python獲取數據網頁數據並創建文件夾保存（基於python3.6）

from urllib.parse import urljoin
import urllib.request

from bs4 import BeautifulSoup


import os
import datetime
import re
import errno


def mkdir_p(path):   #遞歸創建多級目錄
    try:
        os.makedirs(path)
    except OSError as exc: # Python >2.5 (except OSError, exc: for Python <2.5)
        if exc.errno == errno.EEXIST and os.path.isdir(path):
            pass
        else: raise

def get_link(page):  # 尋找鏈接的href
    linkData = []
    for page in page.find_all('td'):
        links = page.select("a")
        for each in links:
            # if str(each.get('href'))[:1] == '/': 過濾if代碼
                data=each.get('href')
                linkData.append(data)
    return(linkData)


def gain(url):      #獲取網頁指定內容
    page = urllib.request.urlopen(url).read()
    soup = BeautifulSoup(page, 'lxml')  #利用soup獲取網頁內容
    links = get_link(soup) #獲取<a href= ? 內容
    return links


def main():
    url = 'https://www.tide-forecast.com/countries/China'
    Web_Link=gain(url)

    for Link in range(len(Web_Link)):
        Link_Add = Web_Link[Link]
        Link_One = re.split("/", Link_Add)   #去除'/'，將Link_Add變成數組
        Link_Address = Link_One[2]           #獲取數組第3位值
        Link_Address = (Link_Address + '.js')
        url_Tide = 'https://www.tide-forecast.com/tides/'
        connet = urljoin(url_Tide, Link_Address)          # 拼接網址路徑
        file = os.path.join('D:\\TideData\\China' + "/" )  # 拼接絕對路徑
        mkdir_p(file)
        print(connet)
        if os.path.isfile(file):
           print('文件已存在')
        else:
            start = datetime.datetime.now().replace(microsecond=0)  #計時工具
            
            url = connet
            wp = urllib.request.urlopen(url)  #打開數據網頁數據
            content = wp.read()                
            fp = open(file + Link_Address, "wb")     #寫入指定文件夾 
            fp.write(content)            #寫入數據
            fp.close()                    #關閉文件

            end = datetime.datetime.now().replace(microsecond=0)
            print("用時: ", end='')
            print(end - start)





if __name__ == '__main__':
    main()