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

[hitomi] more metadata

Browse Source
This commit is contained in:
Mike Fährmann 2015-10-29 17:53:29 +01:00
parent 9cfe2c78a5
commit 2472d0722a
1 changed files with 22 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
gallery_dl/extractor/hitomi.py
View File

@ -11,6 +11,7 @@
from .common import Extractor, Message
from .. import text
import os.path
import string
info = {
"category": "hitomi",
@ -44,15 +45,33 @@ class HitomiExtractor(Extractor):
def get_job_metadata(self, page):
"""Collect metadata for extractor-job"""
group = ""
gtype = ""
series = ""
_ , pos = text.extract(page, '<h1><a href="/reader/', '')
title , pos = text.extract(page, '.html">', "</a></h1>", pos)
title , pos = text.extract(page, '.html">', "</a>", pos)
_ , pos = text.extract(page, '<li><a href="/artist/', '', pos)
artist, pos = text.extract(page, '.html">', '</a</li>', pos)
artist, pos = text.extract(page, '.html">', '</a>', pos)
test , pos = text.extract(page, '<li><a href="/group/', '', pos)
if test is not None:
group , pos = text.extract(page, '.html">', '</a>', pos)
test , pos = text.extract(page, '<a href="/type/', '', pos)
if test is not None:
gtype , pos = text.extract(page, '.html">', '</a>', pos)
_ , pos = text.extract(page, '<tdLanguage</td>', '', pos)
lang , pos = text.extract(page, '.html">', '</a>', pos)
test , pos = text.extract(page, '<a href="/series/', '', pos)
if test is not None:
series, pos = text.extract(page, '.html">', '</a>', pos)
return {
"category": info["category"],
"gallery-id": self.gid,
"title": title,
"artist": artist,
"artist": string.capwords(artist),
"group": string.capwords(group),
"type": gtype[1:-1].capitalize(),
"lang": lang.capitalize(),
"series": string.capwords(series),
}
@staticmethod