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

[shimmie2] use 'self.groups' to access matched URL values

Browse Source
This commit is contained in:
Mike Fährmann
2024-10-10 19:01:30 +02:00
parent 09d4c281b6
commit 0f7d032773
1 changed files with 10 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
gallery_dl/extractor/shimmie2.py
View File

@@ -99,20 +99,15 @@ class Shimmie2TagExtractor(Shimmie2Extractor):
subcategory = "tag" subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}") directory_fmt = ("{category}", "{search_tags}")
file_url_fmt = "{}/_images/{}/{}%20-%20{}.{}" file_url_fmt = "{}/_images/{}/{}%20-%20{}.{}"
pattern = BASE_PATTERN + r"post/list/([^/?#]+)(?:/(\d+))?()" pattern = BASE_PATTERN + r"post/list/([^/?#]+)(?:/(\d+))?"
example = "https://vidya.pics/post/list/TAG/1" example = "https://vidya.pics/post/list/TAG/1"
def __init__(self, match):
Shimmie2Extractor.__init__(self, match)
lastindex = match.lastindex
self.tags = text.unquote(match.group(lastindex-2))
self.page = match.group(lastindex-1)
def metadata(self): def metadata(self):
self.tags = text.unquote(self.groups[-2])
return {"search_tags": self.tags} return {"search_tags": self.tags}
def posts(self): def posts(self):
pnum = text.parse_int(self.page, 1) pnum = text.parse_int(self.groups[-1], 1)
file_url_fmt = self.file_url_fmt.format file_url_fmt = self.file_url_fmt.format
init = True init = True
@@ -166,7 +161,7 @@ class Shimmie2TagExtractor(Shimmie2Extractor):
return return
def _posts_giantessbooru(self): def _posts_giantessbooru(self):
pnum = text.parse_int(self.page, 1) pnum = text.parse_int(self.groups[-1], 1)
file_url_fmt = (self.root + "/index.php?q=/image/{}.jpg").format file_url_fmt = (self.root + "/index.php?q=/image/{}.jpg").format
while True: while True:
@@ -203,18 +198,15 @@ class Shimmie2PostExtractor(Shimmie2Extractor):
pattern = BASE_PATTERN + r"post/view/(\d+)" pattern = BASE_PATTERN + r"post/view/(\d+)"
example = "https://vidya.pics/post/view/12345" example = "https://vidya.pics/post/view/12345"
def __init__(self, match):
Shimmie2Extractor.__init__(self, match)
self.post_id = match.group(match.lastindex)
def posts(self): def posts(self):
url = "{}/post/view/{}".format(self.root, self.post_id) post_id = self.groups[-1]
url = "{}/post/view/{}".format(self.root, post_id)
page = self.request(url).text page = self.request(url).text
extr = text.extract_from(page) extr = text.extract_from(page)
quote = self._quote_type(page) quote = self._quote_type(page)
post = { post = {
"id" : self.post_id, "id" : post_id,
"tags" : extr(": ", "<").partition(" - ")[0].rstrip(")"), "tags" : extr(": ", "<").partition(" - ")[0].rstrip(")"),
"md5" : extr("/_thumbs/", "/"), "md5" : extr("/_thumbs/", "/"),
"file_url": self.root + ( "file_url": self.root + (
@@ -232,12 +224,12 @@ class Shimmie2PostExtractor(Shimmie2Extractor):
return (post,) return (post,)
def _posts_giantessbooru(self): def _posts_giantessbooru(self):
url = "{}/index.php?q=/post/view/{}".format( post_id = self.groups[-1]
self.root, self.post_id) url = "{}/index.php?q=/post/view/{}".format(self.root, post_id)
extr = text.extract_from(self.request(url).text) extr = text.extract_from(self.request(url).text)
return ({ return ({
"id" : self.post_id, "id" : post_id,
"tags" : extr(": ", "<").partition(" - ")[0].rstrip(")"), "tags" : extr(": ", "<").partition(" - ")[0].rstrip(")"),
"md5" : "", "md5" : "",
"file_url": self.root + extr("id='main_image' src='.", "'"), "file_url": self.root + extr("id='main_image' src='.", "'"),