diff options
Diffstat (limited to 'yt_dlp/utils.py')
| -rw-r--r-- | yt_dlp/utils.py | 91 |
1 files changed, 62 insertions, 29 deletions
diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py index 88adbd3b9..e70c5f909 100644 --- a/yt_dlp/utils.py +++ b/yt_dlp/utils.py @@ -2492,9 +2492,9 @@ class GeoRestrictedError(ExtractorError): geographic location due to geographic restrictions imposed by a website. """ - def __init__(self, msg, countries=None): - super(GeoRestrictedError, self).__init__(msg, expected=True) - self.msg = msg + def __init__(self, msg, countries=None, **kwargs): + kwargs['expected'] = True + super(GeoRestrictedError, self).__init__(msg, **kwargs) self.countries = countries @@ -2542,23 +2542,33 @@ class PostProcessingError(YoutubeDLError): self.msg = msg -class ExistingVideoReached(YoutubeDLError): - """ --max-downloads limit has been reached. """ - pass +class DownloadCancelled(YoutubeDLError): + """ Exception raised when the download queue should be interrupted """ + msg = 'The download was cancelled' + def __init__(self, msg=None): + if msg is not None: + self.msg = msg + YoutubeDLError.__init__(self, self.msg) -class RejectedVideoReached(YoutubeDLError): - """ --max-downloads limit has been reached. """ - pass +class ExistingVideoReached(DownloadCancelled): + """ --break-on-existing triggered """ + msg = 'Encountered a video that is already in the archive, stopping due to --break-on-existing' -class ThrottledDownload(YoutubeDLError): - """ Download speed below --throttled-rate. """ - pass + +class RejectedVideoReached(DownloadCancelled): + """ --break-on-reject triggered """ + msg = 'Encountered a video that did not match filter, stopping due to --break-on-reject' -class MaxDownloadsReached(YoutubeDLError): +class MaxDownloadsReached(DownloadCancelled): """ --max-downloads limit has been reached. """ + msg = 'Maximum number of downloads reached, stopping due to --max-downloads' + + +class ThrottledDownload(YoutubeDLError): + """ Download speed below --throttled-rate. """ pass @@ -3714,14 +3724,14 @@ def parse_resolution(s): if s is None: return {} - mobj = re.search(r'\b(?P<w>\d+)\s*[xX×]\s*(?P<h>\d+)\b', s) + mobj = re.search(r'(?<![a-zA-Z0-9])(?P<w>\d+)\s*[xX×,]\s*(?P<h>\d+)(?![a-zA-Z0-9])', s) if mobj: return { 'width': int(mobj.group('w')), 'height': int(mobj.group('h')), } - mobj = re.search(r'\b(\d+)[pPiI]\b', s) + mobj = re.search(r'(?<![a-zA-Z0-9])(\d+)[pPiI](?![a-zA-Z0-9])', s) if mobj: return {'height': int(mobj.group(1))} @@ -4050,6 +4060,8 @@ class LazyList(collections.abc.Sequence): def __exhaust(self): self.__cache.extend(self.__iterable) + # Discard the emptied iterable to make it pickle-able + self.__iterable = [] return self.__cache def exhaust(self): @@ -4501,6 +4513,7 @@ OUTTMPL_TYPES = { 'description': 'description', 'annotation': 'annotations.xml', 'infojson': 'info.json', + 'link': None, 'pl_thumbnail': None, 'pl_description': 'description', 'pl_infojson': 'info.json', @@ -4729,7 +4742,7 @@ def determine_protocol(info_dict): if protocol is not None: return protocol - url = info_dict['url'] + url = sanitize_url(info_dict['url']) if url.startswith('rtmp'): return 'rtmp' elif url.startswith('mms'): @@ -4748,9 +4761,11 @@ def determine_protocol(info_dict): def render_table(header_row, data, delim=False, extraGap=0, hideEmpty=False): """ Render a list of rows, each as a list of values """ + def width(string): + return len(remove_terminal_sequences(string)) def get_max_lens(table): - return [max(len(compat_str(v)) for v in col) for col in zip(*table)] + return [max(width(str(v)) for v in col) for col in zip(*table)] def filter_using_list(row, filterArray): return [col for (take, col) in zip(filterArray, row) if take] @@ -4762,10 +4777,15 @@ def render_table(header_row, data, delim=False, extraGap=0, hideEmpty=False): table = [header_row] + data max_lens = get_max_lens(table) + extraGap += 1 if delim: - table = [header_row] + [['-' * ml for ml in max_lens]] + data - format_str = ' '.join('%-' + compat_str(ml + extraGap) + 's' for ml in max_lens[:-1]) + ' %s' - return '\n'.join(format_str % tuple(row) for row in table) + table = [header_row] + [[delim * (ml + extraGap) for ml in max_lens]] + data + max_lens[-1] = 0 + for row in table: + for pos, text in enumerate(map(str, row)): + row[pos] = text + (' ' * (max_lens[pos] - width(text) + extraGap)) + ret = '\n'.join(''.join(row) for row in table) + return ret def _match_one(filter_part, dct, incomplete): @@ -6229,6 +6249,12 @@ URL=%(url)s Icon=text-html '''.lstrip() +LINK_TEMPLATES = { + 'url': DOT_URL_LINK_TEMPLATE, + 'desktop': DOT_DESKTOP_LINK_TEMPLATE, + 'webloc': DOT_WEBLOC_LINK_TEMPLATE, +} + def iri_to_uri(iri): """ @@ -6486,6 +6512,13 @@ def jwt_encode_hs256(payload_data, key, headers={}): return token +# can be extended in future to verify the signature and parse header and return the algorithm used if it's not HS256 +def jwt_decode_hs256(jwt): + header_b64, payload_b64, signature_b64 = jwt.split('.') + payload_data = json.loads(base64.urlsafe_b64decode(payload_b64)) + return payload_data + + def supports_terminal_sequences(stream): if compat_os_name == 'nt': if get_windows_version() < (10, 0, 10586): @@ -6498,12 +6531,12 @@ def supports_terminal_sequences(stream): return False -TERMINAL_SEQUENCES = { - 'DOWN': '\n', - 'UP': '\x1b[A', - 'ERASE_LINE': '\x1b[K', - 'RED': '\033[0;31m', - 'YELLOW': '\033[0;33m', - 'BLUE': '\033[0;34m', - 'RESET_STYLE': '\033[0m', -} +_terminal_sequences_re = re.compile('\033\\[[^m]+m') + + +def remove_terminal_sequences(string): + return _terminal_sequences_re.sub('', string) + + +def number_of_digits(number): + return len('%d' % number) |