文泉下载后pdf生成和目录的获取by_Python

本文来源吾爱破解论坛

本帖最后由 858043016 于 2020-2-20 12:22 编辑

1.获取书名和目录
网页分别是
名称
https://lib-nuanxin.wqxuetang.com/v1/book/initbook?bid=3206295
目录
https://lib-nuanxin.wqxuetang.com/v1/book/catatree?bid=3206295
返回格式是json
2.pymupdf
生成PDF以及添加目录
3.代码
3.1只生成目录，结合FreePic2PDF使用，已经生成utf-16文件了，复制整个文件就可以使用
[Python] 纯文本查看 复制代码

import requests as req
import json
import os
def get_cata(book_id):
    cata=""
    url_name = "https://lib-nuanxin.wqxuetang.com/v1/book/catatree?bid={}".format(book_id)
    response = req.post(url=url_name, headers=headers)
    book_cata = json.loads(response.text)
    for i in book_cata['data']:
        cata=cata+str(i['label'])+'\t'+str(i['pnum'])+'\n'
        # print(i['level'],i['label'],i['pnum'])
        if ('children' in i):
            for j in (i['children']):
                # print("\t",j['level'],j['label'],j['pnum'])
                cata=cata+'\t'+str(j['label'])+'\t'+str(j['pnum'])+'\n'
    return cata

with open('Cookies.txt', 'r') as f:
    cookies=f.read()
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Cookie': cookies,
    'Host': 'lib-nuanxin.wqxuetang.com',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'none',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
}
book_id=input('输入书的id:\n')
with open('FreePic2Pdf_bkmk.txt', 'w',encoding='utf-16') as f:
    cookies=f.write(get_cata(book_id))

import fitz
import requests as req
import json
import os
import img2pdf

def get_name(book_id):
    url_name="https://lib-nuanxin.wqxuetang.com/v1/book/initbook?bid={}".format(book_id)
    response = req.post(url=url_name, headers=headers)
    book_more=json.loads(response.text)
    return(book_more['data']['name'],book_more['data']['pages'])
def get_cata(book_id):
    cata=[]
    url_name = "https://lib-nuanxin.wqxuetang.com/v1/book/catatree?bid={}".format(book_id)
    response = req.post(url=url_name, headers=headers)
    book_cata = json.loads(response.text)
    for i in book_cata['data']:
        cata.append([int(i['level']), i['label'], int(i['pnum'])])
        # print(i['level'],i['label'],i['pnum'])
        if ('children' in i):
            for j in (i['children']):
                # print("\t",j['level'],j['label'],j['pnum'])
                cata.append([int(j['level']), j['label'], int(j['pnum'])])
    return cata

def pic2pdf(book_id):
    name, page_all = get_name(book_id)
    print("开始进行{}_{},一共{}页".format(book_id,name,page_all))
    #生成目录
    path_tem = path_raw+"\\temp\\{}_{}_P{}.pdf".format(name, book_id, page_all)
    path_final = path_raw+"\\{}_{}_P{}.pdf".format(name, book_id, page_all)
    imgList = os.listdir(path_raw)
    print("获取了{}页图片".format(len(imgList)))
    imgList.sort(key=lambda x:int(x[:-4]))
    img_all=[]
    for img in imgList:
        img_path=path_raw+"\\{}".format(img)
        img_all.append(img_path)
    pfn_bytes = img2pdf.convert(img_all, with_pdfrw=False);
    #判断临时目录是否存在
    if os.path.exists(path_raw+"\\temp") == False:
        os.mkdir(path_raw+"\\temp")
    with open(path_tem, "wb") as f:
        f.write(pfn_bytes)
        f.close()
    print("准备生成目录...")
    #添加目录
    try:
        doc = fitz.open(path_tem)
        toc = get_cata(book_id)
        doc.setToC(toc)
        doc.save(path_final)  # 保存pdf文件
        doc.close()
        print("保存成功{}".format(path_final))
        os.remove(path_tem)
        os.remove(path_raw+"\\temp")
    except:
        print("添加目录错误，检查页码是否正确")

