github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

unescape items in text.split_html()

Browse Source
This commit is contained in:
Mike Fährmann
2021-03-29 02:12:29 +02:00
parent 36291176bc
commit 387fe415d5
4 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gallery_dl/extractor/aryion.py
View File

@@ -126,8 +126,8 @@ class AryionExtractor(Extractor):
"user" : self.user or artist, "user" : self.user or artist,
"title" : title, "title" : title,
"artist": artist, "artist": artist,
"path" : text.split_html(text.unescape(extr( "path" : text.split_html(extr(
"cookiecrumb'>", '</span')))[4:-1:2], "cookiecrumb'>", '</span'))[4:-1:2],
"date" : extr("class='pretty-date' title='", "'"), "date" : extr("class='pretty-date' title='", "'"),
"size" : text.parse_int(clen), "size" : text.parse_int(clen),
"views" : text.parse_int(extr("Views</b>:", "<").replace(",", "")), "views" : text.parse_int(extr("Views</b>:", "<").replace(",", "")),

7
gallery_dl/extractor/dynastyscans.py
View File

@@ -1,19 +1,18 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015-2019 Mike Fährmann # Copyright 2015-2021 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation. # published by the Free Software Foundation.
"""Extract manga-chapters from https://dynasty-scans.com/""" """Extractors for https://dynasty-scans.com/"""
from .common import ChapterExtractor, Extractor, Message from .common import ChapterExtractor, Extractor, Message
from .. import text from .. import text
import json import json
import re import re
BASE_PATTERN = r"(?:https?://)?(?:www\.)?dynasty-scans\.com" BASE_PATTERN = r"(?:https?://)?(?:www\.)?dynasty-scans\.com"
@@ -36,7 +35,7 @@ class DynastyscansBase():
return { return {
"url" : self.root + url, "url" : self.root + url,
"image_id": text.parse_int(image_id), "image_id": text.parse_int(image_id),
"tags" : text.split_html(text.unescape(tags)), "tags" : text.split_html(tags),
"date" : text.remove_html(date), "date" : text.remove_html(date),
"source" : text.unescape(src), "source" : text.unescape(src),
} }

7
gallery_dl/text.py
View File

@@ -27,11 +27,12 @@ def remove_html(txt, repl=" ", sep=" "):
return txt.strip() return txt.strip()
def split_html(txt, sep=None): def split_html(txt):
"""Split input string by html-tags""" """Split input string by HTML tags"""
try: try:
return [ return [
x.strip() for x in HTML_RE.split(txt) unescape(x).strip()
for x in HTML_RE.split(txt)
if x and not x.isspace() if x and not x.isspace()
] ]
except TypeError: except TypeError:

4
test/test_text.py
View File

@@ -59,6 +59,10 @@ class TestText(unittest.TestCase):
self.assertEqual( self.assertEqual(
f("<div><b class='a'>Hello</b><i>World.</i></div>"), result) f("<div><b class='a'>Hello</b><i>World.</i></div>"), result)
# escaped HTML entities
self.assertEqual(
f("<i>&lt;foo&gt;</i> <i>&lt;bar&gt; </i>"), ["<foo>", "<bar>"])
# empty HTML # empty HTML
self.assertEqual(f("<div></div>"), empty) self.assertEqual(f("<div></div>"), empty)
self.assertEqual(f(" <div> </div> "), empty) self.assertEqual(f(" <div> </div> "), empty)