From a2cfbe445fc4eb22f95f16b8abd1742eeb40fd16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= Date: Wed, 15 Apr 2015 22:24:27 +0200 Subject: [PATCH] add extractor '3dbooru' --- gallery_dl/extractor/3dbooru.py | 31 +++++++++++++++++++++++++++++++ gallery_dl/extractor/booru.py | 5 ++++- 2 files changed, 35 insertions(+), 1 deletion(-) create mode 100644 gallery_dl/extractor/3dbooru.py diff --git a/gallery_dl/extractor/3dbooru.py b/gallery_dl/extractor/3dbooru.py new file mode 100644 index 00000000..a8c90305 --- /dev/null +++ b/gallery_dl/extractor/3dbooru.py @@ -0,0 +1,31 @@ +# -*- coding: utf-8 -*- + +# Copyright 2015 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. + +"""Extract image-urls from http://behoimi.org/""" + +from .booru import JSONBooruExtractor + +info = { + "category": "3dbooru", + "extractor": "ThreeDeeBooruExtractor", + "directory": ["{category}", "{tags}"], + "filename": "{category}_{id}_{name}", + "pattern": [ + r"(?:https?://)?(?:www\.)?http://behoimi\.org/post(?:/(?:index)?)?\?tags=([^&]+).*", + ], +} + +class ThreeDeeBooruExtractor(JSONBooruExtractor): + + def __init__(self, match, config): + JSONBooruExtractor.__init__(self, match, config, info) + self.api_url = "http://behoimi.org/post/index.json" + self.headers = { + "Referer": "http://behoimi.org/post/show/", + "User-Agent": "Mozilla/5.0" + } diff --git a/gallery_dl/extractor/booru.py b/gallery_dl/extractor/booru.py index ce6b0326..88600397 100644 --- a/gallery_dl/extractor/booru.py +++ b/gallery_dl/extractor/booru.py @@ -27,10 +27,12 @@ class BooruExtractor(SequentialExtractor): self.tags = urllib.parse.unquote(match.group(1)) self.page = "page" self.params = {"tags": self.tags} + self.headers = {} def items(self): yield Message.Version, 1 yield Message.Directory, self.get_job_metadata() + yield Message.Headers, self.headers for data in self.items_impl(): yield Message.Url, self.get_file_url(data), self.get_file_metadata(data) @@ -76,7 +78,8 @@ class JSONBooruExtractor(BooruExtractor): self.update_page(reset=True) while True: images = json.loads( - self.request(self.api_url, verify=True, params=self.params).text + self.request(self.api_url, verify=True, params=self.params, + headers=self.headers).text ) if len(images) == 0: return