03}"]
filename_fmt = "{comic}_{issue:>03}_{page:>03}.{extension}"
root = "http://readcomiconline.to"
+ useragent = "Wget/1.19.2 (linux-gnu)"
- def __init__(self, match):
- kissmanga.KissmangaExtractor.__init__(self, match)
- self.session.headers["User-Agent"] = "Wget/1.19.2 (linux-gnu)"
+ request = cloudflare.request_func
-class ReadcomiconlineComicExtractor(ReadcomiconlineExtractor,
- kissmanga.KissmangaMangaExtractor):
+class ReadcomiconlineComicExtractor(ReadcomiconlineBase, MangaExtractor):
"""Extractor for comics from readcomiconline.to"""
subcategory = "comic"
- pattern = [r"(?i)(?:https?://)?(?:www\.)?readcomiconline\.to/"
- r"Comic/[^/?&#]+/?$"]
+ pattern = [r"(?i)(?:https?://)?(?:www\.)?(readcomiconline\.to"
+ r"/Comic/[^/?&#]+/?)$"]
test = [
("http://readcomiconline.to/Comic/W-i-t-c-h", {
"url": "c5a530538a30b176916e30cbe223a93d83cb2691",
@@ -42,6 +40,10 @@ class ReadcomiconlineComicExtractor(ReadcomiconlineExtractor,
}),
]
+ def __init__(self, match):
+ MangaExtractor.__init__(self, match)
+ self.session.headers["User-Agent"] = self.useragent
+
def chapters(self, page):
results = []
comic, pos = text.extract(page, '', '<')
@@ -58,19 +60,21 @@ class ReadcomiconlineComicExtractor(ReadcomiconlineExtractor,
return results
-class ReadcomiconlineIssueExtractor(ReadcomiconlineExtractor,
- kissmanga.KissmangaChapterExtractor):
+class ReadcomiconlineIssueExtractor(ReadcomiconlineBase, ChapterExtractor):
"""Extractor for comic-issues from readcomiconline.to"""
subcategory = "issue"
- pattern = [r"(?i)(?:https?://)?(?:www\.)?readcomiconline\.to/"
- r"Comic/[^/?&#]+/[^/?&#]+\?id=\d+"]
+ pattern = [r"(?i)(?:https?://)?(?:www\.)?readcomiconline\.to"
+ r"/Comic/[^/?&#]+/[^/?&#]+\?id=\d+"]
test = [("http://readcomiconline.to/Comic/W-i-t-c-h/Issue-130?id=22289", {
"url": "a45c77f8fbde66091fe2346d6341f9cf3c6b1bc5",
"keyword": "dee8a8a44659825afe1d69e1d809a48b03e98c68",
})]
- def get_job_metadata(self, page):
- """Collect metadata for extractor-job"""
+ def __init__(self, match):
+ ChapterExtractor.__init__(self, match.group(0))
+ self.session.headers["User-Agent"] = self.useragent
+
+ def get_metadata(self, page):
comic, pos = text.extract(page, " - Read\r\n ", "\r\n")
iinfo, pos = text.extract(page, " ", "\r\n", pos)
match = re.match(r"(?:Issue )?#(\d+)|(.+)", iinfo)
@@ -82,6 +86,10 @@ class ReadcomiconlineIssueExtractor(ReadcomiconlineExtractor,
}
@staticmethod
- def get_image_urls(page):
- """Extract list of all image-urls for a manga chapter"""
- return list(text.extract_iter(page, 'lstImages.push("', '"'))
+ def get_images(page):
+ return [
+ (url, None)
+ for url in text.extract_iter(
+ page, 'lstImages.push("', '"'
+ )
+ ]
diff --git a/gallery_dl/extractor/spectrumnexus.py b/gallery_dl/extractor/spectrumnexus.py
index 2cfc1d99..93630196 100644
--- a/gallery_dl/extractor/spectrumnexus.py
+++ b/gallery_dl/extractor/spectrumnexus.py
@@ -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', '', ' · SPECTRUM NEXUS '),
@@ -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, '