X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FYoutubeDL.py;h=f8b8fb0c18df3bc1e86903f095b48782a8c38a93;hb=edab9dbf4d00a7f76fbfd2df9ef4b205c88e47a8;hp=c18ce9660711c7845b36e34285042d54a13f5072;hpb=6789defea9b1fc7ff631e9da8a281504167ced10;p=youtube-dl diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c18ce9660..f8b8fb0c1 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -154,7 +154,7 @@ class YoutubeDL(object): allsubtitles: Downloads all the subtitles of the video (requires writesubtitles or writeautomaticsub) listsubtitles: Lists all available subtitles for the video - subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt) + subtitlesformat: The format code for subtitles subtitleslangs: List of languages of the subtitles to download keepvideo: Keep the video file after post-processing daterange: A DateRange object, download only if the upload_date is in the range. @@ -228,6 +228,12 @@ class YoutubeDL(object): external_downloader: Executable of the external downloader to call. listformats: Print an overview of available video formats and exit. list_thumbnails: Print a table of all thumbnails and exit. + match_filter: A function that gets called with the info_dict of + every video. + If it returns a message, the video is ignored. + If it returns None, the video is downloaded. + match_filter_func in utils.py is one example for this. + no_color: Do not emit color codes in output. The following parameters are not used by YoutubeDL itself, they are used by @@ -485,7 +491,7 @@ class YoutubeDL(object): else: if self.params.get('no_warnings'): return - if self._err_file.isatty() and os.name != 'nt': + if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': _msg_header = '\033[0;33mWARNING:\033[0m' else: _msg_header = 'WARNING:' @@ -497,7 +503,7 @@ class YoutubeDL(object): Do the same as trouble, but prefixes the message with 'ERROR:', colored in red if stderr is a tty file. ''' - if self._err_file.isatty() and os.name != 'nt': + if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': _msg_header = '\033[0;31mERROR:\033[0m' else: _msg_header = 'ERROR:' @@ -554,7 +560,7 @@ class YoutubeDL(object): self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') return None - def _match_entry(self, info_dict): + def _match_entry(self, info_dict, incomplete): """ Returns None iff the file should be downloaded """ video_title = info_dict.get('title', info_dict.get('id', 'video')) @@ -583,9 +589,17 @@ class YoutubeDL(object): if max_views is not None and view_count > max_views: return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')): - return 'Skipping "%s" because it is age restricted' % title + return 'Skipping "%s" because it is age restricted' % video_title if self.in_download_archive(info_dict): return '%s has already been recorded in archive' % video_title + + if not incomplete: + match_filter = self.params.get('match_filter') + if match_filter is not None: + ret = match_filter(info_dict) + if ret is not None: + return ret + return None @staticmethod @@ -779,7 +793,7 @@ class YoutubeDL(object): 'extractor_key': ie_result['extractor_key'], } - reason = self._match_entry(entry) + reason = self._match_entry(entry, incomplete=True) if reason is not None: self.to_screen('[download] ' + reason) continue @@ -826,26 +840,43 @@ class YoutubeDL(object): '!=': operator.ne, } operator_rex = re.compile(r'''(?x)\s*\[ - (?Pwidth|height|tbr|abr|vbr|filesize|fps) + (?Pwidth|height|tbr|abr|vbr|asr|filesize|fps) \s*(?P%s)(?P\s*\?)?\s* (?P[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?) \]$ ''' % '|'.join(map(re.escape, OPERATORS.keys()))) m = operator_rex.search(format_spec) + if m: + try: + comparison_value = int(m.group('value')) + except ValueError: + comparison_value = parse_filesize(m.group('value')) + if comparison_value is None: + comparison_value = parse_filesize(m.group('value') + 'B') + if comparison_value is None: + raise ValueError( + 'Invalid value %r in format specification %r' % ( + m.group('value'), format_spec)) + op = OPERATORS[m.group('op')] + if not m: - raise ValueError('Invalid format specification %r' % format_spec) + STR_OPERATORS = { + '=': operator.eq, + '!=': operator.ne, + } + str_operator_rex = re.compile(r'''(?x)\s*\[ + \s*(?Pext|acodec|vcodec|container|protocol) + \s*(?P%s)(?P\s*\?)? + \s*(?P[a-zA-Z0-9_-]+) + \s*\]$ + ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) + m = str_operator_rex.search(format_spec) + if m: + comparison_value = m.group('value') + op = STR_OPERATORS[m.group('op')] - try: - comparison_value = int(m.group('value')) - except ValueError: - comparison_value = parse_filesize(m.group('value')) - if comparison_value is None: - comparison_value = parse_filesize(m.group('value') + 'B') - if comparison_value is None: - raise ValueError( - 'Invalid value %r in format specification %r' % ( - m.group('value'), format_spec)) - op = OPERATORS[m.group('op')] + if not m: + raise ValueError('Invalid format specification %r' % format_spec) def _filter(f): actual_value = f.get(m.group('key')) @@ -938,6 +969,9 @@ class YoutubeDL(object): def has_header(self, h): return h in self.headers + def get_header(self, h, default=None): + return self.headers.get(h, default) + pr = _PseudoRequest(info_dict['url']) self.cookiejar.add_cookie_header(pr) return pr.headers.get('Cookie') @@ -964,9 +998,11 @@ class YoutubeDL(object): thumbnails.sort(key=lambda t: ( t.get('preference'), t.get('width'), t.get('height'), t.get('id'), t.get('url'))) - for t in thumbnails: + for i, t in enumerate(thumbnails): if 