Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-23 11:12:40 +01:00
Code Issues Releases Wiki Activity

[khinsider] fix and improve metadata extraction

Browse Source
This commit is contained in:
Mike Fährmann 2020-02-07 18:20:38 +01:00
parent 4a3d2405de
commit 6426e3efc7
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 29 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
gallery_dl/extractor/khinsider.py
View File

@ -1,12 +1,12 @@
# -*- coding: utf-8 -*-
# Copyright 2016-2019 Mike Fährmann
# Copyright 2016-2020 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extract soundtracks from https://downloads.khinsider.com/"""
"""Extractors for https://downloads.khinsider.com/"""
from .common import Extractor, Message, AsynchronousMixin
from .. import text, exception
@ -16,54 +16,52 @@ class KhinsiderSoundtrackExtractor(AsynchronousMixin, Extractor):
"""Extractor for soundtracks from khinsider.com"""
category = "khinsider"
subcategory = "soundtrack"
directory_fmt = ("{category}", "{album}")
archive_fmt = "{album}_{filename}.{extension}"
directory_fmt = ("{category}", "{album[name]}")
archive_fmt = "{filename}.{extension}"
pattern = (r"(?:https?://)?downloads\.khinsider\.com"
r"/game-soundtracks/album/([^/?&#]+)")
root = "https://downloads.khinsider.com"
test = (("https://downloads.khinsider.com"
"/game-soundtracks/album/horizon-riders-wii"), {
"pattern": r"https?://\d+\.\d+\.\d+\.\d+/ost/horizon-riders-wii/[^/]+"
r"/Horizon%20Riders%20Wii%20-%20Full%20Soundtrack\.mp3",
"count": 1,
"keyword": "b4f460c78dd23e1f1121f4ac784dd67ded7c2679",
"keyword": "b6bf8444ad77307c03212e91e73b1563338bd079",
})
root = "https://downloads.khinsider.com"
def __init__(self, match):
Extractor.__init__(self, match)
self.album = match.group(1)
def items(self):
url = (self.root + "/game-soundtracks/album/" + self.album)
url = self.root + "/game-soundtracks/album/" + self.album
page = self.request(url, encoding="utf-8").text
data = self.get_job_metadata(page)
yield Message.Version, 1
yield Message.Directory, data
for url, track in self.get_album_tracks(page):
track.update(data)
yield Message.Url, url, track
def get_job_metadata(self, page):
"""Collect metadata for extractor-job"""
if "Download all songs at once:" not in page:
raise exception.NotFoundError("soundtrack")
data = text.extract_all(page, (
("album", "Album name: <b>", "</b>"),
("count", "Number of Files: <b>", "</b>"),
("size" , "Total Filesize: <b>", "</b>"),
("date" , "Date added: <b>", "</b>"),
("type" , "Album type: <b>", "</b>"),
))[0]
data["album"] = text.unescape(data["album"])
return data
def get_album_tracks(self, page):
"""Collect url and metadata for all tracks of a soundtrack"""
data = self.metadata(page)
yield Message.Version, 1
yield Message.Directory, data
for track in self.tracks(page):
track.update(data)
yield Message.Url, track["url"], track
def metadata(self, page):
extr = text.extract_from(page)
return {"album": {
"name" : text.unescape(extr("Album name: <b>", "<")),
"count": text.parse_int(extr("Number of Files: <b>", "<")),
"size" : text.parse_bytes(extr("Total Filesize: <b>", "<")[:-1]),
"date" : extr("Date added: <b>", "<"),
"type" : extr("Album type: <b>", "<"),
}}
def tracks(self, page):
page = text.extract(page, '<table id="songlist">', '</table>')[0]
for num, url in enumerate(text.extract_iter(
page, '<td class="clickable-row"><a href="', '"'), 1):
url = text.urljoin(self.root, url)
page = self.request(url, encoding="utf-8").text
url = text.extract(
page, '<p><a style="color: #21363f;" href="', '"')[0]
yield url, text.nameext_from_url(url, {"num": num})
url = text.extract(page, 'style="color: #21363f;" href="', '"')[0]
yield text.nameext_from_url(url, {"num": num, "url": url})