDownloader(object): else: exponent = long(math.log(bytes, 1024.0)) suffix = 'bkMGTPEZY'[exponent] - converted = float(bytes) / float(1024**exponent) + converted = float(bytes) / float(1024 ** exponent) return '%.2f%s' % (converted, suffix) @staticmethod @@ -599,7 +610,7 @@ class FileDownloader(object): os.rename(old_filename, new_filename) except (IOError, OSError), err: self.trouble(u'ERROR: unable to rename file') - + def try_utime(self, filename, last_modified_hdr): """Try to set the last-modified time of the given file.""" if last_modified_hdr is None: @@ -613,7 +624,7 @@ class FileDownloader(object): if filetime is None: return try: - os.utime(filename,(time.time(), filetime)) + os.utime(filename, (time.time(), filetime)) except: pass @@ -706,9 +717,11 @@ class FileDownloader(object): return try: - self.pmkdir(filename) + dn = os.path.dirname(filename) + if dn != '' and not os.path.exists(dn): + os.makedirs(dn) except (OSError, IOError), err: - self.trouble(u'ERROR: unable to create directories: %s' % str(err)) + self.trouble(u'ERROR: unable to create directory ' + unicode(err)) return if self.params.get('writedescription', False): @@ -721,7 +734,7 @@ class FileDownloader(object): finally: descfile.close() except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn)) + self.trouble(u'ERROR: Cannot write description file ' + descfn) return if self.params.get('writeinfojson', False): @@ -739,7 +752,7 @@ class FileDownloader(object): finally: infof.close() except (OSError, IOError): - self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn)) + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) return try: @@ -819,6 +832,11 @@ class FileDownloader(object): cursize = os.path.getsize(tmpfilename) if prevsize == cursize and retval == 1: break + # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those + if prevsize == cursize and retval == 2 and cursize > 1024: + self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + retval = 0 + break if retval == 0: self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename)) self.try_rename(tmpfilename, filename) @@ -855,7 +873,7 @@ class FileDownloader(object): # 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) + request.add_header('Range', 'bytes=%d-' % resume_len) open_mode = 'ab' count = 0 @@ -881,7 +899,7 @@ class FileDownloader(object): else: # Examine the reported length if (content_length is not None and - (resume_len - 100 < long(content_length) < resume_len + 100)): + (resume_len - 100 < long(content_length) < resume_len + 100)): # The file had already been fully downloaded. # Explanation to the above condition: in issue #175 it was revealed that # YouTube sometimes adds or removes a few bytes from the end of the file, @@ -926,6 +944,7 @@ class FileDownloader(object): if stream is None: try: (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) + assert stream is not None filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) except (OSError, IOError), err: @@ -947,6 +966,9 @@ class FileDownloader(object): # Apply rate limit self.slow_down(start, byte_counter - resume_len) + if stream is None: + self.trouble(u'\nERROR: Did not get any data blocks') + return False stream.close() self.report_finish() if data_len is not None and byte_counter != data_len: @@ -959,6 +981,7 @@ class FileDownloader(object): return True + class InfoExtractor(object): """Information Extractor class. @@ -1030,6 +1053,7 @@ class InfoExtractor(object): """Real extraction process. Redefine in subclasses.""" pass + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -1039,7 +1063,7 @@ class YoutubeIE(InfoExtractor): _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'] + _available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13'] _video_extensions = { '13': '3gp', '17': 'mp4', @@ -1184,7 +1208,7 @@ class YoutubeIE(InfoExtractor): 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)) + % (video_id, el_type)) request = urllib2.Request(video_info_url) try: video_info_webpage = urllib2.urlopen(request).read() @@ -1504,6 +1528,7 @@ class DailymotionIE(InfoExtractor): # Retrieve video webpage to extract further information request = urllib2.Request(url) + request.add_header('Cookie', 'family_filter=off') try: self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() @@ -1513,25 +1538,29 @@ class DailymotionIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) - mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) + mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - mediaURL = urllib.unquote(mobj.group(1)) + sequence = urllib.unquote(mobj.group(1)) + mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') # if needed add http://www.dailymotion.com/ if relative URL video_url = mediaURL - # '' - mobj = re.search(r'(?im)Dailymotion\s*[\-:]\s*(.+?)', webpage) + mobj = re.search(r'(?im)Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?', 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)(.