'width' in t and 'height' in t: t['resolution'] = '%dx%d' % (t['width'], t['height']) + if t.get('id') is None: + t['id'] = '%d' % i if thumbnails and 'thumbnail' not in info_dict: info_dict['thumbnail'] = thumbnails[-1]['url'] @@ -983,6 +1019,15 @@ class YoutubeDL(object): info_dict['timestamp']) info_dict['upload_date'] = upload_date.strftime('%Y%m%d') + if self.params.get('listsubtitles', False): + if 'automatic_captions' in info_dict: + self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions') + self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles') + return + info_dict['requested_subtitles'] = self.process_subtitles( + info_dict['id'], info_dict.get('subtitles'), + info_dict.get('automatic_captions')) + # This extractors handle format selection themselves if info_dict['extractor'] in ['Youku']: if download: @@ -1074,7 +1119,8 @@ class YoutubeDL(object): else self.params['merge_output_format']) selected_format = { 'requested_formats': formats_info, - 'format': rf, + 'format': '%s+%s' % (formats_info[0].get('format'), + formats_info[1].get('format')), 'format_id': '%s+%s' % (formats_info[0].get('format_id'), formats_info[1].get('format_id')), 'width': formats_info[0].get('width'), @@ -1110,6 +1156,59 @@ class YoutubeDL(object): info_dict.update(formats_to_download[-1]) return info_dict + def process_subtitles(self, video_id, available_subs, available_autocaps): + """Select the requested subtitles and their format""" + if available_autocaps and self.params.get('writeautomaticsub'): + available_subs = available_subs.copy() + for lang, cap_info in available_autocaps.items(): + if lang not in available_subs: + available_subs[lang] = cap_info + + if not available_subs: + return available_subs + + if self.params.get('allsubtitles', False): + requested_langs = available_subs.keys() + else: + if self.params.get('subtitleslangs', False): + requested_langs = self.params.get('subtitleslangs') + elif 'en' in available_subs: + requested_langs = ['en'] + else: + requested_langs = [list(available_subs.keys())[0]] + + formats_query = self.params.get('subtitlesformat', 'best') + formats_preference = formats_query.split('/') if formats_query else [] + subs = {} + for lang in requested_langs: + formats = available_subs.get(lang) + if formats is None: + self.report_warning('%s subtitles not available for %s' % (lang, video_id)) + continue + if isinstance(formats, compat_str): + # TODO: convert all IE with subtitles support to the new format + # and remove this + subs[lang] = { + 'ext': formats_preference[0], + 'data': formats, + } + continue + for ext in formats_preference: + if ext == 'best': + f = formats[-1] + break + matches = list(filter(lambda f: f['ext'] == ext, formats)) + if matches: + f = matches[-1] + break + else: + f = formats[-1] + self.report_warning( + 'No subtitle format found matching "%s" for language %s, ' + 'using %s' % (formats_query, lang, f['ext'])) + subs[lang] = f + return subs + def process_info(self, info_dict): """Process a single resolved IE result.""" @@ -1130,7 +1229,7 @@ class YoutubeDL(object): if 'format' not in info_dict: info_dict['format'] = info_dict['ext'] - reason = self._match_entry(info_dict) + reason = self._match_entry(info_dict, incomplete=False) if reason is not None: self.to_screen('[download] ' + reason) return @@ -1212,15 +1311,22 @@ class YoutubeDL(object): subtitles_are_requested = any([self.params.get('writesubtitles', False), self.params.get('writeautomaticsub')]) - if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: + if subtitles_are_requested and info_dict.get('requested_subtitles'): # subtitles download errors are already managed as troubles in relevant IE # that way it will silently go on when used with unsupporting IE - subtitles = info_dict['subtitles'] - sub_format = self.params.get('subtitlesformat', 'srt') - for sub_lang in subtitles.keys(): - sub = subtitles[sub_lang] - if sub is None: - continue + subtitles = info_dict['requested_subtitles'] + for sub_lang, sub_info in subtitles.items(): + sub_format = sub_info['ext'] + if sub_info.get('data') is not None: + sub_data = sub_info['data'] + else: + try: + uf = self.urlopen(sub_info['url']) + sub_data = uf.read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.report_warning('Unable to download subtitle for "%s": %s' % + (sub_lang, compat_str(err))) + continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): @@ -1228,7 +1334,7 @@ class YoutubeDL(object): else: self.to_screen('[info] Writing video subtitles to: ' + sub_filename) with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) + subfile.write(sub_data) except (OSError, IOError): self.report_error('Cannot write subtitles file ' + sub_filename) return @@ -1523,7 +1629,6 @@ class YoutubeDL(object): line(f, idlen) for f in formats if f.get('preference') is None or f['preference'] >= -1000] if len(formats) > 1: - formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' header_line = line({ @@ -1550,6 +1655,17 @@ class YoutubeDL(object): ['ID', 'width', 'height', 'URL'], [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails])) + def list_subtitles(self, video_id, subtitles, name='subtitles'): + if not subtitles: + self.to_screen('%s has no %s' % (video_id, name)) + return + self.to_screen( + 'Available %s for %s:' % (name, video_id)) + self.to_screen(render_table( + ['Language', 'formats'], + [[lang, ', '.join(f['ext'] for f in reversed(formats))] + for lang, formats in subtitles.items()])) + def urlopen(self, req): """ Start an HTTP download """