#获取cookies
with open('Cookies.txt', 'r') as f:
    cookies=f.read()
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Cookie': cookies,
    'Host': 'lib-nuanxin.wqxuetang.com',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'none',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
}
book_id=input('输入书的id:\n')
path_raw=input('输入放着图片的文件夹的全部路径:\n')
pic2pdf(book_id)

import json
import os
import fitz
import img2pdf
import requests as req
def get_name(book_id):
    url_name = 'https://www.wqxuetang.com/v1/book/initbook?bid={}'.format(book_id)
    response = req.post(url=url_name, headers=headers)
    book_more=json.loads(response.text)
    return(book_more['data']['name'],book_more['data']['pages'])
def get_cata(book_id):
    cata=[]
    url_name='https://www.wqxuetang.com/v1/book/catatree?bid={}'.format(book_id)
    response = req.post(url=url_name, headers=headers)
    book_cata = json.loads(response.text)
    for i in book_cata['data']:
        cata.append([int(i['level']), i['label'], int(i['pnum'])])
        # print(i['level'],i['label'],i['pnum'])
        if ('children' in i):
            for j in (i['children']):
                # print("\t",j['level'],j['label'],j['pnum'])
                cata.append([int(j['level']), j['label'], int(j['pnum'])])
    return cata

headers = {
    'Accept': 'application/json,text/plain,*/*',
    'Accept - Encoding': 'gzip,deflate,br',
    'Accept - Language': 'zh-CN,zh;q = 0.9',
    'BA': 'bapkg/com.bookask.wqxuetang,baver/0.0.1',
    'Connection': 'keep - alive',
    'Cookie':'',
    'Host':'www.wqxuetang.com',
    'Referer':'https://www.wqxuetang.com/',
    'User - Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}
def pic2pdf(book_id):
    name, page_all = get_name(book_id)
    print("开始进行{}_{},一共{}页".format(book_id,name,page_all))
    #生成目录
    path_tem = path_raw+"\\temp\\{}_{}_P{}.pdf".format(name, book_id, page_all)
    path_final = path_raw+"\\{}_{}_P{}.pdf".format(name, book_id, page_all)
    imgList = os.listdir(path_raw)
    print("获取了{}页图片".format(len(imgList)))
    imgList.sort(key=lambda x:int(x[:-4]))
    img_all=[]
    for img in imgList:
        img_path=path_raw+"\\{}".format(img)
        img_all.append(img_path)
    pfn_bytes = img2pdf.convert(img_all, with_pdfrw=False);
    #判断临时目录是否存在
    if os.path.exists(path_raw+"\\temp") == False:
        os.mkdir(path_raw+"\\temp")
    with open(path_tem, "wb") as f:
        f.write(pfn_bytes)
        f.close()
    print("准备生成目录...")
    #添加目录
    try:
        doc = fitz.open(path_tem)
        toc = get_cata(book_id)
        doc.setToC(toc)
        doc.save(path_final)  # 保存pdf文件
        doc.close()
        print("保存成功{}".format(path_final))
        os.remove(path_tem)
    except:
        print("添加目录错误，检查页码是否正确")

flag=input("单独添加目录输入1\n")
if flag=='1':
    print("-进入单独添加目录-")
    try:
        book_id = input('输入书的id:\n')
        path = input("输入文件目录包括pdf名称")
        doc = fitz.open(path)
        toc = get_cata(book_id)
        doc.setToC(toc)
        doc.save(path)  # 保存pdf文件
        doc.close()
        print("添加成功{}".format(path))
    except:
        print("添加目录失败")


else:
    print("-进入PDF合成及目录添加-")
    book_id = input('输入书的id:\n')
    path_raw = input('输入放着图片的文件夹的全部路径:\n')
    pic2pdf(book_id)

https://www.52pojie.cn/thread-1103527-1-1.html