diff options
Diffstat (limited to 'gallery_dl/extractor/bunkr.py')
| -rw-r--r-- | gallery_dl/extractor/bunkr.py | 44 |
1 files changed, 38 insertions, 6 deletions
diff --git a/gallery_dl/extractor/bunkr.py b/gallery_dl/extractor/bunkr.py index 5509f5a..26123b8 100644 --- a/gallery_dl/extractor/bunkr.py +++ b/gallery_dl/extractor/bunkr.py @@ -12,6 +12,8 @@ from .lolisafe import LolisafeAlbumExtractor from .. import text from urllib.parse import urlsplit, urlunsplit +BASE_PATTERN = r"(?:https?://)?(?:app\.)?bunkr+\.(?:la|[sr]u|is|to)" + MEDIA_DOMAIN_OVERRIDES = { "cdn9.bunkr.ru" : "c9.bunkr.ru", "cdn12.bunkr.ru": "media-files12.bunkr.la", @@ -28,7 +30,7 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor): """Extractor for bunkrr.su albums""" category = "bunkr" root = "https://bunkrr.su" - pattern = r"(?:https?://)?(?:app\.)?bunkr+\.(?:la|[sr]u|is|to)/a/([^/?#]+)" + pattern = BASE_PATTERN + r"/a/([^/?#]+)" example = "https://bunkrr.su/a/ID" def fetch_album(self, album_id): @@ -53,11 +55,7 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor): for url in urls: if url.startswith("/"): try: - page = self.request(self.root + text.unescape(url)).text - if url[1] == "v": - url = text.extr(page, '<source src="', '"') - else: - url = text.extr(page, '<img src="', '"') + url = self._extract_file(text.unescape(url)) except Exception as exc: self.log.error("%s: %s", exc.__class__.__name__, exc) continue @@ -72,3 +70,37 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor): url = urlunsplit((scheme, domain, path, query, fragment)) yield {"file": text.unescape(url)} + + def _extract_file(self, path): + page = self.request(self.root + path).text + if path[1] == "v": + url = text.extr(page, '<source src="', '"') + else: + url = text.extr(page, '<img src="', '"') + if not url: + url = text.rextract( + page, ' href="', '"', page.rindex("Download"))[0] + return url + + +class BunkrMediaExtractor(BunkrAlbumExtractor): + """Extractor for bunkrr.su media links""" + subcategory = "media" + directory_fmt = ("{category}",) + pattern = BASE_PATTERN + r"/[vid]/([^/?#]+)" + example = "https://bunkrr.su/v/FILENAME" + + def fetch_album(self, album_id): + try: + url = self._extract_file(urlsplit(self.url).path) + except Exception as exc: + self.log.error("%s: %s", exc.__class__.__name__, exc) + return (), {} + + return ({"file": text.unescape(url)},), { + "album_id" : "", + "album_name" : "", + "album_size" : -1, + "description": "", + "count" : 1, + } |