summaryrefslogtreecommitdiffstats
path: root/gallery_dl/extractor/booru.py
blob: 12d98b127414302a5f2d34e54c2bab6fa6a2cfda (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
# -*- coding: utf-8 -*-

# Copyright 2015-2022 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 *booru sites"""

from .common import BaseExtractor, Message
from .. import text
import operator


class BooruExtractor(BaseExtractor):
    """Base class for *booru extractors"""
    basecategory = "booru"
    filename_fmt = "{category}_{id}_{md5}.{extension}"
    page_start = 0
    per_page = 100

    def items(self):
        self.login()
        data = self.metadata()
        tags = self.config("tags", False)
        notes = self.config("notes", False)

        for post in self.posts():
            try:
                url = self._file_url(post)
                if url[0] == "/":
                    url = self.root + url
            except (KeyError, TypeError):
                self.log.debug("Unable to fetch download URL for post %s "
                               "(md5: %s)", post.get("id"), post.get("md5"))
                continue

            page_html = None
            if tags:
                page_html = self._extended_tags(post)
            if notes:
                self._notes(post, page_html)
            text.nameext_from_url(url, post)
            post.update(data)
            self._prepare(post)

            yield Message.Directory, post
            yield Message.Url, url, post

    def skip(self, num):
        pages = num // self.per_page
        self.page_start += pages
        return pages * self.per_page

    def login(self):
        """Login and set necessary cookies"""

    def metadata(self):
        """Return a dict with general metadata"""
        return ()

    def posts(self):
        """Return an iterable with post objects"""
        return ()

    _file_url = operator.itemgetter("file_url")

    def _prepare(self, post):
        """Prepare the 'post's metadata"""

    def _extended_tags(self, post, page=None):
        """Generate extended tag information

        The return value of this function will be
        passed to the _notes function as the page parameter.
        This makes it possible to reuse the same HTML both for
        extracting tags and notes.
        """

    def _notes(self, post, page=None):
        """Generate information about notes"""