{"id":17249,"date":"2020-02-02T22:50:41","date_gmt":"2020-02-02T14:50:41","guid":{"rendered":"http:\/\/4563.org\/?p=17249"},"modified":"2020-02-02T22:50:41","modified_gmt":"2020-02-02T14:50:41","slug":"%e6%b8%85%e5%8d%8e%e6%96%87%e6%b3%89%e5%ad%a6%e5%a0%82%e5%8d%8f%e7%a8%8b%e4%b8%8b%e8%bd%bd","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=17249","title":{"rendered":"\u6e05\u534e\u6587\u6cc9\u5b66\u5802\u534f\u7a0b\u4e0b\u8f7d"},"content":{"rendered":"\n

\t\t\t\t\tyjsx86<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

\u6e05\u534e\u6587\u6cc9\u5b66\u5802\u534f\u7a0b\u4e0b\u8f7d<\/h3>\n

\t\t \u672c\u5e16\u6700\u540e\u7531 yjsx86 \u4e8e 2020-2-2 22:08 \u7f16\u8f91 <\/p>\n

\u534f\u7a0b\u4e0b\u8f7d\uff0c \u589e\u52a0\u4e0b\u8f7d\u901f\u5ea6\uff0c \u8bd5\u8bd5\u770b
github\u4e0a\u90a3\u4e2a\u8bd5\u7528\u4e86\u4e00\u4e0b \u4f1a\u51fa\u73b0not found \u8fd8\u662fnot load \u6765\u7740\u5bfc\u81f4\u4e0b\u8f7d\u5931\u8d25
\u8fd9\u4e2a\u4f1a\u628a\u4e0b\u8f7d\u5931\u8d25\u7684\u91cd\u56de\u961f\u5217\uff0c \u6700\u7ec8\u4f1a\u4e0b\u8f7d\u6210\u529f\u7684(\u6d4b\u8bd5\u7684\u65f6\u5019\u6709\u4e24\u5f20\u56fe\u603b\u662f\u4e0b\u8f7d\u5931\u8d25\uff0c \u7a0b\u5e8f\u91cd\u8bd5\u4e86\u4e0a\u767e\u6b21\u540e\u6210\u529f\u4e86\uff01)
import requests
import jwt
import json
import time
import aiohttp
import asyncio
import os
import logging<\/p>\n

logging.basicConfig(level=logging.INFO)<\/p>\n

class Wqxuetang():<\/p>\n

    def __init__(self, bookid, max_threads=4):
      self.bookid = bookid
      self.max_threads = max_threads
      self.work_queue = asyncio.Queue()
      self.jwt_secret = "g0NnWdSE8qEjdMD8a1aq12qEYphwErKctvfd3IktWHWiOBpVsgkecur38aBRPn2w"
      self.session = requests.session()
      self.jwtkey = self.get_jwt_key()
      self.timeoutlist = []
      (self.bookname, self.totalpages) = self.bookinfo()
      self.totalpages = int(self.totalpages)
      self.creat_and_enter_book_dir()<\/p>\n

    def creat_and_enter_book_dir(self):
      curpath = os.getcwd()
      newpath = curpath + os.path.sep + self.bookname
      os.mkdir(newpath)
      os.chdir(newpath)
            <\/p>\n

    def bookinfo(self):
      url = f"https:\/\/lib-nuanxin.wqxuetang.com\/v1\/read\/initread?bid={self.bookid}"
      r = self.session.get(url)
      info = json.loads(r.text)
      data = info[‘data’]
      return data[‘name’], data[‘canreadpages’]<\/p>\n

    def get_jwt_key(self):
      url = "https:\/\/lib-nuanxin.wqxuetang.com\/v1\/read\/k?bid=%s" % self.bookid
      r = self.session.get(url, timeout=5)
      j = json.loads(r.text)
      return j[‘data’]<\/p>\n

    def get_jwt_token(self, page):
      cur_time = time.time()
      jwttoken = jwt.encode({
            "p": page,
            "t": int(cur_time)*1000,
            "b": str(self.bookid),
            "w": 1000,
            "k": json.dumps(self.jwtkey),
            "iat": int(cur_time)
      }, self.jwt_secret, algorithm=’HS256′).decode(‘ascii’)
      return jwttoken<\/p>\n

    async def download_img(self, page, task_id):
      token = self.get_jwt_token(page)
      url = f"https:\/\/lib-nuanxin.wqxuetang.com\/page\/img\/{self.bookid}\/{page}?k={token}"
      headers = {
            ‘referer’: f’https:\/\/lib-nuanxin.wqxuetang.com\/read\/pdf\/{self.bookid}’,
            ‘user-agent’: ‘Mozilla\/5.0 (Windows NT 10.0; WOW64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/69.0.3497.100 Safari\/537.36’
      }
      try:
            async with aiohttp.ClientSession() as session:
                async with session.get(url, headers=headers, timeout=5) as response:
                  r = await response.read()
      except Exception:
            logging.warning(f"\u7ebf\u7a0b {task_id} -> \u7b2c {page} \u5f20\u4e0b\u8f7d\u5931\u8d25, \u91cd\u56de\u961f\u5217\uff01\uff01\uff01")
            self.work_queue.put_nowait(page)
      else:
            with open(f"{self.bookname+str(page)}.png", "wb") as f:
                f.write(r)
            logging.info(f"\u7ebf\u7a0b {task_id} -> \u7b2c {page} \u5f20\u4e0b\u8f7d\u5b8c\u6210")<\/p>\n

