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

merge #7952: [hentaifoundry] add 'descriptions' option

Browse Source
This commit is contained in:
Mike Fährmann
2025-08-02 17:30:38 +02:00
parent 1fbc341e60 afa720d3e0
commit efd7821075
4 changed files with 47 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
gallery_dl/extractor/hentaifoundry.py
View File

@@ -32,6 +32,10 @@ class HentaifoundryExtractor(Extractor):
self.start_post = 0
self.start_page = 1
def _init(self):
if self.config("descriptions") == "html":
self._process_description = self._process_description_html
def items(self):
self._init_site_filters()
data = self.metadata()
@@ -77,9 +81,9 @@ class HentaifoundryExtractor(Extractor):
"artist" : text.unescape(extr('/profile">', '<')),
"_body" : extr(
'<div class="boxbody"', '<div class="boxfooter"'),
"description": text.unescape(text.remove_html(extr(
'>Description</div>', '</section>')
.replace("\r\n", "\n"), "", "")),
"description": self._process_description(extr(
"<div class='picDescript'>", '</section>')
.replace("\r\n", "\n")),
"ratings" : [text.unescape(r) for r in text.extract_iter(extr(
"class='ratings_box'", "</div>"), "title='", "'")],
"date" : text.parse_datetime(extr("datetime='", "'")),
@@ -106,6 +110,14 @@ class HentaifoundryExtractor(Extractor):
return text.nameext_from_url(data["src"], data)
def _process_description(self, description):
return text.unescape(text.remove_html(description, "", ""))
def _process_description_html(self, description):
pos1 = description.rfind('</div') # picDescript
pos2 = description.rfind('</div', None, pos1) # boxBody
return str.strip(description[0:pos2])
def _parse_story(self, html):
"""Collect url and metadata for a story"""
extr = text.extract_from(html)