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

[directlink] separate filenames from paths

Browse Source 
With this, all default filename formats specify an '{extension}'
and PathFormat.set_extension() reliably works for all files.
This commit is contained in:
Mike Fährmann
2019-11-28 23:39:35 +01:00
parent 41a3169c67
commit db35c3b581
1 changed files with 20 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
gallery_dl/extractor/directlink.py
View File

@@ -15,25 +15,30 @@ from .. import text
class DirectlinkExtractor(Extractor): class DirectlinkExtractor(Extractor):
"""Extractor for direct links to images and other media files""" """Extractor for direct links to images and other media files"""
category = "directlink" category = "directlink"
filename_fmt = "{domain}/{path}" filename_fmt = "{domain}/{path}/{filename}.{extension}"
archive_fmt = "{domain}/{path}" archive_fmt = filename_fmt
pattern = (r"(?i)https?://(?P<domain>[^/?&#]+)/(?P<path>[^?&#]+\." pattern = (r"(?i)https?://(?P<domain>[^/?&#]+)/(?P<path>[^?&#]+\."
r"(?:jpe?g|jpe|png|gif|web[mp]|mp4|mkv|og[gmv]|opus))" r"(?:jpe?g|jpe|png|gif|web[mp]|mp4|mkv|og[gmv]|opus))"
r"(?:\?(?P<query>[^/?#]*))?(?:#(?P<fragment>.*))?$") r"(?:\?(?P<query>[^/?#]*))?(?:#(?P<fragment>.*))?$")
test = ( test = (
(("https://en.wikipedia.org/static/images/project-logos/enwiki.png"), { (("https://en.wikipedia.org/static/images/project-logos/enwiki.png"), {
"url": "18c5d00077332e98e53be9fed2ee4be66154b88d", "url": "18c5d00077332e98e53be9fed2ee4be66154b88d",
"keyword": "e81b9fe3022e971365dd859f38e4ef717a6c69ed", "keyword": "105770a3f4393618ab7b811b731b22663b5d3794",
}),
# empty path
(("https://example.org/file.webm"), {
"url": "2d807ed7059d1b532f1bb71dc24b510b80ff943f",
"keyword": "29dad729c40fb09349f83edafa498dba1297464a",
}), }),
# more complex example # more complex example
("https://example.org/path/file.webm?que=1&ry=2#fragment", { ("https://example.org/path/to/file.webm?que=1&ry=2#fragment", {
"url": "fd4aec8a32842343394e6078a06c3e6b647bf671", "url": "114b8f1415cc224b0f26488ccd4c2e7ce9136622",
"keyword": "ff75764b1ae66615b723a6357b8193fa2de84678", "keyword": "06014abd503e3b2b58aa286f9bdcefdd2ae336c0",
}), }),
# percent-encoded characters # percent-encoded characters
("https://example.org/%27%3C%23/%23%3E%27.jpg?key=%3C%26%3E", { ("https://example.org/%27%3C%23/%23%3E%27.jpg?key=%3C%26%3E", {
"url": "2627e8140727fdf743f86fe18f69f99a052c9718", "url": "2627e8140727fdf743f86fe18f69f99a052c9718",
"keyword": "4d19dc12e41ffcb4cbec2013e335cf482377c35e", "keyword": "831790fddda081bdddd14f96985ab02dc5b5341f",
}), }),
# upper case file extension (#296) # upper case file extension (#296)
("https://post-phinf.pstatic.net/MjAxOTA1MjlfMTQ4/MDAxNTU5MTI2NjcyNTkw" ("https://post-phinf.pstatic.net/MjAxOTA1MjlfMTQ4/MDAxNTU5MTI2NjcyNTkw"
@@ -46,11 +51,14 @@ class DirectlinkExtractor(Extractor):
self.data = match.groupdict() self.data = match.groupdict()
def items(self): def items(self):
text.nameext_from_url(self.url, self.data) data = self.data
for key, value in self.data.items(): for key, value in data.items():
if value: if value:
self.data[key] = text.unquote(value) data[key] = text.unquote(value)
data["path"], _, name = data["path"].rpartition("/")
data["filename"], _, ext = name.rpartition(".")
data["extension"] = ext.lower()
yield Message.Version, 1 yield Message.Version, 1
yield Message.Directory, self.data yield Message.Directory, data
yield Message.Url, self.url, self.data yield Message.Url, self.url, data