[Python] 分享个韩国等漫画离线阅读和备份小脚本
本帖最后由 Amd794 于 2020-7-26 23:24 编辑先上图看下效果
下载链接:https://github.com/Amd794/kanleying, 配合这个 https://www.52pojie.cn/thread-953874-1-1.html 使用时时监测漫画的更新动态, 你懂我意思吧!
注意事项:
[*]运行前要安装下环境 打开终端运行下pip install -r requirements.txt, 或者安装在虚拟环境.
[*]如果要下载完后压缩备份, 需要改下下WinRAR.exe的路径, 例如: D:/Sorfwares/WinRAR/WinRAR.exe.
[*] @staticmethod
def download_images(images_dict):
images_url = images_dict.get('images_url')
a_title = images_dict.get('a_title').strip(' ')
comic_title = images_dict.get('comic_title').strip(' ')
print(f'开始下载{comic_title}-{a_title}\n')
file_path = f'./{os.path.basename(__file__).strip(".py")}/{comic_title}/{a_title}/'
if not os.path.exists(file_path):
os.makedirs(file_path)
download(images_url, file_path, 10)
suffix = ['jpg', 'png', 'gif', 'jpeg']
file_list = sorted(
[file_path + str(imgFileName) for imgFileName in os.listdir(file_path) if
imgFileName.endswith(tuple(suffix))],
key=lambda x: int(os.path.basename(x).split('.'))
)
file_name = f'{file_path}/{comic_title}-{a_title}'
print(f'开始生成html{comic_title}-{a_title}\n')
Comic.render_to_html(f'{file_name}.html', a_title,
)
print(f'开始生成PDF{comic_title}-{a_title}\n')
Comic.make_pdf(f'{file_name}.pdf', file_list)
comment = {
'Website': 'https://amd794.com',
'Password_1': '百度云',
'Password_2': f'{comic_title}-{a_title}',
}
with open(f'{file_path}/Password.txt', 'w', encoding='utf-8') as f:
f.write(str(comment))
print(f'开始压缩文件{comic_title}-{a_title}\n')
Comic.compress(f'{file_name}.rar', f'{file_path}/*', f'{comic_title}-{a_title}')
[*]看个人需要把相应的代码注释掉, 比如我不用生成个pdf活着压缩文件什么的.
双击如图的文件运行, 输入漫画地址, 例如: https://m.happymh.com/manga/wuliandianfeng
输入0是下载全部章节, >5是下载6往后的所有章节, 直接回车是下载最后一章节, 或者下载某几章节
支持的漫画网站有如下等, 你有好的网站请务必告诉我.抹掉的网址就当个小彩蛋，细心的同志就能找到．
try_to_fix.py
# !/usr/bin/python3
# -*- coding: utf-8 -*-
# Time : 2020/3/30 23:49
# Author: Amd794
# Email : 2952277346@qq.com
# Github: https://github.com/Amd794
import os
import platform as pf
import subprocess
import requests
from PIL import Image, ImageFont, ImageDraw
requests.packages.urllib3.disable_warnings()
def create_img(text, img_save_path):
font_size = 24
liens = text.split('\n')
im = Image.new("RGB", (len(text) * 12, len(liens) * (font_size + 5)), '#fff')
dr = ImageDraw.Draw(im)
font_path = r"C:\Windows\Fonts\STKAITI.TTF"
font = ImageFont.truetype(font_path, font_size)
dr.text((0, 0), text, font=font, fill="blue")
im.save(img_save_path)
def make_pdf(pdf_name, file_list):
im_list = []
im1 = Image.open(file_list)
file_list.pop(0)
for i in file_list:
img = Image.open(i)
if img.mode == "RGBA":
img = img.convert('RGB')
im_list.append(img)
else:
im_list.append(img)
im1.save(pdf_name, "PDF", resolution=100.0, save_all=True, append_images=im_list)
def try_download_error_img(error_file):
fail_url = []
with open(error_file) as f:
images_url = f.read().split('\n')
images_url =
for image_url in images_url:
image_url, name = image_url.split(' ')
response = requests.get(image_url, verify=False)
with open(name, 'wb') as f:
if response:
f.write(response.content)
print(f'成功{image_url}-{name}')
else:
f.close()
fail_url.append(image_url + ' ' + name + '\n')
print(f'失败{image_url}-{name}')
create_img(f'温馨提示{image_url}-{name}已经失效', name)
if fail_url:
with open(error_file, 'w') as f:
f.write(''.join(fail_url))
else:
print('全部完成')
os.remove(error_file)
def compress(target, source, pwd='', delete_source=False, ):
"""
压缩加密，并删除原数据
window系统调用rar程序
linux等其他系统调用内置命令 zip -P123 tar source
默认不删除原文件
"""
if pwd: pwd = '-p' + pwd
if pf.system() == "Windows":
cmd = f'rar a {pwd} {target} {source} -x*.rar -x*.py'
