move extractors from booru.py into their own gelbooru_v02 module

pull/1331/head
Mike Fährmann 4 years ago
parent 04e7a7c8a9
commit 08d7934c6e
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

@ -35,6 +35,7 @@ modules = [
"furaffinity",
"fuskator",
"gelbooru",
"gelbooru_v02",
"gfycat",
"hbrowse",
"hentai2read",

@ -9,12 +9,8 @@
"""Extractors for *booru sites"""
from .common import BaseExtractor, Message
from .. import text, util, exception
from xml.etree import ElementTree
import collections
from .. import text
import operator
import re
class BooruExtractor(BaseExtractor):
@ -66,174 +62,8 @@ class BooruExtractor(BaseExtractor):
_file_url = operator.itemgetter("file_url")
@staticmethod
def _prepare(post):
post["date"] = text.parse_datetime(
post["created_at"], "%a %b %d %H:%M:%S %z %Y")
def _prepare(self, post):
"""Prepare the 'post's metadata"""
def _extended_tags(self, post, page=None):
if not page:
url = "{}/index.php?page=post&s=view&id={}".format(
self.root, post["id"])
page = self.request(url).text
html = text.extract(page, '<ul id="tag-', '</ul>')[0]
if html:
tags = collections.defaultdict(list)
pattern = re.compile(
r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'&]+)", re.S)
for tag_type, tag_name in pattern.findall(html):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
post["tags_" + key] = " ".join(value)
def _api_request(self, params):
url = self.root + "/index.php?page=dapi&s=post&q=index"
return ElementTree.fromstring(self.request(url, params=params).text)
def _pagination(self, params):
params["pid"] = self.page_start
params["limit"] = self.per_page
while True:
root = self._api_request(params)
for post in root:
yield post.attrib
if len(root) < self.per_page:
return
params["pid"] += 1
BASE_PATTERN = BooruExtractor.update({
"rule34": {
"root": "https://rule34.xxx",
},
"safebooru": {
"root": "https://safebooru.org",
},
"realbooru": {
"root": "https://realbooru.com",
},
})
class BooruPostExtractor(BooruExtractor):
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=view&id=(\d+)"
test = (
("https://rule34.xxx/index.php?page=post&s=view&id=1995545", {
"content": "97e4bbf86c3860be18de384d02d544251afe1d45",
"options": (("tags", True),),
"keyword": {
"tags_artist": "danraku",
"tags_character": "kashima_(kantai_collection)",
"tags_copyright": "kantai_collection",
"tags_general": str,
"tags_metadata": str,
},
}),
("https://safebooru.org/index.php?page=post&s=view&id=1169132", {
"url": "cf05e37a3c62b2d55788e2080b8eabedb00f999b",
"content": "93b293b27dabd198afafabbaf87c49863ac82f27",
"options": (("tags", True),),
"keyword": {
"tags_artist": "kawanakajima",
"tags_character": "heath_ledger ronald_mcdonald the_joker",
"tags_copyright": "dc_comics mcdonald's the_dark_knight",
"tags_general": str,
},
}),
("https://realbooru.com/index.php?page=post&s=view&id=668483", {
"url": "2421b5b0e15d5e20f9067090a8b0fd4114d3e7d9",
"content": "7f5873ce3b6cd295ea2e81fcb49583098ea9c8da",
}),
)
def __init__(self, match):
BooruExtractor.__init__(self, match)
self.post_id = match.group(match.lastindex)
def posts(self):
return self._pagination({"id": self.post_id})
class BooruTagExtractor(BooruExtractor):
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=list&tags=([^&#]+)"
test = (
("https://rule34.xxx/index.php?page=post&s=list&tags=danraku", {
"content": "97e4bbf86c3860be18de384d02d544251afe1d45",
"pattern": r"https?://.*rule34\.xxx/images/\d+/[0-9a-f]+\.jpg",
"count": 1,
}),
("https://safebooru.org/index.php?page=post&s=list&tags=bonocho", {
"url": "17c61b386530cf4c30842c9f580d15ef1cd09586",
"content": "e5ad4c5bf241b1def154958535bef6c2f6b733eb",
}),
("https://realbooru.com/index.php?page=post&s=list&tags=wine", {
"count": ">= 64",
}),
)
def __init__(self, match):
BooruExtractor.__init__(self, match)
tags = match.group(match.lastindex)
self.tags = text.unquote(tags.replace("+", " "))
def metadata(self):
return {"search_tags": self.tags}
def posts(self):
return self._pagination({"tags" : self.tags})
class BooruPoolExtractor(BooruExtractor):
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool}")
archive_fmt = "p_{pool}_{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=pool&s=show&id=(\d+)"
test = (
("https://rule34.xxx/index.php?page=pool&s=show&id=179", {
"count": 3,
}),
("https://safebooru.org/index.php?page=pool&s=show&id=11", {
"count": 5,
}),
("https://realbooru.com/index.php?page=pool&s=show&id=1", {
"count": 3,
}),
)
def __init__(self, match):
BooruExtractor.__init__(self, match)
self.pool_id = match.group(match.lastindex)
self.post_ids = ()
def skip(self, num):
self.page_start += num
return num
def metadata(self):
url = "{}/index.php?page=pool&s=show&id={}".format(
self.root, self.pool_id)
page = self.request(url).text
name, pos = text.extract(page, "<h4>Pool: ", "</h4>")
if not name:
raise exception.NotFoundError("pool")
self.post_ids = text.extract_iter(
page, 'class="thumb" id="p', '"', pos)
return {
"pool": text.parse_int(self.pool_id),
"pool_name": text.unescape(name),
}
def posts(self):
params = {}
for params["id"] in util.advance(self.post_ids, self.page_start):
for post in self._api_request(params):
yield post.attrib
"""Generate extended tag information"""

