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
|
# -*- 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://sturdychan.help/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:sturdychan.help|2chen\.(?:moe|club))"
class _2chenThreadExtractor(Extractor):
"""Extractor for 2chen threads"""
category = "2chen"
subcategory = "thread"
root = "https://sturdychan.help"
directory_fmt = ("{category}", "{board}", "{thread} {title}")
filename_fmt = "{time} {filename}.{extension}"
archive_fmt = "{board}_{thread}_{hash}_{time}"
pattern = BASE_PATTERN + r"/([^/?#]+)/(\d+)"
example = "https://sturdychan.help/a/12345/"
def __init__(self, match):
Extractor.__init__(self, match)
self.board, self.thread = match.groups()
def items(self):
url = "{}/{}/{}".format(self.root, self.board, self.thread)
page = self.request(url, encoding="utf-8", notfound="thread").text
data = self.metadata(page)
yield Message.Directory, data
for post in self.posts(page):
url = post["url"]
if not url:
continue
if url[0] == "/":
url = self.root + url
post["url"] = url = url.partition("?")[0]
post.update(data)
post["time"] = text.parse_int(post["date"].timestamp())
yield Message.Url, url, text.nameext_from_url(
post["filename"], post)
def metadata(self, page):
board, pos = text.extract(page, 'class="board">/', '/<')
title = text.extract(page, "<h3>", "</h3>", pos)[0]
return {
"board" : board,
"thread": self.thread,
"title" : text.unescape(title),
}
def posts(self, page):
"""Return iterable with relevant posts"""
return map(self.parse, text.extract_iter(
page, 'class="glass media', '</article>'))
def parse(self, post):
extr = text.extract_from(post)
return {
"name" : text.unescape(extr("<span>", "</span>")),
"date" : text.parse_datetime(
extr("<time", "<").partition(">")[2],
"%d %b %Y (%a) %H:%M:%S"
),
"no" : extr('href="#p', '"'),
"url" : extr('</a><a href="', '"'),
"filename": text.unescape(extr('download="', '"')),
"hash" : extr('data-hash="', '"'),
}
class _2chenBoardExtractor(Extractor):
"""Extractor for 2chen boards"""
category = "2chen"
subcategory = "board"
root = "https://sturdychan.help"
pattern = BASE_PATTERN + r"/([^/?#]+)(?:/catalog|/?$)"
example = "https://sturdychan.help/a/"
def __init__(self, match):
Extractor.__init__(self, match)
self.board = match.group(1)
def items(self):
url = "{}/{}/catalog".format(self.root, self.board)
page = self.request(url, notfound="board").text
data = {"_extractor": _2chenThreadExtractor}
for thread in text.extract_iter(
page, '<figure><a href="', '"'):
yield Message.Queue, self.root + thread, data
|
