diff options
Diffstat (limited to 'gallery_dl/extractor/danbooru.py')
| -rw-r--r-- | gallery_dl/extractor/danbooru.py | 65 |
1 files changed, 54 insertions, 11 deletions
diff --git a/gallery_dl/extractor/danbooru.py b/gallery_dl/extractor/danbooru.py index 1746647..c3dfd91 100644 --- a/gallery_dl/extractor/danbooru.py +++ b/gallery_dl/extractor/danbooru.py @@ -20,12 +20,22 @@ class DanbooruExtractor(BaseExtractor): page_limit = 1000 page_start = None per_page = 200 + useragent = util.USERAGENT request_interval = (0.5, 1.5) def _init(self): self.ugoira = self.config("ugoira", False) self.external = self.config("external", False) - self.includes = False + + includes = self.config("metadata") + if includes: + if isinstance(includes, (list, tuple)): + includes = ",".join(includes) + elif not isinstance(includes, str): + includes = "artist_commentary,children,notes,parent,uploader" + self.includes = includes + ",id" + else: + self.includes = False threshold = self.config("threshold") if isinstance(threshold, int): @@ -46,16 +56,6 @@ class DanbooruExtractor(BaseExtractor): return pages * self.per_page def items(self): - self.session.headers["User-Agent"] = util.USERAGENT - - includes = self.config("metadata") - if includes: - if isinstance(includes, (list, tuple)): - includes = ",".join(includes) - elif not isinstance(includes, str): - includes = "artist_commentary,children,notes,parent,uploader" - self.includes = includes + ",id" - data = self.metadata() for post in self.posts(): @@ -108,6 +108,13 @@ class DanbooruExtractor(BaseExtractor): yield Message.Directory, post yield Message.Url, url, post + def items_artists(self): + for artist in self.artists(): + artist["_extractor"] = DanbooruTagExtractor + url = "{}/posts?tags={}".format( + self.root, text.quote(artist["name"])) + yield Message.Queue, url, artist + def metadata(self): return () @@ -294,3 +301,39 @@ class DanbooruPopularExtractor(DanbooruExtractor): def posts(self): return self._pagination("/explore/posts/popular.json", self.params) + + +class DanbooruArtistExtractor(DanbooruExtractor): + """Extractor for danbooru artists""" + subcategory = "artist" + pattern = BASE_PATTERN + r"/artists/(\d+)" + example = "https://danbooru.donmai.us/artists/12345" + + items = DanbooruExtractor.items_artists + + def artists(self): + url = "{}/artists/{}.json".format(self.root, self.groups[-1]) + return (self.request(url).json(),) + + +class DanbooruArtistSearchExtractor(DanbooruExtractor): + """Extractor for danbooru artist searches""" + subcategory = "artist-search" + pattern = BASE_PATTERN + r"/artists/?\?([^#]+)" + example = "https://danbooru.donmai.us/artists?QUERY" + + items = DanbooruExtractor.items_artists + + def artists(self): + url = self.root + "/artists.json" + params = text.parse_query(self.groups[-1]) + params["page"] = text.parse_int(params.get("page"), 1) + + while True: + artists = self.request(url, params=params).json() + + yield from artists + + if len(artists) < 20: + return + params["page"] += 1 |