+?)', webpage) + mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -1553,6 +1582,7 @@ class DailymotionIE(InfoExtractor): except UnavailableVideoError: self._downloader.trouble(u'\nERROR: unable to download video') + class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" @@ -1646,7 +1676,6 @@ class GoogleIE(InfoExtractor): else: # we need something to pass to process_info video_thumbnail = '' - try: # Process video information self._downloader.process_info({ @@ -1846,7 +1875,8 @@ class YahooIE(InfoExtractor): 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.' + if not video_description: + video_description = 'No description available.' # Extract video height and width mobj = re.search(r'', webpage) @@ -1867,8 +1897,8 @@ class YahooIE(InfoExtractor): 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') + '&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() @@ -1897,13 +1927,128 @@ class YahooIE(InfoExtractor): 'thumbnail': video_thumbnail.decode('utf-8'), 'description': video_description, 'thumbnail': video_thumbnail, - 'description': video_description, 'player_url': None, }) except UnavailableVideoError: self._downloader.trouble(u'\nERROR: unable to download video') +class VimeoIE(InfoExtractor): + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(VimeoIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[vimeo] %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(1) + + # Retrieve video webpage to extract further information + request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers) + 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 + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract title + mobj = re.search(r'(.*?)', 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) + + # Extract uploader + mobj = re.search(r'http://vimeo.com/(.*?)', 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'(.*?)', 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'', 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.' + video_description = 'Foo.' + + # Vimeo specific: extract request signature + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature') + return + sig = mobj.group(1).decode('utf-8') + + # Vimeo specific: Extract request signature expiration + mobj = re.search(r'(.*?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract request signature expiration') + return + sig_exp = mobj.group(1).decode('utf-8') + + video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp) + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'mp4', + '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.""" @@ -1961,11 +2106,11 @@ class GenericIE(InfoExtractor): return video_url = urllib.unquote(mobj.group(1)) - video_id = os.path.basename(video_url) + 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] + 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 @@ -2038,7 +2183,7 @@ class YoutubeSearchIE(InfoExtractor): prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -2052,7 +2197,7 @@ class YoutubeSearchIE(InfoExtractor): 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)) + 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 @@ -2096,6 +2241,7 @@ class YoutubeSearchIE(InfoExtractor): pagenum = pagenum + 1 + class GoogleSearchIE(InfoExtractor): """Information Extractor for Google Video search queries.""" _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' @@ -2129,7 +2275,7 @@ class GoogleSearchIE(InfoExtractor): prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -2143,7 +2289,7 @@ class GoogleSearchIE(InfoExtractor): 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)) + 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 @@ -2187,6 +2333,7 @@ class GoogleSearchIE(InfoExtractor): pagenum = pagenum + 1 + class YahooSearchIE(InfoExtractor): """Information Extractor for Yahoo! Video search queries.""" _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' @@ -2220,7 +2367,7 @@ class YahooSearchIE(InfoExtractor): prefix, query = query.split(':') prefix = prefix[8:] - query = query.encode('utf-8') + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -2234,7 +2381,7 @@ class YahooSearchIE(InfoExtractor): 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)) + 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 @@ -2278,10 +2425,11 @@ class YahooSearchIE(InfoExtractor): pagenum = pagenum + 1 + class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' @@ -2354,6 +2502,7 @@ class YoutubePlaylistIE(InfoExtractor): self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return + class YoutubeUserIE(InfoExtractor): """Information Extractor for YouTube users.""" @@ -2375,7 +2524,7 @@ class YoutubeUserIE(InfoExtractor): def report_download_page(self, username, start_index): """Report attempt to download user page.""" self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % - (username, start_index, start_index + self._GDATA_PAGE_SIZE)) + (username, start_index, start_index + self._GDATA_PAGE_SIZE)) def _real_initialize(self): self._youtube_ie.initialize() @@ -2439,7 +2588,7 @@ class YoutubeUserIE(InfoExtractor): video_ids = video_ids[playliststart:playlistend] self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" % - (username, all_ids_count, len(video_ids))) + (username, all_ids_count, len(video_ids))) for video_id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) @@ -2524,6 +2673,7 @@ class DepositFilesIE(InfoExtractor): except UnavailableVideoError, err: self._downloader.trouble(u'ERROR: unable to download file') + class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" @@ -2819,6 +2969,226 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'\nERROR: unable to download video') +class MyVideoIE(InfoExtractor): + """Information Extractor for myvideo.de.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(MyVideoIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) + + def _real_initialize(self): + return + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._download.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group(1) + simple_title = mobj.group(2).decode('utf-8') + # should actually not be necessary + simple_title = sanitize_title(simple_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title) + + # Get video webpage + request = urllib2.Request('http://www.myvideo.de/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 to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + mobj = re.search(r'', + webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + video_url = mobj.group(1) + ('/%s.flv' % video_id) + + mobj = re.search('([^<]+)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + + video_title = mobj.group(1) + video_title = sanitize_title(video_title) + + try: + print(video_url) + self._downloader.process_info({ + 'id': video_id, + 'url': video_url, + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': video_title, + 'stitle': simple_title, + 'ext': u'flv', + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'\nERROR: Unable to download video') + +class ComedyCentralIE(InfoExtractor): + """Information extractor for The Daily Show and Colbert Report """ + + _VALID_URL = r'^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?Pthedailyshow|colbertnation)\.com/full-episodes/(?P.*)$' + + @staticmethod + def suitable(url): + return (re.match(ComedyCentralIE._VALID_URL, url) is not None) + + def report_extraction(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) + + def report_config_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) + + def report_index_download(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + + def report_player_url(self, episode_id): + self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) + + def _simplify_title(self, title): + res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) + res = res.strip(ur'_') + return res + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + if mobj.group('shortname'): + if mobj.group('shortname') in ('tds', 'thedailyshow'): + url = 'http://www.thedailyshow.com/full-episodes/' + else: + url = 'http://www.colbertnation.com/full-episodes/' + mobj = re.match(self._VALID_URL, url) + assert mobj is not None + + dlNewest = not mobj.group('episode') + if dlNewest: + epTitle = mobj.group('showname') + else: + epTitle = mobj.group('episode') + + req = urllib2.Request(url) + self.report_extraction(epTitle) + try: + htmlHandle = urllib2.urlopen(req) + html = htmlHandle.read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) + return + if dlNewest: + url = htmlHandle.geturl() + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) + return + if mobj.group('episode') == '': + self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) + return + epTitle = mobj.group('episode') + + mMovieParams = re.findall('', html) + if len(mMovieParams) == 0: + self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) + return + + playerUrl_raw = mMovieParams[0][0] + self.report_player_url(epTitle) + try: + urlHandle = urllib2.urlopen(playerUrl_raw) + playerUrl = urlHandle.geturl() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err)) + return + + uri = mMovieParams[0][1] + indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri}) + self.report_index_download(epTitle) + try: + indexXml = urllib2.urlopen(indexUrl).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err)) + return + + idoc = xml.etree.ElementTree.fromstring(indexXml) + itemEls = idoc.findall('.//item') + for itemEl in itemEls: + mediaId = itemEl.findall('./guid')[0].text + shortMediaId = mediaId.split(':')[-1] + showId = mediaId.split(':')[-2].replace('.com', '') + officialTitle = itemEl.findall('./title')[0].text + officialDate = itemEl.findall('./pubDate')[0].text + + configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + + urllib.urlencode({'uri': mediaId})) + configReq = urllib2.Request(configUrl) + self.report_config_download(epTitle) + try: + configXml = urllib2.urlopen(configReq).