github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[chevereto] combine 'image' & 'video' extractors into a 'file' extractor

Browse Source
This commit is contained in:
Mike Fährmann
2026-02-14 19:21:35 +01:00
parent 1c8d07885c
commit 41998cbb8f
5 changed files with 106 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/supportedsites.md
View File

@@ -1360,19 +1360,19 @@ Consider all listed sites to potentially be NSFW.
<tr id="jpgfish" title="jpgfish">
<td>JPG Fish</td>
<td>https://jpg7.cr/</td>
<td>Albums, Categories, individual Images, User Profiles, Videos</td>
<td>Albums, Categories, Files, User Profiles</td>
<td></td>
</tr>
<tr id="imagepond" title="imagepond">
<td>ImagePond</td>
<td>https://imagepond.net/</td>
<td>Albums, Categories, individual Images, User Profiles, Videos</td>
<td>Albums, Categories, Files, User Profiles</td>
<td></td>
</tr>
<tr id="imglike" title="imglike">
<td>Nude Celeb</td>
<td>https://imglike.com/</td>
<td>Albums, Categories, individual Images, User Profiles, Videos</td>
<td>Albums, Categories, Files, User Profiles</td>
<td></td>
</tr>

143
gallery_dl/extractor/chevereto.py
View File

@@ -98,10 +98,10 @@ BASE_PATTERN = CheveretoExtractor.update({
})
class CheveretoImageExtractor(CheveretoExtractor):
"""Extractor for chevereto images"""
subcategory = "image"
pattern = BASE_PATTERN + r"(/im(?:g|age)/[^/?#]+)"
class CheveretoFileExtractor(CheveretoExtractor):
"""Extractor for chevereto files"""
subcategory = "file"
pattern = BASE_PATTERN + r"(/(?:im(?:g|age)|video)/[^/?#]+)"
example = "https://jpg7.cr/img/TITLE.ID"
def items(self):
@@ -109,76 +109,67 @@ class CheveretoImageExtractor(CheveretoExtractor):
page = self.request(url).text
extr = text.extract_from(page)
type = text.extr(page, 'property="og:type" content="', '"')
title = extr('property="og:title" content="', '"')
url = (extr('<meta property="og:image" content="', '"') or
extr('url: "', '"'))
if not url or url.endswith("/loading.svg"):
pos = page.find(" download=")
url = text.rextr(page, 'href="', '"', pos)
if not url.startswith("https://"):
url = util.decrypt_xor(
url, b"seltilovessimpcity@simpcityhatesscrapers",
fromhex=True)
album_url, _, album_name = extr("Added to <a", "</a>").rpartition(">")
file = {
"id" : self.path.rpartition("/")[2].rpartition(".")[2],
"url" : url,
"title": text.unescape(title),
"album": text.remove_html(album_name),
"date" : self.parse_datetime_iso(extr('<span title="', '"')),
"user" : extr('username: "', '"'),
}
if type == "video":
file = {
"id" : self.path.rpartition(".")[2],
"type" : "video",
"title" : text.unescape(extr(
'property="og:title" content="', '"')),
"thumbnail": extr(
'property="og:image" content="', '"'),
"url" : extr(
'property="og:video" content="', '"'),
"width" : text.parse_int(extr(
'property="video:width" content="', '"')),
"height" : text.parse_int(extr(
'property="video:height" content="', '"')),
"duration" : extr(
'class="far fa-clock"></i>', "—"),
"album" : extr(
"Added to <a", "</a>"),
"date" : self.parse_datetime_iso(extr(
'<span title="', '"')),
"user" : extr('username: "', '"'),
}
file["album_slug"], _, file["album_id"] = text.rextr(
album_url, "/", '"').rpartition(".")
album_url, _, album_name = file["album"].rpartition(">")
file["album"] = text.remove_html(album_name)
file["album_slug"], _, file["album_id"] = text.rextr(
album_url, "/", '"').rpartition(".")
text.nameext_from_url(file["url"], file)
yield Message.Directory, "", file
yield Message.Url, file["url"], file
try:
min, _, sec = file["duration"].partition(":")
file["duration"] = int(min) * 60 + int(sec)
except Exception:
