1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
# -*- coding: utf-8 -*-
# Copyright 2018-2023 Mike Fährmann
#
# 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://piczel.tv/"""
from .common import Extractor, Message
from .. import text
class PiczelExtractor(Extractor):
"""Base class for piczel extractors"""
category = "piczel"
directory_fmt = ("{category}", "{user[username]}")
filename_fmt = "{category}_{id}_{title}_{num:>02}.{extension}"
archive_fmt = "{id}_{num}"
root = "https://piczel.tv"
root_api = root
def items(self):
for post in self.posts():
post["tags"] = [t["title"] for t in post["tags"] if t["title"]]
post["date"] = text.parse_datetime(
post["created_at"], "%Y-%m-%dT%H:%M:%S.%f%z")
if post["multi"]:
images = post["images"]
del post["images"]
yield Message.Directory, post
for post["num"], image in enumerate(images):
if "id" in image:
del image["id"]
post.update(image)
url = post["image"]["url"]
yield Message.Url, url, text.nameext_from_url(url, post)
else:
yield Message.Directory, post
post["num"] = 0
url = post["image"]["url"]
yield Message.Url, url, text.nameext_from_url(url, post)
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,
}
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
class PiczelUserExtractor(PiczelExtractor):
"""Extractor for all images from a user's gallery"""
subcategory = "user"
pattern = r"(?:https?://)?(?:www\.)?piczel\.tv/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)
return self._pagination(url)
class PiczelFolderExtractor(PiczelExtractor):
"""Extractor for images inside a user's folder"""
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+)")
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))
class PiczelImageExtractor(PiczelExtractor):
"""Extractor for individual images"""
subcategory = "image"
pattern = r"(?:https?://)?(?:www\.)?piczel\.tv/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)
return (self.request(url).json(),)
|