    async def handle_tasks(self, task_id):
      while not self.work_queue.empty():
            page = await self.work_queue.get()
            await self.download_img(page, task_id)
      logging.info(f"\u7ebf\u7a0b {task_id} \u7ed3\u675f\u5de5\u4f5c\uff01~")<\/p>\n

    def main(self):
      
      loop = asyncio.get_event_loop()
      tasks =
      loop.run_until_complete(asyncio.wait(tasks))
      loop.close()<\/p>\n

if __name__ == "__main__":
    bookid = 3187882
    # \u53c2\u65701\uff1a\u4e66\u53f7\uff0c \u53c2\u65702\uff1a\u7ebf\u7a0b\u6570
    # \u9ed8\u8ba4\u4e66\u540d\u4e3a\u4e0b\u8f7d\u6587\u4ef6\u5939\u540d
    w = Wqxuetang(bookid, 4)
    w.main()<\/p>\n

\t\t\t\t\thaierwx21410<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\t\u9876\u4e00\u9876\uff0c\u8bf7\u95ee\u697c\u4e3b\uff0c\u8fd9\u4e2a\u4e0b\u8f7d\u4e0b\u6765\u662f\u56fe\u7247\u4e48\uff1f\u8fd8\u662fpdf\u554a\t\t\t\t<\/p>\n

\t\t\t\t\tyjsx86<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\thaierwx21410 \u5927\u4f6c\u6709\u8bdd\u8bf4 : 2020-2-2 22:10
\u9876\u4e00\u9876\uff0c\u8bf7\u95ee\u697c\u4e3b\uff0c\u8fd9\u4e2a\u4e0b\u8f7d\u4e0b\u6765\u662f\u56fe\u7247\u4e48\uff1f\u8fd8\u662fpdf\u554a<\/p>\n

\u4e0b\u8f7d\u4e0b\u6765\u7684\u56fe\u7247 \uff0c \u9700\u8981pdf\u7684\u8bdd\u81ea\u5df1\u5408\u6210\u5427\t\t\t\t<\/p>\n

\t\t\t\t\tjxpal<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\t\u9876\u4e00\u4e0b\uff0c\u987a\u4fbfmark\t\t\t\t<\/p>\n

\t\t\t\t\t\u4e1c\u5357\u897f\u5317<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\t\u9a6c\u514b\u4e00\u4e0b\t\t\t\t<\/p>\n

\t\t\t\t\t\u675c\u752b<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\t\ud83d\ude42 \u6bcf\u5e74618\u4e70\u7684\u4e66\u5806\u6210\u5c71\u4e86\u90fd\t\t\t\t<\/p>\n

\t\t\t\t\tvopcloud<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\timport requests
import jwt
import json
import time
import aiohttp
import asyncio
import os
import logging
import sys<\/p>\n

logging.basicConfig(level=logging.INFO)<\/p>\n

class Wqxuetang():<\/p>\n

    def __init__(self, bookid, max_threads=4):
      self.bookid = bookid
      self.max_threads = max_threads
      self.work_queue = asyncio.Queue()
      self.jwt_secret = "g0NnWdSE8qEjdMD8a1aq12qEYphwErKctvfd3IktWHWiOBpVsgkecur38aBRPn2w"
      self.session = requests.session()
      self.jwtkey = self.get_jwt_key()
      self.timeoutlist = []
      (self.bookname, self.totalpages) = self.bookinfo()
      self.totalpages = int(self.totalpages)
      self.creat_and_enter_book_dir()<\/p>\n

    def creat_and_enter_book_dir(self):
      curpath = os.getcwd()
      newpath = curpath + os.path.sep + self.bookname
      os.mkdir(newpath)
      os.chdir(newpath)<\/p>\n

    def bookinfo(self):
      url = f"https:\/\/lib-nuanxin.wqxuetang.com\/v1\/read\/initread?bid={self.bookid}"
      r = self.session.get(url)
      info = json.loads(r.text)
      data = info[‘data’]
      return data[‘name’], data[‘canreadpages’]<\/p>\n

    def get_jwt_key(self):
      url = "https:\/\/lib-nuanxin.wqxuetang.com\/v1\/read\/k?bid=%s" % self.bookid
      r = self.session.get(url, timeout=5)
      j = json.loads(r.text)
      return j[‘data’]<\/p>\n

