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

[mangapark] support .net and .com mirrors

Browse Source
This commit is contained in:
Mike Fährmann 2018-07-05 14:45:05 +02:00
parent c20c0a4820
commit 2eefaa99a3
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
2 changed files with 21 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
gallery_dl/extractor/mangapark.py
View File

@ -15,7 +15,7 @@ from .. import text
class MangaparkExtractor(): class MangaparkExtractor():
"""Base class for mangapark extractors""" """Base class for mangapark extractors"""
category = "mangapark" category = "mangapark"
root = "https://mangapark.me" root_fmt = "https://mangapark.{}"
@staticmethod @staticmethod
def parse_chapter_path(path, data): def parse_chapter_path(path, data):
@ -37,11 +37,20 @@ class MangaparkExtractor():
class MangaparkMangaExtractor(MangaparkExtractor, MangaExtractor): class MangaparkMangaExtractor(MangaparkExtractor, MangaExtractor):
"""Extractor for manga from mangapark.me""" """Extractor for manga from mangapark.me"""
pattern = [r"(?:https?://)?(?:www\.)?(mangapark\.me/manga/[^/]+)/?$"] pattern = [r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)"
test = [("https://mangapark.me/manga/aria", { r"(/manga/[^/?&#]+)/?$"]
"url": "4cb5606530b4eeacde7a4c9fd38296eb6ff46563", test = [
"keyword": "e87ab8e7ad2571bbe587881e7fd422e8f582f818", ("https://mangapark.me/manga/aria", {
})] "url": "4cb5606530b4eeacde7a4c9fd38296eb6ff46563",
"keyword": "e87ab8e7ad2571bbe587881e7fd422e8f582f818",
}),
("https://mangapark.net/manga/aria", None),
("https://mangapark.com/manga/aria", None),
]
def __init__(self, match):
self.root = self.root_fmt.format(match.group(1))
MangaExtractor.__init__(self, match, self.root + match.group(2))
def chapters(self, page): def chapters(self, page):
results = [] results = []
@ -69,8 +78,8 @@ class MangaparkMangaExtractor(MangaparkExtractor, MangaExtractor):
class MangaparkChapterExtractor(MangaparkExtractor, ChapterExtractor): class MangaparkChapterExtractor(MangaparkExtractor, ChapterExtractor):
"""Extractor for manga-chapters from mangapark.me""" """Extractor for manga-chapters from mangapark.me"""
pattern = [(r"(?:https?://)?(?:www\.)?mangapark\.me(/manga/[^/]+" pattern = [(r"(?:https?://)?(?:www\.)?mangapark\.(me|net|com)"
r"/s\d+(?:/v\d+)?/c\d+[^/]*(?:/e\d+)?)")] r"(/manga/[^/]+/s\d+(?:/v\d+)?/c\d+[^/]*(?:/e\d+)?)")]
test = [ test = [
("https://mangapark.me/manga/gosu/s2/c55", { ("https://mangapark.me/manga/gosu/s2/c55", {
"count": 50, "count": 50,
@ -85,10 +94,13 @@ class MangaparkChapterExtractor(MangaparkExtractor, ChapterExtractor):
"count": 15, "count": 15,
"keyword": "8d5d1608d4182495ea43ad665e25b755b6468be2", "keyword": "8d5d1608d4182495ea43ad665e25b755b6468be2",
}), }),
("https://mangapark.net/manga/gosu/s2/c55", None),
("https://mangapark.com/manga/gosu/s2/c55", None),
] ]
def __init__(self, match): def __init__(self, match):
self.path = match.group(1) tld, self.path = match.groups()
self.root = self.root_fmt.format(tld)
url = self.root + self.path + "?zoom=2" url = self.root + self.path + "?zoom=2"
ChapterExtractor.__init__(self, url) ChapterExtractor.__init__(self, url)
@ -111,16 +123,13 @@ class MangaparkChapterExtractor(MangaparkExtractor, ChapterExtractor):
def get_images(self, page): def get_images(self, page):
pos = 0 pos = 0
num = 0
while True: while True:
url, pos = text.extract(page, ' target="_blank" href="', '"', pos) url, pos = text.extract(page, ' target="_blank" href="', '"', pos)
if not url: if not url:
return return
num += 1
width , pos = text.extract(page, ' width="', '"', pos) width , pos = text.extract(page, ' width="', '"', pos)
height, pos = text.extract(page, ' _heighth="', '"', pos) height, pos = text.extract(page, ' _heighth="', '"', pos)
yield text.urljoin(self.root, url), { yield text.urljoin(self.root, url), {
"page": num,
"width": width, "width": width,
"height": height, "height": height,
} }

2
test/test_results.py
View File

@ -22,8 +22,6 @@ TRAVIS_SKIP = {
# temporary issues, etc. # temporary issues, etc.
BROKEN = { BROKEN = {
"imgth", # "temporary offline"
"mangahere", # lots of 502 Bad Gateway responses
"whatisthisimnotgoodwithcomputers", "whatisthisimnotgoodwithcomputers",
} }