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
|
# -*- coding: utf-8 -*-
# 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://4archive.org/"""
from .common import Extractor, Message
from .. import text, util
class _4archiveThreadExtractor(Extractor):
"""Extractor for 4archive threads"""
category = "4archive"
subcategory = "thread"
directory_fmt = ("{category}", "{board}", "{thread} {title}")
filename_fmt = "{no} {filename}.{extension}"
archive_fmt = "{board}_{thread}_{no}"
root = "https://4archive.org"
referer = False
pattern = r"(?:https?://)?4archive\.org/board/([^/?#]+)/thread/(\d+)"
example = "https://4archive.org/board/a/thread/12345/"
def __init__(self, match):
Extractor.__init__(self, match)
self.board, self.thread = match.groups()
def items(self):
url = f"{self.root}/board/{self.board}/thread/{self.thread}"
page = self.request(url).text
data = self.metadata(page)
posts = self.posts(page)
if not data["title"]:
data["title"] = posts[0]["com"][:50]
for post in posts:
post.update(data)
post["time"] = int(util.datetime_to_timestamp(post["date"]))
yield Message.Directory, post
if "url" in post:
yield Message.Url, post["url"], text.nameext_from_url(
post["filename"], post)
def metadata(self, page):
return {
"board" : self.board,
"thread": text.parse_int(self.thread),
"title" : text.unescape(text.extr(
page, 'class="subject">', "</span>"))
}
def posts(self, page):
return [
self.parse(post)
for post in page.split('class="postContainer')[1:]
]
def parse(self, post):
extr = text.extract_from(post)
data = {
"name": extr('class="name">', "</span>"),
"date": text.parse_datetime(
(extr('class="dateTime">', "<") or
extr('class="dateTime postNum" >', "<")).strip(),
"%Y-%m-%d %H:%M:%S"),
"no" : text.parse_int(extr(">Post No.", "<")),
}
if 'class="file"' in post:
extr('class="fileText"', ">File: <a")
data.update({
"url" : extr('href="', '"'),
"filename": extr('alt="Image: ', '"'),
"size" : text.parse_bytes(extr(" (", ", ")[:-1]),
"width" : text.parse_int(extr("", "x")),
"height" : text.parse_int(extr("", "px")),
})
extr("<blockquote ", "")
data["com"] = text.unescape(text.remove_html(
extr(">", "</blockquote>")))
return data
class _4archiveBoardExtractor(Extractor):
"""Extractor for 4archive boards"""
category = "4archive"
subcategory = "board"
root = "https://4archive.org"
pattern = r"(?:https?://)?4archive\.org/board/([^/?#]+)(?:/(\d+))?/?$"
example = "https://4archive.org/board/a/"
def __init__(self, match):
Extractor.__init__(self, match)
self.board = match[1]
self.num = text.parse_int(match[2], 1)
def items(self):
data = {"_extractor": _4archiveThreadExtractor}
while True:
url = f"{self.root}/board/{self.board}/{self.num}"
page = self.request(url).text
if 'class="thread"' not in page:
return
for thread in text.extract_iter(page, 'class="thread" id="t', '"'):
url = f"{self.root}/board/{self.board}/thread/{thread}"
yield Message.Queue, url, data
self.num += 1
|
