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

[mangahere] fix extraction

Browse Source 
would switch to HTTPS, but there seem to be certificate issues
This commit is contained in:
Mike Fährmann
2017-09-26 17:08:59 +02:00
parent 8e14714c2b
commit 1ab4c7986f
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
gallery_dl/extractor/mangahere.py
View File

@@ -10,6 +10,7 @@
from .common import MangaExtractor, AsynchronousExtractor, Message from .common import MangaExtractor, AsynchronousExtractor, Message
from .. import text, util from .. import text, util
from urllib.parse import urljoin
import re import re
@@ -44,7 +45,7 @@ class MangahereMangaExtractor(MangaExtractor):
volume, pos = text.extract(page, 'span class="mr6">', '<', pos) volume, pos = text.extract(page, 'span class="mr6">', '<', pos)
title, pos = text.extract(page, '/span>', '<', pos) title, pos = text.extract(page, '/span>', '<', pos)
date, pos = text.extract(page, 'class="right">', '</span>', pos) date, pos = text.extract(page, 'class="right">', '</span>', pos)
results.append((url, { results.append((urljoin("http:", url), {
"manga": manga, "title": title, "date": date, "manga": manga, "title": title, "date": date,
"volume": util.safe_int(volume.rpartition(" ")[2]), "volume": util.safe_int(volume.rpartition(" ")[2]),
"chapter": util.safe_int(chapter), "chapter": util.safe_int(chapter),
@@ -88,7 +89,7 @@ class MangahereChapterExtractor(AsynchronousExtractor):
def get_job_metadata(self, page): def get_job_metadata(self, page):
"""Collect metadata for extractor-job""" """Collect metadata for extractor-job"""
manga, pos = text.extract(page, '<title>', '</title>') manga, pos = text.extract(page, '<title>', '</title>')
chid , pos = text.extract(page, '.mhcdn.net/store/manga/', '/', pos) chid , pos = text.extract(page, '.net/store/manga/', '/', pos)
_ , pos = text.extract(page, '<select class="wid60"', '', pos) _ , pos = text.extract(page, '<select class="wid60"', '', pos)
_ , pos = text.extract(page, '</select>', '', pos) _ , pos = text.extract(page, '</select>', '', pos)
count, pos = text.extract(page, '>', '<', pos-30) count, pos = text.extract(page, '>', '<', pos-30)