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

[tmohentai] inherit from GalleryExtractor. refactor metadata.

Browse Source
This commit is contained in:
jsouthgb
2023-11-20 21:35:32 -05:00
parent ed965eecbb
commit 31963fa947
1 changed files with 28 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
gallery_dl/extractor/tmohentai.py
View File

@@ -6,14 +6,15 @@
"""Extractors for https://tmohentai.com/"""
from .common import Extractor, Message
from .common import GalleryExtractor, Message
from .. import text
BASE_PATTERN = r'(?:https?://)?tmohentai\.com'
class TmohentaiExtractor(Extractor):
class TmohentaiGalleryExtractor(GalleryExtractor):
category = 'tmohentai'
subcategory = 'gallery'
root = 'http://tmohentai.com'
directory_fmt = ('{category}', '{title}')
filename_fmt = '{title}_{filename}.{extension}'
@@ -22,71 +23,51 @@ class TmohentaiExtractor(Extractor):
example = 'https://tmohentai.com/contents/12345a67b89c0'
def __init__(self, match):
Extractor.__init__(self, match)
GalleryExtractor.__init__(self, match)
self.contents = match.group(2)
self.reader = match.group(3)
self.id_string = match.group(4)
def parse_location(self):
if self.contents:
url = '{}/reader/{}/paginated'.format(self.root, self.id_string)
else:
url_str = self.url.rpartition('/')
if url_str[-1].isdigit():
url = url_str[0]
else:
url = self.url
url = self.url
if self.reader:
url = '{}/contents/{}'.format(self.root, self.id_string)
return url
@staticmethod
def get_file_info(page_src):
file = text.extr(page_src, 'data-original="', '"')
file_loc, _, file_name = file.rpartition('/')
start_num, ext = file_name.split('.')
return file_loc, start_num, ext
def items(self):
url = self.parse_location()
page_src = self.request(
page = self.request(
text.ensure_http_scheme(url)).text
data = self.metadata(page)
data = self.metadata()
yield Message.Directory, data
imgs = self.images(page)
file_loc, start_num, ext = self.get_file_info(page_src)
page_nums = text.extract_iter(
page_src, 'option value="', '"')
for num, page in enumerate(page_nums, start=int(start_num)):
file = '{}/{:>03}.{}'.format(file_loc, num, ext)
img = text.nameext_from_url(file, {
'num' : num,
cdn = 'https://imgrojo.tmohentai.com/contents'
for num, _ in enumerate(imgs, start=0):
url = ('{}/{}/{:>03}.webp'.format(cdn, self.id_string, num))
img = text.nameext_from_url(url, {
'num' : num + 1,
'title' : data['title'],
'id_string': self.id_string,
})
yield Message.Url, file, img
yield Message.Url, url, img
def metadata(self):
contents = '{}/contents/{}'.format(self.root, self.id_string)
contents_src = self.request(text.ensure_http_scheme(contents)).text
def images(self, page):
pages = text.extract_iter(
page, 'class="lanzador', '>')
return pages
genders_src = text.extr(contents_src, 'Genders</label>', '</ul>')
genders_list = text.extract_iter(genders_src, '">', '</a>')
def metadata(self, page):
extr = text.extract_from(page, page.index('tag tag-accepted">'))
tags_src = text.extr(contents_src, 'Tags</label>', '</ul>')
tags_list = text.extract_iter(tags_src, '">', '</a>')
upload_src = text.extr(contents_src, 'Uploaded By</label>', '/a>')
data = {
'title' : text.extr(contents_src, '<h3>', '</h3>').strip(),
'title' : text.extr(page, '<h3>', '</h3>').strip(),
'id_string': self.id_string,
'artists' : text.remove_html(
text.extr(contents_src, 'tag tag-accepted">', '</a>')),
'genders' : list(genders_list),
'tags' : list(tags_list),
'uploader' : text.extr(upload_src, '">', '<'),
'language' : text.extr(
contents_src, '<a><span class="flag-icon'
' flag-icon-es"></span>&nbsp;', '</a>'),
'artists' : text.remove_html(extr('">', '</a>')),
'genders' : text.split_html(extr('Genders</label>', '<div')),
'tags' : text.split_html(extr('Tags</label>', '</ul>')),
'uploader' : text.remove_html(extr('Uploaded By</label>', '</a>')),
'language' : extr('&nbsp;', '\n</a>'),
}
return data