    def get_jwt_token(self, page):
      cur_time = time.time()
      jwttoken = jwt.encode({
            "p": page,
            "t": int(cur_time)*1000,
            "b": str(self.bookid),
            "w": 1000,
            "k": json.dumps(self.jwtkey),
            "iat": int(cur_time)
      }, self.jwt_secret, algorithm=’HS256′).decode(‘ascii’)
      return jwttoken<\/p>\n

    async def download_img(self, page, task_id):
      token = self.get_jwt_token(page)
      url = f"https:\/\/lib-nuanxin.wqxuetang.com\/page\/img\/{self.bookid}\/{page}?k={token}"
      headers = {
            ‘referer’: f’https:\/\/lib-nuanxin.wqxuetang.com\/read\/pdf\/{self.bookid}’,
            ‘user-agent’: ‘Mozilla\/5.0 (Windows NT 10.0; WOW64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/69.0.3497.100 Safari\/537.36’
      }
      try:
            async with aiohttp.ClientSession() as session:
                async with session.get(url, headers=headers, timeout=5) as response:
                  r = await response.read()
      except Exception:
            logging.warning(f"\u7ebf\u7a0b {task_id} -> \u7b2c {page} \u5f20\u4e0b\u8f7d\u5931\u8d25, \u91cd\u56de\u961f\u5217\uff01\uff01\uff01")
            self.work_queue.put_nowait(page)
      else:
            if sys.getsizeof(r)==10433:
                self.work_queue.put_nowait(page)
                logging.warning(f"\u7ebf\u7a0b {task_id} -> \u7b2c {page} \u5f20\u52a0\u8f7d\u5931\u8d25, \u91cd\u56de\u961f\u5217\uff01\uff01\uff01")
            else:
                with open(f"{self.bookname+str(page)}.png", "wb") as f:
                  f.write(r)
                logging.info(f"\u7ebf\u7a0b {task_id} -> \u7b2c {page} \u5f20\u4e0b\u8f7d\u5b8c\u6210")<\/p>\n

    async def handle_tasks(self, task_id):
      while not self.work_queue.empty():
            page = await self.work_queue.get()
            await self.download_img(page, task_id)
      logging.info(f"\u7ebf\u7a0b {task_id} \u7ed3\u675f\u5de5\u4f5c\uff01~")<\/p>\n

    def main(self):
      
      loop = asyncio.get_event_loop()
      tasks =
      loop.run_until_complete(asyncio.wait(tasks))
      loop.close()<\/p>\n

if __name__ == "__main__":
    bookid = int(sys.argv)
    # \u53c2\u65701\uff1a\u4e66\u53f7\uff0c \u53c2\u65702\uff1a\u7ebf\u7a0b\u6570
    # \u9ed8\u8ba4\u4e66\u540d\u4e3a\u4e0b\u8f7d\u6587\u4ef6\u5939\u540d
    w = Wqxuetang(bookid, 4)
    w.main()
\u697c\u4e3b\uff0c\u6211\u53d1\u73b0\u597d\u50cf\u6709\u4e9b\u4e0b\u8f7d\u4e0b\u6765\u7684\u56fe\u7247\u6709\u95ee\u9898\uff0c\u56fe\u7247\u90fd\u663e\u793a\u52a0\u8f7d\u4e2d\uff0c\u4f46\u662f\u8fd9\u4e9b\u4e0b\u8f7d\u5f02\u5e38\u7684\u56fe\u7247\u5927\u5c0f\u90fd\u4e00\u6837\uff0c\u5c31\u7b80\u5355\u7c97\u66b4\u52a0\u4e86\u4e2a\u5224\u65ad\uff0c\u4e0d\u77e5\u697c\u4e3b\u6709\u6ca1\u6709\u5565\u597d\u65b9\u6cd5\uff1f\t\t\t\t<\/p>\n

\t\t\t\t\tyjsx86<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\tvopcloud \u5927\u4f6c\u6709\u8bdd\u8bf4 : 2020-2-2 22:46
\u697c\u4e3b\uff0c\u6211\u53d1\u73b0\u597d\u50cf\u6709\u4e9b\u4e0b\u8f7d\u4e0b\u6765\u7684\u56fe\u7247\u6709\u95ee\u9898\uff0c\u56fe\u7247\u90fd\u663e\u793a\u52a0\u8f7d\u4e2d\uff0c\u4f46\u662f\u8fd9\u4e9b\u4e0b\u8f7d\u5f02\u5e38\u7684\u56fe\u7247\u5927\u5c0f\u90fd\u4e00\u6837\uff0c\u5c31\u7b80 …<\/p>\n

\u7ed9\u4e2abookid\u6211\u8bd5\u8bd5\t\t\t <\/p>\n","protected":false},"excerpt":{"rendered":"

yjsx86 \u5927\u4f6c\u6709\u8bdd\u8bf4 : \u6e05\u534e…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/17249"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=17249"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/17249\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17249"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17249"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17249"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}