1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-24 03:32:33 +01:00
gallery-dl/gallery_dl/extractor/chan.py

60 lines
2.0 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
2016-10-03 08:23:40 +02:00
# 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
# published by the Free Software Foundation.
"""Base classes for extractors for different Futaba Channel boards"""
2015-10-05 17:15:31 +02:00
from .common import Extractor, Message
2015-10-03 15:43:02 +02:00
from .. import text
2016-10-03 08:23:40 +02:00
class ChanThreadExtractor(Extractor):
"""Base class for extractors for Futaba Channel boards"""
2016-10-03 08:23:40 +02:00
category = "chan"
subcategory = "thread"
2015-11-21 03:13:06 +01:00
directory_fmt = ["{category}", "{board}-{thread}"]
filename_fmt = "{tim}-{filename}{ext}"
api_url = ""
file_url = ""
2016-10-03 08:23:40 +02:00
def __init__(self, match):
2015-10-05 17:15:31 +02:00
Extractor.__init__(self)
self.metadata = {
2016-10-03 08:23:40 +02:00
"board": match.group(1),
"thread": match.group(2),
}
def items(self):
yield Message.Version, 1
2016-10-03 08:23:40 +02:00
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
self.update(post)
2016-10-15 23:06:54 +02:00
yield Message.Url, self.build_url(post), post
2015-09-07 16:32:20 +02:00
if "extra_files" in post:
for file in post["extra_files"]:
self.update(post, file)
2016-10-15 23:06:54 +02:00
yield Message.Url, self.build_url(post), post
def update(self, post, data=None):
"""Update keyword dictionary"""
post.update(data or self.metadata)
post["extension"] = post["ext"][1:]
2016-10-15 23:06:54 +02:00
def build_url(self, post):
"""Construct an image url out of a post object"""
return self.file_url.format_map(post)
@staticmethod
def get_thread_title(post):
"""Return thread title from first post"""
2015-11-11 00:51:07 +01:00
title = post["sub"] if "sub" in post else text.remove_html(post["com"])
return text.unescape(title)[:50]