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

[warosu] Attribute fix

Browse Source
This commit is contained in:
NecRaul
2025-06-16 12:33:16 +04:00
parent 0a3fac2dfe
commit f56e810f42
1 changed files with 12 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
gallery_dl/extractor/warosu.py
View File

@@ -18,7 +18,7 @@ class WarosuThreadExtractor(Extractor):
subcategory = "thread"
root = "https://warosu.org"
directory_fmt = ("{category}", "{board}", "{thread} - {title}")
filename_fmt = "{tim}-{filename}.{extension}"
filename_fmt = "{tim} {filename}.{extension}"
archive_fmt = "{board}_{thread}_{tim}"
pattern = r"(?:https?://)?(?:www\.)?warosu\.org/([^/]+)/thread/(\d+)"
example = "https://warosu.org/a/thread/12345"
@@ -47,7 +47,7 @@ class WarosuThreadExtractor(Extractor):
def metadata(self, page):
boardname = text.extr(page, "<title>", "</title>")
title = text.unescape(text.extr(page, "class=filetitle>", "<"))
title = text.unescape(text.extr(page, "class=\"filetitle\">", "<"))
return {
"board" : self.board,
"board_name": boardname.split(" - ")[1],
@@ -57,14 +57,15 @@ class WarosuThreadExtractor(Extractor):
def posts(self, page):
"""Build a list of all post objects"""
page = text.extr(page, "<div class=content", "</form>")
page = text.extr(page, "<div class=\"content\"", "</form>")
needle = "<table>"
return [self.parse(post) for post in page.split(needle)]
def parse(self, post):
"""Build post object by extracting data from an HTML post"""
data = self._extract_post(post)
if "<span class=fileinfo>" in post and self._extract_image(post, data):
if "<span class=\"fileinfo\">" in post and \
self._extract_image(post, data):
part = data["image"].rpartition("/")[2]
data["tim"], _, data["extension"] = part.partition(".")
data["ext"] = "." + data["extension"]
@@ -73,9 +74,9 @@ class WarosuThreadExtractor(Extractor):
def _extract_post(self, post):
extr = text.extract_from(post)
return {
"no" : extr("id=p", ">"),
"name": extr("class=postername>", "<").strip(),
"time": extr("class=posttime title=", "000>"),
"no" : extr("id=\"p", "\""),
"name": extr("class=\"postername \">", "<").strip(),
"time": extr("class=\"posttime\" title=\"", "000\">"),
"now" : extr("", "<").strip(),
"com" : text.unescape(text.remove_html(extr(
"<blockquote>", "</blockquote>").strip())),
@@ -83,14 +84,15 @@ class WarosuThreadExtractor(Extractor):
def _extract_image(self, post, data):
extr = text.extract_from(post)
data["fsize"] = extr("<span class=fileinfo> File: ", ", ")
extr("<span class=\"fileinfo\">", "")
data["fsize"] = extr("File: ", ", ")
data["w"] = extr("", "x")
data["h"] = extr("", ", ")
data["filename"] = text.unquote(extr(
"", "<").rstrip().rpartition(".")[0])
extr("<br>", "")
extr("<br />", "")
url = extr("<a href=", ">")
url = extr("<a href=\"", "\">")
if url:
if url[0] == "/":
data["image"] = self.root + url