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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
|
# -*- coding: utf-8 -*-
# Copyright 2020-2023 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://www.subscribestar.com/"""
from .common import Extractor, Message
from .. import text, util, exception
from ..cache import cache
import re
BASE_PATTERN = r"(?:https?://)?(?:www\.)?subscribestar\.(com|adult)"
class SubscribestarExtractor(Extractor):
"""Base class for subscribestar extractors"""
category = "subscribestar"
root = "https://www.subscribestar.com"
directory_fmt = ("{category}", "{author_name}")
filename_fmt = "{post_id}_{id}.{extension}"
archive_fmt = "{id}"
cookies_domain = ".subscribestar.com"
cookies_names = ("_personalization_id",)
_warning = True
def __init__(self, match):
tld, self.item = match.groups()
if tld == "adult":
self.root = "https://subscribestar.adult"
self.cookies_domain = ".subscribestar.adult"
self.subcategory += "-adult"
Extractor.__init__(self, match)
def items(self):
self.login()
for post_html in self.posts():
media = self._media_from_post(post_html)
data = self._data_from_post(post_html)
content = data["content"]
if "<html><body>" in content:
data["content"] = content = text.extr(
content, "<body>", "</body>")
data["title"] = text.unescape(
text.rextract(content, "<h1>", "</h1>")[0] or "")
yield Message.Directory, data
for num, item in enumerate(media, 1):
item.update(data)
item["num"] = num
text.nameext_from_url(item.get("name") or item["url"], item)
if item["url"][0] == "/":
item["url"] = self.root + item["url"]
yield Message.Url, item["url"], item
def posts(self):
"""Yield HTML content of all relevant posts"""
def request(self, url, **kwargs):
while True:
response = Extractor.request(self, url, **kwargs)
if response.history and (
"/verify_subscriber" in response.url or
"/age_confirmation_warning" in response.url):
raise exception.StopExtraction(
"HTTP redirect to %s", response.url)
content = response.content
if len(content) < 250 and b">redirected<" in content:
url = text.unescape(text.extr(
content, b'href="', b'"').decode())
self.log.debug("HTML redirect message for %s", url)
continue
return response
def login(self):
if self.cookies_check(self.cookies_names):
return
username, password = self._get_auth_info()
if username:
self.cookies_update(self._login_impl(
(username, self.cookies_domain), password))
if self._warning:
if not username or not self.cookies_check(self.cookies_names):
self.log.warning("no '_personalization_id' cookie set")
SubscribestarExtractor._warning = False
@cache(maxage=28*86400, keyarg=1)
def _login_impl(self, username, password):
username = username[0]
self.log.info("Logging in as %s", username)
if self.root.endswith(".adult"):
self.cookies.set("18_plus_agreement_generic", "true",
domain=self.cookies_domain)
# load login page
url = self.root + "/login"
page = self.request(url).text
headers = {
"Accept": "*/*;q=0.5, text/javascript, application/javascript, "
"application/ecmascript, application/x-ecmascript",
"Referer": self.root + "/login",
"X-CSRF-Token": text.unescape(text.extr(
page, '<meta name="csrf-token" content="', '"')),
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"X-Requested-With": "XMLHttpRequest",
}
def check_errors(response):
errors = response.json().get("errors")
if errors:
self.log.debug(errors)
try:
msg = '"{}"'.format(errors.popitem()[1])
except Exception:
msg = None
raise exception.AuthenticationError(msg)
return response
# submit username / email
url = self.root + "/session.json"
data = {"email": username}
response = check_errors(self.request(
url, method="POST", headers=headers, data=data, fatal=False))
# submit password
url = self.root + "/session/password.json"
data = {"password": password}
response = check_errors(self.request(
url, method="POST", headers=headers, data=data, fatal=False))
# return cookies
return {
cookie.name: cookie.value
for cookie in response.cookies
}
def _media_from_post(self, html):
media = []
gallery = text.extr(html, 'data-gallery="', '"')
if gallery:
for item in util.json_loads(text.unescape(gallery)):
if "/previews" in item["url"]:
self._warn_preview()
else:
media.append(item)
attachments = text.extr(
html, 'class="uploads-docs"', 'class="post-edit_form"')
if attachments:
for att in re.split(
r'class="doc_preview[" ]', attachments)[1:]:
media.append({
"id" : text.parse_int(text.extr(
att, 'data-upload-id="', '"')),
"name": text.unescape(text.extr(
att, 'doc_preview-title">', '<')),
"url" : text.unescape(text.extr(att, 'href="', '"')),
"type": "attachment",
})
audios = text.extr(
html, 'class="uploads-audios"', 'class="post-edit_form"')
if audios:
for audio in re.split(
r'class="audio_preview-data[" ]', audios)[1:]:
media.append({
"id" : text.parse_int(text.extr(
audio, 'data-upload-id="', '"')),
"name": text.unescape(text.extr(
audio, 'audio_preview-title">', '<')),
"url" : text.unescape(text.extr(audio, 'src="', '"')),
"type": "audio",
})
return media
def _data_from_post(self, html):
extr = text.extract_from(html)
return {
"post_id" : text.parse_int(extr('data-id="', '"')),
"author_id" : text.parse_int(extr('data-user-id="', '"')),
"author_name": text.unescape(extr('href="/', '"')),
"author_nick": text.unescape(extr('>', '<')),
"date" : self._parse_datetime(extr(
'class="post-date">', '</').rpartition(">")[2]),
"content" : extr(
'<div class="post-content" data-role="post_content-text">',
'</div><div class="post-uploads for-youtube"').strip(),
"tags" : list(text.extract_iter(extr(
'<div class="post_tags for-post">',
'<div class="post-actions">'), '?tag=', '"')),
}
def _parse_datetime(self, dt):
if dt.startswith("Updated on "):
dt = dt[11:]
date = text.parse_datetime(dt, "%b %d, %Y %I:%M %p")
if date is dt:
date = text.parse_datetime(dt, "%B %d, %Y %I:%M %p")
return date
def _warn_preview(self):
self.log.warning("Preview image detected")
self._warn_preview = util.noop
class SubscribestarUserExtractor(SubscribestarExtractor):
"""Extractor for media from a subscribestar user"""
subcategory = "user"
pattern = BASE_PATTERN + r"/(?!posts/)([^/?#]+)"
example = "https://www.subscribestar.com/USER"
def posts(self):
needle_next_page = 'data-role="infinite_scroll-next_page" href="'
page = self.request("{}/{}".format(self.root, self.item)).text
while True:
posts = page.split('<div class="post ')[1:]
if not posts:
return
yield from posts
url = text.extr(posts[-1], needle_next_page, '"')
if not url:
return
page = self.request(self.root + text.unescape(url)).json()["html"]
class SubscribestarPostExtractor(SubscribestarExtractor):
"""Extractor for media from a single subscribestar post"""
subcategory = "post"
pattern = BASE_PATTERN + r"/posts/(\d+)"
example = "https://www.subscribestar.com/posts/12345"
def posts(self):
url = "{}/posts/{}".format(self.root, self.item)
return (self.request(url).text,)
def _data_from_post(self, html):
extr = text.extract_from(html)
return {
"post_id" : text.parse_int(extr('data-id="', '"')),
"date" : self._parse_datetime(extr(
'<div class="section-title_date">', '<')),
"content" : extr(
'<div class="post-content" data-role="post_content-text">',
'</div><div class="post-uploads for-youtube"').strip(),
"tags" : list(text.extract_iter(extr(
'<div class="post_tags for-post">',
'<div class="post-actions">'), '?tag=', '"')),
"author_name": text.unescape(extr(
'class="star_link" href="/', '"')),
"author_id" : text.parse_int(extr('data-user-id="', '"')),
"author_nick": text.unescape(extr('alt="', '"')),
}
|
