Pixiv has too many link formats

__init__.py

@@ -32,7 +32,8 @@ class SocialSiteId(enum.Enum):
     KO_FI = 20
     BEHANCE_PAGE = 21
     TIKTOK_USER = 7085
-    PIXIV_USER = 23
+    PIXIV_USER_ID = 5435
+    PIXIV_USER_NICKNAME = 31
     CARRD_PAGE = 24
     HENTAI_FOUNDRY = 25
     YOUTUBE_CHANNEL_HANDLE = 26
@@ -42,6 +43,8 @@ class SocialSiteId(enum.Enum):
     ARTSY_ARTIST = 2042
     LINK_COLLECTION_PAGE = 29
     DEVIANT_ART_ACCOUNT = 7737
+    DANBOORU_ARTIST = 30
+    BANDCAMP_PROFILE = 3283
 
     def wikidata_property(self, client):
         return client.get(WIKIDATA_PROPERTIES[self])
@@ -49,7 +52,13 @@ class SocialSiteId(enum.Enum):
     def is_aggregator(self):
         return self in AGGERAGOR_SOCIALS
 
-AGGERAGOR_SOCIALS = {SocialSiteId.LINKTREE_PAGE, SocialSiteId.WIKIDATA}
+AGGERAGOR_SOCIALS = {
+        SocialSiteId.LINKTREE_PAGE,
+        SocialSiteId.WIKIDATA,
+        SocialSiteId.CARRD_PAGE,
+        SocialSiteId.LINK_COLLECTION_PAGE,
+        SocialSiteId.DANBOORU_ARTIST,
+}
 
 @enforce_types
 @dataclass(frozen = True)
@@ -63,6 +72,8 @@ class SocialLink(object):
 class WikidataInfo(object):
     property_id: Optional[int]
     issuer_id: Optional[int]
+    id_version_of: Optional[SocialSiteId] = None
+    nickname_version_of: Optional[SocialSiteId] = None
 
 WIKIDATA_PROPERTIES = {
     SocialSiteId.EMAIL: WikidataInfo(968, None),
@@ -82,7 +93,9 @@ WIKIDATA_PROPERTIES = {
     SocialSiteId.TUMBLR: WikidataInfo(3943, None),
     SocialSiteId.TIKTOK_USER: WikidataInfo(7085, None),
 
-    SocialSiteId.PIXIV_USER: WikidataInfo(None, 306956),
+    SocialSiteId.PIXIV_USER_ID: WikidataInfo(5435, 306956, id_version_of = SocialSiteId.PIXIV_USER_NICKNAME),
+    SocialSiteId.PIXIV_USER_NICKNAME: WikidataInfo(None, 306956, nickname_version_of = SocialSiteId.PIXIV_USER_ID),
+
     SocialSiteId.MASTODON_PAGE: WikidataInfo(4033, None),
     SocialSiteId.PATREON_PAGE: WikidataInfo(4175, 15861362),
     SocialSiteId.ARTSTATION_PAGE: WikidataInfo(None, 65551500),
@@ -90,12 +103,14 @@ WIKIDATA_PROPERTIES = {
 
     SocialSiteId.CARRD_PAGE: WikidataInfo(None, 106036503),
     SocialSiteId.HENTAI_FOUNDRY: WikidataInfo(None, 115903301),
-    SocialSiteId.YOUTUBE_CHANNEL_HANDLE: WikidataInfo(11245, 866),
+    SocialSiteId.YOUTUBE_CHANNEL_HANDLE: WikidataInfo(11245, 866, nickname_version_of = SocialSiteId.YOUTUBE_CHANNEL_ID),
-    SocialSiteId.YOUTUBE_CHANNEL_ID: WikidataInfo(2397, None),
+    SocialSiteId.YOUTUBE_CHANNEL_ID: WikidataInfo(2397, 866, id_version_of = SocialSiteId.YOUTUBE_CHANNEL_HANDLE),
     SocialSiteId.VIMEO_CHANNEL: WikidataInfo(4015, 156376),
     SocialSiteId.NEWGROUNDS_PAGE: WikidataInfo(None, 263655),
     SocialSiteId.ARTSY_ARTIST: WikidataInfo(2042, 4796642),
     SocialSiteId.DEVIANT_ART_ACCOUNT: WikidataInfo(7737, None),
+    SocialSiteId.DANBOORU_ARTIST: WikidataInfo(None, 64514853),
+    SocialSiteId.BANDCAMP_PROFILE: WikidataInfo(3283, 545966),
 }
 
 def re_social_subdomain(main_domain):
@@ -103,6 +118,7 @@ def re_social_subdomain(main_domain):
     return r'^(?:https?:\/\/)?([\w_-]+)\.'+re.escape(main_domain)+'(\/.*)?$'
 
 RE_ID = r'@?([^/]+)'
+RE_ANY_SUBPATH = r'(|\/|\/.*)$'
 
 def re_social_path(main_domain):
     #return r'^(?:https?:\/\/)?(?:www\.)?'+re.escape(main_domain)+'\/'+RE_ID+'\/?$'
@@ -113,10 +129,13 @@ def re_social_path_adv(main_domain, *path):
     l = [r'^', '(?:https?:\/\/)?', r'(?:www\.)?', re.escape(main_domain)]
 
     for p in path:
+        if p != RE_ANY_SUBPATH:
             l.append(r'\/')
-        l.append(RE_ID if p == RE_ID else re.escape(p))
+        l.append(p if p in {RE_ID, RE_ANY_SUBPATH} else re.escape(p))
+    if path[-1] != RE_ANY_SUBPATH:
         l.append(r'\/?$')
-    return ''.join(l)
+    regex = ''.join(l)
+    return regex
 
 MAILTO_URL = r'^mailto:(?:[\w._.]+@[\w._.]+)$'
 
@@ -130,7 +149,7 @@ SONGKICK_ARTIST_URL = r'^(?:https?:\/\/)?(?:www\.)?songkick\.com\/artists\/(\d+)
 TUMBLR_PAGE_URL = re_social_path('tumblr.com')
 TUMBLR_PAGE_URL_2 = re_social_subdomain('tumblr.com')
 INSTAGRAM_URL = re_social_path('instagram.com')
-PATREON_URL = re_social_path('patreon.com')
+PATREON_URL = re_social_path_adv('patreon.com', RE_ID, RE_ANY_SUBPATH)
 ARTSTATION_URL = re_social_path('artstation.com')
 INPRNT_URL = re_social_path_adv('inprnt.com', 'gallery', RE_ID)
 FACEBOOK_PAGE_URL = re_social_path('facebook.com')
@@ -138,11 +157,14 @@ SUBSTACK_PREFIX_URL = re_social_subdomain('substack.com')
 ETSY_SHOP_URL = re_social_path_adv('etsy.com', 'shop', RE_ID)
 BEHANCE_PAGE_URL = re_social_path('behance.net')
 TIKTOK_USER_URL = re_social_path('tiktok.com')
-PIXIV_USER_URL = r'^(?:https?:\/\/)?(?:www\.)?pixiv\.net(?:\/en)?\/users/(\d+)\/?$'
+PIXIV_USER_ID_URL = r'^(?:https?:\/\/)?(?:www\.)?pixiv\.net(?:\/en)?\/users/(\d+)\/?$'
-PIXIV_USER_URL_2 = r'^(?:https?:\/\/)?(?:www\.)?pixiv\.net(?:\/en)?\/member\.php\/?[?]id=(\d+)$'
+PIXIV_USER_ID_URL_2 = r'^(?:https?:\/\/)?(?:www\.)?pixiv\.net(?:\/en)?\/member\.php\/?[?]id=(\d+)$'
+PIXIV_FANBOX_USER_NICKNAME_URL = re_social_subdomain('fanbox.cc')
+PIXIV_USER_NICKNAME_URL = re_social_path_adv('pixiv.net', 'stacc', RE_ID)
+PIXIV_SKETCH_USER_NICKNAME_URL = re_social_path_adv('sketch.pixiv.net', RE_ID)
 