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014-2020 Mike Fährmann
# Copyright 2014-2021 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
@ -8,13 +8,14 @@
"""Extractors for https://gelbooru.com/"""
from . import booru
from . import gelbooru_v02
from .. import text, exception
class GelbooruBase():
"""Base class for gelbooru extractors"""
category = "gelbooru"
basecategory = "booru"
root = "https://gelbooru.com"
@staticmethod
@ -27,7 +28,8 @@ class GelbooruBase():
return url
class GelbooruTagExtractor(GelbooruBase, booru.BooruTagExtractor):
class GelbooruTagExtractor(GelbooruBase,
gelbooru_v02.GelbooruV02TagExtractor):
"""Extractor for images from gelbooru.com based on search-tags"""
pattern = (r"(?:https?://)?(?:www\.)?gelbooru\.com/(?:index\.php)?"
r"\?page=post&s=list&tags=(?P<tags>[^&#]+)")
@ -42,7 +44,8 @@ class GelbooruTagExtractor(GelbooruBase, booru.BooruTagExtractor):
)
class GelbooruPoolExtractor(GelbooruBase, booru.BooruPoolExtractor):
class GelbooruPoolExtractor(GelbooruBase,
gelbooru_v02.GelbooruV02PoolExtractor):
"""Extractor for image-pools from gelbooru.com"""
pattern = (r"(?:https?://)?(?:www\.)?gelbooru\.com/(?:index\.php)?"
r"\?page=pool&s=show&id=(?P<pool>\d+)")
@ -72,7 +75,8 @@ class GelbooruPoolExtractor(GelbooruBase, booru.BooruPoolExtractor):
}
class GelbooruPostExtractor(GelbooruBase, booru.BooruPostExtractor):
class GelbooruPostExtractor(GelbooruBase,
gelbooru_v02.GelbooruV02PostExtractor):
"""Extractor for single images from gelbooru.com"""
pattern = (r"(?:https?://)?(?:www\.)?gelbooru\.com/(?:index\.php)?"
r"\?page=post&s=view&id=(?P<post>\d+)")

