Add --force-generic-extractor

For some extractors that are hard to workout a good _VALID_URL we use very vague and unrestrictive ones,
e.g. just allowing anything after hostname and capturing part of URL as id.
If some of these extractors happen to have an video embed of some different hoster or platform
and this scenario was not handled in extractor itself we end up with inability to download this embed
until extractor is fixed to support embed of this kind.
Forcing downloader to use the generic extractor can be a neat temporary solution for this problem.
Example: FiveTV extractor with Tvigle embed - http://www.5-tv.ru/rabota/broadcasts/48/
This commit is contained in:
Sergey M․ 2015-06-12 19:20:12 +06:00
parent 9872d3110c
commit d22dec74ff
4 changed files with 14 additions and 1 deletions

View file

@ -139,6 +139,7 @@ class YoutubeDL(object):
outtmpl: Template for output names. outtmpl: Template for output names.
restrictfilenames: Do not allow "&" and spaces in file names restrictfilenames: Do not allow "&" and spaces in file names
ignoreerrors: Do not stop on download errors. ignoreerrors: Do not stop on download errors.
force_generic_extractor: Force downloader to use the generic extractor
nooverwrites: Prevent overwriting files. nooverwrites: Prevent overwriting files.
playliststart: Playlist item to start at. playliststart: Playlist item to start at.
playlistend: Playlist item to end at. playlistend: Playlist item to end at.
@ -282,6 +283,7 @@ class YoutubeDL(object):
self._num_downloads = 0 self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self._err_file = sys.stderr self._err_file = sys.stderr
self._force_generic_extractor_required = params.get('force_generic_extractor', False)
self.params = params self.params = params
self.cache = Cache(self) self.cache = Cache(self)
@ -633,6 +635,10 @@ class YoutubeDL(object):
extra_info is a dict containing the extra values to add to each result extra_info is a dict containing the extra values to add to each result
''' '''
if not ie_key and self._force_generic_extractor_required:
self._force_generic_extractor_required = False
ie_key = 'Generic'
if ie_key: if ie_key:
ies = [self.get_info_extractor(ie_key)] ies = [self.get_info_extractor(ie_key)]
else: else:

View file

@ -293,6 +293,7 @@ def _real_main(argv=None):
'autonumber_size': opts.autonumber_size, 'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames, 'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors, 'ignoreerrors': opts.ignoreerrors,
'force_generic_extractor': opts.force_generic_extractor,
'ratelimit': opts.ratelimit, 'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites, 'nooverwrites': opts.nooverwrites,
'retries': opts_retries, 'retries': opts_retries,

View file

@ -977,7 +977,9 @@ class GenericIE(InfoExtractor):
'upload_date': upload_date, 'upload_date': upload_date,
} }
if not self._downloader.params.get('test', False) and not is_intentional: if (not self._downloader.params.get('test', False) and
not is_intentional and
not self._downloader.params.get('force_generic_extractor', False)):
self._downloader.report_warning('Falling back on generic information extractor.') self._downloader.report_warning('Falling back on generic information extractor.')
if not full_response: if not full_response:

View file

@ -150,6 +150,10 @@ def parseOpts(overrideArguments=None):
'--extractor-descriptions', '--extractor-descriptions',
action='store_true', dest='list_extractor_descriptions', default=False, action='store_true', dest='list_extractor_descriptions', default=False,
help='Output descriptions of all supported extractors') help='Output descriptions of all supported extractors')
general.add_option(
'--force-generic-extractor',
action='store_true', dest='force_generic_extractor', default=False,
help='Force extraction to use the generic extractor')
general.add_option( general.add_option(
'--default-search', '--default-search',
dest='default_search', metavar='PREFIX', dest='default_search', metavar='PREFIX',