p = subprocess.Popen(cmd, executable=r'D:/Sorfwares/WinRAR/WinRAR.exe')
p.wait()
else:
cmd = f'zip a {pwd} {target} {source} -x*.rar -x*.py'
p = subprocess.Popen(cmd)
p.wait()
# os.system(" ".join(cmd))
if delete_source:
os.remove(source)
if __name__ == '__main__':
error_file = 'error_urls.txt'
file_name = ''
for imgFileName in os.listdir('.'):
if imgFileName.endswith('pdf'):
file_name = (os.path.splitext(imgFileName))
print(f'当前正常尝试修复---->{file_name}')
try_download_error_img(error_file)
suffix = ['jpg', 'png', 'gif', 'jpeg']
file_list = ['./' + str(imgFileName) for imgFileName in os.listdir('.') if imgFileName.endswith(tuple(suffix))]
file_list.sort(key=lambda x: int(os.path.basename(x).split('.')))
# print(file_list)
make_pdf(file_name + '-重构' + '.pdf', file_list)
os.remove(file_name + '.pdf')
print(file_name + '-重构' + '.pdf' + '---->successful')
compress(f'{file_name}.rar', '*', file_name)
kanleying.py
# !/usr/bin/python3
# -*- coding: utf-8 -*-
# Time : 2020/3/24 22:37
# Author: Amd794
# Email : 2952277346@qq.com
# Github: https://github.com/Amd794
import os
from pprint import pprint
import pyquery
from PIL import Image, ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
from threading_download_images import get_response, download
import re
import subprocess
import platform as pf
class Util(object):
@staticmethod
def make_pdf(pdf_name, file_list):
im_list = []
im1 = Image.open(file_list)
file_list.pop(0)
for i in file_list:
img = Image.open(i)
if img.mode == "RGBA":
img = img.convert('RGB')
im_list.append(img)
else:
im_list.append(img)
im1.save(pdf_name, "PDF", resolution=100.0, save_all=True, append_images=im_list)
@staticmethod
def render_to_html(html, title, imgs: list):
chapter_num = len(Comic.detail_dicts)
template_path = 'template.html'
imgs_html = ''
lis_html = ''
for img in imgs:
imgs_html += f'<img src="{img}" alt="" style="width: 100%">\n'
for li in range(chapter_num):
lis_html += f'''<li><a href="../{Comic.detail_dicts.get("a_title")}/{Comic.detail_dicts.get(
"comic_title")}-{Comic.detail_dicts.get("a_title")}.html" rel="nofollow">{Comic.detail_dicts[
li].get("a_title")}</a></li>\n'''
with open(template_path, 'r', encoding='utf-8') as r:
render_data = re.sub('{{title}}', title, r.read())
render_data = re.sub('{{imgs}}', imgs_html, render_data)
render_data = re.sub('{{lis_html}}', lis_html, render_data)
render_data = re.sub('{{chapter_num}}', str(chapter_num), render_data)
with open(html, 'w', encoding='utf-8') as w:
w.write(render_data)
@staticmethod
def compress(target, source, pwd='', delete_source=False, ):
"""
压缩加密，并删除原数据
window系统调用rar程序
linux等其他系统调用内置命令 zip -P123 tar source
默认不删除原文件
"""
if pwd: pwd = '-p' + pwd
if pf.system() == "Windows":
cmd = f'rar a {pwd} {target} {source} -zcomment.txt'
p = subprocess.Popen(cmd, executable=r'D:/Sorfwares/WinRAR/WinRAR.exe')
p.wait()
else:
cmd = f'zip a {pwd} {target} {source}'
p = subprocess.Popen(cmd)
p.wait()
# os.system(" ".join(cmd))
if delete_source:
os.remove(source)
class Comic(Util):
kanleying_type = {
'detail_lis': '#chapterlistload li',
'comic_title': '.banner_detail .info h1',
'comic_pages': 'div.comicpage div',
}
mm820_type = {
'detail_lis': '.chapter-list li',
'comic_title': '.title-warper h1',
'comic_pages': 'div.comiclist div',
}
rules_dict = {
# https://www.mh1234.com/
'mh1234': {
'detail_lis': '#chapter-list-1 li',
'comic_title': '.title h1',
},
# https://www.90ff.com/
'90ff': {
'detail_lis': '#chapter-list-1 li',
'comic_title': '.book-title h1',
},
# https://www.36mh.com/
'36mh': {
'detail_lis': '#chapter-list-4 li',