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) + return + + cdoc = xml.etree.ElementTree.fromstring(configXml) + turls = [] + for rendition in cdoc.findall('.//rendition'): + finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) + turls.append(finfo) + + if len(turls) == 0: + self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') + continue + + # For now, just pick the highest bitrate + format,video_url = turls[-1] + + self._downloader.increment_downloads() + + effTitle = showId + '-' + epTitle + info = { + 'id': shortMediaId, + 'url': video_url, + 'uploader': showId, + 'upload_date': officialDate, + 'title': effTitle, + 'stitle': self._simplify_title(effTitle), + 'ext': 'mp4', + 'format': format, + 'thumbnail': None, + 'description': officialTitle, + 'player_url': playerUrl + } + + try: + self._downloader.process_info(info) + except UnavailableVideoError, err: + self._downloader.trouble(u'\nERROR: unable to download ' + mediaId) + continue + + class PostProcessor(object): """Post Processor class. @@ -2865,6 +3235,7 @@ class PostProcessor(object): """ return information # by default, do nothing + class FFmpegExtractAudioPP(PostProcessor): def __init__(self, downloader=None, preferredcodec=None): @@ -2954,24 +3325,27 @@ def updateSelf(downloader, filename): 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...') + downloader.to_screen('Updating to latest version...') try: - latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' - latest_version = urllib.urlopen(latest_url).read().strip() - prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version - newcontent = urllib.urlopen(prog_url).read() + try: + urlh = urllib.urlopen(UPDATE_URL) + newcontent = urlh.read() + finally: + urlh.close() except (IOError, OSError), err: sys.exit('ERROR: unable to download latest version') try: - stream = open(filename, 'w') - stream.write(newcontent) - stream.close() + outf = open(filename, 'wb') + try: + outf.write(newcontent) + finally: + outf.close() except (IOError, OSError), err: sys.exit('ERROR: unable to overwrite current version') - downloader.to_screen('Updated to version %s' % latest_version) + downloader.to_screen('Updated youtube-dl. Restart to use the new version.') def parseOpts(): # Deferred imports @@ -2996,11 +3370,12 @@ def parseOpts(): if columns: return int(columns) - # TODO: Breaks on phihag's system - #if sys.platform.startswith('linux'): - # try: - # return os.popen('stty size', 'r').read().split()[1] - # except: pass + try: + sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out,err = sp.communicate() + return int(out.split()[1]) + except: + pass return None max_width = 80 @@ -3016,7 +3391,7 @@ def parseOpts(): kw = { 'version' : __version__, 'formatter' : fmt, - 'usage' : '%prog [options] url...', + 'usage' : '%prog [options] url [url...]', 'conflict_handler' : 'resolve', } @@ -3035,7 +3410,7 @@ def parseOpts(): general.add_option('-v', '--version', action='version', help='print program version and exit') general.add_option('-U', '--update', - action='store_true', dest='update_self', help='update this program to latest stable version') + action='store_true', dest='update_self', help='update this program to latest version') general.add_option('-i', '--ignore-errors', action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) general.add_option('-r', '--rate-limit', @@ -3158,7 +3533,8 @@ def main(): # General configuration cookie_processor = urllib2.HTTPCookieProcessor(jar) - urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())) + opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()) + urllib2.install_opener(opener) socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) # Batch file verification @@ -3215,20 +3591,29 @@ def main(): # 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) - deposit_files_ie = DepositFilesIE() - facebook_ie = FacebookIE() - bliptv_ie = BlipTVIE() - generic_ie = GenericIE() + extractors = [ # Order does matter + youtube_ie, + MetacafeIE(youtube_ie), + DailymotionIE(), + YoutubePlaylistIE(youtube_ie), + YoutubeUserIE(youtube_ie), + YoutubeSearchIE(youtube_ie), + google_ie, + GoogleSearchIE(google_ie), + PhotobucketIE(), + yahoo_ie, + YahooSearchIE(yahoo_ie), + DepositFilesIE(), + FacebookIE(), + BlipTVIE(), + VimeoIE(), + MyVideoIE(), + ComedyCentralIE(), + + GenericIE() + ] # File downloader fd = FileDownloader({ @@ -3269,24 +3654,8 @@ def main(): 'writedescription': opts.writedescription, 'writeinfojson': opts.writeinfojson, }) - 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) - fd.add_info_extractor(deposit_files_ie) - fd.add_info_extractor(facebook_ie) - fd.add_info_extractor(bliptv_ie) - - # This must come last since it's the - # fallback if none of the others work - fd.add_info_extractor(generic_ie) + for extractor in extractors: + fd.add_info_extractor(extractor) # PostProcessors if opts.extractaudio: