From b6fab35b9f525cfb5a16e45d8412c6f24c7f621c Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Sun, 25 Nov 2012 20:39:42 +0100 Subject: alias %(title)s to %(stitle)s --- youtube_dl/FileDownloader.py | 1 + 1 file changed, 1 insertion(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 4449fe711..08bd83354 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -322,6 +322,7 @@ class FileDownloader(object): template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) template_dict['autonumber'] = unicode('%05d' % self._num_downloads) + template_dict['title'] = template_dict['stitle'] # Keep both for backwards compatibility filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError), err: -- cgit v1.2.3 From 51937c086943a3bdbf6f707c75d041ed3b0ba743 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 26 Nov 2012 04:05:54 +0100 Subject: Add some parentheses around print for #180 --- youtube_dl/FileDownloader.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 08bd83354..9feff9bb0 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -364,17 +364,17 @@ class FileDownloader(object): # Forced printings if self.params.get('forcetitle', False): - print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceurl', False): - print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcedescription', False) and 'description' in info_dict: - print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcefilename', False) and filename is not None: - print filename.encode(preferredencoding(), 'xmlcharrefreplace') + print(filename.encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceformat', False): - print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') + print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')) # Do nothing else if in simulate mode if self.params.get('simulate', False): -- cgit v1.2.3 From 7ec1a206eaedcb35c16ba54289d3c7f92baa59ce Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 26 Nov 2012 04:13:43 +0100 Subject: Remove longs (int does the right thing since Python 2.2, see PEP 237) --- youtube_dl/FileDownloader.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 9feff9bb0..ff6963262 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -139,23 +139,23 @@ class FileDownloader(object): new_min = max(bytes / 2.0, 1.0) new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB if elapsed_time < 0.001: - return long(new_max) + return int(new_max) rate = bytes / elapsed_time if rate > new_max: - return long(new_max) + return int(new_max) if rate < new_min: - return long(new_min) - return long(rate) + return int(new_min) + return int(rate) @staticmethod def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into a long integer.""" + """Parse a string indicating a byte quantity into an integer.""" matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) if matchobj is None: return None number = float(matchobj.group(1)) multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) - return long(round(number * multiplier)) + return int(round(number * multiplier)) def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" -- cgit v1.2.3 From 92b91c18780938283c505f5662c458e049bf3567 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 26 Nov 2012 04:23:20 +0100 Subject: Use character instead of byte strings --- youtube_dl/FileDownloader.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index ff6963262..37a842cdd 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -180,7 +180,8 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" - print >>sys.stderr, message.encode(preferredencoding()) + assert type(message) == type(u'') + sys.stderr.write((message + u'\n').encode(preferredencoding())) def to_cons_title(self, message): """Set console/terminal window title to message.""" -- cgit v1.2.3 From 1c469a9480e9d8bea45950898eb46e07b0c58290 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 26 Nov 2012 23:58:46 +0100 Subject: New optoin --restrict-filenames --- youtube_dl/FileDownloader.py | 65 ++++++++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 32 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 37a842cdd..4c79be432 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -44,37 +44,38 @@ class FileDownloader(object): Available options: - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. - quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - forcethumbnail: Force printing thumbnail URL. - forcedescription: Force printing description. - forcefilename: Force printing final filename. - simulate: Do not download the video files. - format: Video format code. - format_limit: Highest quality format to try. - outtmpl: Template for output names. - ignoreerrors: Do not stop on download errors. - ratelimit: Download speed limit, in bytes/sec. - nooverwrites: Prevent overwriting files. - retries: Number of times to retry for HTTP error 5xx - 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. - matchtitle: Download only matching titles. - rejecttitle: Reject downloads for matching titles. - logtostderr: Log messages to stderr instead of stdout. - consoletitle: Display progress in console window's titlebar. - nopart: Do not use temporary .part files. - updatetime: Use the Last-modified header to set output file timestamps. - writedescription: Write the video description to a .description file - writeinfojson: Write the video description to a .info.json file - writesubtitles: Write the video subtitles to a .srt file - subtitleslang: Language of the subtitles to download + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + restrictfilenames: Do not allow "&" and spaces in file names + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 5xx + 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. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + writesubtitles: Write the video subtitles to a .srt file + subtitleslang: Language of the subtitles to download """ params = None @@ -349,7 +350,7 @@ class FileDownloader(object): def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" - info_dict['stitle'] = sanitize_filename(info_dict['title']) + info_dict['stitle'] = sanitize_filename(info_dict['title'], self.params.get('restrictfilenames')) reason = self._match_entry(info_dict) if reason is not None: -- cgit v1.2.3 From aa2a94ed81857705e0fc0765cb884ed58fbdf5a5 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 13:01:32 +0100 Subject: Encode the entire filename --- youtube_dl/FileDownloader.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 4c79be432..dce1a23a4 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -322,9 +322,8 @@ class FileDownloader(object): """Generate the output filename.""" try: template_dict = dict(info_dict) - template_dict['epoch'] = unicode(long(time.time())) + template_dict['epoch'] = unicode(int(time.time())) template_dict['autonumber'] = unicode('%05d' % self._num_downloads) - template_dict['title'] = template_dict['stitle'] # Keep both for backwards compatibility filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError), err: @@ -350,7 +349,8 @@ class FileDownloader(object): def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" - info_dict['stitle'] = sanitize_filename(info_dict['title'], self.params.get('restrictfilenames')) + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] reason = self._match_entry(info_dict) if reason is not None: @@ -363,6 +363,7 @@ class FileDownloader(object): raise MaxDownloadsReached() filename = self.prepare_filename(info_dict) + filename = sanitize_filename(filename, self.params.get('restrictfilenames')) # Forced printings if self.params.get('forcetitle', False): -- cgit v1.2.3 From 97cd3afc7525394c46398f1526d412d081c02085 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 13:11:06 +0100 Subject: warn if %(stitle)s is being used --- youtube_dl/FileDownloader.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index dce1a23a4..b6aebe4ac 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -94,6 +94,9 @@ class FileDownloader(object): self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self.params = params + if '%(stitle)s' in self.params['outtmpl']: + self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + @staticmethod def format_bytes(bytes): if bytes is None: -- cgit v1.2.3 From cc872b68a895bae05bd266cc59d53f6e3c638f6c Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 16:42:50 +0100 Subject: Actually merge #379 --- youtube_dl/FileDownloader.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index b6aebe4ac..bd0f75773 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -62,6 +62,8 @@ class FileDownloader(object): ratelimit: Download speed limit, in bytes/sec. nooverwrites: Prevent overwriting files. retries: Number of times to retry for HTTP error 5xx + buffersize: Size of download buffer in bytes. + noresizebuffer: Do not automatically resize the download buffer. continuedl: Try to continue downloads if possible. noprogress: Do not print the progress bar. playliststart: Playlist item to start at. @@ -644,7 +646,7 @@ class FileDownloader(object): data_len = long(data_len) + resume_len data_len_str = self.format_bytes(data_len) byte_counter = 0 + resume_len - block_size = 1024 + block_size = self.params.get('buffersize', 1024) start = time.time() while True: # Download and write @@ -670,7 +672,8 @@ class FileDownloader(object): except (IOError, OSError), err: self.trouble(u'\nERROR: unable to write data: %s' % str(err)) return False - block_size = self.best_block_size(after - before, len(data_block)) + if not self.params.get('noresizebuffer', False): + block_size = self.best_block_size(after - before, len(data_block)) # Progress message speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) -- cgit v1.2.3 From 717b1f72ed6070212a72ac823547cb3c776a6264 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 27 Nov 2012 17:20:25 +0100 Subject: default info_dict['format'] to info_dict['ext'] and make the YT one more verbose --- youtube_dl/FileDownloader.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index b6aebe4ac..69d169904 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -355,6 +355,9 @@ class FileDownloader(object): # Keep for backwards compatibility info_dict['stitle'] = info_dict['title'] + if not 'format' in info_dict: + info_dict['format'] = info_dict['ext'] + reason = self._match_entry(info_dict) if reason is not None: self.to_screen(u'[download] ' + reason) -- cgit v1.2.3 From dcd60025f89d3e87c0766b1163f7577c5e673342 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 18:27:46 +0100 Subject: Fix filename sanitation (Closes #555) --- youtube_dl/FileDownloader.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index bd0f75773..d7d5b1521 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -327,8 +327,10 @@ class FileDownloader(object): """Generate the output filename.""" try: template_dict = dict(info_dict) - template_dict['epoch'] = unicode(int(time.time())) - template_dict['autonumber'] = unicode('%05d' % self._num_downloads) + template_dict['epoch'] = int(time.time()) + template_dict['autonumber'] = u'%05d' % self._num_downloads + + template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError), err: @@ -368,7 +370,6 @@ class FileDownloader(object): raise MaxDownloadsReached() filename = self.prepare_filename(info_dict) - filename = sanitize_filename(filename, self.params.get('restrictfilenames')) # Forced printings if self.params.get('forcetitle', False): -- cgit v1.2.3 From dd109dee8ebd51a019529fa494e56651162ad6d9 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 19:02:37 +0100 Subject: Remove mentions of unicode --- youtube_dl/FileDownloader.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index d7d5b1521..777a52545 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -330,7 +330,7 @@ class FileDownloader(object): template_dict['epoch'] = int(time.time()) template_dict['autonumber'] = u'%05d' % self._num_downloads - template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) + template_dict = dict((k, sanitize_filename(u(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError), err: @@ -397,7 +397,7 @@ class FileDownloader(object): if dn != '' and not os.path.exists(dn): # dn is already encoded os.makedirs(dn) except (OSError, IOError), err: - self.trouble(u'ERROR: unable to create directory ' + unicode(err)) + self.trouble(u'ERROR: unable to create directory ' + u(err)) return if self.params.get('writedescription', False): -- cgit v1.2.3 From 95649b3936e10a48c4a5009eecfb7647756bde39 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 19:05:03 +0100 Subject: Replace long with int (see PEP 237) --- youtube_dl/FileDownloader.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 777a52545..6d52dc923 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -108,7 +108,7 @@ class FileDownloader(object): if bytes == 0.0: exponent = 0 else: - exponent = long(math.log(bytes, 1024.0)) + exponent = int(math.log(bytes, 1024.0)) suffix = 'bkMGTPEZY'[exponent] converted = float(bytes) / float(1024 ** exponent) return '%.2f%s' % (converted, suffix) @@ -127,7 +127,7 @@ class FileDownloader(object): if current == 0 or dif < 0.001: # One millisecond return '--:--' rate = float(current) / dif - eta = long((float(total) - float(current)) / rate) + eta = int((float(total) - float(current)) / rate) (eta_mins, eta_secs) = divmod(eta, 60) if eta_mins > 99: return '--:--' @@ -617,7 +617,7 @@ 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 < int(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, @@ -644,7 +644,7 @@ class FileDownloader(object): data_len = data.info().get('Content-length', None) if data_len is not None: - data_len = long(data_len) + resume_len + data_len = int(data_len) + resume_len data_len_str = self.format_bytes(data_len) byte_counter = 0 + resume_len block_size = self.params.get('buffersize', 1024) @@ -694,7 +694,7 @@ class FileDownloader(object): stream.close() self.report_finish() if data_len is not None and byte_counter != data_len: - raise ContentTooShortError(byte_counter, long(data_len)) + raise ContentTooShortError(byte_counter, int(data_len)) self.try_rename(tmpfilename, filename) # Update file modification time -- cgit v1.2.3 From 03c5b0fbd4de40ebf21a7ba2e389fb5fba50666c Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 27 Nov 2012 19:30:09 +0100 Subject: IE._WORKING attribute in order to warn the users and skip the tests on broken IEs --- youtube_dl/FileDownloader.py | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 69d169904..1fdd2071f 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -481,6 +481,11 @@ class FileDownloader(object): if not ie.suitable(url): continue + # Warn if the _WORKING attribute is False + if not ie.working(): + self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' + u'and will probably not work. If you want to go on, use the -i option.') + # Suitable InfoExtractor found suitable_found = True -- cgit v1.2.3 From c806f804d85dc53f08b1a13d9cfdbe0a8eb58b15 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 21:07:25 +0100 Subject: Only encode when output stream is binary --- youtube_dl/FileDownloader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 6d52dc923..4e9b55f49 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -179,7 +179,7 @@ class FileDownloader(object): if not self.params.get('quiet', False): terminator = [u'\n', u''][skip_eol] output = message + terminator - if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr output = output.encode(preferredencoding(), 'ignore') self._screen_file.write(output) self._screen_file.flush() -- cgit v1.2.3 From f462df021a881c406afefc62bbf905ea582700ea Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 27 Nov 2012 23:15:33 +0100 Subject: Use None on missing required info_dict fields --- youtube_dl/FileDownloader.py | 1 + 1 file changed, 1 insertion(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 1fdd2071f..a7997c4f2 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -327,6 +327,7 @@ class FileDownloader(object): template_dict = dict(info_dict) template_dict['epoch'] = unicode(int(time.time())) template_dict['autonumber'] = unicode('%05d' % self._num_downloads) + template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError), err: -- cgit v1.2.3 From 96731798dbdd5a8878ac5cf29b69c6c7c821311b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 23:29:18 +0100 Subject: Rename util.u to util.compat_str --- youtube_dl/FileDownloader.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 870c82272..815b81296 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -332,7 +332,7 @@ class FileDownloader(object): template_dict['autonumber'] = u'%05d' % self._num_downloads template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) - template_dict = dict((k, sanitize_filename(u(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) + template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename @@ -403,7 +403,7 @@ class FileDownloader(object): if dn != '' and not os.path.exists(dn): # dn is already encoded os.makedirs(dn) except (OSError, IOError), err: - self.trouble(u'ERROR: unable to create directory ' + u(err)) + self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) return if self.params.get('writedescription', False): -- cgit v1.2.3 From e08bee320e7c2933590d108ff4f8546b4dff935f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 23:31:55 +0100 Subject: Use except .. as everywhere (#180) --- youtube_dl/FileDownloader.py | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 815b81296..411d01a41 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -247,7 +247,7 @@ class FileDownloader(object): if old_filename == new_filename: return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError), err: + except (IOError, OSError) as err: self.trouble(u'ERROR: unable to rename file') def try_utime(self, filename, last_modified_hdr): @@ -305,7 +305,7 @@ class FileDownloader(object): """Report file has already been fully downloaded.""" try: self.to_screen(u'[download] %s has already been downloaded' % file_name) - except (UnicodeEncodeError), err: + except (UnicodeEncodeError) as err: self.to_screen(u'[download] The file has already been downloaded') def report_unable_to_resume(self): @@ -336,7 +336,7 @@ class FileDownloader(object): filename = self.params['outtmpl'] % template_dict return filename - except (ValueError, KeyError), err: + except (ValueError, KeyError) as err: self.trouble(u'ERROR: invalid system charset or erroneous output template') return None @@ -402,7 +402,7 @@ class FileDownloader(object): dn = os.path.dirname(encodeFilename(filename)) if dn != '' and not os.path.exists(dn): # dn is already encoded os.makedirs(dn) - except (OSError, IOError), err: + except (OSError, IOError) as err: self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) return @@ -459,19 +459,19 @@ class FileDownloader(object): else: try: success = self._do_download(filename, info_dict) - except (OSError, IOError), err: + except (OSError, IOError) as err: raise UnavailableVideoError - except (urllib2.URLError, httplib.HTTPException, socket.error), err: + except (urllib2.URLError, httplib.HTTPException, socket.error) as err: self.trouble(u'ERROR: unable to download video data: %s' % str(err)) return - except (ContentTooShortError, ), err: + except (ContentTooShortError, ) as err: self.trouble(u'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: + except (PostProcessingError) as err: self.trouble(u'ERROR: postprocessing: %s' % str(err)) return @@ -612,7 +612,7 @@ class FileDownloader(object): data = info_dict['urlhandle'] data = urllib2.urlopen(request) break - except (urllib2.HTTPError, ), err: + except (urllib2.HTTPError, ) as err: if (err.code < 500 or err.code >= 600) and err.code != 416: # Unexpected HTTP error raise @@ -622,7 +622,7 @@ class FileDownloader(object): # Open the connection again without the range header data = urllib2.urlopen(basic_request) content_length = data.info()['Content-Length'] - except (urllib2.HTTPError, ), err: + except (urllib2.HTTPError, ) as err: if err.code < 500 or err.code >= 600: raise else: @@ -676,12 +676,12 @@ class FileDownloader(object): assert stream is not None filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) - except (OSError, IOError), err: + except (OSError, IOError) as err: self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) return False try: stream.write(data_block) - except (IOError, OSError), err: + except (IOError, OSError) as err: self.trouble(u'\nERROR: unable to write data: %s' % str(err)) return False if not self.params.get('noresizebuffer', False): -- cgit v1.2.3 From 01ba00ca42899436c13439226ec61651a6ea6af0 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 23:54:09 +0100 Subject: Prepare urllib references for 2/3 compatibility --- youtube_dl/FileDownloader.py | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 411d01a41..89beaf453 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -9,7 +9,6 @@ import socket import subprocess import sys import time -import urllib2 if os.name == 'nt': import ctypes @@ -461,7 +460,7 @@ class FileDownloader(object): success = self._do_download(filename, info_dict) except (OSError, IOError) as err: raise UnavailableVideoError - except (urllib2.URLError, httplib.HTTPException, socket.error) as err: + except (compat_urllib_error.URLError, httplib.HTTPException, socket.error) as err: self.trouble(u'ERROR: unable to download video data: %s' % str(err)) return except (ContentTooShortError, ) as err: @@ -585,8 +584,8 @@ class FileDownloader(object): # Do not include the Accept-Encoding header headers = {'Youtubedl-no-compression': 'True'} - basic_request = urllib2.Request(url, None, headers) - request = urllib2.Request(url, None, headers) + basic_request = compat_urllib_request.Request(url, None, headers) + request = compat_urllib_request.Request(url, None, headers) # Establish possible resume length if os.path.isfile(encodeFilename(tmpfilename)): @@ -610,9 +609,9 @@ class FileDownloader(object): try: if count == 0 and 'urlhandle' in info_dict: data = info_dict['urlhandle'] - data = urllib2.urlopen(request) + data = compat_urllib_request.urlopen(request) break - except (urllib2.HTTPError, ) as err: + except (compat_urllib_error.HTTPError, ) as err: if (err.code < 500 or err.code >= 600) and err.code != 416: # Unexpected HTTP error raise @@ -620,9 +619,9 @@ class FileDownloader(object): # Unable to resume (requested range not satisfiable) try: # Open the connection again without the range header - data = urllib2.urlopen(basic_request) + data = compat_urllib_request.urlopen(basic_request) content_length = data.info()['Content-Length'] - except (urllib2.HTTPError, ) as err: + except (compat_urllib_error.HTTPError, ) as err: if err.code < 500 or err.code >= 600: raise else: -- cgit v1.2.3 From 89fb51dd2d4d7464b919f17b9d5d24a448319dfc Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 23:56:10 +0100 Subject: Remove ur references for Python 3.3 support --- youtube_dl/FileDownloader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 89beaf453..868023db9 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -201,7 +201,7 @@ class FileDownloader(object): def fixed_template(self): """Checks if the output template is fixed.""" - return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) + return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) def trouble(self, message=None): """Determine action to take when a download problem appears. -- cgit v1.2.3 From 348d0a7a18fd4aa2512418b8be48f5011fbd3f99 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 00:13:00 +0100 Subject: Py2/3 compatibility for http.client --- youtube_dl/FileDownloader.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 868023db9..f1931b04d 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,7 +1,6 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -import httplib import math import os import re @@ -460,7 +459,7 @@ class FileDownloader(object): success = self._do_download(filename, info_dict) except (OSError, IOError) as err: raise UnavailableVideoError - except (compat_urllib_error.URLError, httplib.HTTPException, socket.error) as err: + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self.trouble(u'ERROR: unable to download video data: %s' % str(err)) return except (ContentTooShortError, ) as err: -- cgit v1.2.3 From 64a57846d3fe3aa919ee3539956763c8ef3211b6 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 00:33:38 +0100 Subject: correct to_stderr --- youtube_dl/FileDownloader.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index f1931b04d..2b76a3b09 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -185,7 +185,10 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" assert type(message) == type(u'') - sys.stderr.write((message + u'\n').encode(preferredencoding())) + output = message + u'\n' + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding()) + sys.stderr.write(output) def to_cons_title(self, message): """Set console/terminal window title to message.""" -- cgit v1.2.3 From 8cd10ac4efb5168f3ceb18ec94338bce73e166a7 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 00:46:21 +0100 Subject: Fix printing title etc. --- youtube_dl/FileDownloader.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 2b76a3b09..6ddbfc469 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -380,17 +380,17 @@ class FileDownloader(object): # Forced printings if self.params.get('forcetitle', False): - print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceurl', False): - print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - print(info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcedescription', False) and 'description' in info_dict: - print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forcefilename', False) and filename is not None: - print(filename.encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(filename.encode(preferredencoding(), 'xmlcharrefreplace')) if self.params.get('forceformat', False): - print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')) # Do nothing else if in simulate mode if self.params.get('simulate', False): -- cgit v1.2.3 From e6137fd61d47ba8624e9baa84701adf929e38849 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 00:53:09 +0100 Subject: Remove superfluous encodings --- youtube_dl/FileDownloader.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 6ddbfc469..9e9f2a0e4 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -380,17 +380,17 @@ class FileDownloader(object): # Forced printings if self.params.get('forcetitle', False): - compat_print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['title']) if self.params.get('forceurl', False): - compat_print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['url']) if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - compat_print(info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['thumbnail']) if self.params.get('forcedescription', False) and 'description' in info_dict: - compat_print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['description']) if self.params.get('forcefilename', False) and filename is not None: - compat_print(filename.encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(filename) if self.params.get('forceformat', False): - compat_print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')) + compat_print(info_dict['format']) # Do nothing else if in simulate mode if self.params.get('simulate', False): -- cgit v1.2.3 From 59ae15a507cbf93de13f8fda8444d2d9a251747a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 02:04:46 +0100 Subject: Convert all tabs to 4 spaces (PEP8) --- youtube_dl/FileDownloader.py | 1398 +++++++++++++++++++++--------------------- 1 file changed, 699 insertions(+), 699 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 9e9f2a0e4..9dc3523e0 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -10,707 +10,707 @@ import sys import time if os.name == 'nt': - import ctypes + import ctypes from utils import * class FileDownloader(object): - """File Downloader class. - - File downloader objects are the ones responsible of downloading the - actual video file and writing it to disk if the user has requested - it, among some other tasks. In most cases there should be one per - program. As, given a video URL, the downloader doesn't know how to - extract all the needed information, task that InfoExtractors do, it - has to pass the URL to one of them. - - For this, file downloader objects have a method that allows - InfoExtractors to be registered in a given order. When it is passed - a URL, the file downloader handles it to the first InfoExtractor it - finds that reports being able to handle it. The InfoExtractor extracts - all the information about the video or videos the URL refers to, and - asks the FileDownloader to process the video information, possibly - downloading the video. - - File downloaders accept a lot of parameters. In order not to saturate - the object constructor with arguments, it receives a dictionary of - options instead. These options are available through the params - attribute for the InfoExtractors to use. The FileDownloader also - registers itself as the downloader in charge for the InfoExtractors - that are added to it, so this is a "mutual registration". - - Available options: - - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. - quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - forcethumbnail: Force printing thumbnail URL. - forcedescription: Force printing description. - forcefilename: Force printing final filename. - simulate: Do not download the video files. - format: Video format code. - format_limit: Highest quality format to try. - outtmpl: Template for output names. - restrictfilenames: Do not allow "&" and spaces in file names - ignoreerrors: Do not stop on download errors. - ratelimit: Download speed limit, in bytes/sec. - nooverwrites: Prevent overwriting files. - retries: Number of times to retry for HTTP error 5xx - buffersize: Size of download buffer in bytes. - noresizebuffer: Do not automatically resize the download buffer. - 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. - matchtitle: Download only matching titles. - rejecttitle: Reject downloads for matching titles. - logtostderr: Log messages to stderr instead of stdout. - consoletitle: Display progress in console window's titlebar. - nopart: Do not use temporary .part files. - updatetime: Use the Last-modified header to set output file timestamps. - writedescription: Write the video description to a .description file - writeinfojson: Write the video description to a .info.json file - writesubtitles: Write the video subtitles to a .srt file - subtitleslang: Language of the subtitles to download - """ - - params = None - _ies = [] - _pps = [] - _download_retcode = None - _num_downloads = None - _screen_file = None - - def __init__(self, params): - """Create a FileDownloader object with the given options.""" - self._ies = [] - self._pps = [] - self._download_retcode = 0 - self._num_downloads = 0 - self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] - self.params = params - - if '%(stitle)s' in self.params['outtmpl']: - self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') - - @staticmethod - def format_bytes(bytes): - if bytes is None: - return 'N/A' - if type(bytes) is str: - bytes = float(bytes) - if bytes == 0.0: - exponent = 0 - else: - exponent = int(math.log(bytes, 1024.0)) - suffix = 'bkMGTPEZY'[exponent] - converted = float(bytes) / float(1024 ** exponent) - return '%.2f%s' % (converted, suffix) - - @staticmethod - def calc_percent(byte_counter, data_len): - if data_len is None: - return '---.-%' - return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) - - @staticmethod - def calc_eta(start, now, total, current): - if total is None: - return '--:--' - dif = now - start - if current == 0 or dif < 0.001: # One millisecond - return '--:--' - rate = float(current) / dif - eta = int((float(total) - float(current)) / rate) - (eta_mins, eta_secs) = divmod(eta, 60) - if eta_mins > 99: - return '--:--' - return '%02d:%02d' % (eta_mins, eta_secs) - - @staticmethod - def calc_speed(start, now, bytes): - dif = now - start - if bytes == 0 or dif < 0.001: # One millisecond - return '%10s' % '---b/s' - return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) - - @staticmethod - def best_block_size(elapsed_time, bytes): - new_min = max(bytes / 2.0, 1.0) - new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB - if elapsed_time < 0.001: - return int(new_max) - rate = bytes / elapsed_time - if rate > new_max: - return int(new_max) - if rate < new_min: - return int(new_min) - return int(rate) - - @staticmethod - def parse_bytes(bytestr): - """Parse a string indicating a byte quantity into an integer.""" - matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) - if matchobj is None: - return None - number = float(matchobj.group(1)) - multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) - return int(round(number * multiplier)) - - def add_info_extractor(self, ie): - """Add an InfoExtractor object to the end of the list.""" - self._ies.append(ie) - ie.set_downloader(self) - - def add_post_processor(self, pp): - """Add a PostProcessor object to the end of the chain.""" - self._pps.append(pp) - pp.set_downloader(self) - - def to_screen(self, message, skip_eol=False): - """Print message to stdout if not in quiet mode.""" - assert type(message) == type(u'') - if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] - output = message + terminator - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding(), 'ignore') - self._screen_file.write(output) - self._screen_file.flush() - - def to_stderr(self, message): - """Print message to stderr.""" - assert type(message) == type(u'') - output = message + u'\n' - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding()) - sys.stderr.write(output) - - def to_cons_title(self, message): - """Set console/terminal window title to message.""" - if not self.params.get('consoletitle', False): - return - if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): - # c_wchar_p() might not be necessary if `message` is - # already of type unicode() - ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) - elif 'TERM' in os.environ: - sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) - - def fixed_template(self): - """Checks if the output template is fixed.""" - return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) - - def trouble(self, message=None): - """Determine action to take when a download problem appears. - - Depending on if the downloader has been configured to ignore - download errors or not, this method may throw an exception or - not when errors are found, after printing the message. - """ - if message is not None: - self.to_stderr(message) - if not self.params.get('ignoreerrors', False): - raise DownloadError(message) - self._download_retcode = 1 - - def slow_down(self, start_time, byte_counter): - """Sleep if the download speed is over the rate limit.""" - rate_limit = self.params.get('ratelimit', None) - if rate_limit is None or byte_counter == 0: - return - now = time.time() - elapsed = now - start_time - if elapsed <= 0.0: - return - speed = float(byte_counter) / elapsed - if speed > rate_limit: - time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) - - def temp_name(self, filename): - """Returns a temporary filename for the given filename.""" - if self.params.get('nopart', False) or filename == u'-' or \ - (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): - return filename - return filename + u'.part' - - def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] - return filename - - def try_rename(self, old_filename, new_filename): - try: - if old_filename == new_filename: - return - os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError) as 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: - return - if not os.path.isfile(encodeFilename(filename)): - return - timestr = last_modified_hdr - if timestr is None: - return - filetime = timeconvert(timestr) - if filetime is None: - return filetime - try: - os.utime(filename, (time.time(), filetime)) - except: - pass - return filetime - - def report_writedescription(self, descfn): - """ Report that the description file is being written """ - self.to_screen(u'[info] Writing video description to: ' + descfn) - - def report_writesubtitles(self, srtfn): - """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) - - def report_writeinfojson(self, infofn): - """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) - - def report_destination(self, filename): - """Report destination filename.""" - self.to_screen(u'[download] Destination: ' + filename) - - def report_progress(self, percent_str, data_len_str, speed_str, eta_str): - """Report download progress.""" - if self.params.get('noprogress', False): - return - self.to_screen(u'\r[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) - self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % - (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) - - def report_resuming_byte(self, resume_len): - """Report attempt to resume at given byte.""" - self.to_screen(u'[download] Resuming download at byte %s' % resume_len) - - def report_retry(self, count, retries): - """Report retry in case of HTTP error 5xx""" - self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) - - def report_file_already_downloaded(self, file_name): - """Report file has already been fully downloaded.""" - try: - self.to_screen(u'[download] %s has already been downloaded' % file_name) - except (UnicodeEncodeError) as err: - self.to_screen(u'[download] The file has already been downloaded') - - def report_unable_to_resume(self): - """Report it was impossible to resume download.""" - self.to_screen(u'[download] Unable to resume') - - def report_finish(self): - """Report download finished.""" - if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') - else: - self.to_screen(u'') - - def increment_downloads(self): - """Increment the ordinal that assigns a number to each file.""" - self._num_downloads += 1 - - def prepare_filename(self, info_dict): - """Generate the output filename.""" - try: - template_dict = dict(info_dict) - - template_dict['epoch'] = int(time.time()) - template_dict['autonumber'] = u'%05d' % self._num_downloads - - template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) - template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) - - filename = self.params['outtmpl'] % template_dict - return filename - except (ValueError, KeyError) as err: - self.trouble(u'ERROR: invalid system charset or erroneous output template') - return None - - def _match_entry(self, info_dict): - """ Returns None iff the file should be downloaded """ - - title = info_dict['title'] - matchtitle = self.params.get('matchtitle', False) - if matchtitle: - matchtitle = matchtitle.decode('utf8') - if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' - rejecttitle = self.params.get('rejecttitle', False) - if rejecttitle: - rejecttitle = rejecttitle.decode('utf8') - if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' - return None - - def process_info(self, info_dict): - """Process a single dictionary returned by an InfoExtractor.""" - - # Keep for backwards compatibility - info_dict['stitle'] = info_dict['title'] - - if not 'format' in info_dict: - info_dict['format'] = info_dict['ext'] - - reason = self._match_entry(info_dict) - if reason is not None: - self.to_screen(u'[download] ' + reason) - return - - max_downloads = self.params.get('max_downloads') - if max_downloads is not None: - if self._num_downloads > int(max_downloads): - raise MaxDownloadsReached() - - filename = self.prepare_filename(info_dict) - - # Forced printings - if self.params.get('forcetitle', False): - compat_print(info_dict['title']) - if self.params.get('forceurl', False): - compat_print(info_dict['url']) - if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - compat_print(info_dict['thumbnail']) - if self.params.get('forcedescription', False) and 'description' in info_dict: - compat_print(info_dict['description']) - if self.params.get('forcefilename', False) and filename is not None: - compat_print(filename) - if self.params.get('forceformat', False): - compat_print(info_dict['format']) - - # Do nothing else if in simulate mode - if self.params.get('simulate', False): - return - - if filename is None: - return - - try: - dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): # dn is already encoded - os.makedirs(dn) - except (OSError, IOError) as err: - self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) - return - - if self.params.get('writedescription', False): - try: - descfn = filename + u'.description' - self.report_writedescription(descfn) - descfile = open(encodeFilename(descfn), 'wb') - try: - descfile.write(info_dict['description'].encode('utf-8')) - finally: - descfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file ' + descfn) - return - - if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: - # subtitles download errors are already managed as troubles in relevant IE - # that way it will silently go on when used with unsupporting IE - try: - srtfn = filename.rsplit('.', 1)[0] + u'.srt' - self.report_writesubtitles(srtfn) - srtfile = open(encodeFilename(srtfn), 'wb') - try: - srtfile.write(info_dict['subtitles'].encode('utf-8')) - finally: - srtfile.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) - return - - if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' - self.report_writeinfojson(infofn) - try: - json.dump - except (NameError,AttributeError): - self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') - return - try: - infof = open(encodeFilename(infofn), 'wb') - try: - json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) - json.dump(json_info_dict, infof) - finally: - infof.close() - except (OSError, IOError): - self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) - return - - if not self.params.get('skip_download', False): - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): - success = True - else: - try: - success = self._do_download(filename, info_dict) - except (OSError, IOError) as err: - raise UnavailableVideoError - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) - return - except (ContentTooShortError, ) as err: - self.trouble(u'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) as err: - self.trouble(u'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 - - # Warn if the _WORKING attribute is False - if not ie.working(): - self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' - u'and will probably not work. If you want to go on, use the -i option.') - - # Suitable InfoExtractor found - suitable_found = True - - # Extract information from URL and process it - videos = ie.extract(url) - for video in videos or []: - video['extractor'] = ie.IE_NAME - try: - self.increment_downloads() - self.process_info(video) - except UnavailableVideoError: - self.trouble(u'\nERROR: unable to download video') - - # Suitable InfoExtractor had been found; go to next URL - break - - if not suitable_found: - self.trouble(u'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) - tmpfilename = self.temp_name(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', tmpfilename] - args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] - if self.params.get('verbose', False): - try: - import pipes - shell_quote = lambda args: ' '.join(map(pipes.quote, args)) - except ImportError: - shell_quote = repr - self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) - retval = subprocess.call(args) - while retval == 2 or retval == 1: - prevsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(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(encodeFilename(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(encodeFilename(tmpfilename))) - self.try_rename(tmpfilename, filename) - return True - else: - self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) - return False - - def _do_download(self, filename, info_dict): - url = info_dict['url'] - player_url = info_dict.get('player_url', None) - - # Check file already present - if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): - self.report_file_already_downloaded(filename) - return True - - # Attempt to download using rtmpdump - if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url, player_url) - - tmpfilename = self.temp_name(filename) - stream = None - - # Do not include the Accept-Encoding header - headers = {'Youtubedl-no-compression': 'True'} - basic_request = compat_urllib_request.Request(url, None, headers) - request = compat_urllib_request.Request(url, None, headers) - - # Establish possible resume length - if os.path.isfile(encodeFilename(tmpfilename)): - resume_len = os.path.getsize(encodeFilename(tmpfilename)) - else: - resume_len = 0 - - open_mode = 'wb' - if resume_len != 0: - if self.params.get('continuedl', False): - self.report_resuming_byte(resume_len) - request.add_header('Range','bytes=%d-' % resume_len) - open_mode = 'ab' - else: - resume_len = 0 - - count = 0 - retries = self.params.get('retries', 0) - while count <= retries: - # Establish connection - try: - if count == 0 and 'urlhandle' in info_dict: - data = info_dict['urlhandle'] - data = compat_urllib_request.urlopen(request) - break - except (compat_urllib_error.HTTPError, ) as err: - if (err.code < 500 or err.code >= 600) and err.code != 416: - # Unexpected HTTP error - raise - elif err.code == 416: - # Unable to resume (requested range not satisfiable) - try: - # Open the connection again without the range header - data = compat_urllib_request.urlopen(basic_request) - content_length = data.info()['Content-Length'] - except (compat_urllib_error.HTTPError, ) as err: - if err.code < 500 or err.code >= 600: - raise - else: - # Examine the reported length - if (content_length is not None and - (resume_len - 100 < int(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, - # changing the file size slightly and causing problems for some users. So - # I decided to implement a suggested change and consider the file - # completely downloaded if the file size differs less than 100 bytes from - # the one in the hard drive. - self.report_file_already_downloaded(filename) - self.try_rename(tmpfilename, filename) - return True - else: - # The length does not match, we start the download over - self.report_unable_to_resume() - open_mode = 'wb' - break - # Retry - count += 1 - if count <= retries: - self.report_retry(count, retries) - - if count > retries: - self.trouble(u'ERROR: giving up after %s retries' % retries) - return False - - data_len = data.info().get('Content-length', None) - if data_len is not None: - data_len = int(data_len) + resume_len - data_len_str = self.format_bytes(data_len) - byte_counter = 0 + resume_len - block_size = self.params.get('buffersize', 1024) - start = time.time() - while True: - # Download and write - before = time.time() - data_block = data.read(block_size) - after = time.time() - if len(data_block) == 0: - break - byte_counter += len(data_block) - - # Open file just in time - 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) as err: - self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) - return False - try: - stream.write(data_block) - except (IOError, OSError) as err: - self.trouble(u'\nERROR: unable to write data: %s' % str(err)) - return False - if not self.params.get('noresizebuffer', False): - block_size = self.best_block_size(after - before, len(data_block)) - - # Progress message - speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) - if data_len is None: - self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') - else: - percent_str = self.calc_percent(byte_counter, data_len) - eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) - self.report_progress(percent_str, data_len_str, speed_str, eta_str) - - # 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: - raise ContentTooShortError(byte_counter, int(data_len)) - self.try_rename(tmpfilename, filename) - - # Update file modification time - if self.params.get('updatetime', True): - info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) - - return True + """File Downloader class. + + File downloader objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, file downloader objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the file downloader handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + asks the FileDownloader to process the video information, possibly + downloading the video. + + File downloaders accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + restrictfilenames: Do not allow "&" and spaces in file names + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 5xx + buffersize: Size of download buffer in bytes. + noresizebuffer: Do not automatically resize the download buffer. + 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. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + consoletitle: Display progress in console window's titlebar. + nopart: Do not use temporary .part files. + updatetime: Use the Last-modified header to set output file timestamps. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + writesubtitles: Write the video subtitles to a .srt file + subtitleslang: Language of the subtitles to download + """ + + params = None + _ies = [] + _pps = [] + _download_retcode = None + _num_downloads = None + _screen_file = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._download_retcode = 0 + self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self.params = params + + if '%(stitle)s' in self.params['outtmpl']: + self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + + @staticmethod + def format_bytes(bytes): + if bytes is None: + return 'N/A' + if type(bytes) is str: + bytes = float(bytes) + if bytes == 0.0: + exponent = 0 + else: + exponent = int(math.log(bytes, 1024.0)) + suffix = 'bkMGTPEZY'[exponent] + converted = float(bytes) / float(1024 ** exponent) + return '%.2f%s' % (converted, suffix) + + @staticmethod + def calc_percent(byte_counter, data_len): + if data_len is None: + return '---.-%' + return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) + + @staticmethod + def calc_eta(start, now, total, current): + if total is None: + return '--:--' + dif = now - start + if current == 0 or dif < 0.001: # One millisecond + return '--:--' + rate = float(current) / dif + eta = int((float(total) - float(current)) / rate) + (eta_mins, eta_secs) = divmod(eta, 60) + if eta_mins > 99: + return '--:--' + return '%02d:%02d' % (eta_mins, eta_secs) + + @staticmethod + def calc_speed(start, now, bytes): + dif = now - start + if bytes == 0 or dif < 0.001: # One millisecond + return '%10s' % '---b/s' + return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) + + @staticmethod + def best_block_size(elapsed_time, bytes): + new_min = max(bytes / 2.0, 1.0) + new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB + if elapsed_time < 0.001: + return int(new_max) + rate = bytes / elapsed_time + if rate > new_max: + return int(new_max) + if rate < new_min: + return int(new_min) + return int(rate) + + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into an integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return int(round(number * multiplier)) + + def add_info_extractor(self, ie): + """Add an InfoExtractor object to the end of the list.""" + self._ies.append(ie) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + def to_screen(self, message, skip_eol=False): + """Print message to stdout if not in quiet mode.""" + assert type(message) == type(u'') + if not self.params.get('quiet', False): + terminator = [u'\n', u''][skip_eol] + output = message + terminator + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding(), 'ignore') + self._screen_file.write(output) + self._screen_file.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + assert type(message) == type(u'') + output = message + u'\n' + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding()) + sys.stderr.write(output) + + def to_cons_title(self, message): + """Set console/terminal window title to message.""" + if not self.params.get('consoletitle', False): + return + if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + # c_wchar_p() might not be necessary if `message` is + # already of type unicode() + ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) + elif 'TERM' in os.environ: + sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + """ + if message is not None: + self.to_stderr(message) + if not self.params.get('ignoreerrors', False): + raise DownloadError(message) + self._download_retcode = 1 + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def temp_name(self, filename): + """Returns a temporary filename for the given filename.""" + if self.params.get('nopart', False) or filename == u'-' or \ + (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): + return filename + return filename + u'.part' + + def undo_temp_name(self, filename): + if filename.endswith(u'.part'): + return filename[:-len(u'.part')] + return filename + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) + except (IOError, OSError) as 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: + return + if not os.path.isfile(encodeFilename(filename)): + return + timestr = last_modified_hdr + if timestr is None: + return + filetime = timeconvert(timestr) + if filetime is None: + return filetime + try: + os.utime(filename, (time.time(), filetime)) + except: + pass + return filetime + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: ' + descfn) + + def report_writesubtitles(self, srtfn): + """ Report that the subtitles file is being written """ + self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_screen(u'[download] Destination: ' + filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """Report download progress.""" + if self.params.get('noprogress', False): + return + self.to_screen(u'\r[download] %s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) + + def report_resuming_byte(self, resume_len): + """Report attempt to resume at given byte.""" + self.to_screen(u'[download] Resuming download at byte %s' % resume_len) + + def report_retry(self, count, retries): + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError) as err: + self.to_screen(u'[download] The file has already been downloaded') + + def report_unable_to_resume(self): + """Report it was impossible to resume download.""" + self.to_screen(u'[download] Unable to resume') + + def report_finish(self): + """Report download finished.""" + if self.params.get('noprogress', False): + self.to_screen(u'[download] Download completed') + else: + self.to_screen(u'') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 + + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + + template_dict['epoch'] = int(time.time()) + template_dict['autonumber'] = u'%05d' % self._num_downloads + + template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) + template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) + + filename = self.params['outtmpl'] % template_dict + return filename + except (ValueError, KeyError) as err: + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle: + matchtitle = matchtitle.decode('utf8') + if not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle: + rejecttitle = rejecttitle.decode('utf8') + if re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return None + + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] + + if not 'format' in info_dict: + info_dict['format'] = info_dict['ext'] + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) + return + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # Forced printings + if self.params.get('forcetitle', False): + compat_print(info_dict['title']) + if self.params.get('forceurl', False): + compat_print(info_dict['url']) + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + compat_print(info_dict['thumbnail']) + if self.params.get('forcedescription', False) and 'description' in info_dict: + compat_print(info_dict['description']) + if self.params.get('forcefilename', False) and filename is not None: + compat_print(filename) + if self.params.get('forceformat', False): + compat_print(info_dict['format']) + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + if filename is None: + return + + try: + dn = os.path.dirname(encodeFilename(filename)) + if dn != '' and not os.path.exists(dn): # dn is already encoded + os.makedirs(dn) + except (OSError, IOError) as err: + self.trouble(u'ERROR: unable to create directory ' + compat_str(err)) + return + + if self.params.get('writedescription', False): + try: + descfn = filename + u'.description' + self.report_writedescription(descfn) + descfile = open(encodeFilename(descfn), 'wb') + try: + descfile.write(info_dict['description'].encode('utf-8')) + finally: + descfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write description file ' + descfn) + return + + if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + # subtitles download errors are already managed as troubles in relevant IE + # that way it will silently go on when used with unsupporting IE + try: + srtfn = filename.rsplit('.', 1)[0] + u'.srt' + self.report_writesubtitles(srtfn) + srtfile = open(encodeFilename(srtfn), 'wb') + try: + srtfile.write(info_dict['subtitles'].encode('utf-8')) + finally: + srtfile.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + u'.info.json' + self.report_writeinfojson(infofn) + try: + json.dump + except (NameError,AttributeError): + self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') + return + try: + infof = open(encodeFilename(infofn), 'wb') + try: + json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) + json.dump(json_info_dict, infof) + finally: + infof.close() + except (OSError, IOError): + self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + return + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): + success = True + else: + try: + success = self._do_download(filename, info_dict) + except (OSError, IOError) as err: + raise UnavailableVideoError + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ) as err: + self.trouble(u'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) as err: + self.trouble(u'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 + + # Warn if the _WORKING attribute is False + if not ie.working(): + self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' + u'and will probably not work. If you want to go on, use the -i option.') + + # Suitable InfoExtractor found + suitable_found = True + + # Extract information from URL and process it + videos = ie.extract(url) + for video in videos or []: + video['extractor'] = ie.IE_NAME + try: + self.increment_downloads() + self.process_info(video) + except UnavailableVideoError: + self.trouble(u'\nERROR: unable to download video') + + # Suitable InfoExtractor had been found; go to next URL + break + + if not suitable_found: + self.trouble(u'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) + tmpfilename = self.temp_name(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', tmpfilename] + args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] + if self.params.get('verbose', False): + try: + import pipes + shell_quote = lambda args: ' '.join(map(pipes.quote, args)) + except ImportError: + shell_quote = repr + self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) + retval = subprocess.call(args) + while retval == 2 or retval == 1: + prevsize = os.path.getsize(encodeFilename(tmpfilename)) + self.to_screen(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(encodeFilename(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(encodeFilename(tmpfilename))) + self.try_rename(tmpfilename, filename) + return True + else: + self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + return False + + def _do_download(self, filename, info_dict): + url = info_dict['url'] + player_url = info_dict.get('player_url', None) + + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): + self.report_file_already_downloaded(filename) + return True + + # Attempt to download using rtmpdump + if url.startswith('rtmp'): + return self._download_with_rtmpdump(filename, url, player_url) + + tmpfilename = self.temp_name(filename) + stream = None + + # Do not include the Accept-Encoding header + headers = {'Youtubedl-no-compression': 'True'} + basic_request = compat_urllib_request.Request(url, None, headers) + request = compat_urllib_request.Request(url, None, headers) + + # Establish possible resume length + if os.path.isfile(encodeFilename(tmpfilename)): + resume_len = os.path.getsize(encodeFilename(tmpfilename)) + else: + resume_len = 0 + + open_mode = 'wb' + if resume_len != 0: + if self.params.get('continuedl', False): + self.report_resuming_byte(resume_len) + request.add_header('Range','bytes=%d-' % resume_len) + open_mode = 'ab' + else: + resume_len = 0 + + count = 0 + retries = self.params.get('retries', 0) + while count <= retries: + # Establish connection + try: + if count == 0 and 'urlhandle' in info_dict: + data = info_dict['urlhandle'] + data = compat_urllib_request.urlopen(request) + break + except (compat_urllib_error.HTTPError, ) as err: + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error + raise + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = compat_urllib_request.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (compat_urllib_error.HTTPError, ) as err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < int(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, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + self.try_rename(tmpfilename, filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False + + data_len = data.info().get('Content-length', None) + if data_len is not None: + data_len = int(data_len) + resume_len + data_len_str = self.format_bytes(data_len) + byte_counter = 0 + resume_len + block_size = self.params.get('buffersize', 1024) + start = time.time() + while True: + # Download and write + before = time.time() + data_block = data.read(block_size) + after = time.time() + if len(data_block) == 0: + break + byte_counter += len(data_block) + + # Open file just in time + 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) as err: + self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) + return False + try: + stream.write(data_block) + except (IOError, OSError) as err: + self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + return False + if not self.params.get('noresizebuffer', False): + block_size = self.best_block_size(after - before, len(data_block)) + + # Progress message + speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) + if data_len is None: + self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') + else: + percent_str = self.calc_percent(byte_counter, data_len) + eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + + # 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: + raise ContentTooShortError(byte_counter, int(data_len)) + self.try_rename(tmpfilename, filename) + + # Update file modification time + if self.params.get('updatetime', True): + info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) + + return True -- cgit v1.2.3 From 9e8056d5a7b6b366874088cd30d23ba4a52d3861 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 03:34:40 +0100 Subject: Use relative imports --- youtube_dl/FileDownloader.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 9dc3523e0..a135be352 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import absolute_import + import math import os import re @@ -12,7 +14,7 @@ import time if os.name == 'nt': import ctypes -from utils import * +from .utils import * class FileDownloader(object): -- cgit v1.2.3 From 6ad98fb3fda767fb8da0d3c40da408ec2a09b5d4 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 18:21:06 +0100 Subject: Correct exception raising --- youtube_dl/FileDownloader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index a135be352..48c8eb126 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -463,7 +463,7 @@ class FileDownloader(object): try: success = self._do_download(filename, info_dict) except (OSError, IOError) as err: - raise UnavailableVideoError + raise UnavailableVideoError() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self.trouble(u'ERROR: unable to download video data: %s' % str(err)) return -- cgit v1.2.3 From 796173d08b514182eedc704541eb55d5c9e1dc0d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 3 Dec 2012 15:36:24 +0100 Subject: Keep video IDs verbatim if possible (Closes #571) --- youtube_dl/FileDownloader.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 48c8eb126..c471cc160 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -334,8 +334,11 @@ class FileDownloader(object): template_dict['epoch'] = int(time.time()) template_dict['autonumber'] = u'%05d' % self._num_downloads - template_dict = dict((key, u'NA' if val is None else val) for key, val in template_dict.items()) - template_dict = dict((k, sanitize_filename(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) + sanitize = lambda k,v: sanitize_filename( + u'NA' if v is None else compat_str(v), + restricted=self.params.get('restrictfilenames'), + is_id=(k==u'id')) + template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename -- cgit v1.2.3 From 37c8fd48421ce8bbbe25da962b2e8d5ca2629dd0 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 11 Dec 2012 09:49:27 +0100 Subject: added a test mode to FileDownloader that fetches only first 10K --- youtube_dl/FileDownloader.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index c471cc160..aad12fc1f 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -78,6 +78,7 @@ class FileDownloader(object): writeinfojson: Write the video description to a .info.json file writesubtitles: Write the video subtitles to a .srt file subtitleslang: Language of the subtitles to download + test: Download only first bytes to test the downloader. """ params = None @@ -594,6 +595,9 @@ class FileDownloader(object): basic_request = compat_urllib_request.Request(url, None, headers) request = compat_urllib_request.Request(url, None, headers) + if self.params.get('test', False): + request.add_header('Range','bytes=0-10240') + # Establish possible resume length if os.path.isfile(encodeFilename(tmpfilename)): resume_len = os.path.getsize(encodeFilename(tmpfilename)) -- cgit v1.2.3 From 59ce20191588028ee90551b40b33a8a36d778eec Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 11 Dec 2012 11:02:21 +0100 Subject: print traceback on trouble if --verbose (why didn't I think of this before!?) --- youtube_dl/FileDownloader.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index aad12fc1f..b43acd19b 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -10,6 +10,7 @@ import socket import subprocess import sys import time +import traceback if os.name == 'nt': import ctypes @@ -217,6 +218,8 @@ class FileDownloader(object): """ if message is not None: self.to_stderr(message) + if self.params.get('verbose'): + self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack()))) if not self.params.get('ignoreerrors', False): raise DownloadError(message) self._download_retcode = 1 -- cgit v1.2.3 From 80d3177e5c07c4970e7cebcf2b38dcdf1e289786 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Mon, 17 Dec 2012 16:25:03 +0100 Subject: various py3 fixes; all tests green on 3.3 --- youtube_dl/FileDownloader.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index b43acd19b..61d3654e2 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -453,9 +453,9 @@ class FileDownloader(object): self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') return try: - infof = open(encodeFilename(infofn), 'wb') + infof = open(encodeFilename(infofn), 'w') try: - json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) + json_info_dict = dict((k, info_dict[k]) for k in info_dict if not k in ['urlhandle']) json.dump(json_info_dict, infof) finally: infof.close() -- cgit v1.2.3 From ce4be3a91d5fe8f2970d00be5663a7aad12d2a6d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 17 Dec 2012 19:48:10 +0100 Subject: Remove some antipatterns and ensure that we always write the JSON file with UTF-8 --- youtube_dl/FileDownloader.py | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 61d3654e2..e8c62ce07 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -4,6 +4,7 @@ from __future__ import absolute_import import math +import io import os import re import socket @@ -453,12 +454,9 @@ class FileDownloader(object): self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') return try: - infof = open(encodeFilename(infofn), 'w') - try: - json_info_dict = dict((k, info_dict[k]) for k in info_dict if not k in ['urlhandle']) + with io.open(encodeFilename(infofn), 'w', 'utf-8') as infof: + json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) json.dump(json_info_dict, infof) - finally: - infof.close() except (OSError, IOError): self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) return -- cgit v1.2.3 From f4bfd65ff2bfce77a6953281c037ca8e516b7648 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 20 Dec 2012 13:13:24 +0100 Subject: Correct JSON writing (Closes #596) --- youtube_dl/FileDownloader.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index e8c62ce07..be70ec755 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -454,9 +454,8 @@ class FileDownloader(object): self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') return try: - with io.open(encodeFilename(infofn), 'w', 'utf-8') as infof: - json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) - json.dump(json_info_dict, infof) + json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) + write_json_file(json_info_dict, encodeFilename(infofn)) except (OSError, IOError): self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) return -- cgit v1.2.3 From 9b14f51a3eaf5b63dad288e092d8a083dd931ceb Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 20 Dec 2012 13:14:27 +0100 Subject: Remove legacy code --- youtube_dl/FileDownloader.py | 5 ----- 1 file changed, 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index be70ec755..a7f3e1064 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -448,11 +448,6 @@ class FileDownloader(object): if self.params.get('writeinfojson', False): infofn = filename + u'.info.json' self.report_writeinfojson(infofn) - try: - json.dump - except (NameError,AttributeError): - self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') - return try: json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) write_json_file(json_info_dict, encodeFilename(infofn)) -- cgit v1.2.3 From bfa6389b74866d5406f68a06c589193b12f83c38 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 20 Dec 2012 13:25:54 +0100 Subject: Clean up legacy code --- youtube_dl/FileDownloader.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index a7f3e1064..a861086c3 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -421,11 +421,8 @@ class FileDownloader(object): try: descfn = filename + u'.description' self.report_writedescription(descfn) - descfile = open(encodeFilename(descfn), 'wb') - try: - descfile.write(info_dict['description'].encode('utf-8')) - finally: - descfile.close() + with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: + descfile.write(info_dict['description']) except (OSError, IOError): self.trouble(u'ERROR: Cannot write description file ' + descfn) return -- cgit v1.2.3 From 1a2c3c0f3ee8f91d650a2a252d2795ea88203ca0 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Thu, 20 Dec 2012 14:18:23 +0100 Subject: some py3 fixes, both needed and recommended; we should pass 2to3 as cleanly as possible now --- youtube_dl/FileDownloader.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index a861086c3..d9a4ecd3a 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -433,11 +433,8 @@ class FileDownloader(object): try: srtfn = filename.rsplit('.', 1)[0] + u'.srt' self.report_writesubtitles(srtfn) - srtfile = open(encodeFilename(srtfn), 'wb') - try: - srtfile.write(info_dict['subtitles'].encode('utf-8')) - finally: - srtfile.close() + with io.open(encodeFilename(srtfn), 'w', encoding='utf-8') as srtfile: + srtfile.write(info_dict['subtitles']) except (OSError, IOError): self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) return -- cgit v1.2.3 From 95fedbf86bd6c8820b01768db53355fe488dff5e Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Mon, 31 Dec 2012 19:09:37 +0100 Subject: three small edits * ask for a --verbose log when reporting bugs in README.md * re-enable Escapist test, seems stable now * check that we are not downloading multiple videos when the template is fixed (NOT a complete fix: not detecting playlists) --- youtube_dl/FileDownloader.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index d9a4ecd3a..53c68237b 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -493,6 +493,10 @@ class FileDownloader(object): # Extract information from URL and process it videos = ie.extract(url) + + if len(videos) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + for video in videos or []: video['extractor'] = ie.IE_NAME try: -- cgit v1.2.3 From 0214ce7c7584bd27c6e175065e3991d97af05855 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Mon, 31 Dec 2012 19:21:28 +0100 Subject: Ok, the Escapist test was passing only in my Travis repo, do not ask me why; also, a small bugfix to the latest commit --- youtube_dl/FileDownloader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 53c68237b..ebc2552df 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -494,7 +494,7 @@ class FileDownloader(object): # Extract information from URL and process it videos = ie.extract(url) - if len(videos) > 1 and self.fixed_template(): + if len(videos or []) > 1 and self.fixed_template(): raise SameFileError(self.params['outtmpl']) for video in videos or []: -- cgit v1.2.3 From 1c256f7047051bf351ed5aedb95d8e705685a06b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 1 Jan 2013 20:27:53 +0100 Subject: ExtractorError for errors during extraction --- youtube_dl/FileDownloader.py | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index ebc2552df..756fc72ec 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -210,7 +210,7 @@ class FileDownloader(object): """Checks if the output template is fixed.""" return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) - def trouble(self, message=None): + def trouble(self, message=None, tb=None): """Determine action to take when a download problem appears. Depending on if the downloader has been configured to ignore @@ -220,7 +220,9 @@ class FileDownloader(object): if message is not None: self.to_stderr(message) if self.params.get('verbose'): - self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack()))) + if tb is None: + tb = u''.join(traceback.format_list(traceback.extract_stack())) + self.to_stderr(tb) if not self.params.get('ignoreerrors', False): raise DownloadError(message) self._download_retcode = 1 @@ -485,14 +487,24 @@ class FileDownloader(object): # Warn if the _WORKING attribute is False if not ie.working(): - self.trouble(u'WARNING: the program functionality for this site has been marked as broken, ' - u'and will probably not work. If you want to go on, use the -i option.') + self.to_stderr(u'WARNING: the program functionality for this site has been marked as broken, ' + u'and will probably not work. If you want to go on, use the -i option.') # Suitable InfoExtractor found suitable_found = True # Extract information from URL and process it - videos = ie.extract(url) + try: + videos = ie.extract(url) + except ExtractorError as de: # An error we somewhat expected + self.trouble(u'ERROR: ' + compat_str(de), compat_str(u''.join(traceback.format_tb(de.traceback)))) + break + except Exception as e: + if self.params.get('ignoreerrors', False): + self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc())) + break + else: + raise if len(videos or []) > 1 and self.fixed_template(): raise SameFileError(self.params['outtmpl']) -- cgit v1.2.3 From 01951dda7a27d3bd2331f22ded5d33876cf1dad9 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 3 Jan 2013 15:39:55 +0100 Subject: Make ExtractorError usable for other causes --- youtube_dl/FileDownloader.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 756fc72ec..55afbdbed 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -216,12 +216,15 @@ class FileDownloader(object): Depending on if the downloader has been configured to ignore download errors or not, this method may throw an exception or not when errors are found, after printing the message. + + tb, if given, is additional traceback information. """ if message is not None: self.to_stderr(message) if self.params.get('verbose'): if tb is None: - tb = u''.join(traceback.format_list(traceback.extract_stack())) + tb_data = traceback.format_list(traceback.extract_stack()) + tb = u''.join(tb_data) self.to_stderr(tb) if not self.params.get('ignoreerrors', False): raise DownloadError(message) @@ -497,7 +500,7 @@ class FileDownloader(object): try: videos = ie.extract(url) except ExtractorError as de: # An error we somewhat expected - self.trouble(u'ERROR: ' + compat_str(de), compat_str(u''.join(traceback.format_tb(de.traceback)))) + self.trouble(u'ERROR: ' + compat_str(de), de.format_traceback()) break except Exception as e: if self.params.get('ignoreerrors', False): -- cgit v1.2.3 From f5ebb61495a2ed3ee5563bedc72889be7198c7f2 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 3 Jan 2013 20:26:38 +0100 Subject: Support page URL in RTMP downloads --- youtube_dl/FileDownloader.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'youtube_dl/FileDownloader.py') diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 55afbdbed..be9e4918e 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -537,7 +537,7 @@ class FileDownloader(object): if info is None: break - def _download_with_rtmpdump(self, filename, url, player_url): + def _download_with_rtmpdump(self, filename, url, player_url, page_url): self.report_destination(filename) tmpfilename = self.temp_name(filename) @@ -551,7 +551,11 @@ class FileDownloader(object): # 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', tmpfilename] + basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename] + if player_url is not None: + basic_args += ['-W', player_url] + if page_url is not None: + basic_args += ['--pageUrl', page_url] args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] if self.params.get('verbose', False): try: @@ -584,7 +588,6 @@ class FileDownloader(object): def _do_download(self, filename, info_dict): url = info_dict['url'] - player_url = info_dict.get('player_url', None) # Check file already present if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): @@ -593,7 +596,9 @@ class FileDownloader(object): # Attempt to download using rtmpdump if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url, player_url) + return self._download_with_rtmpdump(filename, url, + info_dict.get('player_url', None), + info_dict.get('page_url', None)) tmpfilename = self.temp_name(filename) stream = None -- cgit v1.2.3