[extractor] Support multiple archive ids for one video (#4307)

Closes #4352
This commit is contained in:
pukkandan 2022-07-13 15:03:05 +05:30
parent f14a2d8382
commit 1e8fe57e5c
6 changed files with 13 additions and 7 deletions

View file

@ -138,7 +138,6 @@ ### Differences in default behavior
* Some metadata are embedded into different fields when using `--add-metadata` as compared to youtube-dl. Most notably, `comment` field contains the `webpage_url` and `synopsis` contains the `description`. You can [use `--parse-metadata`](#modifying-metadata) to modify this to your liking or use `--compat-options embed-metadata` to revert this
* `playlist_index` behaves differently when used with options like `--playlist-reverse` and `--playlist-items`. See [#302](https://github.com/yt-dlp/yt-dlp/issues/302) for details. You can use `--compat-options playlist-index` if you want to keep the earlier behavior
* The output of `-F` is listed in a new format. Use `--compat-options list-formats` to revert this
* All *experiences* of a funimation episode are considered as a single video. This behavior breaks existing archives. Use `--compat-options seperate-video-versions` to extract information from only the default player
* Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading
* Youtube channel URLs are automatically redirected to `/video`. Append a `/featured` to the URL to download only the videos in the home page. If the channel does not have a videos tab, we try to download the equivalent `UU` playlist instead. For all other tabs, if the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections
* Unavailable videos are also listed for youtube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this
@ -2132,6 +2131,7 @@ #### No longer supported
--no-include-ads Default
--write-annotations No supported site has annotations now
--no-write-annotations Default
--compat-options seperate-video-versions No longer needed
#### Removed
These options were deprecated since 2014 and have now been entirely removed

View file

@ -3455,11 +3455,9 @@ def in_download_archive(self, info_dict):
if fn is None:
return False
vid_id = self._make_archive_id(info_dict)
if not vid_id:
return False # Incomplete video information
return vid_id in self.archive
vid_ids = [self._make_archive_id(info_dict)]
vid_ids.extend(info_dict.get('_old_archive_ids', []))
return any(id_ in self.archive for id_ in vid_ids)
def record_download_archive(self, info_dict):
fn = self.params.get('download_archive')

View file

@ -334,6 +334,7 @@ class InfoExtractor:
'private', 'premium_only', 'subscriber_only', 'needs_auth',
'unlisted' or 'public'. Use 'InfoExtractor._availability'
to set it
_old_archive_ids: A list of old archive ids needed for backward compatibility
__post_extractor: A function to be called just before the metadata is
written to either disk, logger or console. The function
must return a dict which will be added to the info_dict.

View file

@ -249,7 +249,8 @@ def _real_extract(self, url):
self._sort_formats(formats, ('lang', 'source'))
return {
'id': initial_experience_id if only_initial_experience else episode_id,
'id': episode_id,
'_old_archive_ids': [initial_experience_id],
'display_id': display_id,
'duration': duration,
'title': episode['episodeTitle'],

View file

@ -22,6 +22,9 @@ def _extract_from_webpage(self, url, webpage):
entry.update({
'id': f'{video_id}-{num}',
'title': f'{title} ({num})',
'_old_archive_ids': [
f'Generic {f"{video_id}-{num}" if len(entries) > 1 else video_id}',
],
})
self._sort_formats(entry['formats'])
yield entry

View file

@ -1162,8 +1162,11 @@ def _real_extract(self, url):
})
thumbnails.append(thumb)
old_id = self._search_regex(r'%7C(\d+)(?:-\d+)?.mp4', formats[-1]['url'], 'old id', default=None)
return {
'id': clip.get('id') or video_id,
'_old_archive_ids': [f'{self.ie_key()} {old_id}'] if old_id else None,
'display_id': video_id,
'title': clip.get('title') or video_id,
'formats': formats,