diff options
Diffstat (limited to 'youtube_dlc/YoutubeDL.py')
| -rw-r--r-- | youtube_dlc/YoutubeDL.py | 85 |
1 files changed, 56 insertions, 29 deletions
diff --git a/youtube_dlc/YoutubeDL.py b/youtube_dlc/YoutubeDL.py index dd55ba0f2..ef6fe0a78 100644 --- a/youtube_dlc/YoutubeDL.py +++ b/youtube_dlc/YoutubeDL.py @@ -210,6 +210,8 @@ class YoutubeDL(object): download_archive: File name of a file where all downloads are recorded. Videos already present in the file are not downloaded again. + break_on_existing: Stop the download process after attempting to download a file that's + in the archive. cookiefile: File name where cookies should be read from and dumped to. nocheckcertificate:Do not verify SSL certificates prefer_insecure: Use HTTP instead of HTTPS to retrieve information. @@ -821,31 +823,30 @@ class YoutubeDL(object): if not ie.suitable(url): continue - ie = self.get_info_extractor(ie.ie_key()) + ie_key = ie.ie_key() + ie = self.get_info_extractor(ie_key) if not ie.working(): self.report_warning('The program functionality for this site has been marked as broken, ' 'and will probably not work.') try: - ie_result = ie.extract(url) - if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) - break - if isinstance(ie_result, list): - # Backwards compatibility: old IE result format - ie_result = { - '_type': 'compat_list', - 'entries': ie_result, - } - if info_dict: - if info_dict.get('id'): - ie_result['id'] = info_dict['id'] - if info_dict.get('title'): - ie_result['title'] = info_dict['title'] - self.add_default_extra_info(ie_result, ie, url) - if process: - return self.process_ie_result(ie_result, download, extra_info) - else: - return ie_result + temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url) + except (AssertionError, IndexError, AttributeError): + temp_id = None + if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}): + self.to_screen("[%s] %s: has already been recorded in archive" % ( + ie_key, temp_id)) + break + + return self.__extract_info(url, ie, download, extra_info, process, info_dict) + + else: + self.report_error('no suitable InfoExtractor for URL %s' % url) + + def __handle_extraction_exceptions(func): + def wrapper(self, *args, **kwargs): + try: + return func(self, *args, **kwargs) except GeoRestrictedError as e: msg = e.msg if e.countries: @@ -853,20 +854,38 @@ class YoutubeDL(object): map(ISO3166Utils.short2full, e.countries)) msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.' self.report_error(msg) - break except ExtractorError as e: # An error we somewhat expected self.report_error(compat_str(e), e.format_traceback()) - break except MaxDownloadsReached: raise except Exception as e: if self.params.get('ignoreerrors', False): self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc())) - break else: raise + return wrapper + + @__handle_extraction_exceptions + def __extract_info(self, url, ie, download, extra_info, process, info_dict): + ie_result = ie.extract(url) + if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) + return + if isinstance(ie_result, list): + # Backwards compatibility: old IE result format + ie_result = { + '_type': 'compat_list', + 'entries': ie_result, + } + if info_dict: + if info_dict.get('id'): + ie_result['id'] = info_dict['id'] + if info_dict.get('title'): + ie_result['title'] = info_dict['title'] + self.add_default_extra_info(ie_result, ie, url) + if process: + return self.process_ie_result(ie_result, download, extra_info) else: - self.report_error('no suitable InfoExtractor for URL %s' % url) + return ie_result def add_default_extra_info(self, ie_result, ie, url): self.add_extra_info(ie_result, { @@ -1038,12 +1057,15 @@ class YoutubeDL(object): reason = self._match_entry(entry, incomplete=True) if reason is not None: - self.to_screen('[download] ' + reason) - continue + if reason.endswith('has already been recorded in the archive') and self.params.get('break_on_existing'): + print('[download] tried downloading a file that\'s already in the archive, stopping since --break-on-existing is set.') + break + else: + self.to_screen('[download] ' + reason) + continue - entry_result = self.process_ie_result(entry, - download=download, - extra_info=extra) + entry_result = self.__process_iterable_entry(entry, download, extra) + # TODO: skip failed (empty) entries? playlist_results.append(entry_result) ie_result['entries'] = playlist_results self.to_screen('[download] Finished downloading playlist: %s' % playlist) @@ -1072,6 +1094,11 @@ class YoutubeDL(object): else: raise Exception('Invalid result type: %s' % result_type) + @__handle_extraction_exceptions + def __process_iterable_entry(self, entry, download, extra_info): + return self.process_ie_result( + entry, download=download, extra_info=extra_info) + def _build_format_filter(self, filter_spec): " Returns a function to filter the formats according to the filter_spec " |