diff options
| author | 2023-10-03 18:31:58 -0400 | |
|---|---|---|
| committer | 2023-10-03 18:31:58 -0400 | |
| commit | b8758ecd073910ce3220b2e68399147b425c37b8 (patch) | |
| tree | d6aee20213508c8f425cbacb3d714367eca904c5 /gallery_dl/extractor/rule34us.py | |
| parent | e2f67519f8c1750a71aab3dc56b8345fff21bac5 (diff) | |
New upstream version 1.26.0.upstream/1.26.0
Diffstat (limited to 'gallery_dl/extractor/rule34us.py')
| -rw-r--r-- | gallery_dl/extractor/rule34us.py | 39 |
1 files changed, 5 insertions, 34 deletions
diff --git a/gallery_dl/extractor/rule34us.py b/gallery_dl/extractor/rule34us.py index 00b6972..6439a22 100644 --- a/gallery_dl/extractor/rule34us.py +++ b/gallery_dl/extractor/rule34us.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright 2021 Mike Fährmann +# Copyright 2021-2023 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 @@ -10,8 +10,8 @@ from .booru import BooruExtractor from .. import text -import re import collections +import re class Rule34usExtractor(BooruExtractor): @@ -19,8 +19,7 @@ class Rule34usExtractor(BooruExtractor): root = "https://rule34.us" per_page = 42 - def __init__(self, match): - BooruExtractor.__init__(self, match) + def _init(self): self._find_tags = re.compile( r'<li class="([^-"]+)-tag"[^>]*><a href="[^;"]+;q=([^"]+)').findall @@ -55,11 +54,7 @@ class Rule34usTagExtractor(Rule34usExtractor): directory_fmt = ("{category}", "{search_tags}") archive_fmt = "t_{search_tags}_{id}" pattern = r"(?:https?://)?rule34\.us/index\.php\?r=posts/index&q=([^&#]+)" - test = ("https://rule34.us/index.php?r=posts/index&q=[terios]_elysion", { - "pattern": r"https://img\d*\.rule34\.us" - r"/images/../../[0-9a-f]{32}\.\w+", - "count": 10, - }) + example = "https://rule34.us/index.php?r=posts/index&q=TAG" def __init__(self, match): Rule34usExtractor.__init__(self, match) @@ -96,31 +91,7 @@ class Rule34usPostExtractor(Rule34usExtractor): subcategory = "post" archive_fmt = "{id}" pattern = r"(?:https?://)?rule34\.us/index\.php\?r=posts/view&id=(\d+)" - test = ( - ("https://rule34.us/index.php?r=posts/view&id=3709005", { - "pattern": r"https://img\d*\.rule34\.us/images/14/7b" - r"/147bee6fc2e13f73f5f9bac9d4930b13\.png", - "content": "d714342ea84050f82dda5f0c194d677337abafc5", - }), - ("https://rule34.us/index.php?r=posts/view&id=4576310", { - "pattern": r"https://video\.rule34\.us/images/a2/94" - r"/a294ff8e1f8e0efa041e5dc9d1480011\.mp4", - "keyword": { - "extension": "mp4", - "file_url": str, - "filename": "a294ff8e1f8e0efa041e5dc9d1480011", - "height": "3982", - "id": "4576310", - "md5": "a294ff8e1f8e0efa041e5dc9d1480011", - "score": r"re:\d+", - "tags": "tagme, video", - "tags_general": "video", - "tags_metadata": "tagme", - "uploader": "Anonymous", - "width": "3184", - }, - }), - ) + example = "https://rule34.us/index.php?r=posts/view&id=12345" def __init__(self, match): Rule34usExtractor.__init__(self, match) |
