1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 02:32:33 +01:00

[nijie] support /history_nuita.php listings (closes #2541)

This commit is contained in:
Mike Fährmann 2022-05-01 17:45:38 +02:00
parent 4aca29b7b4
commit d11e2191ae
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
4 changed files with 47 additions and 10 deletions

View File

@ -1648,7 +1648,7 @@ Description
extractor.nijie.include
----------------------------
-----------------------
Type
``string`` or ``list`` of ``strings``
Default
@ -1658,7 +1658,7 @@ Description
when processing a user profile.
Possible values are
``"illustration"``, ``"doujin"``, ``"favorite"``.
``"illustration"``, ``"doujin"``, ``"favorite"``, ``"nuita"``.
You can use ``"all"`` instead of listing all values separately.

View File

@ -538,7 +538,7 @@ Consider all sites to be NSFW unless otherwise known.
<tr>
<td>nijie</td>
<td>https://nijie.info/</td>
<td>Doujin, Favorites, Illustrations, individual Images, User Profiles</td>
<td>Doujin, Favorites, Illustrations, individual Images, Nuita History, User Profiles</td>
<td>Required</td>
</tr>
<tr>

View File

@ -91,6 +91,10 @@ class NijieExtractor(AsynchronousMixin, Extractor):
"url": url,
})
@staticmethod
def _extract_user_name(page):
return text.unescape(text.extract(page, "<br />", "<")[0] or "")
def login(self):
"""Login and obtain session cookies"""
if not self._check_cookies(self.cookienames):
@ -119,9 +123,8 @@ class NijieExtractor(AsynchronousMixin, Extractor):
while True:
page = self.request(url, params=params, notfound="artist").text
if not self.user_name:
self.user_name = text.unescape(text.extract(
page, '<br />', '<')[0] or "")
if self.user_name is None:
self.user_name = self._extract_user_name(page)
yield from text.extract_iter(page, 'illust_id="', '"')
if '<a rel="next"' not in page:
@ -137,11 +140,12 @@ class NijieUserExtractor(NijieExtractor):
test = ("https://nijie.info/members.php?id=44",)
def items(self):
base = "{}/{{}}.php?id={}".format(self.root, self.user_id)
fmt = "{}/{{}}.php?id={}".format(self.root, self.user_id).format
return self._dispatch_extractors((
(NijieIllustrationExtractor, base.format("members_illust")),
(NijieDoujinExtractor , base.format("members_dojin")),
(NijieFavoriteExtractor , base.format("user_like_illust_view")),
(NijieIllustrationExtractor, fmt("members_illust")),
(NijieDoujinExtractor , fmt("members_dojin")),
(NijieFavoriteExtractor , fmt("user_like_illust_view")),
(NijieNuitaExtractor , fmt("history_nuita")),
), ("illustration", "doujin"))
@ -217,6 +221,36 @@ class NijieFavoriteExtractor(NijieExtractor):
return data
class NijieNuitaExtractor(NijieExtractor):
"""Extractor for a nijie user's 抜いた list"""
subcategory = "nuita"
directory_fmt = ("{category}", "nuita", "{user_id}")
archive_fmt = "n_{user_id}_{image_id}_{num}"
pattern = BASE_PATTERN + r"/history_nuita\.php\?id=(\d+)"
test = ("https://nijie.info/history_nuita.php?id=728995", {
"range": "1-10",
"count": 10,
"keyword": {
"user_id" : 728995,
"user_name": "",
},
})
def image_ids(self):
return self._pagination("history_nuita")
def _extract_data(self, page):
data = NijieExtractor._extract_data(page)
data["user_id"] = self.user_id
data["user_name"] = self.user_name
return data
@staticmethod
def _extract_user_name(page):
return text.unescape(text.extract(
page, "<title>", "さんの抜いた")[0] or "")
class NijieImageExtractor(NijieExtractor):
"""Extractor for a work/image from nijie.info"""
subcategory = "image"

View File

@ -183,6 +183,9 @@ SUBCATEGORY_MAP = {
"mangadex": {
"feed" : "Followed Feed",
},
"nijie": {
"nuita" : "Nuita History",
},
"pinterest": {
"board": "",
"pinit": "pin.it Links",