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

[cfake] add support (#707 #6021 #8549 #8430)

Browse Source 
* Create cfake.py
* Update __init__.py
* Create cfake.py tests
* update
    - simplify & combine code
    - adjust 'pattern': use '[^/?#]', match lines and groups
    - generalize example URLs
    - update default filenames
* update docs/supportedsites
* update test results

---------

Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>
This commit is contained in:
SpiffyChatterbox
2025-11-15 14:55:00 -05:00
committed by GitHub
parent 2578f7b5c1
commit f6e67116f2
5 changed files with 298 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/supportedsites.md
View File

@@ -181,6 +181,12 @@ Consider all listed sites to potentially be NSFW.
<td>Albums, Files</td>
<td></td>
</tr>
<tr id="cfake" title="cfake">
<td>Celebrity Fakes</td>
<td>https://cfake.com/</td>
<td>Categories, Celebrities, Countries, Created</td>
<td></td>
</tr>
<tr id="naver-chzzk" title="naver-chzzk">
<td>CHZZK</td>
<td>https://chzzk.naver.com/</td>

1
gallery_dl/extractor/__init__.py
View File

@@ -40,6 +40,7 @@ modules = [
"booth",
"bunkr",
"catbox",
"cfake",
"chevereto",
"cien",
"civitai",

149
gallery_dl/extractor/cfake.py Normal file
View File

@@ -0,0 +1,149 @@
# -*- coding: utf-8 -*-
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://cfake.com/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:www\.)?cfake\.com"
class CfakeExtractor(Extractor):
"""Base class for cfake extractors"""
category = "cfake"
root = "https://cfake.com"
directory_fmt = ("{category}", "{type}", "{type_name} ({type_id})")
filename_fmt = "{category}_{type_name}_{id}.{extension}"
archive_fmt = "{id}"
def items(self):
type, type_name, type_id, sub_id, pnum = self.groups
if type.endswith("ies"):
type = type[:-3] + "y"
kwdict = self.kwdict
kwdict["type"] = type
kwdict["type_id"] = text.parse_int(type_id)
kwdict["type_name"] = text.unquote(type_name).replace("_", " ")
kwdict["sub_id"] = text.parse_int(sub_id)
kwdict["page"] = pnum = text.parse_int(pnum, 1)
yield Message.Directory, {}
base = f"{self.root}/images/{type}/{type_name}/{type_id}"
if sub_id:
base = f"{base}/{sub_id}"
while True:
url = base if pnum < 2 else f"{base}/p{pnum}"
page = self.request(url).text
# Extract and yield images
num = 0
for image in self._extract_images(page):
num += 1
image["num"] = num + (pnum - 1) * 50
url = image["url"]
yield Message.Url, url, text.nameext_from_url(url, image)
# Check for next page
if not num or not (pnum := self._check_pagination(page)):
return
kwdict["page"] = pnum
def _extract_images(self, page):
"""Extract image URLs and metadata from a gallery page"""
for item in text.extract_iter(
page, '<a href="javascript:showimage(', '</div></div>'):
# Extract image path from showimage call
# Format: 'big.php?show=2025/filename.jpg&id_picture=...
show_param = text.extr(item, "show=", "&")
if not show_param:
continue
# Extract metadata
picture_id = text.extr(item, "id_picture=", "&")
name_param = text.extr(item, "p_name=", "'")
# Extract date
date = text.extr(item, 'id="date_vignette">', '</div>')
# Extract rating
rating_text = text.extr(item, 'class="current-rating"', '</li>')
rating = text.extr(rating_text, 'width:', 'px')
# Convert thumbnail path to full image path
# show_param is like "2025/filename.jpg"
image_url = f"{self.root}/medias/photos/{show_param}"
yield {
"url": image_url,
"id": text.parse_int(picture_id) if picture_id else 0,
"name": text.unescape(name_param) if name_param else "",
"date": date,
"rating": rating,
}
def _check_pagination(self, page):
"""Check if there are more pages and return next page number"""
# Look for current page indicator
# Format: id="num_page_current" ><a href=".../ p1">1</a>
current_section = text.extr(
page, 'id="num_page_current"', '</div>')
if not current_section:
return None
# Extract current page number from the link text
current_page_str = text.extr(current_section, '">', '</a>')
if not current_page_str:
return None
current_page = text.parse_int(current_page_str)
if not current_page:
return None
next_page = current_page + 1
# Check if next page link exists anywhere in the page
# Look for href="/images/.../pN" pattern
if f'/p{next_page}"' in page or f'/p{next_page} ' in page:
return next_page
return None
class CfakeCelebrityExtractor(CfakeExtractor):
"""Extractor for celebrity image galleries from cfake.com"""
subcategory = "celebrity"
pattern = (BASE_PATTERN + r"/images/(celebrity)"
r"/([^/?#]+)/(\d+)()(?:/p(\d+))?")
example = "https://cfake.com/images/celebrity/NAME/123"
class CfakeCategoryExtractor(CfakeExtractor):
"""Extractor for category image galleries from cfake.com"""
subcategory = "category"
pattern = (BASE_PATTERN + r"/images/(categories)"
r"/([^/?#]+)/(\d+)()(?:/p(\d+))?")
example = "https://cfake.com/images/categories/NAME/123"
class CfakeCreatedExtractor(CfakeExtractor):
"""Extractor for 'created' image galleries from cfake.com"""
subcategory = "created"
pattern = (BASE_PATTERN + r"/images/(created)"
r"/([^/?#]+)/(\d+)/(\d+)(?:/p(\d+))?")
example = "https://cfake.com/images/created/NAME/12345/123"
class CfakeCountryExtractor(CfakeExtractor):
"""Extractor for country image galleries from cfake.com"""
subcategory = "country"
pattern = (BASE_PATTERN + r"/images/(country)"
r"/([^/?#]+)/(\d+)/(\d+)(?:/p(\d+))?")
example = "https://cfake.com/images/country/NAME/12345/123"

