From cf6ef584a08294241f0206ca7dce6cabc54ed10d Mon Sep 17 00:00:00 2001 From: Jon Michael Aanes Date: Sat, 9 Nov 2024 17:54:15 +0100 Subject: [PATCH] Ruff --- socials_util/__init__.py | 173 ++++++++++++++++++++++++++------------- test/test_parsing.py | 5 +- 2 files changed, 119 insertions(+), 59 deletions(-) diff --git a/socials_util/__init__.py b/socials_util/__init__.py index 34653b1..49d8fe2 100644 --- a/socials_util/__init__.py +++ b/socials_util/__init__.py @@ -5,9 +5,9 @@ Python library for parsing and processing URLs of Social Media Sites. Used by one-page-internet. """ +import dataclasses import re import urllib.parse -import dataclasses import aenum import enforce_typing @@ -205,7 +205,6 @@ WIKIDATA_PROPERTIES: dict[SocialSiteId | int, WikidataInfo] = { } - RE_ID = r'@?([^\s/]+)' RE_DUAL_ID = r'@?([^\s/]+/[^\s/]+)' RE_ANY_SUBPATH = r'(|\/|\/\S*)$' @@ -214,12 +213,14 @@ SPECIAL_REGEX_LITERALS = frozenset({RE_ID, RE_DUAL_ID, RE_ANY_SUBPATH}) REGEX_LITERALS_TO_FORMATTER = {RE_ID: '{id}', RE_DUAL_ID: '{id}', RE_ANY_SUBPATH: ''} DOES_NOT_NEED_AUTO_SLASH = frozenset({RE_ANY_SUBPATH}) + @enforce_typing.enforce_types @dataclasses.dataclass(frozen=True) class SocialPathFormat: regex: str formatter: str + def social_path_format_adv(main_domain: str, *path: str) -> SocialPathFormat: if main_domain.startswith('www.'): msg = f'Redundant www: {main_domain}' @@ -248,19 +249,24 @@ def social_path_format_adv(main_domain: str, *path: str) -> SocialPathFormat: formatter_builder.append('/') return SocialPathFormat( - regex = ''.join(regex_builder), - formatter = ''.join(formatter_builder), + regex=''.join(regex_builder), + formatter=''.join(formatter_builder), ) + def social_path_format(main_domain: str) -> SocialPathFormat: return social_path_format_adv(main_domain, RE_ID) + def re_social_subdomain(main_domain: str) -> SocialPathFormat: return SocialPathFormat( - regex = r'^(?:https?:\/\/)?(?:www\.)?([\w_-]+)\.' + re.escape(main_domain) + r'(\/.*)?$', - formatter = 'https://{id}.' + main_domain, + regex=r'^(?:https?:\/\/)?(?:www\.)?([\w_-]+)\.' + + re.escape(main_domain) + + r'(\/.*)?$', + formatter='https://{id}.' + main_domain, ) + def re_social_path(main_domain: str) -> str: return social_path_format(main_domain).regex @@ -286,108 +292,145 @@ PIXIV_USER_ID_URL_2 = ( ) URL_FORMATS: list[tuple[object, SocialPathFormat]] = [ - # Twitter (SocialSiteId.TWITTER, social_path_format_adv('x.com', RE_ID, RE_ANY_SUBPATH)), - (SocialSiteId.TWITTER, social_path_format_adv('twitter.com', RE_ID, RE_ANY_SUBPATH)), - + ( + SocialSiteId.TWITTER, + social_path_format_adv('twitter.com', RE_ID, RE_ANY_SUBPATH), + ), # Linktr.ee (SocialSiteId.LINKTREE_PAGE, social_path_format('linktr.ee')), - # Twitch.tv (SocialSiteId.TWITCH, social_path_format('twitch.tv')), - # Wikidata (SocialSiteId.WIKIDATA, social_path_format_adv('wikidata.org', 'wiki', RE_ID)), - # Tumblr (SocialSiteId.TUMBLR, social_path_format('tumblr.com')), (SocialSiteId.TUMBLR, re_social_subdomain('tumblr.com')), (SocialSiteId.TUMBLR, social_path_format('tumblr.com/blog')), (SocialSiteId.TUMBLR, social_path_format('tumblr.com/blog/view')), - # Instagram (SocialSiteId.INSTAGRAM_PAGE, social_path_format('instagram.com')), - # Patreon - (SocialSiteId.PATREON_PAGE, social_path_format_adv('patreon.com', RE_ID, RE_ANY_SUBPATH)), - + ( + SocialSiteId.PATREON_PAGE, + social_path_format_adv('patreon.com', RE_ID, RE_ANY_SUBPATH), + ), # Artstation - (SocialSiteId.ARTSTATION_PAGE, social_path_format_adv('artstation.com', RE_ID, RE_ANY_SUBPATH)), + ( + SocialSiteId.ARTSTATION_PAGE, + social_path_format_adv('artstation.com', RE_ID, RE_ANY_SUBPATH), + ), (SocialSiteId.ARTSTATION_PAGE, re_social_subdomain('artstation.com')), - # Inprnt (SocialSiteId.INPRNT_PAGE, social_path_format_adv('inprnt.com', 'gallery', RE_ID)), - # Facebook (SocialSiteId.FACEBOOK_PAGE, social_path_format('facebook.com')), - # Substack (SocialSiteId.SUBSTACK, re_social_subdomain('substack.com')), - # Etsy shop (SocialSiteId.ETSY_SHOP, social_path_format_adv('etsy.com', 'shop', RE_ID)), - # Behance (SocialSiteId.BEHANCE_PAGE, social_path_format('behance.net')), - # Tiktok (SocialSiteId.TIKTOK_USER, social_path_format('tiktok.com')), - # Pixiv - (SocialSiteId.PIXIV_USER_NICKNAME, social_path_format_adv('pixiv.net', 'stacc', RE_ID)), + ( + SocialSiteId.PIXIV_USER_NICKNAME, + social_path_format_adv('pixiv.net', 'stacc', RE_ID), + ), (SocialSiteId.PIXIV_USER_NICKNAME, re_social_subdomain('fanbox.cc')), - (SocialSiteId.PIXIV_USER_NICKNAME, social_path_format_adv('sketch.pixiv.net', RE_ID)), - + ( + SocialSiteId.PIXIV_USER_NICKNAME, + social_path_format_adv('sketch.pixiv.net', RE_ID), + ), # Carrd (SocialSiteId.CARRD_PAGE, re_social_subdomain('carrd.co')), - # Youtube - (SocialSiteId.YOUTUBE_CHANNEL_HANDLE, social_path_format_adv('youtube.com', RE_ID, RE_ANY_SUBPATH)), - (SocialSiteId.YOUTUBE_CHANNEL_HANDLE, social_path_format_adv('youtube.com', 'c', RE_ID)), - (SocialSiteId.YOUTUBE_CHANNEL_ID, social_path_format_adv('youtube.com', 'channel', RE_ID)), - + ( + SocialSiteId.YOUTUBE_CHANNEL_HANDLE, + social_path_format_adv('youtube.com', RE_ID, RE_ANY_SUBPATH), + ), + ( + SocialSiteId.YOUTUBE_CHANNEL_HANDLE, + social_path_format_adv('youtube.com', 'c', RE_ID), + ), + ( + SocialSiteId.YOUTUBE_CHANNEL_ID, + social_path_format_adv('youtube.com', 'channel', RE_ID), + ), # Vimeo (SocialSiteId.VIMEO_CHANNEL, social_path_format_adv('vimeo.com', RE_ID)), - # Newgrounds (SocialSiteId.NEWGROUNDS_PAGE, re_social_subdomain('newgrounds.com')), - # Artsy - (SocialSiteId.ARTSY_ARTIST, social_path_format_adv( 'artsy.net', 'artist', RE_ID, RE_ANY_SUBPATH)), - + ( + SocialSiteId.ARTSY_ARTIST, + social_path_format_adv('artsy.net', 'artist', RE_ID, RE_ANY_SUBPATH), + ), # Artnet - (SocialSiteId.ARTNET_ARTIST, social_path_format_adv( 'artnet.com', 'artists', RE_ID, RE_ANY_SUBPATH)), - + ( + SocialSiteId.ARTNET_ARTIST, + social_path_format_adv('artnet.com', 'artists', RE_ID, RE_ANY_SUBPATH), + ), # Deviant art (SocialSiteId.DEVIANT_ART_ACCOUNT, social_path_format_adv('deviantart.com', RE_ID)), (SocialSiteId.DEVIANT_ART_ACCOUNT, re_social_subdomain('deviantart.com')), - # Danbooru - (SocialSiteId.DANBOORU_ARTIST, social_path_format_adv('danbooru.donmai.us', 'artists', RE_ID)), - + ( + SocialSiteId.DANBOORU_ARTIST, + social_path_format_adv('danbooru.donmai.us', 'artists', RE_ID), + ), # Bandcamp (SocialSiteId.BANDCAMP_PROFILE, re_social_subdomain('bandcamp.com')), - # Bluesky - (SocialSiteId.BLUESKY_PROFILE, social_path_format_adv('bsky.app', 'profile', RE_ID)), - + ( + SocialSiteId.BLUESKY_PROFILE, + social_path_format_adv('bsky.app', 'profile', RE_ID), + ), # Medium - (SocialSiteId.MEDIUM_BLOG, social_path_format_adv('medium.com', RE_ID), ), - (SocialSiteId.MEDIUM_BLOG, re_social_subdomain('medium.com'), ), + ( + SocialSiteId.MEDIUM_BLOG, + social_path_format_adv('medium.com', RE_ID), + ), + ( + SocialSiteId.MEDIUM_BLOG, + re_social_subdomain('medium.com'), + ), # Ko-fi - (SocialSiteId.KO_FI, social_path_format_adv('ko-fi.com', RE_ID), ), - (SocialSiteId.KO_FI, social_path_format_adv('ko-fi.com', RE_ID, 'shop'), ), + ( + SocialSiteId.KO_FI, + social_path_format_adv('ko-fi.com', RE_ID), + ), + ( + SocialSiteId.KO_FI, + social_path_format_adv('ko-fi.com', RE_ID, 'shop'), + ), # Threads - (SocialSiteId.THREADS_USERNAME, social_path_format_adv('threads.net', RE_ID), ), + ( + SocialSiteId.THREADS_USERNAME, + social_path_format_adv('threads.net', RE_ID), + ), # Itch.io - (SocialSiteId.ITCH_IO_DEVELOPER, re_social_subdomain('itch.io'), ), + ( + SocialSiteId.ITCH_IO_DEVELOPER, + re_social_subdomain('itch.io'), + ), # Cohost - (SocialSiteId.COHOST_PROFILE, social_path_format_adv('cohost.org', RE_ID), ), + ( + SocialSiteId.COHOST_PROFILE, + social_path_format_adv('cohost.org', RE_ID), + ), # Soundcloud - (SocialSiteId.SOUNDCLOUD_ARTIST, social_path_format_adv('soundcloud.com', RE_ID), ), + ( + SocialSiteId.SOUNDCLOUD_ARTIST, + social_path_format_adv('soundcloud.com', RE_ID), + ), # IGDB - (SocialSiteId.IGDB_GAME_ID, social_path_format_adv('igdb.com', 'games', RE_ID), ), + ( + SocialSiteId.IGDB_GAME_ID, + social_path_format_adv('igdb.com', 'games', RE_ID), + ), # Steam game ( SocialSiteId.STEAM_APPLICATION_ID, @@ -399,16 +442,25 @@ URL_FORMATS: list[tuple[object, SocialPathFormat]] = [ social_path_format_adv('github.com', RE_DUAL_ID, RE_ANY_SUBPATH), ), # Plurk - (SocialSiteId.PLURK, social_path_format_adv('plurk.com', RE_ID), ), + ( + SocialSiteId.PLURK, + social_path_format_adv('plurk.com', RE_ID), + ), # Linked in ( SocialSiteId.LINKEDIN_PERSONAL_PROFILE, social_path_format_adv('linkedin.com', 'in', RE_ID), ), # Google Blogger - (SocialSiteId.GOOGLE_BLOGGER_PAGE, re_social_subdomain('blogspot.com'), ), + ( + SocialSiteId.GOOGLE_BLOGGER_PAGE, + re_social_subdomain('blogspot.com'), + ), # Cara - (SocialSiteId.CARA_PROFILE, social_path_format_adv('cara.app', RE_ID, RE_ANY_SUBPATH), ), + ( + SocialSiteId.CARA_PROFILE, + social_path_format_adv('cara.app', RE_ID, RE_ANY_SUBPATH), + ), ] REGEXES: list[tuple[str, object]] = [ @@ -491,12 +543,17 @@ def to_parse_result(url: str | urllib.parse.ParseResult) -> urllib.parse.ParseRe msg = f'Expected {urllib.parse.ParseResult} or {str}' raise TypeError(msg) -def to_url(social_site_id: SocialSiteId, social_id: str) -> urllib.parse.ParseResult | None: - for (ssi, fmt) in URL_FORMATS: + +def to_url( + social_site_id: SocialSiteId, + social_id: str, +) -> urllib.parse.ParseResult | None: + for ssi, fmt in URL_FORMATS: if ssi == social_site_id: return to_parse_result(fmt.formatter.format(id=social_id)) return None + def determine_social_from_url( url_not_normalized: str | urllib.parse.ParseResult, ) -> SocialLink | None: diff --git a/test/test_parsing.py b/test/test_parsing.py index b636015..fe14fb5 100644 --- a/test/test_parsing.py +++ b/test/test_parsing.py @@ -212,7 +212,9 @@ NOT_PARSABLE = [ PARSABLE_SOCIAL_IDS_COMBINED, ) def test_parse_social_ids( - url: str, expected_social_site_id: SocialSiteId, expected_social_id: str, + url: str, + expected_social_site_id: SocialSiteId, + expected_social_id: str, ) -> None: social_link: SocialLink | None = determine_social_from_url(url) assert social_link is not None, url @@ -243,6 +245,7 @@ def test_determine_social_from_url_internally() -> None: with pytest.raises(TypeError): assert socials_util.determine_social_from_url_internally(None) + def test_normalize_url(): social_link = determine_social_from_url('http://twitter.com/dril') assert social_link is not None