Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 02:32:33 +01:00
Code Issues Releases Wiki Activity

[powermanga] just inherit from redhawkscans

Browse Source
This commit is contained in:
Mike Fährmann 2015-11-01 01:47:58 +01:00
parent d6325865e8
commit 6dcfed16fc
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 9 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
gallery_dl/extractor/powermanga.py
View File

@ -8,55 +8,22 @@
"""Extract manga pages from http://powermanga.org/"""
from .common import Extractor, Message
from .. import text
import os.path
import json
from .redhawkscans import RedHawkScansExtractor
info = {
"category": "powermanga",
"extractor": "PowerMangaExtractor",
"directory": ["{category}", "{manga}", "c{chapter:>03} - {title}"],
"filename": "{manga}_c{chapter:>03}_{page:>03}.{extension}",
"directory": ["{category}", "{manga}", "c{chapter:>03}{chapter-minor} - {title}"],
"filename": "{manga}_c{chapter:>03}{chapter-minor}_{page:>03}.{extension}",
"pattern": [
r"(?:https?://)?(read(?:er)?\.powermanga\.org/read/[^/]+/([^/]+)/\d+/(\d+))/.*",
r"(?:https?://)?read(?:er)?\.powermanga\.org/read/(.+)(?:/page)?",
],
}
class PowerMangaExtractor(Extractor):
class PowerMangaExtractor(RedHawkScansExtractor):
def __init__(self, match):
Extractor.__init__(self)
self.url = match.group(1)
self.language = match.group(2)
self.chapter = match.group(3)
def items(self):
yield Message.Version, 1
data, pages = self.get_job_metadata()
yield Message.Directory, data
for page_index, page_data in enumerate(pages, 1):
name, ext = os.path.splitext(page_data["filename"])
page_data.update(data)
page_data["page"] = page_index
page_data["name"] = name
page_data["extension"] = ext[1:]
yield Message.Url, "https" + page_data["url"][4:], page_data
def get_job_metadata(self):
"""Collect metadata for extractor-job"""
url = "https://" + self.url + "/page/1"
page = self.request(url).text
manga, pos = text.extract(page, '<title>', ' :: ')
_ , pos = text.extract(page, '<h1 class="tbtitle dnone">', '', pos)
title, pos = text.extract(page, 'title="Chapter {}: '
.format(self.chapter), '"', pos)
json_data, _ = text.extract(page, 'var pages = ', ';\n', pos)
return {
"category": info["category"],
"manga": text.unescape(manga),
"chapter": self.chapter,
"lang": self.language,
"language": "English", #TODO: lookup table for language codes (en, it, ch, ...)
"title": text.unescape(title),
}, json.loads(json_data)
RedHawkScansExtractor.__init__(self, match)
extra = "er" if "://reader" in match.string else ""
self.category = info["category"]
self.url_base = "https://read" + extra + ".powermanga.org/read/"