'comic_title': '.book-title h1',
},
# https://www.18comic.biz/
'18comic': {
'detail_lis': '.btn-toolbara',
'comic_title': '.panel-heading div',
'comic_pages': '.panel-body .row div',
},
# https://m.happymh.com/
'happymh': {
'comic_title': '.mg-title',
'comic_pages': '.scan-list div',
},
}
detail_dicts = []
current_host_key = ''
@staticmethod
def _happymh(response, comic_title):
chapter_url = re.findall('"url":"(.*?)",', response.text)
chapter_name = re.findall('"chapterName":"(.*?)",', response.text)
for chapter in zip(chapter_name, chapter_url):
name, url = chapter
detail_dict = {
'a_title': eval("'" + name + "'"),
'a_href': url,
'comic_title': comic_title,
}
Comic.detail_dicts.append(detail_dict)
return Comic.detail_dicts[::-1]
@staticmethod
def get_detail_dicts(url, host_url, host_key) -> list:
response = get_response(url)
pq = pyquery.PyQuery(response.text)
Comic.current_host_key = host_key
rule = Comic.rules_dict.get(host_key, '')
if not rule: raise KeyError('该网站还没/有适配')
if Comic.current_host_key == 'happymh':
comic_title = pq(rule.get('comic_title')).text()
return Comic._happymh(response, comic_title)
def detail_one_page(detail_url):
response = get_response(detail_url)
pq = pyquery.PyQuery(response.text)
lis = pq(rule.get('detail_lis'))
comic_title = pq(rule.get('comic_title')).text()
if Comic.current_host_key == '18comic':
if not lis.length:
detail_dict = {
'a_title': '共一话',
'a_href': host_url + pq('div.read-block a:first-child').attr('href').lstrip('/'),
'comic_title': comic_title,
}
Comic.detail_dicts.append(detail_dict)
return Comic.detail_dicts
else:
print(f'该漫画共{len(lis)}章节')
for li in lis:
a_title = pyquery.PyQuery(li)('a').text()
a_href = pyquery.PyQuery(li)('a').attr('href')
for ch in r'\/:| <.･>?*"':
a_title = a_title.replace(ch, '･')# 去除特殊字符
comic_title = comic_title.replace(ch, '･')# 去除特殊字符
if Comic.current_host_key == 'dongmanmanhua':
a_title = a_title.split('･')
detail_dict = {
'a_title': a_title,
'a_href': host_url + a_href.lstrip('/') if host_key not in a_href else a_href,
'comic_title': comic_title,
}
Comic.detail_dicts.append(detail_dict)
detail_one_page(url)
# 处理特殊情况 pyquery 好像不支持nth-child(n+3)这种类型过滤
if Comic.current_host_key == 'hmba':
Comic.detail_dicts = Comic.detail_dicts
if Comic.current_host_key == 'dongmanmanhua':
total_pages = len(pq('.paginate a'))
for i in range(2, total_pages + 1):
detail_one_page(url + f'&page={i}')
Comic.detail_dicts.reverse()
return Comic.detail_dicts
# 该站点进行了分页处理, 需要特殊处理
@staticmethod
def _mm820(detail_url, pages: int):
images_url = []
for i in range(2, pages + 1):
response = get_response(detail_url + f'?page={i}')
pq = pyquery.PyQuery(response.text)
divs = pq(Comic.rules_dict.get(Comic.current_host_key).get('comic_pages'))
for div in divs:
img_src = pyquery.PyQuery(div)('img').attr('data-original')
if not img_src:
img_src = pyquery.PyQuery(div)('img').attr('src')
images_url.append(img_src)
return images_url
@staticmethod
def _cswhcs(pq):
def is_next_url():
next_url = ''
fanye = pq('div.fanye')
if '下一页' in fanye.text():
next_url = pyquery.PyQuery(fanye)('a:nth-last-child(2)').attr('href')
if next_url:
next_url = 'https://cswhcs.com' + next_url
else:
next_url = None
return next_url
images_url = []
next_url = is_next_url()
while next_url:
print(next_url)
if next_url:
response = get_response(next_url)
pq = pyquery.PyQuery(response.text)
divs = pq(Comic.rules_dict.get(Comic.current_host_key).get('comic_pages'))
for div in divs:
img_src = pyquery.PyQuery(div)('img').attr('data-original')
if not img_src:
img_src = pyquery.PyQuery(div)('img').attr('src')
