github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[2chen] implement generic 2chen board extractors

Browse Source 
support
- https://sturdychan.help/
- https://schan.help/ (#8680)
This commit is contained in:
Mike Fährmann
2025-12-13 18:08:50 +01:00
parent a8ca947154
commit 8f621b32bd
4 changed files with 93 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docs/supportedsites.md
View File

@@ -19,12 +19,6 @@ Consider all listed sites to potentially be NSFW.
<td>Boards, Threads</td>
<td></td>
</tr>
<tr id="2chen" title="2chen">
<td>2chen</td>
<td>https://sturdychan.help/</td>
<td>Boards, Threads</td>
<td></td>
</tr>
<tr id="35photo" title="35photo">
<td>35PHOTO</td>
<td>https://35photo.pro/</td>
@@ -1274,6 +1268,22 @@ Consider all listed sites to potentially be NSFW.
<td></td>
</tr>
<tr id="2chen" title="2chen">
<td colspan="4"><strong>2chen Instances</strong></td>
</tr>
<tr id="sturdychan" title="sturdychan">
<td>Sturdychan</td>
<td>https://sturdychan.help/</td>
<td>Boards, Threads</td>
<td></td>
</tr>
<tr id="schan" title="schan">
<td>Schan</td>
<td>https://schan.help/</td>
<td>Boards, Threads</td>
<td></td>
</tr>
<tr id="blogger" title="blogger">
<td colspan="4"><strong>Blogger Instances</strong></td>
</tr>

67
gallery_dl/extractor/2chen.py
View File

@@ -1,40 +1,55 @@
# -*- coding: utf-8 -*-
# Copyright 2022-2025 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://sturdychan.help/"""
"""Extractors for 2chen boards"""
from .common import Extractor, Message
from .common import BaseExtractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:sturdychan.help|2chen\.(?:moe|club))"
class _2chenExtractor(BaseExtractor):
basecategory = "2chen"
class _2chenThreadExtractor(Extractor):
BASE_PATTERN = _2chenExtractor.update({
"sturdychan": {
"root": "https://sturdychan.help",
"pattern": r"(?:sturdychan\.help|2chen\.(?:moe|club))",
},
"schan": {
"root": "https://schan.help/",
"pattern": r"schan\.help",
},
})
class _2chenThreadExtractor(_2chenExtractor):
"""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}"
archive_fmt = "{board}_{thread}_{no}_{time}"
pattern = rf"{BASE_PATTERN}/([^/?#]+)/(\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 = f"{self.root}/{self.board}/{self.thread}"
board = self.groups[-2]
thread = self.kwdict["thread"] = self.groups[-1]
url = f"{self.root}/{board}/{thread}"
page = self.request(url, encoding="utf-8", notfound="thread").text
data = self.metadata(page)
yield Message.Directory, "", data
self.kwdict["board"], pos = text.extract(
page, 'class="board">/', '/<')
self.kwdict["title"] = text.unescape(text.extract(
page, "<h3>", "</h3>", pos)[0])
yield Message.Directory, "", {}
for post in self.posts(page):
url = post["url"]
if not url:
continue
@@ -42,20 +57,10 @@ class _2chenThreadExtractor(Extractor):
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(
@@ -70,26 +75,20 @@ class _2chenThreadExtractor(Extractor):
"%d %b %Y (%a) %H:%M:%S"
),
"no" : extr('href="#p', '"'),
"url" : extr('</a><a href="', '"'),
"filename": text.unescape(extr('download="', '"')),
"url" : text.extr(extr("<figure>", "</"), 'href="', '"'),
"hash" : extr('data-hash="', '"'),
}
class _2chenBoardExtractor(Extractor):
class _2chenBoardExtractor(_2chenExtractor):
"""Extractor for 2chen boards"""
category = "2chen"
subcategory = "board"
root = "https://sturdychan.help"
pattern = rf"{BASE_PATTERN}/([^/?#]+)(?:/catalog|/?$)"
example = "https://sturdychan.help/a/"
def __init__(self, match):
Extractor.__init__(self, match)
self.board = match[1]
def items(self):
url = f"{self.root}/{self.board}/catalog"
url = f"{self.root}/{self.groups[-1]}/catalog"
page = self.request(url, notfound="board").text
data = {"_extractor": _2chenThreadExtractor}
for thread in text.extract_iter(

37
test/results/schan.py Normal file
View File

@@ -0,0 +1,37 @@
# -*- 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.
gallery_dl = __import__("gallery_dl.extractor.2chen")
_2chen = getattr(gallery_dl.extractor, "2chen")
__tests__ = (
{
"#url" : "https://schan.help/tv/757",
"#category": ("2chen", "schan", "thread"),
"#class" : _2chen._2chenThreadExtractor,
"#pattern" : r"https://schan\.help/assets/images/src/\w{40}\.\w+$",
"#count" : ">= 179",
"board" : "tv",
"date" : "type:datetime",
"hash" : "",
"name" : "Anonymous",
"no" : r"re:\d+",
"thread": "757",
"time" : int,
"title" : "「/ttg/ #1: The Future of Schan」",
"url" : str,
},
{
"#url" : "https://schan.help/tv/",
"#category": ("2chen", "schan", "board"),
"#class" : _2chen._2chenBoardExtractor,
"#pattern" : _2chen._2chenThreadExtractor.pattern,
},
)

14
test/results/2chen.py → test/results/sturdychan.py
View File

@@ -11,7 +11,7 @@ _2chen = getattr(gallery_dl.extractor, "2chen")
__tests__ = (
{
"#url" : "https://sturdychan.help/tv/268929",
"#category": ("", "2chen", "thread"),
"#category": ("2chen", "sturdychan", "thread"),
"#class" : _2chen._2chenThreadExtractor,
"#pattern" : r"https://sturdychan\.help/assets/images/src/\w{40}\.\w+$",
"#count" : ">= 179",
@@ -29,38 +29,38 @@ __tests__ = (
{
"#url" : "https://2chen.club/tv/1",
"#category": ("", "2chen", "thread"),
"#category": ("2chen", "sturdychan", "thread"),
"#class" : _2chen._2chenThreadExtractor,
},
{
"#url" : "https://2chen.moe/jp/303786",
"#category": ("", "2chen", "thread"),
"#category": ("2chen", "sturdychan", "thread"),
"#class" : _2chen._2chenThreadExtractor,
},
{
"#url" : "https://sturdychan.help/co/",
"#category": ("", "2chen", "board"),
"#category": ("2chen", "sturdychan", "board"),
"#class" : _2chen._2chenBoardExtractor,
"#pattern" : _2chen._2chenThreadExtractor.pattern,
},
{
"#url" : "https://2chen.moe/co",
"#category": ("", "2chen", "board"),
"#category": ("2chen", "sturdychan", "board"),
"#class" : _2chen._2chenBoardExtractor,
},
{
"#url" : "https://2chen.club/tv",
"#category": ("", "2chen", "board"),
"#category": ("2chen", "sturdychan", "board"),
"#class" : _2chen._2chenBoardExtractor,
},
{
"#url" : "https://2chen.moe/co/catalog",
"#category": ("", "2chen", "board"),
"#category": ("2chen", "sturdychan", "board"),
"#class" : _2chen._2chenBoardExtractor,
},