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

rewrite extractors to use text-module

Browse Source
This commit is contained in:
Mike Fährmann
2015-10-03 15:43:02 +02:00
parent 2962bf36f6
commit 42b8e81a68
11 changed files with 66 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
gallery_dl/extractor/redhawkscans.py
View File

@@ -8,9 +8,8 @@
"""Extract manga pages from http://manga.redhawkscans.com/"""
from .common import SequentialExtractor
from .common import Message
from .common import unescape
from .common import SequentialExtractor, Message
from .. import text
import os.path
import json
import re
@@ -50,16 +49,16 @@ class RedHawkScansExtractor(SequentialExtractor):
response = self.request(self.url_base + self.part)
response.encoding = "utf-8"
page = response.text
_ , pos = self.extract(page, '<h1 class="tbtitle dnone">', '')
manga , pos = self.extract(page, 'title="', '"', pos)
chapter , pos = self.extract(page, '">', '</a>', pos)
json_data, pos = self.extract(page, 'var pages = ', ';\r\n', pos)
_ , 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 = ', ';\r\n', pos)
match = re.match(r"(Chapter (\d+)([^:+]*)(?:: (.*))?|[^:]+)", chapter)
return {
"category": info["category"],
"manga": unescape(manga),
"manga": text.unescape(manga),
"chapter": match.group(2) or match.group(1),
"chapter-minor": match.group(3) or "",
"language": "English",
"title": unescape(match.group(4) or ""),
"title": text.unescape(match.group(4) or ""),
}, json.loads(json_data)