diff options
Diffstat (limited to 'gallery_dl/extractor/comick.py')
| -rw-r--r-- | gallery_dl/extractor/comick.py | 184 |
1 files changed, 106 insertions, 78 deletions
diff --git a/gallery_dl/extractor/comick.py b/gallery_dl/extractor/comick.py index 7ef4607..6c54156 100644 --- a/gallery_dl/extractor/comick.py +++ b/gallery_dl/extractor/comick.py @@ -20,83 +20,27 @@ class ComickBase(): category = "comick" root = "https://comick.io" - @memcache(keyarg=1) - def _manga_info(self, slug): - url = f"{self.root}/comic/{slug}" - page = self.request(url).text - data = self._extract_nextdata(page) - props = data["props"]["pageProps"] - comic = props["comic"] - - genre = [] - theme = [] - format = "" - for item in comic["md_comic_md_genres"]: - item = item["md_genres"] - group = item["group"] - if group == "Genre": - genre.append(item["name"]) - elif group == "Theme": - theme.append(item["name"]) - else: - format = item["name"] - - if mu := comic["mu_comics"]: - tags = [c["mu_categories"]["title"] - for c in mu["mu_comic_categories"]] - publisher = [p["mu_publishers"]["title"] - for p in mu["mu_comic_publishers"]] - else: - tags = publisher = () - - return { - "manga": comic["title"], - "manga_id": comic["id"], - "manga_hid": comic["hid"], - "manga_slug": slug, - "manga_titles": [t["title"] for t in comic["md_titles"]], - "artist": [a["name"] for a in props["artists"]], - "author": [a["name"] for a in props["authors"]], - "genre" : genre, - "theme" : theme, - "format": format, - "tags" : tags, - "publisher": publisher, - "published": text.parse_int(comic["year"]), - "description": comic["desc"], - "demographic": props["demographic"], - "origin": comic["iso639_1"], - "mature": props["matureContent"], - "rating": comic["content_rating"], - "rank" : comic["follow_rank"], - "score" : text.parse_float(comic["bayesian_rating"]), - "status": "Complete" if comic["status"] == 2 else "Ongoing", - "links" : comic["links"], - "_build_id": data["buildId"], - } - - def _chapter_info(self, manga, chstr): - slug = manga['manga_slug'] - url = (f"{self.root}/_next/data/{manga['_build_id']}" - f"/comic/{slug}/{chstr}.json") - params = {"slug": slug, "chapter": chstr} - return self.request_json(url, params=params)["pageProps"] - class ComickChapterExtractor(ComickBase, ChapterExtractor): """Extractor for comick.io manga chapters""" archive_fmt = "{chapter_hid}_{page}" - pattern = BASE_PATTERN + r"/comic/([\w-]+)/(\w+-chapter-[^/?#]+)" + pattern = (BASE_PATTERN + r"/comic/([\w-]+)" + r"/(\w+(?:-(?:chapter|volume)-[^/?#]+)?)") example = "https://comick.io/comic/MANGA/ID-chapter-123-en" def metadata(self, page): slug, chstr = self.groups - manga = self._manga_info(slug) - props = self._chapter_info(manga, chstr) + manga = _manga_info(self, slug) + props = _chapter_info(self, manga, chstr) ch = props["chapter"] self._images = ch["md_images"] - chapter, sep, minor = ch["chap"].partition(".") + + if chapter := ch["chap"]: + chapter, sep, minor = chapter.partition(".") + else: + chapter = 0 + sep = minor = "" return { **manga, @@ -133,19 +77,32 @@ class ComickMangaExtractor(ComickBase, MangaExtractor): example = "https://comick.io/comic/MANGA" def items(self): - slug = self.groups[0] - manga = self._manga_info(slug) + manga = _manga_info(self, self.groups[0]) + slug = manga["manga_slug"] + _manga_info.update(slug, manga) for ch in self.chapters(manga): - url = (f"{self.root}/comic/{slug}" - f"/{ch['hid']}-chapter-{ch['chap']}-{ch['lang']}") - ch.update(manga) - chapter, sep, minor = ch["chap"].partition(".") - ch["chapter"] = text.parse_int(chapter) - ch["chapter_minor"] = sep + minor ch["_extractor"] = ComickChapterExtractor + if chapter := ch["chap"]: + url = (f"{self.root}/comic/{slug}" + f"/{ch['hid']}-chapter-{chapter}-{ch['lang']}") + chapter, sep, minor = chapter.partition(".") + ch["volume"] = text.parse_int(ch["vol"]) + ch["chapter"] = text.parse_int(chapter) + ch["chapter_minor"] = sep + minor + elif volume := ch["vol"]: + url = (f"{self.root}/comic/{slug}" + f"/{ch['hid']}-volume-{volume}-{ch['lang']}") + ch["volume"] = text.parse_int(volume) + ch["chapter"] = 0 + ch["chapter_minor"] = "" + else: + url = f"{self.root}/comic/{slug}/{ch['hid']}" + ch["volume"] = ch["chapter"] = 0 + ch["chapter_minor"] = "" + yield Message.Queue, url, ch def chapters(self, manga): @@ -160,8 +117,15 @@ class ComickMangaExtractor(ComickBase, MangaExtractor): "Sec-Fetch-Site": "same-site", } - query = text.parse_query(query) - params = {"lang": query.get("lang") or None} + query = text.parse_query_list(query, ("lang",)) + + if (lang := query.get("lang")) or (lang := self.config("lang")): + if not isinstance(lang, str): + lang = ",".join(lang) + else: + lang = None + + params = {"lang": lang} params["page"] = page = text.parse_int(query.get("page"), 1) if date_order := query.get("date-order"): @@ -172,7 +136,7 @@ class ComickMangaExtractor(ComickBase, MangaExtractor): params["chap-order"] = \ "0" if self.config("chapter-reverse", False) else "1" - group = query.get("group", None) + group = query.get("group") if group == "0": group = None @@ -190,9 +154,73 @@ class ComickMangaExtractor(ComickBase, MangaExtractor): yield from data["chapters"] else: for ch in data["chapters"]: - if group in ch["group_name"]: + if (groups := ch["group_name"]) and group in groups: yield ch if data["total"] <= limit * page: return params["page"] = page = page + 1 + + +@memcache(keyarg=1) +def _manga_info(self, slug): + url = f"{self.root}/comic/{slug}" + page = self.request(url).text + data = self._extract_nextdata(page) + props = data["props"]["pageProps"] + comic = props["comic"] + + genre = [] + theme = [] + format = "" + for item in comic["md_comic_md_genres"]: + item = item["md_genres"] + group = item["group"] + if group == "Genre": + genre.append(item["name"]) + elif group == "Theme": + theme.append(item["name"]) + else: + format = item["name"] + + if mu := comic["mu_comics"]: + tags = [c["mu_categories"]["title"] + for c in mu["mu_comic_categories"]] + publisher = [p["mu_publishers"]["title"] + for p in mu["mu_comic_publishers"]] + else: + tags = publisher = () + + return { + "manga": comic["title"], + "manga_id": comic["id"], + "manga_hid": comic["hid"], + "manga_slug": comic["slug"], + "manga_titles": [t["title"] for t in comic["md_titles"]], + "artist": [a["name"] for a in props["artists"]], + "author": [a["name"] for a in props["authors"]], + "genre" : genre, + "theme" : theme, + "format": format, + "tags" : tags, + "publisher": publisher, + "published": text.parse_int(comic["year"]), + "description": comic["desc"], + "demographic": props["demographic"], + "origin": comic["iso639_1"], + "mature": props["matureContent"], + "rating": comic["content_rating"], + "rank" : comic["follow_rank"], + "score" : text.parse_float(comic["bayesian_rating"]), + "status": "Complete" if comic["status"] == 2 else "Ongoing", + "links" : comic["links"], + "_build_id": data["buildId"], + } + + +def _chapter_info(self, manga, chstr): + slug = manga['manga_slug'] + url = (f"{self.root}/_next/data/{manga['_build_id']}" + f"/comic/{slug}/{chstr}.json") + params = {"slug": slug, "chapter": chstr} + return self.request_json(url, params=params)["pageProps"] |