import xlrd
def get_bookurl_list(site):book = xlrd.open_workbook(site)sheet1 = book.sheet()[0] #第一张工作表urls = sheet1.col(18) #书籍地址在第18列所以里面也就是18urls = urls[1:] #去除第一行的列名 #xlrd库读出来的excel每一个小格都是一个cell类，cell.value才是真正的数据return urls

import requests
def get_redirect_url(url):# 获得重定向前的链接#url = "重定向前的url"# 请求头，这里我设置了浏览器代理headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}# 请求网页response = requests.get(url,headers)print(response.status_code)  # 打印响应的状态码print(response.url)  # 打印重定向后的网址# 返回重定向后的网址return response.url

from win32com.client import Dispatch #这都是啥玩意儿，咱也不知道，咱也不敢问
def thunderDownload(urls): #处理后网址的列表thunder = Dispatch('ThunderAgent.Agent.1') #这个也可以试试'ThunderAgent.Agent64.1',反正我错了（笑for i in urls:thunder.AddTask(i)thunder.CommitTasks()

def url_process(urls):list1 = []num = 0for i in urls:url = i.value #i为cell类，i.value是真正的数据url = get_redirect_url(url) #调用之前的函数，获得原本的网页链接。url1 = url.replace('book', 'content/pdf')url1 = url1 + '.pdf' #这两行都是对原来网址的处理，处理之后就可以加入迅雷下载啦。list1.append(url1)print(urls.index(i))if len(list1)>5: #本来预想的是每5个就加入迅雷下载任务，没想到我还是太年轻了。thunderDownload(list1)list1 = []num += 1print(num)

开始请求接口
开始执行
请求完成
请求超时
开始请求接口
开始执行
请求完成
请求超时
开始请求接口
开始执行

import threadingclass MyThread(threading.Thread):def __init__(self, target, args=()): #目标函数super(MyThread, self).__init__()self.func = targetself.args = argsdef run(self):#接收返回值self.result = self.func(*self.args)def get_result(self):#线程不结束,返回值为Nonetry:return self.resultexcept Exception:return Nonedef limit_decor(limit_time): #限制真实请求时间的装饰器def functions(func):def run(*params):thre_func = MyThread(target=func,args=params)#主线程结束(超出时长),则线程方法结束thre_func.setDaemon(True)thre_func.start()#计算分段沉睡次数(?sleep_num = int(limit_time // 1)sleep_nums = round(limit_time % 1, 1)#多次短暂沉睡并尝试获取返回值for i in range(sleep_num):time.sleep(1)infor = thre_func.get_result()if infor:return infortime.sleep(sleep_nums)#最终返回值if thre_func.get_result():return thre_func.get_result()else:return "请求超时"return runreturn functionsdef a1(url):print('开始请求接口')#把逻辑封装成一个函数,使用线程调用a_theadiing = MyThread(target=a2,args=url)a_theadiing.start()a_theadiing.join()a = a_theadiing.get_result()print("请求完成")print(a)return a,a_theadiing.result@limit_decor(300) #将时长限制为5分钟，def a2(url):print("开始执行")url = get_redirect_url(url)print("执行完成")return url

def url_process(urls):list1 = []num = 0for i in urls:url = i.value#url = get_redirect_url(url)url = a1([url])[1]if url == "请求超时": continueelse:url1 = url.replace('book', 'content/pdf')url1 = url1 + '.pdf'list1.append(url1)print(urls.index(i))if len(list1)>2:thunderDownload(list1)list1 = []num += 1print(num)