[*chan] code cleanup

This commit is contained in:
Mike Fährmann
2016-10-03 08:23:40 +02:00
parent 14237142d8
commit c20a3b3a01
3 changed files with 17 additions and 26 deletions

View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2015 Mike Fährmann
# Copyright 2015, 2016 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
@@ -8,12 +8,11 @@
"""Extract images and videos from https://www.4chan.org/"""
from .chan import ChanExtractor
from . import chan
class FourchanThreadExtractor(ChanExtractor):
class FourchanThreadExtractor(chan.ChanThreadExtractor):
"""Extractor for images from threads from 4chan.org"""
category = "4chan"
subcategory = "thread"
pattern = [r"(?:https?://)?boards\.4chan\.org/([^/]+)/thread/(\d+)"]
test = [("https://boards.4chan.org/tg/thread/15396072/", {
"url": "39082ad166161966d7ba8e37f2173a824eb540f0",
@@ -22,8 +21,3 @@ class FourchanThreadExtractor(ChanExtractor):
})]
api_url = "https://a.4cdn.org/{board}/thread/{thread}.json"
file_url = "https://i.4cdn.org/{board}/{tim}{ext}"
def __init__(self, match):
ChanExtractor.__init__(
self, match.group(1), match.group(2)
)

View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014, 2015 Mike Fährmann
# Copyright 2014-2016 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
@@ -8,12 +8,11 @@
"""Extract images and videos from https://8ch.net/"""
from .chan import ChanExtractor
from . import chan
class InfinitychanThreadExtractor(ChanExtractor):
class InfinitychanThreadExtractor(chan.ChanThreadExtractor):
"""Extractor for images from threads from 8ch.net"""
category = "8chan"
subcategory = "thread"
pattern = [r"(?:https?://)?(?:www\.)?8ch\.net/([^/]+)/res/(\d+)"]
test = [("https://8ch.net/tg/res/175887.html", {
"url": "cb03fdc650ad8e796fdab553fbd5489f468d3f45",
@@ -22,8 +21,3 @@ class InfinitychanThreadExtractor(ChanExtractor):
})]
api_url = "https://8ch.net/{board}/res/{thread}.json"
file_url = "https://8ch.net/{board}/src/{tim}{ext}"
def __init__(self, match):
ChanExtractor.__init__(
self, match.group(1), match.group(2)
)

View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2015 Mike Fährmann
# Copyright 2015, 2016 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
@@ -11,34 +11,37 @@
from .common import Extractor, Message
from .. import text
class ChanExtractor(Extractor):
class ChanThreadExtractor(Extractor):
"""Base class for extractors for Futaba Channel boards"""
category = "chan"
subcategory = "thread"
directory_fmt = ["{category}", "{board}-{thread}"]
filename_fmt = "{tim}-{filename}{ext}"
api_url = ""
file_url = ""
def __init__(self, board, thread):
def __init__(self, match):
Extractor.__init__(self)
self.metadata = {
"board": board,
"thread": thread,
"board": match.group(1),
"thread": match.group(2),
}
def items(self):
yield Message.Version, 1
posts = self.request(self.api_url.format(**self.metadata)).json()["posts"]
url = self.api_url.format_map(self.metadata)
posts = self.request(url).json()["posts"]
self.metadata["title"] = self.get_thread_title(posts[0])
yield Message.Directory, self.metadata
for post in posts:
if "filename" not in post:
continue
post.update(self.metadata)
yield Message.Url, self.file_url.format(**post), post
yield Message.Url, self.file_url.format_map(post), post
if "extra_files" in post:
for file in post["extra_files"]:
post.update(file)
yield Message.Url, self.file_url.format(**post), post
yield Message.Url, self.file_url.format_map(post), post
@staticmethod
def get_thread_title(post):