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

[redhawkscans] generalize to allow subclassing

Browse Source
This commit is contained in:
Mike Fährmann 2015-11-01 01:46:00 +01:00
parent b47f3b9d78
commit d6325865e8
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
gallery_dl/extractor/redhawkscans.py
View File

@ -20,7 +20,7 @@ info = {
"directory": ["{category}", "{manga}", "c{chapter:>03}{chapter-minor} - {title}"], "directory": ["{category}", "{manga}", "c{chapter:>03}{chapter-minor} - {title}"],
"filename": "{manga}_c{chapter:>03}{chapter-minor}_{page:>03}.{extension}", "filename": "{manga}_c{chapter:>03}{chapter-minor}_{page:>03}.{extension}",
"pattern": [ "pattern": [
r"(?:https?://)?manga\.redhawkscans\.com/reader/read/(.+)(?:/page)?.*", r"(?:https?://)?manga\.redhawkscans\.com/reader/read/(.+)(?:/page)?",
], ],
} }
@ -30,6 +30,7 @@ class RedHawkScansExtractor(Extractor):
def __init__(self, match): def __init__(self, match):
Extractor.__init__(self) Extractor.__init__(self)
self.category = info["category"]
self.part = match.group(1) self.part = match.group(1)
def items(self): def items(self):
@ -52,13 +53,13 @@ class RedHawkScansExtractor(Extractor):
_ , pos = text.extract(page, '<h1 class="tbtitle dnone">', '') _ , pos = text.extract(page, '<h1 class="tbtitle dnone">', '')
manga , pos = text.extract(page, 'title="', '"', pos) manga , pos = text.extract(page, 'title="', '"', pos)
chapter , pos = text.extract(page, '">', '</a>', pos) chapter , pos = text.extract(page, '">', '</a>', pos)
json_data, pos = text.extract(page, 'var pages = ', ';\r\n', pos) json_data, pos = text.extract(page, 'var pages = ', ';', pos)
match = re.match(r"(Chapter (\d+)([^:+]*)(?:: (.*))?|[^:]+)", chapter) match = re.match(r"(\w+ (\d+)([^:+]*)(?:: (.*))?|[^:]+)", chapter)
return { return {
"category": info["category"], "category": self.category,
"manga": text.unescape(manga), "manga": text.unescape(manga),
"chapter": match.group(2) or match.group(1), "chapter": match.group(2) or match.group(1),
"chapter-minor": match.group(3) or "", "chapter-minor": match.group(3) or "",
"language": "English", "language": "English", #TODO: lookup table for language codes (en, it, ch, ...)
"title": text.unescape(match.group(4) or ""), "title": text.unescape(match.group(4) or ""),
}, json.loads(json_data) }, json.loads(json_data)