看漫画学python pdf下载_用python下载漫画并打包成pdf文件

【实例简介】

【实例截图】

【核心代码】

import requests

import time

import json

import re

import os

import img2pdf

from selenium import webdriver

from selenium.webdriver.chrome.options import Options

from fake_useragent import UserAgent

from urllib.parse import urlencode, urljoin, unquote

from lxml import etree

from threading import Thread

base_url = 'https://www.manhuatai.com/'

headers = {

'referer': 'https://www.manhuatai.com/',

'user-agent': UserAgent(verify_ssl=False).random,

}

# 搜索接口，返回搜索列表

def get_search_items(keyword):

"""

:param keyword:

:return:

"""

headers.update({

'x-requested-with': 'XMLHttpRequest'

})

params = {

'd': int(time.time()),

'q': keyword,

}

params = urlencode(params)

res = requests.get('https://www.manhuatai.com/getjson.shtml?', headers=headers, params=params).content.decode('utf-8')

results = json.loads(res)

for index, item in enumerate(results):

print('编号：{}'.format(index))

print('名字：{}'.format(item['cartoon_name']))

print('id：{}'.format(item['cartoon_id']))

print('状态：{}'.format(item['cartoon_status_id']))

print('最新章节：{}'.format(item['latest_cartoon_topic_name']))

print('=' * 50)

return results

# 获取所搜索的漫画章节列表

def get_comic_list(cartoon_name, remove_fw=False):

url = urljoin(base_url, cartoon_name)

res = requests.get(url, headers=headers).content.decode('utf-8')

# print(res)

doc = etree.HTML(res)

c_img = doc.xpath('//*[@id="offlinebtn-container"]/img/@data-url')[0]

c_name = doc.xpath('/html/body/div[1]/div[3]/div/div[1]/div/div[2]/div[2]/ul/li[1]/text()')[0]

c_status = doc.xpath('/html/body/div[1]/div[3]/div/div[1]/div/div[2]/div[2]/ul/li[2]/text()')[0]

c_author = doc.xpath('/html/body/div[1]/div[3]/div/div[1]/div/div[2]/div[2]/ul/li[3]/text()')[0]

c_type = doc.xpath('/html/body/div[1]/div[3]/div/div[1]/div/div[2]/div[2]/ul/li[4]/text()')[0]

c_update = doc.xpath('/html/body/div[1]/div[3]/div/div[1]/div/div[2]/div[2]/ul/li[5]/text()')[0]

print(c_img, c_name, c_status, c_author, c_type, c_update)

# 获取所有下载链接

chapter_list = doc.xpath('//*[@id="topic1"]/li/a/@href')[::-1]

print(chapter_list, chapter_list[::-1])

# if remove_fw:

# chapter_list = list(filter(lambda x: isinstance(int, x.split('/')[-1].split('.')[0]), chapter_list))

# chapter_list_ = list()

if remove_fw:

for index, item in enumerate(chapter_list):

if item.split('/')[-1].split('.')[0][:2] == 'fw':

print(item)

del chapter_list[index]

# print(chapter_list)

return chapter_list

# 分析解析规则并批量下载

def get_parse_format(r_url):

url = urljoin(base_url, r_url)

driver.get(url)

source = driver.page_source

# print(source)

img_url = re.search('

print(img_url)

total_page_num = re.search('第1/(\d )页', source).group(1)

# 引 || 第8话 || 8话GQ

re_text = re.search('(.*?)/comic/(.*?)%2F(.*?)%2F(.*?)%E8%AF%9D(.*?)%2F(\d ).jpg-', img_url)

try:

mh_domain = re_text.group(1)

mh_tou = re_text.group(2)

mh_name = re_text.group(3)

mh_cp_num = unquote(re_text.group(4))

print(mh_cp_num)

mh_char = re_text.group(5)

mh_num = re_text.group(6)

print(total_page_num, mh_domain, mh_tou, mh_name, mh_cp_num, mh_char, mh_num)

for i in range(1, int(total_page_num) 1):

t = Thread(target=download, args=(mh_domain, mh_tou, mh_name, mh_cp_num, mh_char, i,))

t.start()

except AttributeError:

print('非正文图片{}'.format(url))

def download(mh_domain, mh_tou, mh_name, mh_cp_num, mh_char, i):

url = '{}/comic/{}%2F{}%2F{}%E8%AF%9D{}%2F{}.jpg-mht.middle.jpg'.format(mh_domain, mh_tou, mh_name, mh_cp_num, mh_char, i)

# [img]https://mhpic.manhualang.com/comic/D%2F%E6%96%97%E7%BD%97%E5%A4%A7%E9%99%86%E6%8B%86%E5%88%86%E7%89%88%2F%E7%95%AA%E5%A4%96%E7%AF%8722GQ%2F1.jpg[/img]-mht.middle.webp

print(url)

res = requests.get(url, headers=headers).content

cp_num, sec_num = re.search('(\d )', mh_cp_num).group(1), i

if len(mh_cp_num) < 3:

cp_num = '0' * (3 - len(cp_num)) cp_num

if i < 1000:

sec_num = '0' * (3 - len(str(i))) str(i)

with open('./{}/第{}话-{}节.jpg'.format(dir_name, cp_num, sec_num), 'wb') as f:

f.write(res)

# 打包成pdf

def pack_to_pdf(dir_name):

a4inpt = (img2pdf.mm_to_pt(210), img2pdf.mm_to_pt(297))

layout_fun = img2pdf.get_layout_fun(a4inpt)

file_list = list()

for root, dirs, files in os.walk(dir_name):

for file in files:

if file.endswith('.jpg'):

pathname1 = os.path.join(root, file)

file_list.append(pathname1)

file_lis_list = list()

while file_list:

try:

file_lis_list.append(file_list[:501])

del file_list[:501]

except IndexError:

file_lis_list.append(file_list[:-1])

del file_list[::]

for index, item in enumerate(file_lis_list):

try:

with open('{}/{}.pdf'.format(dir_name, index 1), 'wb') as f:

f.write(img2pdf.convert(item, layout_fun=layout_fun))

except Exception as e:

print(e.args, item)

else:

print(item)

if __name__ == '__main__':

search_words = input('请输入你要查找的内容：>>')

search_results = get_search_items(search_words)

choice = input('请选择要下载第几个？（选择对应漫画的编号）')

# remove_side_story = input('是否去掉番外篇？Y/N')

dir_name = search_results[int(choice)]['cartoon_name']

if not os.path.exists(dir_name):

os.mkdir(dir_name)

mh_list = get_comic_list(search_results[int(choice)]['cartoon_id'], '(⊙o⊙)…' != '')

options = Options()

options.add_argument('--headless')

options.add_argument('--disable-gpu')

driver = webdriver.Chrome(chrome_options=options)

for mh in mh_list:

get_parse_format(mh)

print("main")

pack_to_pdf(dir_name)

看漫画学python pdf下载_用python下载漫画并打包成pdf文件相关推荐

用python画圣诞树、樱花树、卡通图案及打包成exe文件
文章目录用python画圣诞树.樱花树.卡通图案及打包成exe文件效果 1.圣诞树--朴素 2.圣诞树--可爱 3.圣诞树--飘雪 4.樱花树--飘落效果 5.樱花树--暖色调 6.哆啦a梦用p ...
keil生成hex文件找不到_骚操作！用Python把公众号文章打包成pdf文件，再也不怕找不到了...
背景做自媒体的人,尤其是做了一年甚至更久的自媒体人,尤其是通过自媒体还有一些小收入的人,他们最怕自己的公众号内容因为各种原因而丢失,那就太可怕了! 在做自媒体内容上花了太多心血,如果突然一下就没了, ...
Python打包成exe文件_详细操作
Python打包成exe文件前言一.安装pyinstaller 1.1 安装pyinstaller,使用安装命令: 1.2 如果遇到需要更新版本请输入: 1.3 检查是否正确安装 1.4 稍等,水 ...
python 概率分布模型_使用python的概率模型进行公司估值
python 概率分布模型 Note from Towards Data Science's editors: While we allow independent authors to publis ...
python如何将图片打包进exe里_史上最详细的Python打包成exe文件教程
打包成exe文件可以让python代码在没有python环境的条件下,依然能够运行,实在是码农们写追女朋友表白.情人节浪漫的必需品! 1.使用豆瓣镜像源下载: pyinstaller 有需要了解如何使 ...
python编程方式_自学python编程的方法路线
怎么自学python编程如何自学Python编程?一堆的Python教程却感觉无从下手呢?我想这应该是很多Python初学者正在纠结的问题. 今天想要分享给大家的是如何自学Python编程,学习这件 ...
python tkinter库、添加gui界面_使用Python中tkinter库简单gui界面制作及打包成exe的操作方法（二）...
使用Python中tkinter库简单gui界面制作及打包成exe的操作方法(二),创建一个,界面,布局,文件,路径使用Python中tkinter库简单gui界面制作及打包成exe的操作方法(二) ...
python文件图标变成小电脑_手把手教你给Python程序写图形界面，并且打包成exe文件-exe文件...
环境配置官网下载Python3,LZ的配置环境是Python3.6,PyCharm 2017.2.1pip3 install PyQt5 #下载PyQt5 pip install PyQt5-too ...
python 时间序列预测_使用Python进行动手时间序列预测
python 时间序列预测 Time series analysis is the endeavor of extracting meaningful summary and statistical ...

看漫画学python pdf下载_用python下载漫画并打包成pdf文件

看漫画学python pdf下载_用python下载漫画并打包成pdf文件相关推荐

最新文章

热门文章