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
|
# -*- coding: utf-8 -*-
# Copyright 2025 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.bellazon.com/"""
from .common import Extractor, Message
from .. import text, exception
BASE_PATTERN = r"(?:https?://)?(?:www\.)?bellazon\.com/main"
class BellazonExtractor(Extractor):
"""Base class for bellazon extractors"""
category = "bellazon"
root = "https://www.bellazon.com/main"
directory_fmt = ("{category}", "{thread[section]}",
"{thread[title]} ({thread[id]})")
filename_fmt = "{post[id]}_{num:>02}_{id}_{filename}.{extension}"
archive_fmt = "{post[id]}/{id}_{filename}"
def items(self):
native = (f"{self.root}/", f"{self.root[6:]}/")
extract_urls = text.re(
r'(?s)<('
r'(?:video .*?<source src|a [^>]*?href)="([^"]+).*?</a>'
r'|img [^>]*?src="([^"]+)"[^>]*>'
r')'
).findall
if self.config("quoted", False):
strip_quoted = None
else:
strip_quoted = text.re(r"(?s)<blockquote .*?</blockquote>").sub
for post in self.posts():
if strip_quoted is None:
urls = extract_urls(post["content"])
else:
urls = extract_urls(strip_quoted("", post["content"]))
data = {"post": post}
post["count"] = data["count"] = len(urls)
yield Message.Directory, data
data["num"] = 0
for info, url, url_img in urls:
url = text.unescape(url or url_img)
if url.startswith(native):
if "/uploads/emoticons/" in url or "/profile/" in url:
continue
data["num"] += 1
if not (alt := text.extr(info, ' alt="', '"')) or (
alt.startswith("post-") and "_thumb." in alt):
name = url
else:
name = text.unescape(alt)
dc = text.nameext_from_url(name, data.copy())
dc["id"] = text.extr(info, 'data-fileid="', '"')
if ext := text.extr(info, 'data-fileext="', '"'):
dc["extension"] = ext
elif "/core/interface/file/attachment.php" in url:
if not dc["id"]:
dc["id"] = url.rpartition("?id=")[2]
if name := text.extr(info, ">", "<").strip():
text.nameext_from_url(name, dc)
if url[0] == "/":
url = f"https:{url}"
yield Message.Url, url, dc
else:
yield Message.Queue, url, data
def _pagination(self, base, pnum=None):
base = f"{self.root}{base}"
if pnum is None:
url = f"{base}/"
pnum = 1
else:
url = f"{base}/page/{pnum}/"
pnum = None
while True:
page = self.request(url).text
yield page
if pnum is None or ' rel="next" ' not in page or text.extr(
page, " rel=\"next\" data-page='", "'") == str(pnum):
return
pnum += 1
url = f"{base}/page/{pnum}/"
def _pagination_reverse(self, base, pnum=None):
base = f"{self.root}{base}"
url = f"{base}/page/9999/" # force redirect to highest page number
with self.request(url) as response:
parts = response.url.rsplit("/", 3)
pnum = text.parse_int(parts[2]) if parts[1] == "page" else 1
page = response.text
while True:
yield page
pnum -= 1
if pnum > 1:
url = f"{base}/page/{pnum}/"
elif pnum == 1:
url = f"{base}/"
else:
return
page = self.request(url).text
def _parse_thread(self, page):
schema = self._extract_jsonld(page)
author = schema["author"]
stats = schema["interactionStatistic"]
url_t = schema["url"]
url_a = author["url"]
path = text.split_html(text.extr(
page, '<nav class="ipsBreadcrumb', "</nav>"))[2:-1]
thread = {
"url" : url_t,
"path" : path,
"title": schema["headline"],
"views": stats[0]["userInteractionCount"],
"posts": stats[1]["userInteractionCount"],
"date" : text.parse_datetime(schema["datePublished"]),
"date_updated": text.parse_datetime(schema["dateModified"]),
"description" : text.unescape(schema["text"]).strip(),
"section" : path[-2],
"author" : author["name"],
"author_url" : url_a,
}
thread["id"], _, thread["slug"] = \
url_t.rsplit("/", 2)[1].partition("-")
thread["author_id"], _, thread["author_slug"] = \
url_a.rsplit("/", 2)[1].partition("-")
return thread
def _parse_post(self, html):
extr = text.extract_from(html)
post = {
"id": extr('id="elComment_', '"'),
"author_url": extr(" href='", "'"),
"date": text.parse_datetime(extr("datetime='", "'")),
"content": extr("<!-- Post content -->", "\n\t\t</div>"),
}
if (pos := post["content"].find(">")) >= 0:
post["content"] = post["content"][pos+1:].strip()
post["author_id"], _, post["author_slug"] = \
post["author_url"].rsplit("/", 2)[1].partition("-")
return post
class BellazonPostExtractor(BellazonExtractor):
subcategory = "post"
pattern = (rf"{BASE_PATTERN}(/topic/\d+-[\w-]+(?:/page/\d+)?)"
rf"/?#(?:findC|c)omment-(\d+)")
example = "https://www.bellazon.com/main/topic/123-SLUG/#findComment-12345"
def posts(self):
path, post_id = self.groups
page = self.request(f"{self.root}{path}").text
pos = page.find(f'id="elComment_{post_id}')
if pos < 0:
raise exception.NotFoundError("post")
html = text.extract(page, "<article ", "</article>", pos-100)[0]
self.kwdict["thread"] = self._parse_thread(page)
return (self._parse_post(html),)
class BellazonThreadExtractor(BellazonExtractor):
subcategory = "thread"
pattern = rf"{BASE_PATTERN}(/topic/\d+-[\w-]+)(?:/page/(\d+))?"
example = "https://www.bellazon.com/main/topic/123-SLUG/"
def posts(self):
if (order := self.config("order-posts")) and \
order[0] not in ("d", "r"):
pages = self._pagination(*self.groups)
reverse = False
else:
pages = self._pagination_reverse(*self.groups)
reverse = True
for page in pages:
if "thread" not in self.kwdict:
self.kwdict["thread"] = self._parse_thread(page)
posts = text.extract_iter(page, "<article ", "</article>")
if reverse:
posts = list(posts)
posts.reverse()
for html in posts:
yield self._parse_post(html)
class BellazonForumExtractor(BellazonExtractor):
subcategory = "forum"
pattern = rf"{BASE_PATTERN}(/forum/\d+-[\w-]+)(?:/page/(\d+))?"
example = "https://www.bellazon.com/main/forum/123-SLUG/"
def items(self):
data = {"_extractor": BellazonThreadExtractor}
for page in self._pagination(*self.groups):
for row in text.extract_iter(
page, '<li data-ips-hook="topicRow"', "</"):
yield Message.Queue, text.extr(row, 'href="', '"'), data
|