pass
else:
url = (extr('<meta property="og:image" content="', '"') or
extr('url: "', '"'))
if not url or url.endswith("/loading.svg"):
pos = page.find(" download=")
url = text.rextr(page, 'href="', '"', pos)
if not url.startswith("https://"):
url = util.decrypt_xor(
url, b"seltilovessimpcity@simpcityhatesscrapers",
fromhex=True)
album_url, _, album_name = extr(
"Added to <a", "</a>").rpartition(">")
file = {
"id" : self.path.rpartition("/")[2].rpartition(".")[2],
"url" : url,
"type" : type,
"title": text.unescape(title),
"album": text.remove_html(album_name),
"date" : self.parse_datetime_iso(extr('<span title="', '"')),
"user" : extr('username: "', '"'),
}
class CheveretoVideoExtractor(CheveretoExtractor):
"""Extractor for chevereto videos"""
subcategory = "video"
pattern = BASE_PATTERN + r"(/video/[^/?#]+)"
example = "https://imagepond.net/video/TITLE.ID"
def items(self):
url = self.root + self.path
page = self.request(url).text
extr = text.extract_from(page)
file = {
"id" : self.path.rpartition(".")[2],
"title" : text.unescape(extr(
'property="og:title" content="', '"')),
"thumbnail": extr(
'property="og:image" content="', '"'),
"url" : extr(
'property="og:video" content="', '"'),
"width" : text.parse_int(extr(
'property="video:width" content="', '"')),
"height" : text.parse_int(extr(
'property="video:height" content="', '"')),
"duration" : extr(
'class="far fa-clock"></i>', "—"),
"album" : extr(
"Added to <a", "</a>"),
"date" : self.parse_datetime_iso(extr('<span title="', '"')),
"user" : extr('username: "', '"'),
}
album_url, _, album_name = file["album"].rpartition(">")
file["album"] = text.remove_html(album_name)
file["album_slug"], _, file["album_id"] = text.rextr(
album_url, "/", '"').rpartition(".")
try:
min, _, sec = file["duration"].partition(":")
file["duration"] = int(min) * 60 + int(sec)
except Exception:
pass
file["album_slug"], _, file["album_id"] = text.rextr(
album_url, "/", '"').rpartition(".")
text.nameext_from_url(file["url"], file)
yield Message.Directory, "", file
@@ -193,19 +184,16 @@ class CheveretoAlbumExtractor(CheveretoExtractor):
def items(self):
url = self.root + self.path
data_image = {"_extractor": CheveretoImageExtractor}
data_video = {"_extractor": CheveretoVideoExtractor}
data = {"_extractor": CheveretoFileExtractor}
if self.path.endswith("/sub"):
albums = self._pagination(url)
else:
albums = (url,)
kwdict = self.kwdict
for album in albums:
for kwdict["num"], item_url in enumerate(self._pagination(
for self.kwdict["num"], item_url in enumerate(self._pagination(
album, self._extract_metadata_album), 1):
data = data_video if "/video/" in item_url else data_image
yield Message.Queue, item_url, data
def _extract_metadata_album(self, page):
@@ -229,7 +217,7 @@ class CheveretoCategoryExtractor(CheveretoExtractor):
example = "https://imglike.com/category/TITLE"
def items(self):
data = {"_extractor": CheveretoImageExtractor}
data = {"_extractor": CheveretoFileExtractor}
for image in self._pagination(self.root + self.path):
yield Message.Queue, image, data
@@ -241,11 +229,8 @@ class CheveretoUserExtractor(CheveretoExtractor):
example = "https://jpg7.cr/USER"
def items(self):
data_image = {"_extractor": CheveretoImageExtractor}
data_video = {"_extractor": CheveretoVideoExtractor}
data_file = {"_extractor": CheveretoFileExtractor}
data_album = {"_extractor": CheveretoAlbumExtractor}
for url in self._pagination(self.root + self.path):
data = (data_album if "/album/" in url else
data_video if "/video/" in url else
data_image)
data = data_album if "/album/" in url else data_file
yield Message.Queue, url, data