 URL_PARSE_CARRD_PAGE = re_social_subdomain('carrd.co')
-URL_PARSE_HENTAI_FOUNDRY= re_social_path_adv('hentai-foundry.com', 'user', RE_ID, 'profile')
+URL_PARSE_HENTAI_FOUNDRY = re_social_path_adv('hentai-foundry.com', 'user', RE_ID, RE_ANY_SUBPATH)
 URL_PARSE_YOUTUBE_CHANNEL_HANDLE_1= re_social_path_adv('youtube.com', RE_ID)
 URL_PARSE_YOUTUBE_CHANNEL_HANDLE_2= re_social_path_adv('youtube.com', 'c', RE_ID)
 URL_PARSE_YOUTUBE_CHANNEL_ID= re_social_path_adv('youtube.com', 'channel', RE_ID)
@@ -151,6 +173,9 @@ URL_PARSE_NEWGROUNDS_PAGE = re_social_subdomain('newgrounds.com')
 URL_PARSE_ARTSY_ARTIST = re_social_path_adv('artsy.net', 'artist', RE_ID)
 URL_PARSE_DEVIANT_ART_ACCOUNT = re_social_path_adv('deviantart.com', RE_ID)
 URL_PARSE_DEVIANT_ART_ACCOUNT_2 = re_social_subdomain('deviantart.com')
+URL_PARSE_DANBOORU_ARTIST = re_social_path_adv('danbooru.donmai.us', 'artists', RE_ID)
+URL_PARSE_BANDCAMP = re_social_subdomain('bandcamp.com')
+
 # TODO: https://<ID>.deviantart.com
 
 REGEXES = [
@@ -187,8 +212,11 @@ REGEXES = [
     (TIKTOK_USER_URL, SocialSiteId.TIKTOK_USER),
 
     # Pixiv
-    (PIXIV_USER_URL, SocialSiteId.PIXIV_USER),
+    (PIXIV_USER_ID_URL, SocialSiteId.PIXIV_USER_ID),
-    (PIXIV_USER_URL_2, SocialSiteId.PIXIV_USER),
+    (PIXIV_USER_ID_URL_2, SocialSiteId.PIXIV_USER_ID),
+    (PIXIV_FANBOX_USER_NICKNAME_URL , SocialSiteId.PIXIV_USER_NICKNAME),
+    (PIXIV_USER_NICKNAME_URL , SocialSiteId.PIXIV_USER_NICKNAME),
+    (PIXIV_SKETCH_USER_NICKNAME_URL, SocialSiteId.PIXIV_USER_NICKNAME),
 
     # Patreon
     (PATREON_URL, SocialSiteId.PATREON_PAGE),
@@ -238,6 +266,12 @@ REGEXES = [
     # Deviant art
     (URL_PARSE_DEVIANT_ART_ACCOUNT, SocialSiteId.DEVIANT_ART_ACCOUNT),
     (URL_PARSE_DEVIANT_ART_ACCOUNT_2, SocialSiteId.DEVIANT_ART_ACCOUNT),
+
+    # Danbooru
+    (URL_PARSE_DANBOORU_ARTIST, SocialSiteId.DANBOORU_ARTIST),
+
+    # Bandcamp
+    (URL_PARSE_BANDCAMP, SocialSiteId.BANDCAMP_PROFILE),
 ]
 
 WELL_KNOWN_MASTODON_INSTANCES = frozenset({
@@ -260,12 +294,12 @@ WELL_KNOWN_MASTODON_INSTANCES = frozenset({
     'fosstodon.org',
 })
 
-def determine_social_from_url_internally(url):
+def determine_social_from_url_internally(url: str):
     assert isinstance(url, str)
 
     # Regexes
     for (social_site_url_regex, social_site_id) in REGEXES:
-        if m := re.match(social_site_url_regex, url, re.I):
+        if m := re.fullmatch(social_site_url_regex, url, re.I):
             groups = m.groups()
             return (social_site_id, groups[0] if len(groups) > 0 else None)