diff options
Diffstat (limited to 'yt_dlp/extractor/common.py')
| -rw-r--r-- | yt_dlp/extractor/common.py | 34 |
1 files changed, 24 insertions, 10 deletions
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index e00d8c42b..aa98c0cc9 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -74,6 +74,7 @@ from ..utils import ( strip_or_none, traverse_obj, unescapeHTML, + UnsupportedError, unified_strdate, unified_timestamp, update_Request, @@ -448,7 +449,9 @@ class InfoExtractor(object): } def __init__(self, downloader=None): - """Constructor. Receives an optional downloader.""" + """Constructor. Receives an optional downloader (a YoutubeDL instance). + If a downloader is not passed during initialization, + it must be set using "set_downloader()" before "extract()" is called""" self._ready = False self._x_forwarded_for_ip = None self._printed_messages = set() @@ -602,10 +605,19 @@ class InfoExtractor(object): if self.__maybe_fake_ip_and_retry(e.countries): continue raise + except UnsupportedError: + raise except ExtractorError as e: - video_id = e.video_id or self.get_temp_id(url) - raise ExtractorError( - e.msg, video_id=video_id, ie=self.IE_NAME, tb=e.traceback, expected=e.expected, cause=e.cause) + kwargs = { + 'video_id': e.video_id or self.get_temp_id(url), + 'ie': self.IE_NAME, + 'tb': e.traceback, + 'expected': e.expected, + 'cause': e.cause + } + if hasattr(e, 'countries'): + kwargs['countries'] = e.countries + raise type(e)(e.msg, **kwargs) except compat_http_client.IncompleteRead as e: raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url)) except (KeyError, StopIteration) as e: @@ -664,7 +676,7 @@ class InfoExtractor(object): See _download_webpage docstring for arguments specification. """ if not self._downloader._first_webpage_request: - sleep_interval = float_or_none(self.get_param('sleep_interval_requests')) or 0 + sleep_interval = self.get_param('sleep_interval_requests') or 0 if sleep_interval > 0: self.to_screen('Sleeping %s seconds ...' % sleep_interval) time.sleep(sleep_interval) @@ -1137,7 +1149,7 @@ class InfoExtractor(object): if mobj: break - _name = self._downloader._color_text(name, 'blue') + _name = self._downloader._format_err(name, self._downloader.Styles.EMPHASIS) if mobj: if group is None: @@ -1537,8 +1549,8 @@ class InfoExtractor(object): 'ie_pref': {'priority': True, 'type': 'extractor'}, 'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)}, 'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)}, - 'lang': {'convert': 'ignore', 'field': 'language_preference'}, - 'quality': {'convert': 'float_none', 'default': -1}, + 'lang': {'convert': 'float', 'field': 'language_preference', 'default': -1}, + 'quality': {'convert': 'float', 'default': -1}, 'filesize': {'convert': 'bytes'}, 'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'}, 'id': {'convert': 'string', 'field': 'format_id'}, @@ -1549,7 +1561,7 @@ class InfoExtractor(object): 'vbr': {'convert': 'float_none'}, 'abr': {'convert': 'float_none'}, 'asr': {'convert': 'float_none'}, - 'source': {'convert': 'ignore', 'field': 'source_preference'}, + 'source': {'convert': 'float', 'field': 'source_preference', 'default': -1}, 'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')}, 'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True}, @@ -3618,9 +3630,11 @@ class SearchInfoExtractor(InfoExtractor): """ Base class for paged search queries extractors. They accept URLs in the format _SEARCH_KEY(|all|[0-9]):{query} - Instances should define _SEARCH_KEY and _MAX_RESULTS. + Instances should define _SEARCH_KEY and optionally _MAX_RESULTS """ + _MAX_RESULTS = float('inf') + @classmethod def _make_valid_url(cls): return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY |