Bilibili漫画下载

BilibiliMangaDownload.py

# Source: https://github.com/LaMP57/BilibiliMangaDownload
# 支持从连续使用多个账号的网页版 SESSDATA，或者使用单个手机抓包得到的 Token，自动购买/解锁章节，验证下载图片完整性连续下载一本漫画的所有章节的功能。

import json
import os
import re
import requests
import zipfile
from io import BytesIO
from PIL import Image
from concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED

AutoBuy = False
PARAM_ID = "appkey=***&mobi_app=android_comic&version=4.7.0&build=***&channel=xiaomi&platform=android&device=android&buvid=***&machine=Xiaomi%2BM2011K2C&access_key=***&is_teenager=0&ts=***"

USE_SESSION = False
if not PARAM_ID:
    PARAM_ID = "device=pc&platform=web"
    USE_SESSION = True

URL_DETAIL = "https://manga.bilibili.com/twirp/comic.v2.Comic/ComicDetail?" + PARAM_ID
URL_IMAGE_INDEX = "https://manga.bilibili.com/twirp/comic.v1.Comic/GetImageIndex?" + PARAM_ID
URL_MANGA_HOST = "https://manga.hdslb.com"
URL_IMAGE_TOKEN = "https://manga.bilibili.com/twirp/comic.v1.Comic/ImageToken?" + PARAM_ID
URL_MANGA_BUY_INFO = "https://manga.bilibili.com/twirp/comic.v1.Comic/GetEpisodeBuyInfo?" + PARAM_ID
URL_MANGA_BUY = "https://manga.bilibili.com/twirp/comic.v1.Comic/BuyEpisode?" + PARAM_ID

def downloadImage(url, path):
    if not os.path.exists(path):
        r = requests.get(url, stream = True, cookies = cookies)
        if r.content.endswith(b'\xff\xd9'):
            f = open(path, 'wb')
            for chunk in r.iter_content(chunk_size = 1024):
                if chunk:
                    f.write(chunk)
            f.close()
        else:
            print("[ERROR]" + path + " 下载失败，重试中...")
            os.remove(path)
            downloadImage(url, path)

def getMangaInfo(mcNum):
    data = requests.post(URL_DETAIL, data = {'comic_id': mcNum}).json()['data']
    data['ep_list'].reverse()
    return filterStr(data['title']), data['ep_list']

def getImages(mcNum, chNum):
    data = requests.post(URL_IMAGE_INDEX, data = {'ep_id': chNum}, cookies = cookies).json()['data']
    data = bytearray(requests.get(data['host'] + data['path']).content[9:])
    key = [chNum&0xff, chNum>>8&0xff, chNum>>16&0xff, chNum>>24&0xff, mcNum&0xff, mcNum>>8&0xff, mcNum>>16&0xff, mcNum>>24&0xff]
    for i in range(len(data)):
        data[i] ^= key[i%8]
    file = BytesIO(data)
    zf = zipfile.ZipFile(file)
    data = json.loads(zf.read('index.dat'))
    zf.close()
    file.close()
    return data['pics']

def getURLwithToken(url):
    data = requests.post(URL_IMAGE_TOKEN, data = {"urls": "[\""+url+"\"]"}, cookies = cookies).json()["data"][0]
    return '%s?token=%s' % (data["url"], data["token"])

def getChapterName(chapterList, chapterID):
    for chapte in chapterList:
        if chapte['id'] == chapterID:
            return filterStr(chapte['short_title'] + ' ' + chapte['title'])
    return None

