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

[booru] adjust/match '_tags' and '_notes' code

Browse Source
This commit is contained in:
Mike Fährmann
2022-11-04 15:04:34 +01:00
parent 88954aa2e4
commit 4fd3c893fa
2 changed files with 26 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
gallery_dl/extractor/gelbooru_v02.py
View File

@@ -98,17 +98,18 @@ class GelbooruV02Extractor(booru.BooruExtractor):
self.root, post["id"])).text
def _tags(self, post, page):
html = text.extract(page, '<ul id="tag-', '</ul>')[0]
if not html:
html = text.extract(page, '<ul class="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)
tag_container = (text.extract(page, '<ul id="tag-', '</ul>')[0] or
text.extract(page, '<ul class="tag-', '</ul>')[0])
if not tag_container:
return
tags = collections.defaultdict(list)
pattern = re.compile(
r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'&]+)", re.S)
for tag_type, tag_name in pattern.findall(tag_container):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
post["tags_" + key] = " ".join(value)
def _notes(self, post, page):
note_container = text.extract(page, 'id="note-container"', "<img ")[0]

26
gallery_dl/extractor/moebooru.py
View File

@@ -31,22 +31,24 @@ class MoebooruExtractor(BooruExtractor):
self.root, post["id"])).text
def _tags(self, post, page):
html = text.extract(page, '<ul id="tag-', '</ul>')[0]
if html:
tags = collections.defaultdict(list)
pattern = re.compile(r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'+]+)")
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)
tag_container = text.extract(page, '<ul id="tag-', '</ul>')[0]
if not tag_container:
return
tags = collections.defaultdict(list)
pattern = re.compile(r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'+]+)")
for tag_type, tag_name in pattern.findall(tag_container):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
post["tags_" + key] = " ".join(value)
def _notes(self, post, page):
notes_container = text.extract(page, 'id="note-container"', "<img ")[0]
if not notes_container:
note_container = text.extract(page, 'id="note-container"', "<img ")[0]
if not note_container:
return
post["notes"] = notes = []
for note in notes_container.split('class="note-box"')[1:]:
for note in note_container.split('class="note-box"')[1:]:
extr = text.extract_from(note)
notes.append({
"width" : int(extr("width:", "p")),
@@ -54,7 +56,7 @@ class MoebooruExtractor(BooruExtractor):
"y" : int(extr("top:", "p")),
"x" : int(extr("left:", "p")),
"id" : int(extr('id="note-body-', '"')),
"body" : text.remove_html(extr(">", "</div>")),
"body" : text.unescape(text.remove_html(extr(">", "</div>"))),
})
def _pagination(self, url, params):