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

use generic chapter-extractor in more modules

Browse Source
This commit is contained in:
Mike Fährmann
2018-02-07 11:22:47 +01:00
parent 347baf7ac5
commit 5b3c34aa96
13 changed files with 178 additions and 303 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
gallery_dl/extractor/spectrumnexus.py
View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2015-2017 Mike Fährmann
# Copyright 2015-2018 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
@@ -8,7 +8,7 @@
"""Extract manga pages from http://www.thespectrum.net/manga_scans/"""
from .common import MangaExtractor, AsynchronousExtractor, Message
from .common import ChapterExtractor, MangaExtractor
from .. import text, util
@@ -33,55 +33,31 @@ class SpectrumnexusMangaExtractor(MangaExtractor):
return results
class SpectrumnexusChapterExtractor(AsynchronousExtractor):
class SpectrumnexusChapterExtractor(ChapterExtractor):
"""Extractor for manga-chapters or -volumes from thespectrum.net"""
category = "spectrumnexus"
subcategory = "chapter"
directory_fmt = ["{category}", "{manga}", "{identifier}"]
filename_fmt = "{manga} {identifier} {page:>03}.{extension}"
pattern = [
(r"(?:https?://)?(view\.thespectrum\.net/series/"
r"[^\.]+\.html)\?ch=(Chapter\+(\d+)|Volume\+(\d+))"),
(r"(?:https?://)?(view\.thespectrum\.net/series/"
r"[^/]+-chapter-(\d+)\.html)"),
]
directory_fmt = ["{category}", "{manga}", "{chapter_string}"]
filename_fmt = "{manga}_{chapter_string}_{page:>03}.{extension}"
pattern = [r"(?:https?://)?view\.thespectrum\.net/series/"
r"([^\.]+\.html)\?ch=(Chapter\+(\d+)|Volume\+(\d+))"]
test = [(("http://view.thespectrum.net/series/"
"toriko.html?ch=Chapter+343&page=1"), {
"url": "c0fc7dc594841217cc622a67edd79f06e9900333",
"keyword": "3d0cb57b6b1c2cbecc7aed33f83c24891a4ff53f",
"keyword": "a8abe126cbc5fc798148b0b155242a470c1ba9d1",
})]
def __init__(self, match):
AsynchronousExtractor.__init__(self)
self.url = "http://" + match.group(1)
self.identifier = match.group(2)
self.chapter = match.group(3)
self.volume = match.group(4)
path, self.chapter_string, self.chapter, self.volume = match.groups()
url = "http://view.thespectrum.net/series/{}?ch={}".format(
path, self.chapter_string)
ChapterExtractor.__init__(self, url)
def items(self):
params = {
"ch": self.identifier,
"page": 1,
}
page = self.request(self.url, params=params).text
data = self.get_job_metadata(page)
yield Message.Version, 1
yield Message.Directory, data.copy()
for i in range(1, data["count"]+1):
url = self.get_image_url(page)
text.nameext_from_url(url, data)
data["page"] = i
yield Message.Url, url, data.copy()
if i < data["count"]:
params["page"] += 1
page = self.request(self.url, params=params).text
def get_job_metadata(self, page):
"""Collect metadata for extractor-job"""
def get_metadata(self, page):
data = {
"chapter": util.safe_int(self.chapter),
"chapter_string": self.chapter_string.replace("+", " "),
"volume": util.safe_int(self.volume),
"identifier": self.identifier.replace("+", " "),
}
data = text.extract_all(page, (
('manga', '<title>', ' &#183; SPECTRUM NEXUS </title>'),
@@ -90,7 +66,9 @@ class SpectrumnexusChapterExtractor(AsynchronousExtractor):
data["count"] = util.safe_int(data["count"])
return data
@staticmethod
def get_image_url(page):
"""Extract url of one manga page"""
return text.extract(page, '<img id="mainimage" src="', '"')[0]
def get_images(self, page):
params = {"page": 1}
while True:
yield text.extract(page, '<img id="mainimage" src="', '"')[0], None
params["page"] += 1
page = self.request(self.url, params=params).text