15
test/results/imagepond.py
View File

@@ -10,8 +10,8 @@ from gallery_dl.extractor import chevereto
__tests__ = (
{
"#url" : "https://imagepond.net/image/IMG-20250217-160622.TJNphg",
"#category": ("chevereto", "imagepond", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "imagepond", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://media.imagepond.net/media/IMG_20250217_1606226b345a5dbd0e8971.jpg",
"#sha1_content": "ec7fac6b427f7af01038619208cd69478e91ddef",
@@ -20,20 +20,22 @@ __tests__ = (
"extension": "jpg",
"filename" : "IMG_20250217_1606226b345a5dbd0e8971",
"id" : "TJNphg",
"title" : "IMG_20250217_160622.jpg",
"type" : "image",
"url" : "https://media.imagepond.net/media/IMG_20250217_1606226b345a5dbd0e8971.jpg",
"user" : "dariusbbb24",
},
{
"#url" : "https://www.imagepond.net/image/IMG-20250217-160622.TJNphg",
"#category": ("chevereto", "imagepond", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "imagepond", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://imagepond.net/video/1000423939.zb8Fxy",
"#category": ("chevereto", "imagepond", "video"),
"#class" : chevereto.CheveretoVideoExtractor,
"#category": ("chevereto", "imagepond", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://media.imagepond.net/media/100042393993a6bfa75fc505e9.mp4",
"album" : "",
@@ -47,6 +49,7 @@ __tests__ = (
"id" : "zb8Fxy",
"thumbnail": "https://media.imagepond.net/media/100042393993a6bfa75fc505e9.fr.jpeg",
"title" : "1000423939",
"type" : "video",
"url" : "https://media.imagepond.net/media/100042393993a6bfa75fc505e9.mp4",
"user" : "christiankita",
"width" : 720,

10
test/results/imglike.py
View File

@@ -10,8 +10,8 @@ from gallery_dl.extractor import chevereto
__tests__ = (
{
"#url" : "https://imglike.com/image/EMT-Skills-Verification-by-EMSA.Lx6dT",
"#category": ("chevereto", "imglike", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "imglike", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://imglike.com/images/2022/08/12/EMT-Skills-Verification-by-EMSA.gif",
"album" : "",
@@ -25,8 +25,8 @@ __tests__ = (
{
"#url" : "https://www.imglike.com/image/EMT-Skills-Verification-by-EMSA.Lx6dT",
"#category": ("chevereto", "imglike", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "imglike", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
@@ -59,7 +59,7 @@ __tests__ = (
"#url" : "https://imglike.com/category/Bursting-boobs",
"#category": ("chevereto", "imglike", "category"),
"#class" : chevereto.CheveretoCategoryExtractor,
"#pattern" : chevereto.CheveretoImageExtractor.pattern,
"#pattern" : chevereto.CheveretoFileExtractor.pattern,
"#range" : "1-100",
"#count" : 100,
},

49
test/results/jpgfish.py
View File

@@ -10,8 +10,8 @@ from gallery_dl.extractor import chevereto
__tests__ = (
{
"#url" : "https://jpg7.cr/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://simp3.selti-delivery.ru/images/funnymeme.jpg",
"#sha1_content": "098e5e9b17ad634358426e0ffd1c93871474d13c",
@@ -23,14 +23,15 @@ __tests__ = (
"filename" : "funnymeme",
"id" : "LecXGS",
"title" : "funnymeme",
"type" : "article",
"url" : "https://simp3.selti-delivery.ru/images/funnymeme.jpg",
"user" : "exearco",
},
{
"#url" : "https://jpg4.su/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://simp3.selti-delivery.ru/images/funnymeme.jpg",
"album" : "",
@@ -45,8 +46,8 @@ __tests__ = (
{
"#url" : "https://jpg6.su/img/LecXGS/",
"#comment" : "image ID without name (#8307)",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://simp3.selti-delivery.ru/images/funnymeme.jpg",
"#sha1_content": "098e5e9b17ad634358426e0ffd1c93871474d13c",
@@ -61,8 +62,8 @@ __tests__ = (
{
"#url" : "https://jpg.church/img/auCruA",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://simp2.selti-delivery.ru/hannahowo_00457.jpg",
"album" : "401-500",
@@ -74,50 +75,50 @@ __tests__ = (
{
"#url" : "https://jpg1.su/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpeg.pet/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpg.pet/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpg.fishing/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpg.fish/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpg.church/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://www.jpg6.su/img/funnymeme.LecXGS",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
},
{
"#url" : "https://jpg6.su/img/test.NLqFQHc",
"#category": ("chevereto", "jpgfish", "image"),
"#class" : chevereto.CheveretoImageExtractor,
"#category": ("chevereto", "jpgfish", "file"),
"#class" : chevereto.CheveretoFileExtractor,
"#results" : "https://simp6.selti-delivery.ru/images3/test--2219f2531862b749d5.png",
"album" : "",