From: Rogério Brito Date: Sat, 18 Jun 2011 05:16:59 +0000 (-0300) Subject: Imported Upstream version 2010.11.19 X-Git-Url: https://git.rapsys.eu/youtubedl/commitdiff_plain/187e6306160793cab151b129f35dbcf432ec6ca8?ds=sidebyside;hp=-c Imported Upstream version 2010.11.19 --- 187e6306160793cab151b129f35dbcf432ec6ca8 diff --git a/.hg_archival.txt b/.hg_archival.txt deleted file mode 100644 index 21226b5..0000000 --- a/.hg_archival.txt +++ /dev/null @@ -1,4 +0,0 @@ -repo: f87cf8f2527c4adda57b14bd79a354f815164a41 -node: 3b1889cc83b5085e178593f4dfa376b429f5be0d -branch: default -tag: 2010.10.24 diff --git a/.hgtags b/.hgtags deleted file mode 100644 index 865c0b6..0000000 --- a/.hgtags +++ /dev/null @@ -1,56 +0,0 @@ -afa03d33275e27c5ef7de0256053894a3c938901 2008.07.22 -385afd90ca13840be83bd736985817e9002775ad 2008.08.09 -9636c1843c6fb35cd2a934d5447210be9a8f9793 2008.09.20 -846c13fabe7837ef578d00e3d492cfae6c832a33 2008.10.16 -c72929f1680dc42e6fa1183be295a83427a290b4 2008.11.01 -ee7b97092712edf401fa237a7cd9b74925409a54 2009.01.31 -ef03a5f5f3337cd07b6d230226e199d4d9bb50ce 2009.02.07 -8dc1b312077f4c5eea95581c62ae256089e0eb50 2009.03.03 -1dd3c78e417e1ac30d03ddd350eca58e7d224066 2009.03.28 -468b207ea6eef08c713c27facc131e6e0dcacc85 2009.04.06 -c42582904adf7184e0e1909cfc80e64359d8294c 2009.04.25 -95b216d50f8ae9e78b16769c237e18fa05c6ac1b 2009.05.11 -31198e942e00619effa7ed3cef92771002eb0e48 2009.05.13 -63a16cc3d504cfce9e6db067c673c3ddcf2402c6 2009.05.23 -63a16cc3d504cfce9e6db067c673c3ddcf2402c6 2009.05.23 -0000000000000000000000000000000000000000 2009.05.23 -0000000000000000000000000000000000000000 2009.05.23 -3f498fb562912768a2ce8e2552747f27f525faa5 2009.05.23 -4bc5ac772e8a5b5dfa4ca88898daec8dd5502c2b 2009.05.25 -cfc3202eb7b61d4a7fd837cb5e3e35535d835f46 2009.05.30 -2793d3270ff9f7ea6e8f00effd6fb1b07e86d4d1 2009.06.29 -df8b882d8b39952a6be64ab8d742044a5d41fb18 2009.08.08 -4597eb63af5c26d07bfbef476a74963d72a78ba4 2009.09.08 -6947c04fb1b4e94cd9422efe6854f8abe80568d2 2009.09.13 -eabc9bc8ab3ca52115a13036a57135d6df128f6f 2009.12.26 -4d808fe755d0cf8dc05f2224d039733217355b9c 2010.01.05 -9afea09eca34c7daf152b90ab8c245964064e3a3 2010.01.06 -9ade3c8f7a53748c3e3edd2009585b8fbbe1f561 2010.01.19 -93ff6dceb3da30991d4e7c7bdf7bbf5ed7baea61 2010.02.13 -c69858fd48506de909499f59ea65d982df93b103 2010.03.07 -af285beaf15be8c4800d7bfdd868dd6058b14d65 2010.03.13 -af285beaf15be8c4800d7bfdd868dd6058b14d65 2010.03.13 -0000000000000000000000000000000000000000 2010.03.13 -0000000000000000000000000000000000000000 2010.03.13 -eadec6d49e8a8d266c2ac6674aef2b415ccd3424 2010.03.13 -a40f32f2978ab2c20450da2a708b8ece806fe147 2010.04.02 -d6f421afc953fcc2d7336e7e4d6248b4d015e360 2010.04.03 -1d3bca5d5e5dd4dc014c3d2681b7a429be9edd2f 2010.04.04 -2bf8bad7237fbfee1bd292d8114588ae1f24b9b2 2010.06.06 -2bf8bad7237fbfee1bd292d8114588ae1f24b9b2 2010.06.06 -0000000000000000000000000000000000000000 2010.06.06 -0000000000000000000000000000000000000000 2010.06.06 -ebc3c1a8ea9490f2406b3f9ef9669556182dc2ce 2010.06.06 -a44566779488ca70b9e1e7cf163e623744139a28 2010.07.14 -a44566779488ca70b9e1e7cf163e623744139a28 2010.07.14 -0000000000000000000000000000000000000000 2010.07.14 -0000000000000000000000000000000000000000 2010.07.14 -70a9a497598a17d803266b3f9aaf4a26286598ee 2010.07.14 -70a9a497598a17d803266b3f9aaf4a26286598ee 2010.07.14 -0000000000000000000000000000000000000000 2010.07.14 -0000000000000000000000000000000000000000 2010.07.14 -ad0c03e542656d8831c4ed3acda7de11d1c3f1c6 2010.07.14 -de50210f6416533d848b341642ad0c8193e22213 2010.07.22 -09a81c91ccebf3d9539c171e43e6e45e1dfbe6b8 2010.07.24 -f8e09aa30813cd4a737893d5b6ede028ffa7fb75 2010.08.04 -3e9eb7881930db0dd1fb52ff16ab79c402621fe4 2010.10.03 diff --git a/LATEST_VERSION b/LATEST_VERSION index 8418210..4f8405c 100644 --- a/LATEST_VERSION +++ b/LATEST_VERSION @@ -1 +1 @@ -2010.10.24 +2010.11.19 diff --git a/youtube-dl b/youtube-dl index 466b506..24722d2 100755 --- a/youtube-dl +++ b/youtube-dl @@ -28,7 +28,7 @@ except ImportError: from cgi import parse_qs std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.11) Gecko/20101019 Firefox/3.6.11', + 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en-us,en;q=0.5', @@ -36,6 +36,21 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +month_name_to_number = { + 'January': '01', + 'February': '02', + 'March': '03', + 'April': '04', + 'May': '05', + 'June': '06', + 'July': '07', + 'August': '08', + 'September': '09', + 'October': '10', + 'November': '11', + 'December': '12', +} + def preferredencoding(): """Get preferred encoding. @@ -204,6 +219,7 @@ class FileDownloader(object): continuedl: Try to continue downloads if possible. noprogress: Do not print the progress bar. playliststart: Playlist item to start at. + playlistend: Playlist item to end at. logtostderr: Log messages to stderr instead of stdout. """ @@ -412,7 +428,7 @@ class FileDownloader(object): try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) - template_dict['ord'] = unicode('%05d' % self._num_downloads) + template_dict['autonumber'] = unicode('%05d' % self._num_downloads) filename = self.params['outtmpl'] % template_dict except (ValueError, KeyError), err: self.trouble(u'ERROR: invalid system charset or erroneous output template') @@ -830,7 +846,7 @@ class YoutubeIE(InfoExtractor): # 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) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers) try: video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -838,9 +854,9 @@ class YoutubeIE(InfoExtractor): return # Attempt to extract SWF player URL - mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) + mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) if mobj is not None: - player_url = mobj.group(1) + player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) else: player_url = None @@ -893,6 +909,23 @@ class YoutubeIE(InfoExtractor): else: # don't panic if we can't find it video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) + # upload date + upload_date = u'NA' + mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL) + if mobj is not None: + try: + if ',' in mobj.group(1): + # Month Day, Year + m, d, y = mobj.group(1).replace(',', '').split() + else: + # Day Month Year, we'll suppose + d, m, y = mobj.group(1).split() + m = month_name_to_number[m] + d = '%02d' % (long(d)) + upload_date = '%s%s%s' % (y, m, d) + except: + upload_date = u'NA' + # description video_description = 'No description available.' if self._downloader.params.get('forcedescription', False): @@ -947,6 +980,7 @@ class YoutubeIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_real_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': upload_date, 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1093,6 +1127,7 @@ class MetacafeIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1181,6 +1216,7 @@ class DailymotionIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1290,6 +1326,7 @@ class GoogleIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': u'NA', + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1371,6 +1408,7 @@ class PhotobucketIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1525,6 +1563,7 @@ class YahooIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url, 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1627,6 +1666,7 @@ class GenericIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1966,11 +2006,10 @@ class YoutubePlaylistIE(InfoExtractor): 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:] - + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + video_ids = video_ids[playliststart:playlistend] + for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return @@ -2026,10 +2065,9 @@ class YoutubeUserIE(InfoExtractor): 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:] + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + video_ids = video_ids[playliststart:playlistend] for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) @@ -2095,9 +2133,9 @@ if __name__ == '__main__': 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_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' latest_version = urllib.urlopen(latest_url).read().strip() - prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version + prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version newcontent = urllib.urlopen(prog_url).read() stream = open(filename, 'w') stream.write(newcontent) @@ -2107,7 +2145,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.10.24', + version='2010.11.19', conflict_handler='resolve', ) @@ -2125,6 +2163,8 @@ if __name__ == '__main__': 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) + parser.add_option('--playlist-end', + dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -2170,6 +2210,8 @@ if __name__ == '__main__': 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('-A', '--auto-number', + action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) filesystem.add_option('-o', '--output', dest='outtmpl', metavar='TEMPLATE', help='output filename template') filesystem.add_option('-a', '--batch-file', @@ -2211,7 +2253,7 @@ if __name__ == '__main__': 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] + batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] except IOError: sys.exit(u'ERROR: batch file could not be read') all_urls = batchurls + args @@ -2223,8 +2265,8 @@ if __name__ == '__main__': 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.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): + parser.error(u'using output template conflicts with using title, literal title or auto number') 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: @@ -2239,11 +2281,18 @@ if __name__ == '__main__': 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') + try: + opts.playliststart = long(opts.playliststart) + if opts.playliststart <= 0: + raise ValueError + except (TypeError, ValueError), err: + parser.error(u'invalid playlist start number specified') + try: + opts.playlistend = long(opts.playlistend) + if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): + raise ValueError + except (TypeError, ValueError), err: + parser.error(u'invalid playlist end number specified') # Information extractors youtube_ie = YoutubeIE() @@ -2276,8 +2325,11 @@ if __name__ == '__main__': 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 opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)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 (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') or u'%(id)s.%(ext)s'), 'ignoreerrors': opts.ignoreerrors, 'ratelimit': opts.ratelimit, @@ -2286,6 +2338,7 @@ if __name__ == '__main__': 'continuedl': opts.continue_dl, 'noprogress': opts.noprogress, 'playliststart': opts.playliststart, + 'playlistend': opts.playlistend, 'logtostderr': opts.outtmpl == '-', }) fd.add_info_extractor(youtube_search_ie)