images_url.append(img_src)
# 判断是否还有下一页
next_url = is_next_url()
return images_url
@staticmethod
def _dongmanmanhua(detail_url, ):
images_url = []
detail_url = 'https:' + detail_url
response = get_response(detail_url)
pq = pyquery.PyQuery(response.text)
imgs = pq(Comic.rules_dict.get(Comic.current_host_key).get('comic_pages'))
for img in imgs:
image_url = pyquery.PyQuery(img).attr('data-url')
images_url.append(image_url)
return images_url
@staticmethod
def _nxueli(detail_url):
response = get_response(detail_url)
chapter_path_regix = 'chapterPath = "(.*?)"'
chapter_images = eval(re.sub(r'\\', '', re.search('chapterImages = (\[.*?\])', response.text).group(1)))
if Comic.current_host_key == 'nxueli':
return ['https://images.nxueli.com' + i for i in chapter_images]
elif Comic.current_host_key == '90ff':
chapter_path = re.search(chapter_path_regix, response.text).group(1)
return
elif Comic.current_host_key == 'mh1234':
chapter_path = re.search(chapter_path_regix, response.text).group(1)
return
elif Comic.current_host_key == '36mh':
chapter_path = re.search(chapter_path_regix, response.text).group(1)
return
elif Comic.current_host_key == 'manhuaniu':
return ['https://restp.dongqiniqin.com/' + i for i in chapter_images]
@staticmethod
def get_images_url(detail_dict: dict) -> dict:
images_url = []
nxueli_type = ('nxueli', '90ff', 'manhuaniu', '36mh', 'mh1234')
cswhcs_type = ('cswhcs', 'kanleying', 'qinqinmh')
mm820_type = ('mm820', 'hanmzj')
detail_url = detail_dict.get('a_href')
a_title = detail_dict.get('a_title')
comic_title = detail_dict.get('comic_title')
if Comic.current_host_key == 'dongmanmanhua':
images_url = Comic._dongmanmanhua(detail_url)
return {'images_url': images_url, 'a_title': a_title, 'comic_title': comic_title}
elif Comic.current_host_key in nxueli_type:
images_url = Comic._nxueli(detail_url)
return {'images_url': images_url, 'a_title': a_title, 'comic_title': comic_title}
elif Comic.current_host_key == 'happymh':
response = get_response(detail_url)
imgs_url = eval(re.search('var scans = (.*?);', response.text).group(1))
imgs_url =
for img_url in imgs_url:
img_src = img_url['url']
images_url.append(img_src)
return {'images_url': images_url, 'a_title': a_title, 'comic_title': comic_title}
response = get_response(detail_url)
pq = pyquery.PyQuery(response.text)
divs = pq(Comic.rules_dict.get(Comic.current_host_key).get('comic_pages'))
for div in divs:
img_src = pyquery.PyQuery(div)('img').attr('data-original')
if not img_src:
img_src = pyquery.PyQuery(div)('img').attr('src')
images_url.append(img_src)
#处理特殊情况
if Comic.current_host_key in cswhcs_type:
images_url.extend(Comic._cswhcs(pq))
if Comic.current_host_key in mm820_type:
# 获取分页数
pages = len(pq('.selectpage option'))
images_url.extend(Comic._mm820(detail_url, pages))
if Comic.current_host_key == '18comic':
images_url =
return {'images_url': images_url, 'a_title': a_title, 'comic_title': comic_title}
@staticmethod
def download_images(images_dict):
images_url = images_dict.get('images_url')
a_title = images_dict.get('a_title').strip(' ')
comic_title = images_dict.get('comic_title').strip(' ')
print(f'开始下载{comic_title}-{a_title}\n')
file_path = f'./{os.path.basename(__file__).strip(".py")}/{comic_title}/{a_title}/'
if not os.path.exists(file_path):
os.makedirs(file_path)
download(images_url, file_path, 10)
suffix = ['jpg', 'png', 'gif', 'jpeg']
file_list = sorted(
[file_path + str(imgFileName) for imgFileName in os.listdir(file_path) if
imgFileName.endswith(tuple(suffix))],
key=lambda x: int(os.path.basename(x).split('.'))
