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

[piczel] fix extraction (#6735)

Browse Source 
- fix pagination
- update API endpoints
- provide 'count' metadata field
- use BASE_PATTERN and self.groups[…]
This commit is contained in:
Mike Fährmann
2024-12-27 15:08:08 +01:00
parent 167a726972
commit bc7e95684d
2 changed files with 86 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
gallery_dl/extractor/piczel.py
View File

@@ -11,6 +11,8 @@
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:www\.)?piczel\.tv"
class PiczelExtractor(Extractor):
"""Base class for piczel extractors"""
@@ -30,6 +32,7 @@ class PiczelExtractor(Extractor):
if post["multi"]:
images = post["images"]
del post["images"]
post["count"] = len(images)
yield Message.Directory, post
for post["num"], image in enumerate(images):
if "id" in image:
@@ -39,6 +42,7 @@ class PiczelExtractor(Extractor):
yield Message.Url, url, text.nameext_from_url(url, post)
else:
post["count"] = 1
yield Message.Directory, post
post["num"] = 0
url = post["image"]["url"]
@@ -47,35 +51,27 @@ class PiczelExtractor(Extractor):
def posts(self):
"""Return an iterable with all relevant post objects"""
def _pagination(self, url, folder_id=None):
params = {
"from_id" : None,
"folder_id": folder_id,
}
def _pagination(self, url, pnum=1):
params = {"page": pnum}
while True:
data = self.request(url, params=params).json()
if not data:
return
params["from_id"] = data[-1]["id"]
for post in data:
if not folder_id or folder_id == post["folder_id"]:
yield post
yield from data["data"]
params["page"] = data["meta"]["next_page"]
if not params["page"]:
return
class PiczelUserExtractor(PiczelExtractor):
"""Extractor for all images from a user's gallery"""
subcategory = "user"
pattern = r"(?:https?://)?(?:www\.)?piczel\.tv/gallery/([^/?#]+)/?$"
pattern = BASE_PATTERN + r"/gallery/([^/?#]+)/?$"
example = "https://piczel.tv/gallery/USER"
def __init__(self, match):
PiczelExtractor.__init__(self, match)
self.user = match.group(1)
def posts(self):
url = "{}/api/users/{}/gallery".format(self.root_api, self.user)
url = "{}/api/users/{}/gallery".format(self.root_api, self.groups[0])
return self._pagination(url)
@@ -84,29 +80,20 @@ class PiczelFolderExtractor(PiczelExtractor):
subcategory = "folder"
directory_fmt = ("{category}", "{user[username]}", "{folder[name]}")
archive_fmt = "f{folder[id]}_{id}_{num}"
pattern = (r"(?:https?://)?(?:www\.)?piczel\.tv"
r"/gallery/(?!image)([^/?#]+)/(\d+)")
pattern = BASE_PATTERN + r"/gallery/(?!image/)[^/?#]+/(\d+)"
example = "https://piczel.tv/gallery/USER/12345"
def __init__(self, match):
PiczelExtractor.__init__(self, match)
self.user, self.folder_id = match.groups()
def posts(self):
url = "{}/api/users/{}/gallery".format(self.root_api, self.user)
return self._pagination(url, int(self.folder_id))
url = "{}/api/gallery/folder/{}".format(self.root_api, self.groups[0])
return self._pagination(url)
class PiczelImageExtractor(PiczelExtractor):
"""Extractor for individual images"""
subcategory = "image"
pattern = r"(?:https?://)?(?:www\.)?piczel\.tv/gallery/image/(\d+)"
pattern = BASE_PATTERN + r"/gallery/image/(\d+)"
example = "https://piczel.tv/gallery/image/12345"
def __init__(self, match):
PiczelExtractor.__init__(self, match)
self.image_id = match.group(1)
def posts(self):
url = "{}/api/gallery/{}".format(self.root_api, self.image_id)
url = "{}/api/gallery/{}".format(self.root_api, self.groups[0])
return (self.request(url).json(),)