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

[2chen] fix extraction (#3356)

Browse Source 
update 'archive_fmt'
update tests
update 'board' regex
This commit is contained in:
enduser420
2022-12-04 20:49:36 +05:30
committed by GitHub
parent 54844944ab
commit 4bc756dfe0
1 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
gallery_dl/extractor/2chen.py
View File

@@ -16,13 +16,15 @@ class _2chenThreadExtractor(Extractor):
subcategory = "thread" subcategory = "thread"
directory_fmt = ("{category}", "{board}", "{thread} {title}") directory_fmt = ("{category}", "{board}", "{thread} {title}")
filename_fmt = "{time} {filename}.{extension}" filename_fmt = "{time} {filename}.{extension}"
archive_fmt = "{board}_{thread}_{hash}" archive_fmt = "{board}_{thread}_{hash}_{time}"
root = "https://2chen.moe" root = "https://2chen.moe"
pattern = r"(?:https?://)?2chen\.moe/([^/?#]+)/(\d+)" pattern = r"(?:https?://)?2chen\.moe/([^/?#]+)/(\d+)"
test = ( test = (
("https://2chen.moe/jp/303786", { ("https://2chen.moe/tv/496715", {
"count": ">= 10", "count": ">= 179",
}), }),
# 404
("https://2chen.moe/jp/303786"),
) )
def __init__(self, match): def __init__(self, match):
@@ -31,7 +33,7 @@ class _2chenThreadExtractor(Extractor):
def items(self): def items(self):
url = "{}/{}/{}".format(self.root, self.board, self.thread) url = "{}/{}/{}".format(self.root, self.board, self.thread)
page = self.request(url, encoding="utf-8").text page = self.request(url, encoding="utf-8", notfound="thread").text
data = self.metadata(page) data = self.metadata(page)
yield Message.Directory, data yield Message.Directory, data
for post in self.posts(page): for post in self.posts(page):
@@ -66,7 +68,7 @@ class _2chenThreadExtractor(Extractor):
"%d %b %Y (%a) %H:%M:%S" "%d %b %Y (%a) %H:%M:%S"
), ),
"no" : extr('href="#p', '"'), "no" : extr('href="#p', '"'),
"url" : extr('</span><a href="', '"'), "url" : extr('</a><a href="', '"'),
"filename": text.unescape(extr('download="', '"')), "filename": text.unescape(extr('download="', '"')),
"hash" : extr('data-hash="', '"'), "hash" : extr('data-hash="', '"'),
} }
@@ -77,7 +79,7 @@ class _2chenBoardExtractor(Extractor):
category = "2chen" category = "2chen"
subcategory = "board" subcategory = "board"
root = "https://2chen.moe" root = "https://2chen.moe"
pattern = r"(?:https?://)?2chen\.moe/([^/?#]+)(?:/catalog)?/?$" pattern = r"(?:https?://)?2chen\.moe/([^/?#]+)(?:/catalog|/?$)"
test = ( test = (
("https://2chen.moe/co/", { ("https://2chen.moe/co/", {
"pattern": _2chenThreadExtractor.pattern "pattern": _2chenThreadExtractor.pattern
@@ -92,7 +94,7 @@ class _2chenBoardExtractor(Extractor):
def items(self): def items(self):
url = "{}/{}/catalog".format(self.root, self.board) url = "{}/{}/catalog".format(self.root, self.board)
page = self.request(url).text page = self.request(url, notfound="board").text
data = {"_extractor": _2chenThreadExtractor} data = {"_extractor": _2chenThreadExtractor}
for thread in text.extract_iter( for thread in text.extract_iter(
page, '<figure><a href="', '"'): page, '<figure><a href="', '"'):