diff options
Diffstat (limited to 'gallery_dl/extractor/bunkr.py')
| -rw-r--r-- | gallery_dl/extractor/bunkr.py | 36 |
1 files changed, 21 insertions, 15 deletions
diff --git a/gallery_dl/extractor/bunkr.py b/gallery_dl/extractor/bunkr.py index 3e12452..e1ee50d 100644 --- a/gallery_dl/extractor/bunkr.py +++ b/gallery_dl/extractor/bunkr.py @@ -80,6 +80,9 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor): # redirect url = response.headers["Location"] + if url[0] == "/": + url = self.root + url + continue root, path = self._split(url) if root not in CF_DOMAINS: continue @@ -105,37 +108,40 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor): "All Bunkr domains require solving a CF challenge") # select alternative domain - root = "https://" + random.choice(DOMAINS) + self.root = root = "https://" + random.choice(DOMAINS) self.log.debug("Trying '%s' as fallback", root) url = root + path def fetch_album(self, album_id): # album metadata - page = self.request(self.root + "/a/" + album_id).text - title, size = text.split_html(text.extr( - page, "<h1", "</span>").partition(">")[2]) - if "&" in title: - title = title.replace( - "<", "<").replace(">", ">").replace("&", "&") + page = self.request( + self.root + "/a/" + album_id, encoding="utf-8").text + title = text.unescape(text.unescape(text.extr( + page, 'property="og:title" content="', '"'))) # files - items = list(text.extract_iter(page, "<!-- item -->", "<!-- -->")) + items = list(text.extract_iter( + page, '<div class="grid-images_box', "</a>")) + return self._extract_files(items), { "album_id" : album_id, "album_name" : title, - "album_size" : text.extr(size, "(", ")"), + "album_size" : text.extr( + page, '<span class="font-semibold">(', ')'), "count" : len(items), } def _extract_files(self, items): for item in items: try: - url = text.extr(item, ' href="', '"') - file = self._extract_file(text.unescape(url)) + url = text.unescape(text.extr(item, ' href="', '"')) + if url[0] == "/": + url = self.root + url + file = self._extract_file(url) info = text.split_html(item) - file["name"] = info[0] - file["size"] = info[2] + file["name"] = info[-3] + file["size"] = info[-2] file["date"] = text.parse_datetime( info[-1], "%H:%M:%S %d/%m/%Y") @@ -179,8 +185,8 @@ class BunkrMediaExtractor(BunkrAlbumExtractor): """Extractor for bunkr.si media links""" subcategory = "media" directory_fmt = ("{category}",) - pattern = BASE_PATTERN + r"(/[vid]/[^/?#]+)" - example = "https://bunkr.si/v/FILENAME" + pattern = BASE_PATTERN + r"(/[fvid]/[^/?#]+)" + example = "https://bunkr.si/f/FILENAME" def fetch_album(self, album_id): try: |