@ -0,0 +1,186 @@
# -*- coding: utf-8 -*-
# Copyright 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 Gelbooru v0.2 sites"""
from . import booru
from .. import text, util, exception
from xml.etree import ElementTree
import collections
import re
class GelbooruV02Extractor(booru.BooruExtractor):
basecategory = "gelbooru_v02"
def _api_request(self, params):
url = self.root + "/index.php?page=dapi&s=post&q=index"
return ElementTree.fromstring(self.request(url, params=params).text)
def _pagination(self, params):
params["pid"] = self.page_start
params["limit"] = self.per_page
while True:
root = self._api_request(params)
for post in root:
yield post.attrib
if len(root) < self.per_page:
return
params["pid"] += 1
@staticmethod
def _prepare(post):
post["date"] = text.parse_datetime(
post["created_at"], "%a %b %d %H:%M:%S %z %Y")
def _extended_tags(self, post, page=None):
if not page:
url = "{}/index.php?page=post&s=view&id={}".format(
self.root, post["id"])
page = self.request(url).text
html = text.extract(page, '<ul id="tag-', '</ul>')[0]
if html:
tags = collections.defaultdict(list)
pattern = re.compile(
r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'&]+)", re.S)
for tag_type, tag_name in pattern.findall(html):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
post["tags_" + key] = " ".join(value)
BASE_PATTERN = GelbooruV02Extractor.update({
"realbooru": {"root": "https://realbooru.com"},
"rule34" : {"root": "https://rule34.xxx"},
"safebooru": {"root": "https://safebooru.org"},
})
class GelbooruV02TagExtractor(GelbooruV02Extractor):
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=list&tags=([^&#]+)"
test = (
("https://rule34.xxx/index.php?page=post&s=list&tags=danraku", {
"content": "0a3aa1e302bd4ed0599305cd4c225ca8d28249b2",
"pattern": r"https?://.*rule34\.xxx/images/\d+/[0-9a-f]+\.jpg",
"count": 1,
}),
("https://safebooru.org/index.php?page=post&s=list&tags=bonocho", {
"url": "17c61b386530cf4c30842c9f580d15ef1cd09586",
"content": "e5ad4c5bf241b1def154958535bef6c2f6b733eb",
}),
("https://realbooru.com/index.php?page=post&s=list&tags=wine", {
"count": ">= 64",
}),
)
def __init__(self, match):
GelbooruV02Extractor.__init__(self, match)
tags = match.group(match.lastindex)
self.tags = text.unquote(tags.replace("+", " "))
def metadata(self):
return {"search_tags": self.tags}
def posts(self):
return self._pagination({"tags" : self.tags})
class GelbooruV02PoolExtractor(GelbooruV02Extractor):
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool}")
archive_fmt = "p_{pool}_{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=pool&s=show&id=(\d+)"
test = (
("https://rule34.xxx/index.php?page=pool&s=show&id=179", {
"count": 3,
}),
("https://safebooru.org/index.php?page=pool&s=show&id=11", {
"count": 5,
}),
("https://realbooru.com/index.php?page=pool&s=show&id=1", {
"count": 3,
}),
)
def __init__(self, match):
GelbooruV02Extractor.__init__(self, match)
self.pool_id = match.group(match.lastindex)
self.post_ids = ()
def skip(self, num):
self.page_start += num
return num
def metadata(self):
url = "{}/index.php?page=pool&s=show&id={}".format(
self.root, self.pool_id)
page = self.request(url).text
name, pos = text.extract(page, "<h4>Pool: ", "</h4>")
if not name:
raise exception.NotFoundError("pool")
self.post_ids = text.extract_iter(
page, 'class="thumb" id="p', '"', pos)
return {
"pool": text.parse_int(self.pool_id),
"pool_name": text.unescape(name),
}
def posts(self):
params = {}
for params["id"] in util.advance(self.post_ids, self.page_start):
for post in self._api_request(params):
yield post.attrib
class GelbooruV02PostExtractor(GelbooruV02Extractor):
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=view&id=(\d+)"
test = (
("https://rule34.xxx/index.php?page=post&s=view&id=1995545", {
"content": "0a3aa1e302bd4ed0599305cd4c225ca8d28249b2",
"options": (("tags", True),),
"keyword": {
"tags_artist": "danraku",
"tags_character": "kashima_(kantai_collection)",
"tags_copyright": "kantai_collection",
"tags_general": str,
"tags_metadata": str,
},
}),
("https://safebooru.org/index.php?page=post&s=view&id=1169132", {
"url": "cf05e37a3c62b2d55788e2080b8eabedb00f999b",
"content": "93b293b27dabd198afafabbaf87c49863ac82f27",
"options": (("tags", True),),
"keyword": {
"tags_artist": "kawanakajima",
"tags_character": "heath_ledger ronald_mcdonald the_joker",
"tags_copyright": "dc_comics mcdonald's the_dark_knight",
"tags_general": str,
},
}),
("https://realbooru.com/index.php?page=post&s=view&id=668483", {
"url": "2421b5b0e15d5e20f9067090a8b0fd4114d3e7d9",
"content": "7f5873ce3b6cd295ea2e81fcb49583098ea9c8da",
}),
)
def __init__(self, match):
GelbooruV02Extractor.__init__(self, match)
self.post_id = match.group(match.lastindex)
def posts(self):
return self._pagination({"id": self.post_id})
Loading…
Cancel
Save