[ie/tiktok:user] Fix extractor #9661
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Authored by: bashonly
Authored by: bashonly
pukkandan
reviewed
Apr 10, 2024
|
|
||
| old_cursor = cursor | ||
| cursor = traverse_obj( | ||
| response, ('itemList', -1, 'createTime', {lambda x: x * 1E3}, {int_or_none})) |
There was a problem hiding this comment.
Suggested change
| response, ('itemList', -1, 'createTime', {lambda x: x * 1E3}, {int_or_none})) | |
| response, ('itemList', -1, 'createTime', {lambda x: int_or_none(x, invscale=1E3})) |
or actually, just
Suggested change
| response, ('itemList', -1, 'createTime', {lambda x: x * 1E3}, {int_or_none})) | |
| response, ('itemList', -1, 'createTime', {lambda x: int(x * 1E3})) |
| cursor = traverse_obj( | ||
| response, ('itemList', -1, 'createTime', {lambda x: x * 1E3}, {int_or_none})) | ||
| if not cursor: | ||
| cursor = old_cursor - 604800000 # jump 1 week back in time |
There was a problem hiding this comment.
Suggested change
| cursor = old_cursor - 604800000 # jump 1 week back in time | |
| cursor = old_cursor - 7 * 86_400_000 # jump 1 week back in time |
is more readable imo. As for the comment, it may be more useful to explain "why 1 week"
| _WORKING = False | ||
| _VALID_URL = [ | ||
| r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])', | ||
| r'tiktokuser:(?P<id>MS4wLjABAAAA[\w-]{64})', |
There was a problem hiding this comment.
We could do something like this if you think it's useful
Suggested change
| r'tiktokuser:(?P<id>MS4wLjABAAAA[\w-]{64})', | |
| r'tiktokuser:(?P<id>MS4wLjABAAAA[\w-]{64})(?:@(?P<username>[\w.-]+))?', |
| _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])' | ||
| _WORKING = False | ||
| _VALID_URL = [ | ||
| r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])', |
There was a problem hiding this comment.
Suggested change
| r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])', | |
| r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w.-]+)/?(?:$|[#?])', |
| _TESTS = [{ | ||
| 'url': 'https://tiktok.com/@corgibobaa?lang=en', | ||
| 'playlist_mincount': 45, | ||
| 'info_dict': { | ||
| 'id': '6935371178089399301', | ||
| 'id': 'MS4wLjABAAAAepiJKgwWhulvCpSuUVsp7sgVVsFJbbNaLeQ6OQ0oAJERGDUIXhb2yxxHZedsItgT', |
There was a problem hiding this comment.
As I said on discord, this isn't necessary to get tiktokuser: working, but I leave it to your discretion
| 'secUid': sec_uid, | ||
| 'type': '1', # pagination type: 0 == oldest-to-newest, 1 == newest-to-oldest | ||
| 'tz_name': 'UTC', | ||
| 'verifyFp': 'verify_%s' % ''.join(random.choices(string.hexdigits, k=7)), |
There was a problem hiding this comment.
Suggested change
| 'verifyFp': 'verify_%s' % ''.join(random.choices(string.hexdigits, k=7)), | |
| 'verifyFp': f'verify_{"".join(random.choices(string.hexdigits, k=7))}', |
Comment on lines
+892
to
+898
| return traverse_obj( | ||
| self._get_universal_data(webpage, user_name), | ||
| ('webapp.user-detail', 'userInfo', 'user', 'secUid', {str})) or traverse_obj( | ||
| self._get_sigi_state(webpage, user_name), | ||
| ('LiveRoom', 'liveRoomUserInfo', 'user', 'secUid'), | ||
| ('UserModule', 'users', ..., 'secUid'), | ||
| get_all=False, expected_type=str) |
There was a problem hiding this comment.
Personally, I try to avoid this type of indenting where it's not obvious where one traverse_obj ends and next begins. But not a big deal
Suggested change
| return traverse_obj( | |
| self._get_universal_data(webpage, user_name), | |
| ('webapp.user-detail', 'userInfo', 'user', 'secUid', {str})) or traverse_obj( | |
| self._get_sigi_state(webpage, user_name), | |
| ('LiveRoom', 'liveRoomUserInfo', 'user', 'secUid'), | |
| ('UserModule', 'users', ..., 'secUid'), | |
| get_all=False, expected_type=str) | |
| return (traverse_obj(self._get_universal_data(webpage, user_name), | |
| ('webapp.user-detail', 'userInfo', 'user', 'secUid', {str})) | |
| or traverse_obj(self._get_sigi_state(webpage, user_name), | |
| ('LiveRoom', 'liveRoomUserInfo', 'user', 'secUid', {str}), | |
| ('UserModule', 'users', ..., 'secUid', {str}, {any}))) |
Comment on lines
+901
to
+905
| user_name, sec_uid = None, None | ||
| if url.startswith('tiktokuser:'): | ||
| sec_uid = self._match_id(url) | ||
| else: | ||
| user_name = self._match_id(url) |
There was a problem hiding this comment.
Suggested change
| user_name, sec_uid = None, None | |
| if url.startswith('tiktokuser:'): | |
| sec_uid = self._match_id(url) | |
| else: | |
| user_name = self._match_id(url) | |
| if url.startswith('tiktokuser:'): | |
| sec_uid, user_name = self._match_id(url), None | |
| else: | |
| sec_uid, user_name = None, self._match_id(url) |
Comment on lines
+907
to
+914
| if not sec_uid: | ||
| for user_url, msg in ( | ||
| (self._UPLOADER_URL_FORMAT % user_name, 'user'), | ||
| (self._UPLOADER_URL_FORMAT % f'{user_name}/live', 'live'), | ||
| ): | ||
| sec_uid = self._get_sec_uid(user_url, user_name, msg) | ||
| if sec_uid: | ||
| break |
There was a problem hiding this comment.
Suggested change
| if not sec_uid: | |
| for user_url, msg in ( | |
| (self._UPLOADER_URL_FORMAT % user_name, 'user'), | |
| (self._UPLOADER_URL_FORMAT % f'{user_name}/live', 'live'), | |
| ): | |
| sec_uid = self._get_sec_uid(user_url, user_name, msg) | |
| if sec_uid: | |
| break | |
| for user_url, msg in ( | |
| (self._UPLOADER_URL_FORMAT % user_name, 'user'), | |
| (self._UPLOADER_URL_FORMAT % f'{user_name}/live', 'live'), | |
| ): | |
| if sec_uid: | |
| break | |
| sec_uid = self._get_sec_uid(user_url, user_name, msg) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
WIP, TODO:
https://www.tiktok.com/@SEC_UIDCloses #3776
Template
Before submitting a pull request make sure you have:
In order to be accepted and merged into yt-dlp each piece of code must be in public domain or released under Unlicense. Check all of the following options that apply:
What is the purpose of your pull request?