# 爬取網頁的中文內容
from urllib import request
from bs4 import BeautifulSoup
import pandas as pds
import xlrd
import docx

#讀取excel
def excel(fname):
          data=pds.read_excel(fname)
          return data

def word(school ,content):
    #建立記憶體中的word文件物件
    file=docx.Document()
    #寫入若干段落
    file.add_paragraph(content)
    #儲存
    file.save("E:/大四上/畢業論文/招生簡章/"+school+"招生簡章.docx")
    



if __name__ == '__main__':

    data=excel("C:/Users/Administrator/Desktop/招生簡章.xlsx")  #讀初始資料
    nrow=data.shape[0]   #獲取資料的行數

    for i in range(0,nrow):
        school = data.values[i][0]
        url =data.values[i][1]
        print("正在爬第"+str(i)+"個招生簡章")

        head = {}
        # 使用代理
        head['User-Agent'] = 'Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166  Safari/535.19'
        req = request.Request(url, headers = head)
        response = request.urlopen(req)
        html = response.read()

        
        # 建立request物件
        soup = BeautifulSoup(html, 'lxml')
        # 找出div中的內容
        soup_text = soup.find(attrs={'class':'content'})
        # 輸出其中的文字
        content = soup_text.text
        
        word(school ,content)#寫入word文件