4
scripts/supportedsites.py
View File

@@ -40,6 +40,7 @@ CATEGORY_MAP = {
"batoto" : "BATO.TO",
"bbc" : "BBC",
"booth" : "BOOTH",
"cfake" : "Celebrity Fakes",
"cien" : "Ci-en",
"cohost" : "cohost!",
"comicvine" : "Comic Vine",
@@ -250,6 +251,9 @@ SUBCATEGORY_MAP = {
"boosty": {
"feed": "Subscriptions Feed",
},
"cfake": {
"created": "Created",
},
"civitai": {
"models": "Model Listings",
"images": "Image Listings",

138
test/results/cfake.py Normal file
View File

@@ -0,0 +1,138 @@
# -*- coding: utf-8 -*-
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
from gallery_dl.extractor import cfake
__tests__ = (
{
"#url" : "https://cfake.com/images/celebrity/Kaley_Cuoco/631/",
"#category": ("", "cfake", "celebrity"),
"#class" : cfake.CfakeCelebrityExtractor,
"#pattern" : r"https://cfake\.com/medias/photos/\d{4}/[0-9a-f]+_cfake\.jpg",
"#range" : "1-20",
"#count" : 20,
"type" : "celebrity",
"type_id" : 631,
"type_name" : "Kaley Cuoco",
"page" : 1,
"id" : int,
"num" : int,
"date" : str,
"rating" : str,
},
{
"#url" : "https://cfake.com/images/celebrity/Kaley_Cuoco/631/p2",
"#comment" : "pagination test - page 2",
"#category": ("", "cfake", "celebrity"),
"#class" : cfake.CfakeCelebrityExtractor,
"#pattern" : r"https://cfake\.com/medias/photos/\d{4}/[0-9a-f]+_cfake\.jpg",
"#range" : "1-5",
"type" : "celebrity",
"type_id" : 631,
"type_name" : "Kaley Cuoco",
"page" : 2,
},
{
"#url" : "https://www.cfake.com/images/celebrity/Chloe_Grace_Moretz/6575/",
"#category": ("", "cfake", "celebrity"),
"#class" : cfake.CfakeCelebrityExtractor,
},
{
"#url" : "https://cfake.com/images/categories/Facial/25/",
"#category": ("", "cfake", "category"),
"#class" : cfake.CfakeCategoryExtractor,
"#pattern" : r"https://cfake\.com/medias/photos/\d{4}/[0-9a-f]+_cfake\.jpg",
"#range" : "1-10",
"#count" : 10,
"type" : "category",
"type_id" : 25,
"type_name" : "Facial",
"page" : 1,
"id" : int,
"num" : int,
},
{
"#url" : "https://cfake.com/images/categories/Big_Tits/35/",
"#category": ("", "cfake", "category"),
"#class" : cfake.CfakeCategoryExtractor,
},
{
"#url" : "https://cfake.com/images/categories/Big_Tits/35/p2",
"#comment" : "category pagination test",
"#category": ("", "cfake", "category"),
"#class" : cfake.CfakeCategoryExtractor,
},
{
"#url" : "https://cfake.com/images/created/Spice_Girls_%28band%29/72/4",
"#category": ("", "cfake", "created"),
"#class" : cfake.CfakeCreatedExtractor,
"#pattern" : r"https://cfake\.com/medias/photos/\d{4}/[0-9a-f]+_cfake\.jpg",
"#range" : "1-10",
"#count" : 10,
"type" : "created",
"type_id" : 72,
"type_name" : "Spice Girls (band)",
"sub_id" : 4,
"page" : 1,
"id" : int,
"num" : int,
},
{
"#url" : "https://cfake.com/images/created/Brooklyn_Nine-Nine/4142/4",
"#category": ("", "cfake", "created"),
"#class" : cfake.CfakeCreatedExtractor,
},
{
"#url" : "https://cfake.com/images/created/Brooklyn_Nine-Nine/4142/4/p2",
"#comment" : "created pagination test",
"#category": ("", "cfake", "created"),
"#class" : cfake.CfakeCreatedExtractor,
},
{
"#url" : "https://cfake.com/images/country/Australia/12/5",
"#category": ("", "cfake", "country"),
"#class" : cfake.CfakeCountryExtractor,
"#pattern" : r"https://cfake\.com/medias/photos/\d{4}/[0-9a-f]+_cfake\.jpg",
"#range" : "1-10",
"#count" : 10,
"type" : "country",
"type_id" : 12,
"type_name" : "Australia",
"sub_id" : 5,
"page" : 1,
"id" : int,
"num" : int,
},
{
"#url" : "https://cfake.com/images/country/Mexico/139/5",
"#category": ("", "cfake", "country"),
"#class" : cfake.CfakeCountryExtractor,
},
{
"#url" : "https://cfake.com/images/country/Mexico/139/5/p3",
"#comment" : "country pagination test",
"#category": ("", "cfake", "country"),
"#class" : cfake.CfakeCountryExtractor,
},
)