diff --git a/gallery_dl/extractor/hentaifox.py b/gallery_dl/extractor/hentaifox.py
index 7e0b63ce..84ad3aff 100644
--- a/gallery_dl/extractor/hentaifox.py
+++ b/gallery_dl/extractor/hentaifox.py
@@ -23,8 +23,8 @@ class HentaifoxGalleryExtractor(HentaifoxBase, GalleryExtractor):
pattern = r"(?:https?://)?(?:www\.)?hentaifox\.com(/gallery/(\d+))"
test = ("https://hentaifox.com/gallery/56622/", {
"pattern": r"https://i\d*\.hentaifox\.com/\d+/\d+/\d+\.jpg",
+ "keyword": "b7ff141331d0c7fc711ab28d45dfbb013a83d8e9",
"count": 24,
- "keyword": "903ebe227d85e484460382fc6cbab42be7a244d5",
})
def __init__(self, match):
@@ -37,19 +37,43 @@ class HentaifoxGalleryExtractor(HentaifoxBase, GalleryExtractor):
return {
"gallery_id": text.parse_int(self.gallery_id),
"title" : text.unescape(extr("
", "
")),
- "parody" : split(extr(">Parodies:" , ""))[::2],
- "characters": split(extr(">Characters:", ""))[::2],
- "tags" : split(extr(">Tags:" , ""))[::2],
- "artist" : split(extr(">Artists:" , ""))[::2],
- "group" : split(extr(">Groups:" , ""))[::2],
- "type" : text.remove_html(extr(">Category:", "")),
+ "parody" : split(extr(">Parodies:" , ""))[::2],
+ "characters": split(extr(">Characters:", ""))[::2],
+ "tags" : split(extr(">Tags:" , ""))[::2],
+ "artist" : split(extr(">Artists:" , ""))[::2],
+ "group" : split(extr(">Groups:" , ""))[::2],
+ "type" : text.remove_html(extr(">Category:", "= 0:
+ extr = text.extract
+ load_id = extr(page, 'id="load_id" value="', '"', pos)[0]
+ load_dir = extr(page, 'id="load_dir" value="', '"', pos)[0]
+ load_pages = extr(page, 'id="load_pages" value="', '"', pos)[0]
+
+ url = self.root + "/includes/thumbs_loader.php"
+ data = {
+ "u_id" : self.gallery_id,
+ "g_id" : load_id,
+ "img_dir" : load_dir,
+ "visible_pages": "0",
+ "total_pages" : load_pages,
+ "type" : "2",
+ }
+ headers = {
+ "Origin": self.root,
+ "Referer": self.gallery_url,
+ "X-Requested-With": "XMLHttpRequest",
+ }
+ page = self.request(
+ url, method="POST", headers=headers, data=data).text
+
return [
- (text.urljoin(self.root, url.replace("t.", ".")), None)
+ (url.replace("t.", "."), None)
for url in text.extract_iter(page, 'data-src="', '"')
]
@@ -64,15 +88,13 @@ class HentaifoxSearchExtractor(HentaifoxBase, Extractor):
("https://hentaifox.com/character/reimu-hakurei/"),
("https://hentaifox.com/artist/distance/"),
("https://hentaifox.com/search/touhou/"),
- ("https://hentaifox.com/tag/full-colour/", {
+ ("https://hentaifox.com/tag/heterochromia/", {
"pattern": HentaifoxGalleryExtractor.pattern,
- "count": ">= 40",
+ "count": ">= 60",
"keyword": {
- "url": str,
+ "url" : str,
"gallery_id": int,
- "thumbnail": r"re:https://i\d*.hentaifox.com/\d+/\d+/thumb\.",
- "title": str,
- "tags": list,
+ "title" : str,
},
}),
)
@@ -87,31 +109,26 @@ class HentaifoxSearchExtractor(HentaifoxBase, Extractor):
yield Message.Queue, gallery["url"], gallery
def galleries(self):
- url = "{}/{}/".format(self.root, self.path)
+ num = 1
while True:
+ url = "{}{}/pag/{}/".format(self.root, self.path, num)
page = self.request(url).text
- info, gpos = text.extract(
- page, 'class="galleries_overview">', 'class="clear">')
- for ginfo in text.extract_iter(info, '