)
file_name = f'{file_path}/{comic_title}-{a_title}'
print(f'开始生成html{comic_title}-{a_title}\n')
Comic.render_to_html(f'{file_name}.html', a_title,
)
print(f'开始生成PDF{comic_title}-{a_title}\n')
Comic.make_pdf(f'{file_name}.pdf', file_list)
comment = {
'Website': 'https://amd794.com',
'Password_1': '百度云',
'Password_2': f'{comic_title}-{a_title}',
}
with open(f'{file_path}/Password.txt', 'w', encoding='utf-8') as f:
f.write(str(comment))
print(f'开始压缩文件{comic_title}-{a_title}\n')
Comic.compress(f'{file_name}.rar', f'{file_path}/*', f'{comic_title}-{a_title}')
def main():
url = input('漫画地址:').strip()
try:
host_key = re.match('https?://\w+\.(.*?)\.\w+/', url).group(1)# kanleying
host_url = re.match('https?://\w+\.(.*?)\.\w+/', url).group()# https://www.kanleying.com/
except AttributeError:
host_key = re.match('https?://(.*?)\.\w+/', url).group(1)# kanleying
host_url = re.match('https?://(.*?)\.\w+/', url).group()# https://kanleying.com/
print(host_url, host_key)
detail_dicts = Comic.get_detail_dicts(url, host_url, host_key)
while True:
# pprint(enumerate(detail_dicts, 1))
index = input('>>>:')
# 下载某章节之后所有章节
if '>' in index:
index = index.split('>')[-1]
index = int(index)
# pprint(detail_dicts)
for detail_dict in detail_dicts:
images_url = Comic.get_images_url(detail_dict)
Comic.download_images(images_url)
continue
# 下载全部
elif index == '0':
for detail_dict in detail_dicts:
images_url = Comic.get_images_url(detail_dict)
Comic.download_images(images_url)
continue
# 下载最新章节
elif not index:
detail_dict = detail_dicts.pop()
images_url = Comic.get_images_url(detail_dict)
Comic.download_images(images_url)
continue
# 下载某几章节 --> 2 6 9
indexes = list(map(int, index.split(' ')))
pprint(indexes)
for i in indexes:
detail_dict = detail_dicts
images_url = Comic.get_images_url(detail_dict)
Comic.download_images(images_url)
if __name__ == '__main__':
main()
threading_download_images.py
# !/usr/bin/python3
# -*- coding: utf-8 -*-
# Time : 2020/3/28 19:22
# Author: Amd794
# Email : 2952277346@qq.com
# Github: https://github.com/Amd794
import os
import threading
import requests
from fake_useragent import UserAgent
requests.packages.urllib3.disable_warnings()
# todo 获取返回的response
def get_response(url, error_file_path='.', max_count=3, timeout=30, ua_type='random', name='', ):
ua = UserAgent()
header = {
'User-Agent': getattr(ua, ua_type),
# 'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Mobile Safari/537.36',
'referer': url,
}
count = 0
while count < max_count:
try:
response = requests.get(url=url, headers=header, verify=False, timeout=timeout)
response.raise_for_status()# 如果status_code不是200,产生异常requests.HTTPError
response.encoding = 'utf-8'
return response
except requests.exceptions.RequestException:
