mirror of
https://github.com/hect0x7/JMComic-Crawler-Python.git
synced 2025-09-26 22:31:30 +08:00
v2.5.34: 更新html正则表达式域名,移除章节发布时间字段 (#408)
Some checks failed
Auto Release & Publish / release (push) Has been cancelled
Some checks failed
Auto Release & Publish / release (push) Has been cancelled
This commit is contained in:
parent
ec794f11d8
commit
e4584d09bd
2
.github/workflows/test_html.yml
vendored
2
.github/workflows/test_html.yml
vendored
@ -16,7 +16,7 @@ jobs:
|
|||||||
test: # This code is based on https://github.com/gaogaotiantian/viztracer/blob/master/.github/workflows/python-package.yml
|
test: # This code is based on https://github.com/gaogaotiantian/viztracer/blob/master/.github/workflows/python-package.yml
|
||||||
strategy:
|
strategy:
|
||||||
matrix:
|
matrix:
|
||||||
python-version: ['3.7', '3.8', '3.11', '3.12']
|
python-version: ['3.9', '3.10', '3.11', '3.13']
|
||||||
os: [ ubuntu-latest ]
|
os: [ ubuntu-latest ]
|
||||||
runs-on: ${{ matrix.os }}
|
runs-on: ${{ matrix.os }}
|
||||||
timeout-minutes: 5
|
timeout-minutes: 5
|
||||||
|
@ -2,7 +2,7 @@
|
|||||||
# 被依赖方 <--- 使用方
|
# 被依赖方 <--- 使用方
|
||||||
# config <--- entity <--- toolkit <--- client <--- option <--- downloader
|
# config <--- entity <--- toolkit <--- client <--- option <--- downloader
|
||||||
|
|
||||||
__version__ = '2.5.33'
|
__version__ = '2.5.34'
|
||||||
|
|
||||||
from .api import *
|
from .api import *
|
||||||
from .jm_plugin import *
|
from .jm_plugin import *
|
||||||
|
@ -457,10 +457,10 @@ class JmAlbumDetail(DetailEntity, Downloadable):
|
|||||||
self.authors: List[str] = authors # 作者
|
self.authors: List[str] = authors # 作者
|
||||||
|
|
||||||
# 有的 album 没有章节,则自成一章。
|
# 有的 album 没有章节,则自成一章。
|
||||||
episode_list: List[Tuple[str, str, str, str]]
|
episode_list: List[Tuple[str, str, str]]
|
||||||
if len(episode_list) == 0:
|
if len(episode_list) == 0:
|
||||||
# photo_id, photo_index, photo_title, photo_pub_date
|
# photo_id, photo_index, photo_title, photo_pub_date
|
||||||
episode_list = [(album_id, "1", name, pub_date)]
|
episode_list = [(album_id, "1", name)]
|
||||||
else:
|
else:
|
||||||
episode_list = self.distinct_episode(episode_list)
|
episode_list = self.distinct_episode(episode_list)
|
||||||
|
|
||||||
@ -505,7 +505,7 @@ class JmAlbumDetail(DetailEntity, Downloadable):
|
|||||||
raise IndexError(f'photo index out of range for album-{self.album_id}: {index} >= {length}')
|
raise IndexError(f'photo index out of range for album-{self.album_id}: {index} >= {length}')
|
||||||
|
|
||||||
# ('212214', '81', '94 突然打來', '2020-08-29')
|
# ('212214', '81', '94 突然打來', '2020-08-29')
|
||||||
pid, pindex, pname, _pub_date = self.episode_list[index]
|
pid, pindex, pname = self.episode_list[index]
|
||||||
|
|
||||||
photo = JmModuleConfig.photo_class()(
|
photo = JmModuleConfig.photo_class()(
|
||||||
photo_id=pid,
|
photo_id=pid,
|
||||||
|
@ -319,7 +319,7 @@ class ZipPlugin(JmOptionPlugin):
|
|||||||
return (
|
return (
|
||||||
downloader.download_success_dict[album]
|
downloader.download_success_dict[album]
|
||||||
if album is not None # after_album
|
if album is not None # after_album
|
||||||
else downloader.download_success_dict[photo.from_album] # after_photo
|
else downloader.download_success_dict[photo.from_album] # after_photo
|
||||||
)
|
)
|
||||||
|
|
||||||
def zip_photo(self, photo, image_list: list, zip_path: str, path_to_delete):
|
def zip_photo(self, photo, image_list: list, zip_path: str, path_to_delete):
|
||||||
|
@ -25,7 +25,7 @@ class JmcomicText:
|
|||||||
pattern_html_album_album_id = compile(r'<span class="number">.*?:JM(\d+)</span>')
|
pattern_html_album_album_id = compile(r'<span class="number">.*?:JM(\d+)</span>')
|
||||||
pattern_html_album_scramble_id = compile(r'var scramble_id = (\d+);')
|
pattern_html_album_scramble_id = compile(r'var scramble_id = (\d+);')
|
||||||
pattern_html_album_name = compile(r'<h1 class="book-name" id="book-name">([\s\S]*?)</h1>')
|
pattern_html_album_name = compile(r'<h1 class="book-name" id="book-name">([\s\S]*?)</h1>')
|
||||||
pattern_html_album_episode_list = compile(r'data-album="(\d+)"[^>]*>\s*?<li.*?>\s*?第(\d+)話([\s\S]*?)<[\s\S]*?>(\d+-\d+-\d+).*?')
|
pattern_html_album_episode_list = compile(r'data-album="(\d+)"[^>]*>\s*?<li.*?>\s*?第(\d+)[话話]([\s\S]*?)<[\s\S]*?>')
|
||||||
pattern_html_album_page_count = compile(r'<span class="pagecount">.*?:(\d+)</span>')
|
pattern_html_album_page_count = compile(r'<span class="pagecount">.*?:(\d+)</span>')
|
||||||
pattern_html_album_pub_date = compile(r'>上架日期 : (.*?)</span>')
|
pattern_html_album_pub_date = compile(r'>上架日期 : (.*?)</span>')
|
||||||
pattern_html_album_update_date = compile(r'>更新日期 : (.*?)</span>')
|
pattern_html_album_update_date = compile(r'>更新日期 : (.*?)</span>')
|
||||||
@ -693,7 +693,7 @@ class JmApiAdaptTool:
|
|||||||
chapter = AdvancedDict(chapter)
|
chapter = AdvancedDict(chapter)
|
||||||
# photo_id, photo_index, photo_title, photo_pub_date
|
# photo_id, photo_index, photo_title, photo_pub_date
|
||||||
episode_list.append(
|
episode_list.append(
|
||||||
(chapter.id, chapter.sort, chapter.name, None)
|
(chapter.id, chapter.sort, chapter.name)
|
||||||
)
|
)
|
||||||
fields['episode_list'] = episode_list
|
fields['episode_list'] = episode_list
|
||||||
for it in 'scramble_id', 'page_count', 'pub_date', 'update_date':
|
for it in 'scramble_id', 'page_count', 'pub_date', 'update_date':
|
||||||
|
Loading…
Reference in New Issue
Block a user