def downloadChapter(mcNum, chapterID, chapterName):
    if not(os.path.exists('downloads/%s/%s' % (mangaTitle, chapterName))) or len(os.listdir('downloads/%s/%s' % (mangaTitle, chapterName))) == 0:
        if not(os.path.exists('downloads/%s/%s' % (mangaTitle, chapterName))):
            os.mkdir('downloads/%s/%s' % (mangaTitle, chapterName))
        try:
            if AutoBuy == True:
                buy_content = requests.post(URL_MANGA_BUY, data = {'ep_id': chapterID,'buy_method':1}, cookies = cookies).content
                print(json.loads(buy_content)["msg"].encode().decode())
                while json.loads(buy_content)["code"] != 0:
                    buy_info_content = json.loads(requests.post(URL_MANGA_BUY_INFO, data = {'ep_id': chapterID}, cookies = cookies).content)
                    coupon_num = buy_info_content["data"]["remain_coupon"]
                    if int(coupon_num) == 0:
                        print("无剩余优惠卷，请输入新的SESSDATA：")
                        cookies['SESSDATA'] = input().strip()
                    else:
                        print("剩余优惠卷%s张，自动使用" % coupon_num)
                    buy_content = requests.post(URL_MANGA_BUY, data = {'ep_id': chapterID,'buy_method':2,'coupon_id':buy_info_content["data"]["recommend_coupon_id"],'auto_pay_gold_status':1}, cookies = cookies).content
                    print(json.loads(buy_content)["msg"].encode().decode())

            print('[INFO]%s开始下载' % chapterName)
            imagesURLs = getImages(mcNum, chapterID)
            imagesIndexLength = len(str(len(imagesURLs)))
            tasks = list()
            for idx, url in enumerate(imagesURLs, 1):
                fullURL = getURLwithToken(url)
                path = 'downloads/%s/%s/%s.jpg' % (mangaTitle, chapterName, str(idx).zfill(imagesIndexLength))
                tasks.append(pool.submit(downloadImage, fullURL, path))
            wait(tasks, return_when = ALL_COMPLETED)
            print('[INFO]%s下载完成' % chapterName)
        except:
            print('[ERROR]%s下载失败' % chapterName)
            os.rmdir('downloads/%s/%s' % (mangaTitle, chapterName))
    else:
        print('[INFO]%s已下载' % chapterName)


def filterStr(name):
    return re.sub(r'[\/:*?"<>|]', '', name).strip().rstrip('.')

if __name__ == "__main__":
    pool = ThreadPoolExecutor(max_workers=4)
    if not(os.path.exists('downloads')):
        os.mkdir('downloads')

    print('请输入mc号：')
    print('mc', end='')
    mcNum = int(input())
    mangaTitle, chapterList = getMangaInfo(mcNum)
    print('[INFO]', mangaTitle)

    if not(os.path.exists('downloads/%s' % mangaTitle)):
        os.mkdir('downloads/%s' % mangaTitle)

    # print('1.下载单章\n2.下载全本')
    # downloadAll = input()
    # if downloadAll == '1':
    #     downloadAll = False
    #     print('请输入要下载的章节号：')
    #     chapterID = int(input())
    # else:
    #     downloadAll = True
    downloadAll = True

    # print('1.均为免费章节\n2.包含付费章节')
    # needsLogin = input()
    needsLogin = "2"
    cookies = dict()
    if needsLogin == '2' and USE_SESSION:
        print('请按说明粘贴SESSDATA：')
        cookies['SESSDATA'] = input().strip()

    if downloadAll:
        for chapter in chapterList:
            chapterName = filterStr(chapter['short_title'] + ' ' + chapter['title'])
            downloadChapter(mcNum, chapter['id'], chapterName)
    else:
        chapterName = getChapterName(chapterList, chapterID)
        downloadChapter(mcNum, chapterID, chapterName)

combine.py

import os
import re
import shutil
name = "大正少女御伽话"
os.mkdir(name+"_out")
d = os.listdir(name)
d.remove('.DS_Store')
d = sorted(d, key=lambda y: int(re.findall(r'\d+', y)[0]))
print(d)
cnt = 1
for i in d:
    s = os.listdir(name+"/"+i)
    s = sorted(s, key=lambda y: int(re.findall(r'\d+', y)[0]))
    for j in s:
        shutil.copy(name+"/"+i+"/"+j,name + "_out/" + str(cnt).zfill(5) + ".jpg")
        cnt += 1