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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
|
# -*- coding: utf-8 -*-
# Copyright 2020 Leonid "Bepis" Pavel
# Copyright 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://imgchest.com/"""
from .common import GalleryExtractor
from .. import text, exception
class ImagechestGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries from imgchest.com"""
category = "imagechest"
root = "https://imgchest.com"
pattern = r"(?:https?://)?(?:www\.)?imgchest\.com/p/([A-Za-z0-9]{11})"
example = "https://imgchest.com/p/abcdefghijk"
def __init__(self, match):
self.gallery_id = match.group(1)
url = self.root + "/p/" + self.gallery_id
GalleryExtractor.__init__(self, match, url)
def _init(self):
access_token = self.config("access-token")
if access_token:
self.api = ImagechestAPI(self, access_token)
self.gallery_url = None
self.metadata = self._metadata_api
self.images = self._images_api
def metadata(self, page):
if "Sorry, but the page you requested could not be found." in page:
raise exception.NotFoundError("gallery")
return {
"gallery_id": self.gallery_id,
"title": text.unescape(text.extr(
page, 'property="og:title" content="', '"').strip())
}
def images(self, page):
if ' load-all">' in page:
url = "{}/p/{}/loadAll".format(self.root, self.gallery_id)
headers = {
"X-Requested-With": "XMLHttpRequest",
"Origin" : self.root,
"Referer" : self.gallery_url,
}
csrf_token = text.extr(page, 'name="csrf-token" content="', '"')
data = {"_token": csrf_token}
page += self.request(
url, method="POST", headers=headers, data=data).text
return [
(url, None)
for url in text.extract_iter(page, 'data-url="', '"')
]
def _metadata_api(self, page):
post = self.api.post(self.gallery_id)
post["date"] = text.parse_datetime(
post["created"], "%Y-%m-%dT%H:%M:%S.%fZ")
for img in post["images"]:
img["date"] = text.parse_datetime(
img["created"], "%Y-%m-%dT%H:%M:%S.%fZ")
post["gallery_id"] = self.gallery_id
post.pop("image_count", None)
self._image_list = post.pop("images")
return post
def _images_api(self, page):
return [
(img["link"], img)
for img in self._image_list
]
class ImagechestAPI():
"""Interface for the Image Chest API
https://imgchest.com/docs/api/1.0/general/overview
"""
root = "https://api.imgchest.com"
def __init__(self, extractor, access_token):
self.extractor = extractor
self.headers = {"Authorization": "Bearer " + access_token}
def file(self, file_id):
endpoint = "/v1/file/" + file_id
return self._call(endpoint)
def post(self, post_id):
endpoint = "/v1/post/" + post_id
return self._call(endpoint)
def user(self, username):
endpoint = "/v1/user/" + username
return self._call(endpoint)
def _call(self, endpoint):
url = self.root + endpoint
while True:
response = self.extractor.request(
url, headers=self.headers, fatal=None, allow_redirects=False)
if response.status_code < 300:
return response.json()["data"]
elif response.status_code < 400:
raise exception.AuthenticationError("Invalid API access token")
elif response.status_code == 429:
self.extractor.wait(seconds=600)
else:
self.extractor.log.debug(response.text)
raise exception.StopExtraction("API request failed")
|
