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

[mangafox] extract more metadata (#3167)

Browse Source
This commit is contained in:
Mike Fährmann
2022-12-13 16:12:48 +01:00
parent 3082544fff
commit 1cbc234819
1 changed files with 58 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
gallery_dl/extractor/mangafox.py
View File

@@ -10,7 +10,6 @@
from .common import ChapterExtractor, MangaExtractor from .common import ChapterExtractor, MangaExtractor
from .. import text from .. import text
import re
BASE_PATTERN = r"(?:https?://)?(?:www\.|m\.)?(?:fanfox\.net|mangafox\.me)" BASE_PATTERN = r"(?:https?://)?(?:www\.|m\.)?(?:fanfox\.net|mangafox\.me)"
@@ -44,14 +43,14 @@ class MangafoxChapterExtractor(ChapterExtractor):
cid , pos = text.extract(page, "var chapter_id =", ";", pos) cid , pos = text.extract(page, "var chapter_id =", ";", pos)
return { return {
"manga": text.unescape(manga), "manga" : text.unescape(manga),
"volume": text.parse_int(self.volume), "volume" : text.parse_int(self.volume),
"chapter": text.parse_int(self.chapter), "chapter" : text.parse_int(self.chapter),
"chapter_minor": self.minor or "", "chapter_minor" : self.minor or "",
"chapter_string": self.cstr, "chapter_string": self.cstr,
"count": text.parse_int(count), "count" : text.parse_int(count),
"sid": text.parse_int(sid), "sid" : text.parse_int(sid),
"cid": text.parse_int(cid), "cid" : text.parse_int(cid),
} }
def images(self, page): def images(self, page):
@@ -76,6 +75,25 @@ class MangafoxMangaExtractor(MangaExtractor):
("https://fanfox.net/manga/kanojo_mo_kanojo", { ("https://fanfox.net/manga/kanojo_mo_kanojo", {
"pattern": MangafoxChapterExtractor.pattern, "pattern": MangafoxChapterExtractor.pattern,
"count": ">=60", "count": ">=60",
"keyword": {
"author": "HIROYUKI",
"chapter": int,
"chapter_minor": r"re:^(\.\d+)?$",
"chapter_string": r"re:(v\d+/)?c\d+",
"date": "type:datetime",
"description": "High school boy Naoya gets a confession from M"
"omi, a cute and friendly girl. However, Naoya "
"already has a girlfriend, Seki... but Momi is "
"too good a catch to let go. Momi and Nagoya's "
"goal becomes clear: convince Seki to accept be"
"ing an item with the two of them. Will she bud"
"ge?",
"lang": "en",
"language": "English",
"manga": "Kanojo mo Kanojo",
"tags": ["Comedy", "Romance", "School Life", "Shounen"],
"volume": int,
},
}), }),
("https://mangafox.me/manga/shangri_la_frontier", { ("https://mangafox.me/manga/shangri_la_frontier", {
"pattern": MangafoxChapterExtractor.pattern, "pattern": MangafoxChapterExtractor.pattern,
@@ -85,34 +103,41 @@ class MangafoxMangaExtractor(MangaExtractor):
) )
def chapters(self, page): def chapters(self, page):
match_info = re.compile(r"Ch (\d+)(\S*)(?: (.*))?").match results = []
manga, pos = text.extract(page, '<p class="title">', '</p>') chapter_match = MangafoxChapterExtractor.pattern.match
author, pos = text.extract(page, '<p>Author(s):', '</p>', pos)
extr = text.extract_from(page)
manga = extr('<p class="title">', '</p>')
author = extr('<p>Author(s):', '</p>')
extr('<dd class="chlist">', '')
genres, _, summary = text.extr(
page, '<div class="manga-genres">', '</section>'
).partition('<div class="manga-summary">')
data = { data = {
"manga" : text.unescape(manga), "manga" : text.unescape(manga),
"author" : text.remove_html(author), "author" : text.remove_html(author),
"lang" : "en", "description": text.unescape(text.remove_html(summary)),
"language": "English", "tags" : text.split_html(genres),
"lang" : "en",
"language" : "English",
} }
results = []
pos = page.index('<dd class="chlist">')
while True: while True:
url, pos = text.extract(page, '<a href="//', '"', pos) url = "https://" + extr('<a href="//', '"')
if url == 'mangafox.la?f=mobile': match = chapter_match(url)
if not match:
return results return results
info, pos = text.extract(page, '>', '<span', pos) _, cstr, volume, chapter, minor = match.groups()
date, pos = text.extract(page, 'right">', '</span>', pos)
match = match_info(text.unescape(info)) chapter = {
if match: "volume" : text.parse_int(volume),
chapter, minor, title = match.groups() "chapter" : text.parse_int(chapter),
chapter_minor = minor "chapter_minor" : minor or "",
else: "chapter_string": cstr,
chapter, _, minor = url[:-7].rpartition("/c")[2].partition(".") "date" : text.parse_datetime(
chapter_minor = "." + minor extr('right">', '</span>'), "%b %d, %Y"),
}
data["chapter"] = text.parse_int(chapter) chapter.update(data)
data["chapter_minor"] = chapter_minor if minor else "" results.append((url, chapter))
data["date"] = date
results.append(("https://" + url, data.copy()))