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
|
# -*- coding: utf-8 -*-
# Copyright 2017-2021 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.2chan.net/"""
from .common import Extractor, Message
from .. import text
class _2chanThreadExtractor(Extractor):
"""Extractor for images from threads on www.2chan.net"""
category = "2chan"
subcategory = "thread"
directory_fmt = ("{category}", "{board_name}", "{thread}")
filename_fmt = "{tim}.{extension}"
archive_fmt = "{board}_{thread}_{tim}"
url_fmt = "https://{server}.2chan.net/{board}/src/{filename}"
pattern = r"(?:https?://)?([^.]+)\.2chan\.net/([^/]+)/res/(\d+)"
test = ("http://dec.2chan.net/70/res/4752.htm", {
"url": "20c211ae7c06b18ec345a057fe0b68dde979b051",
"keyword": "23a529b46313b927fc94b577e5e1fdb3aa164ac1",
})
def __init__(self, match):
Extractor.__init__(self, match)
self.server, self.board, self.thread = match.groups()
def items(self):
url = "https://{}.2chan.net/{}/res/{}.htm".format(
self.server, self.board, self.thread)
page = self.request(url).text
data = self.metadata(page)
yield Message.Version, 1
yield Message.Directory, data
for post in self.posts(page):
if "filename" not in post:
continue
post.update(data)
url = self.url_fmt.format_map(post)
yield Message.Url, url, post
def metadata(self, page):
"""Collect metadata for extractor-job"""
title = text.extract(page, "<title>", "</title>")[0]
title, _, boardname = title.rpartition(" - ")
return {
"server": self.server,
"title": title,
"board": self.board,
"board_name": boardname[:-4],
"thread": self.thread,
}
def posts(self, page):
"""Build a list of all post-objects"""
page = text.extract(
page, '<div class="thre"', '<div style="clear:left"></div>')[0]
return [
self.parse(post)
for post in page.split('<table border=0>')
]
def parse(self, post):
"""Build post-object by extracting data from an HTML post"""
data = self._extract_post(post)
if data["name"]:
data["name"] = data["name"].strip()
path = text.extract(post, '<a href="/', '"')[0]
if path and not path.startswith("bin/jump"):
self._extract_image(post, data)
data["tim"], _, data["extension"] = data["filename"].partition(".")
data["time"] = data["tim"][:-3]
data["ext"] = "." + data["extension"]
return data
@staticmethod
def _extract_post(post):
return text.extract_all(post, (
("post", 'class="csb">' , '<'),
("name", 'class="cnm">' , '<'),
("now" , 'class="cnw">' , '<'),
("no" , 'class="cno">No.', '<'),
(None , '<blockquote', ''),
("com" , '>', '</blockquote>'),
))[0]
@staticmethod
def _extract_image(post, data):
text.extract_all(post, (
(None , '_blank', ''),
("filename", '>', '<'),
("fsize" , '(', ' '),
), 0, data)
|
