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

change Chapter and MangaExtractor classes

Browse Source 
- unify and simplify constructors
- rename get_metadata and get_images to just metadata() and images()
- rename self.url to chapter_url and manga_url
This commit is contained in:
Mike Fährmann
2019-02-11 18:38:47 +01:00
parent 4b1880fa5e
commit 580baef72c
24 changed files with 435 additions and 467 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
gallery_dl/extractor/hentai2read.py
View File

@@ -10,21 +10,65 @@
from .common import ChapterExtractor, MangaExtractor
from .. import text
import re
import json
import re
class Hentai2readMangaExtractor(MangaExtractor):
"""Extractor for hmanga from hentai2read.com"""
class Hentai2readBase():
"""Base class for hentai2read extractors"""
category = "hentai2read"
scheme = "https"
pattern = r"(?:https?://)?(?:www\.)?(hentai2read\.com/[^/]+/?)$"
root = "https://hentai2read.com"
class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
"""Extractor for a single manga chapter from hentai2read.com"""
archive_fmt = "{chapter_id}_{page}"
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?&#]+/(\d+))"
test = ("https://hentai2read.com/amazon_elixir/1/", {
"url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
"keyword": "9845105898d28c6a540cffdea60a1a20fab52431",
})
def __init__(self, match):
self.chapter = match.group(2)
ChapterExtractor.__init__(self, match)
def metadata(self, page):
title, pos = text.extract(page, "<title>", "</title>")
manga_id, pos = text.extract(page, 'data-mid="', '"', pos)
chapter_id, pos = text.extract(page, 'data-cid="', '"', pos)
match = re.match(r"Reading (.+) \(([^)]+)\) Hentai(?: by (.+))? - "
r"(\d+): (.+) . Page 1 ", title)
return {
"manga": match.group(1),
"manga_id": text.parse_int(manga_id),
"chapter": text.parse_int(self.chapter),
"chapter_id": text.parse_int(chapter_id),
"type": match.group(2),
"author": match.group(3),
"title": match.group(5),
"lang": "en",
"language": "English",
}
@staticmethod
def images(page):
images = text.extract(page, "'images' : ", ",\n")[0]
return [
("https://hentaicdn.com/hentai" + part, None)
for part in json.loads(images)
]
class Hentai2readMangaExtractor(Hentai2readBase, MangaExtractor):
"""Extractor for hmanga from hentai2read.com"""
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?&#]+)/?$"
test = (
("http://hentai2read.com/amazon_elixir/", {
("https://hentai2read.com/amazon_elixir/", {
"url": "273073752d418ec887d7f7211e42b832e8c403ba",
"keyword": "13c1ce7e15cbb941f01c843b0e89adc993d939ac",
}),
("http://hentai2read.com/oshikage_riot/", {
("https://hentai2read.com/oshikage_riot/", {
"url": "6595f920a3088a15c2819c502862d45f8eb6bea6",
"keyword": "675c7b7a4fa52cf569c283553bd16b4200a5cd36",
}),
@@ -54,46 +98,3 @@ class Hentai2readMangaExtractor(MangaExtractor):
"chapter": text.parse_int(chapter),
"title": title, "lang": "en", "language": "English",
}))
class Hentai2readChapterExtractor(ChapterExtractor):
"""Extractor for a single manga chapter from hentai2read.com"""
category = "hentai2read"
archive_fmt = "{chapter_id}_{page}"
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com/([^/]+)/(\d+)"
test = ("http://hentai2read.com/amazon_elixir/1/", {
"url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
"keyword": "9845105898d28c6a540cffdea60a1a20fab52431",
})
def __init__(self, match):
url_title, self.chapter = match.groups()
url = "https://hentai2read.com/{}/{}/".format(url_title, self.chapter)
ChapterExtractor.__init__(self, match, url)
def get_metadata(self, page):
title, pos = text.extract(page, "<title>", "</title>")
manga_id, pos = text.extract(page, 'data-mid="', '"', pos)
chapter_id, pos = text.extract(page, 'data-cid="', '"', pos)
match = re.match(r"Reading (.+) \(([^)]+)\) Hentai(?: by (.+))? - "
r"(\d+): (.+) . Page 1 ", title)
return {
"manga": match.group(1),
"manga_id": text.parse_int(manga_id),
"chapter": text.parse_int(self.chapter),
"chapter_id": text.parse_int(chapter_id),
"type": match.group(2),
"author": match.group(3),
"title": match.group(5),
"lang": "en",
"language": "English",
}
@staticmethod
def get_images(page):
"""Extract and return a list of all image-urls"""
images = text.extract(page, "'images' : ", ",\n")[0]
return [
("https://hentaicdn.com/hentai" + part, None)
for part in json.loads(images)
]