diff options
Diffstat (limited to 'gallery_dl/extractor/rawkuma.py')
| -rw-r--r-- | gallery_dl/extractor/rawkuma.py | 63 |
1 files changed, 39 insertions, 24 deletions
diff --git a/gallery_dl/extractor/rawkuma.py b/gallery_dl/extractor/rawkuma.py index 242486d..a4a0c9b 100644 --- a/gallery_dl/extractor/rawkuma.py +++ b/gallery_dl/extractor/rawkuma.py @@ -7,7 +7,7 @@ """Extractors for https://rawkuma.net/""" from .common import MangaExtractor, ChapterExtractor -from .. import text, util +from .. import text BASE_PATTERN = r"(?:https?://)?rawkuma\.(?:net|com)" @@ -21,43 +21,40 @@ class RawkumaBase(): class RawkumaChapterExtractor(RawkumaBase, ChapterExtractor): """Extractor for manga chapters from rawkuma.net""" archive_fmt = "{chapter_id}_{page}" - pattern = BASE_PATTERN + r"/([^/?#]+-chapter-\d+(?:-\d+)?)" - example = "https://rawkuma.net/TITLE-chapter-123/" + pattern = rf"{BASE_PATTERN}(/manga/[^/?#]+/chapter-\d+(?:.\d+)?\.(\d+))" + example = "https://rawkuma.net/manga/7TITLE/chapter-123.321" def __init__(self, match): url = f"{self.root}/{match[1]}/" ChapterExtractor.__init__(self, match, url) def metadata(self, page): - item = util.json_loads(text.extr(page, ',"item":', "}};")) - title = text.rextr( - page, '<h1 class="entry-title', "</h1>").partition(" – ")[2] - date = text.extr(page, 'datetime="', '"') - chapter, sep, minor = item["c"].partition(".") + manga, _, chapter = text.extr( + page, '<title>', "<").rpartition(" Chapter ") + chapter, sep, minor = chapter.partition(" – ")[0].partition(".") return { - "manga" : item["s"], - "manga_id" : text.parse_int(item["mid"]), + "manga" : text.unescape(manga), + "manga_id" : text.parse_int(text.extr(page, "manga_id=", "&")), "chapter" : text.parse_int(chapter), "chapter_minor": sep + minor, - "chapter_id" : text.parse_int(item["cid"]), - "title" : text.unescape(title), - "date" : text.parse_datetime( - date, "%Y-%m-%dWIB%H:%M:%S%z"), - "thumbnail" : item.get("t"), + "chapter_id" : text.parse_int(self.groups[-1]), + # "title" : text.unescape(title), + "date" : self.parse_datetime_iso(text.extr( + page, 'datetime="', '"')), "lang" : "ja", "language" : "Japanese", } def images(self, page): - images = util.json_loads(text.extr(page, '","images":', '}')) - return [(url, None) for url in images] + return [(url, None) for url in text.extract_iter( + page, "<img src='", "'")] class RawkumaMangaExtractor(RawkumaBase, MangaExtractor): """Extractor for manga from rawkuma.net""" chapterclass = RawkumaChapterExtractor - pattern = BASE_PATTERN + r"/manga/([^/?#]+)" + pattern = rf"{BASE_PATTERN}/manga/([^/?#]+)" example = "https://rawkuma.net/manga/TITLE/" def __init__(self, match): @@ -66,18 +63,36 @@ class RawkumaMangaExtractor(RawkumaBase, MangaExtractor): def chapters(self, page): manga = text.unescape(text.extr(page, "<title>", " – ")) + manga_id = text.parse_int(text.extr(page, "manga_id=", "&")) + + url = f"{self.root}/wp-admin/admin-ajax.php" + params = { + "manga_id": manga_id, + "page" : "1", + "action" : "chapter_list", + } + headers = { + "HX-Request" : "true", + "HX-Trigger" : "chapter-list", + "HX-Target" : "chapter-list", + "HX-Current-URL": self.page_url, + "Sec-Fetch-Dest": "empty", + "Sec-Fetch-Mode": "cors", + "Sec-Fetch-Site": "same-origin", + } + html = self.request(url, params=params, headers=headers).text results = [] - for chbox in text.extract_iter( - page, '<li data-num="', "</a>"): - info = text.extr(chbox, '', '"') - chapter, _, title = info.partition(" - ") + for url in text.extract_iter(html, '<a href="', '"'): + info = url[url.rfind("-")+1:-1] + chapter, _, chapter_id = info.rpartition(".") chapter, sep, minor = chapter.partition(".") - results.append((text.extr(chbox, 'href="', '"'), { + results.append((url, { "manga" : manga, + "manga_id" : manga_id, "chapter" : text.parse_int(chapter), "chapter-minor": sep + minor, - "title" : title, + "chapter_id" : text.parse_int(chapter_id), })) return results |