print(f'\033[22;33;m{url} {name}连接超时, 正在进行第{count + 1}次连接重试, {timeout}秒超时重连\033[m')
count += 1
else:
print(f'\033[22;31;m{url}重试{max_count}次后依然连接失败, 放弃连接...\033[m')
if not os.path.exists(error_file_path):
os.makedirs(error_file_path)
with open(os.path.join(error_file_path, 'error_urls.txt'), 'a') as f:
f.write(url + ' ' + name + '\n')
return None
# todo 多线程
def thread_run(threads_num, target, args: tuple):
threads = []
for _ in range(threads_num):
t = threading.Thread(target=target, args=args)
t.start()
threads.append(t)
for t in threads:
t.join()
# todo 下载图片
def download_images(file_path, images: list):
from PIL import Image, ImageFont, ImageDraw
def create_img(text, img_save_path):
font_size = 24
liens = text.split('\n')
im = Image.new("RGB", (len(text) * 12, len(liens) * (font_size + 5)), '#fff')
dr = ImageDraw.Draw(im)
font_path = r"C:\Windows\Fonts\STKAITI.TTF"
font = ImageFont.truetype(font_path, font_size)
dr.text((0, 0), text, font=font, fill="blue")
im.save(img_save_path)
while images:
glock = threading.Lock()
glock.acquire()
image_url = images.pop()
file_name = str(len(images)) + '.jpg'
print(f'{threading.current_thread()}:正在下载{file_name} ---> {image_url}')
glock.release()
response = get_response(image_url, file_path, name=file_name)
if not os.path.exists(file_path):
os.makedirs(file_path)
with open(os.path.join(file_path, file_name), 'wb') as f:
if response:
f.write(response.content)
else:
f.close()
create_img(f'温馨提示{image_url}已经失效', os.path.join(file_path, file_name))
if 'error_urls.txt' in os.listdir(file_path):
from shutil import copyfile
copyfile('./try_to_fix.py', os.path.join(file_path, 'try_to_fix.py'))
def download(image_list: list, file_path=os.getcwd(), threads_num=5):
thread_run(threads_num, download_images, (file_path, image_list,))
if __name__ == '__main__':
imgs = ['h15719904026351411247.jpg?x-oss-process=image/quality,q_90',
'https://cdn.dongmanmanhua.cn/15719904028051411242.jpg?x-oss-process=image/quality,q_90',
'https://cdn.dongmanmanhua.cn/15719904029381411248.jpg?x-oss-process=image/quality,q_90',]
download(imgs, f'./{os.path.basename(__file__).strip(".py")}/test/')
暂时是这样, 如果还有啥补充的想到再说. 如果你喜欢不妨点个赞, 如果你有好的网站的记得分享下俺:$qqq:$qqq
最后分享个成品:
链接：https://pan.baidu.com/s/1377l5KgQIe5u_l79QXejSw
提取码：8bzp
今天看了下好几个网站服务器都蹦了, 大家别用这么恨. 看一本下一本最好.。细水长流成河，粒米积蓄成箩。{:1_937:}{:1_937:} 戒色大师 发表于 2020-7-1 23:23
小白不会用啊
如果有能力和时间我更新打包个exe程序, 或者搭个本地网页界面方便操作. 点赞收藏{:301_972:} 看到没人，顶下:lol
其实好的网站有，但是……{:1_926:} zim万岁 发表于 2020-7-1 22:30
看到没人，顶下
其实好的网站有，但是……
{:301_982:}但是....... zim万岁 发表于 2020-7-1 22:30
看到没人，顶下
其实好的网站有，但是……
什么好的网站有? 我没有网站，肿么办{:1_936:} Amd794 发表于 2020-7-1 22:34
但是.......
那种233333{:1_911:} 可以，拿来看中文韩漫{:301_997:} github上找不到此文件打开链接显示404 ixeliap 发表于 2020-7-1 23:04
github上找不到此文件打开链接显示404
稍等, 我看下什么情况 Amd794 发表于 2020-7-1 23:07
稍等, 我看下什么情况
有了有了