Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 10:42:34 +01:00
Code Issues Releases Wiki Activity

[powermanga] transfer code from redhawkscans

Browse Source
This commit is contained in:
Mike Fährmann 2015-11-21 04:19:23 +01:00
parent e9547ebdf3
commit bcb23e44ce
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 42 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
gallery_dl/extractor/powermanga.py
View File

@ -8,7 +8,11 @@
"""Extract manga pages from http://powermanga.org/"""
from .redhawkscans import RedHawkScansExtractor
from .common import Extractor, Message
from .. import text, iso639_1
import os.path
import json
import re
info = {
"category": "powermanga",
@ -21,10 +25,44 @@ info = {
],
}
class PowerMangaExtractor(RedHawkScansExtractor):
class PowerMangaExtractor(Extractor):
def __init__(self, match):
RedHawkScansExtractor.__init__(self, match)
extra = "er" if "://reader" in match.string else ""
Extractor.__init__(self)
self.category = info["category"]
self.part = match.group(1)
self.lang = match.group(2)
extra = "er" if "://reader" in match.string else ""
self.url_base = "https://read" + extra + ".powermanga.org/read/"
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"""
response = self.request(self.url_base + self.part)
response.encoding = "utf-8"
page = response.text
_ , pos = text.extract(page, '<h1 class="tbtitle dnone">', '')
manga , pos = text.extract(page, 'title="', '"', pos)
chapter , pos = text.extract(page, '">', '</a>', pos)
json_data, pos = text.extract(page, 'var pages = ', ';', pos)
match = re.match(r"(\w+ (\d+)([^:+]*)(?:: (.*))?|[^:]+)", chapter)
return {
"category": self.category,
"manga": text.unescape(manga),
"chapter": match.group(2) or match.group(1),
"chapter-minor": match.group(3) or "",
"lang": self.lang,
"language": iso639_1.code_to_language(self.lang),
"title": text.unescape(match.group(4) or ""),
}, json.loads(json_data)