python automatically open the browser to download zip and extract the content to write to excel

#!/usr/bin/python3
# coding=utf-8
import time
from selenium import webdriver
from  import quote,unquote
import re
import requests
import os
# The following two parameters are to prevent backcrawling, other articles also write this, but I do not use it here
headers = {
 'Accept': '*/*',
 'Accept-Language': 'en-US,en;q=0.5',
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
}
params = {
 'from': 'search',
 'seid': '9698329271136034665'
}


class Download_file():
 def __init__(self,url,order_number,file_path):
 =url
 self.order_number=order_number
 self.file_path=file_path

 # Get the download link for the file
 def _get_files_url(self):
 # Open it with Google Chrome
 driver=()
 # Get the url
 ()
 print()
 (5)
 # Get the corresponding operation object by tag id
 driver.switch_to.frame(0)
 driver.find_element_by_id('search_id').send_keys(self.order_number)
 # Specific pages have specific actions, here the button I need to find has no id, he is using ng-click="queryCheckRecordByTid()"
 driver.find_element_by_class_name('btn').click()
 # driver.find_element_by_id('su').click()
 (3)
 # AngularJS syntax for writing tags is annoying. I'll start here by finding the parent tag of the target tag
 # And then get the target tag through the parent tag #
 dd=driver.find_elements_by_class_name('col-xs-2')
 # I have two <a></a> tags under this parent tag, and I can only have the first one.
 url_list=[]
 for i in dd:
 # Because the downloaded url happens to be the first one, and then it's obtained here as element, so it happens to be the correct url.
 a=i.find_element_by_xpath('.//a')
 # print(a.get_attribute('href'))
 url_list.append(a.get_attribute('href'))
 # download_btn[0].click()
 (3)
 ()
 return url_list

 # Download file
 def download_save(self):
 # Matches may come up with None, so do a little processing
 url_list=self._get_files_url()
 url_list=list(filter(lambda x:x!=None,url_list))
 if len(url_list)==0:
 return False
 # Create a folder to hold the zip
 # The reason for changing the execution path is that it gives the flexibility to create files in user-specified directories.
 (self.file_path)
 if (self.file_path+'/'+'Download_Files') == False:
 ('Download_Files')
 # Change execution path
 (self.file_path + '/'+'Download_Files/')
 for url in url_list:
 # The link comes with the author and filename, but it needs to be decoded, so first extract the target string in regular language, then convert it to Chinese
 ret = (r'_.*\.zip$',url)
 file_info=unquote(())
 file_author=file_info.split('_')[1]
 file_title=file_info.split('_')[2]
 file_object=(url)
 file_name=file_author+'_'+file_title
 print('Downloading:%s'%file_name)
 with open(file_name,'wb') as f:
 (file_object.content)


 # def auto_fill(self):

if __name__ == '__main__':
 url='http://***'
 order_id='***'
 file_path='D:/For discipline/Get_excel'
 test=Download_file(url,order_id,file_path)
 test.download_save()

#!/usr/bin/python3
# coding=utf-8
import os
import time
import xlwt
import zipfile
import re
import pickle
from bs4 import BeautifulSoup
from Download_files import Download_file
class get_excel():
 def __init__(self,file_path):
 self.file_path=file_path


 # Extract the target file
 def _unzip_files(self):
 '''
 This function decompresses the target file and returns a list of files to be processed.
 :return.
 '''
 files_list=(self.file_path)
 # The filenames are stored in a list, so in case you're dealing with other files, first match them with a regular rule
 files_list=list(filter(lambda x:(r'\.zip$',x)!=None,files_list))
 title_list=[]
 for file in files_list:
 title=('.')[0].split('_')[1]
 with (self.file_path+'/'+file,'r') as z:
 # The code is a bit long, mainly for filtering out the target file
 target_file=list(filter(lambda x:(r'Comparison Report.html$',x)!=None,()))
 # The following approach is the more flexible
 contentb=(target_file[0])
 # The big headache here is that the return value is binary, so even if you decode it, there's no way to regularize it.
 # So I'd like to save it and read it in utf8 #
 # Of course I tried decode, but there are still some things within the page that I can't convert, which also causes the regulars to not match
 if (self.file_path+'/'+title+'_'+'ComparisonReport.html')==False:
 with open(self.file_path+'/'+title+'_'+'ComparisonReport.html','wb') as fb:
 (contentb,fb)
 # with open(self.file_path+'/'+target_file[0],'r',encoding='utf-8') as fa:
 # contenta=()
 # print(contenta)
 # sentence=str((r'<b [^"]*red tahoma.*</b>$',contenta))
 # value=(r'\d.*%', sentence)
 # info=[author,title,value]
 # repetition_rate.append(info)
 title_list.append(target_file[0])
 return files_list,title_list


 # Read the contents of an html file
 def read_html(self):
 '''
 The previous function has extracted the target file, but the html file is more troublesome to read.
 So here I use BeautifulSoup library to read the information I want.
 and then return what I want in a list.
 :return.
 '''
 files_list,title_list=self._unzip_files()
 repetition_rate=[]
 for file in files_list:
 # Take out the author and the title, both of which should be written into excel
 file=('.')
 file=file[0].split('_')
 author=file[0]
 title=file[1]
 # The comparison report has been unpacked. Just read it. #
 with open(self.file_path+'/'+title+'_comparison_report.html','rb') as f:
 # Below is the usage of BeautifulSoup, if you can't read it you can go to the official website
 content=()
 content=BeautifulSoup(content,"")
 # print(type(content))
 # Searched the internet, finally I can find the duplication rate I want #
 value=('b',{"class":"red tahoma"}).string
 repetition_rate.append([author,title,value])
 return repetition_rate


 def write_excel(self):
 '''
 Generate xls table
 :return.
 '''
 workbook=(encoding='utf-8')
 booksheet=workbook.add_sheet('Sheet1')
 # Setting the border
 borders = () # Create Borders
  =  #DASHED dashed line, NO_LINE none, THIN solid line
  =  #=1 indicates a solid line
  = 
  = 
 borders.left_colour=0x40
 borders.right_colour = 0x40
 borders.top_colour = 0x40
 borders.bottom_colour = 0x40
 style1=()
 =borders
 # Setting the background color, these operations are very js and css like.
 pattern = ()
  = .SOLID_PATTERN
 pattern.pattern_fore_colour = 44
 style = () # Create the Pattern
  = pattern
 repetition_rate=self.read_html()
 # Write a title
 (0,0,'The Author',style)
 (0,1,'Title',style)
 (0,2,'Repetition rate',style)
 for item in repetition_rate:
 (repetition_rate.index(item)+1,0,item[0],style1)
 (repetition_rate.index(item)+1,1,item[1],style1)
 (repetition_rate.index(item)+1,2,item[2],style1)
 s='Repetition rate.xls'
 (self.file_path+'/'+s)


if __name__ == '__main__':
 # Judge the Download_files folder.
 file_path='D:/For discipline/Get_excel'
 url='http://***'
 order_number='***'
 if ('./Download_Files')==False:
 get_file=Download_file(url,order_number,file_path)
 get_file.download_save()
 (file_path+'/Download_Files')
 test=get_excel('D:/For discipline/Get_excel/Download_Files')
 test.write_excel()

from bs4 import BeautifulSoup

for k in soup.find_all('a'):
 print(k)
 print(k['class'])#Check the class attribute of the a tag
 print(k['id'])#Check the id value of the a tag
 print(k['href'])#checking the href value of the a tag
 print()#Check the string of the a tag
 #('calss')，It can also achieve this effect