Work need to look at the list check enterprise's enterprise information, including all telephone, E-mail, and major personnel information, more data you want to write a crawler ~ all learn to write most penalising success part information, after the change is suddenly refused to visit, but there is no question of browser login view, beg you where is the great god help have a look at the question,
Originally wanted to be like that,

 - coding - 8 # - * - * - 
The import requests 
The import LXML 
The import XLRD 
The import XLWT 
The import sys 
The from bs4 import BeautifulSoup 
The import XLWT 
The import time 
The import urllib 


Def craw (url, key_word) : 
User_Agent='Mozilla/5.0 (Windows NT 10.0; Win64. X64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/Edge/537.36 18.17763 '
Re=r 'https://www.qcc.com/search? Key='+ key_word 
Headers={
'Accept' : 'text/HTML, application/XHTML + XML, application/XML. Q=0.9 */*; Q=0.8 ', 
'the Accept - Encoding' : 'gzip, deflate, br', 
'the Accept - Language' : 'useful - Hans - CN, useful - Hans; Q=0.8, en - US; Q=0.6, en. Q=0.4, ko. Q=0.2 ', 
: 'cookies' r' _XXXXXXXXXXXXXXXX ', 
'Host' : 'www.qcc.com', 
'the Upgrade - Insecure - Request' : '1', 
'the user-agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64. X64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/Edge/18.17763 ', 537.36 
} 

Try: 
The response=requests. Get (url, headers=headers) 
If the response status_code!=200: 
The response. The encoding="utf-8" 
Print (response. Status_code) 
Print (" ERROR ") 
Soup=BeautifulSoup (the response text, 'LXML') 
Except the Exception: 
Both print (' request, the enterprise check is to want to go??? ') 
Try: 
FRTRT com_all_info=soup. Find_all (class_=' ') [0]. The tbody 
Com_all_info_array=com_all_info. Select (" td ") 
Print (' began to crawl the data, please do not open the excel) 
# the try: 
Temp_g_name=com_all_info_array [2]. Select (' a ') [0]. # text company name 

Temp_r_name=com_all_info_array [2]. Select (" p ") [0]. A.t ext # corporate name 

Temp_g_money=com_all_info_array [2]. Select (" p ") [0]. Select (' span) [0]. Text. The strip (' registered capital: ') # registered capital 

Temp_g_date=com_all_info_array [2]. Select (" p ") [0]. Select (' span) [1]. The text. The strip (' establishment date: ') # establishment date 

E=com_all_info_array [2]. Select (" p ") [1]. The select (' a ') [1] # mailbox 
F=e.s trip (' showHisEmail.) strip ('; '). The replace (' {', ' '). The replace ('} ', '). The replace ('/', ' '). The replace ('] ', '). The replace (' : ', '). The replace (' "', ' '). The replace (' e ', '). The replace (' s', '). The replace (' (', ' '). The replace (') ', ') 
G=f.s plit () ", "

L=0 
H=[] 

While l & lt; Len (g) : 
If l % 2==0: 
H.a ppend (STR) (g/l) 
L +=1 

='\ n' temp_r_email. Join (h) 

A=com_all_info_array [2]. Select (" p ") [1]. The select (' a ') [0] # phone 

B=a.s trip (' showHisTel.) strip ('; '). The replace (' {', ' '). The replace ('} ', '). The replace ('/', ' '). The replace ('] ', '). The replace (' : ', '). The replace (' "', ' '). The replace (' t ', '). The replace (' s', '). The replace (' (', ' '). The replace (') ', ') 
C=b.s plit () ", "

J=0 
D=[] 

While j & lt; Len (c) : 
If j % 2==0: 
Da ppend (STR) [j] (c) 
J +=1 

='\ n' temp_r_phone. Join (d) 

Temp_g_addr=com_all_info_array [2]. Select (" p ") [2]. The text. The strip (). The strip (' address: ') # address 

Temp_r_numm=com_all_info_array [2]. Select (" p ") [0]. Select (' span) [1]. The text. The strip (' unified social credit code: ') # reference code 

G_name_list. Append (temp_g_name) 

R_name_list. Append (temp_r_name) 

G_money_list. Append (temp_g_money) 

G_date_list. Append (temp_g_date) 

R_email_list. Append (temp_r_email) 

R_phone_list. Append (temp_r_phone) 

G_addr_list. Append (temp_g_addr) 

R_numm_list. Append (temp_r_numm) 


# the except Exception: 
# print (' error! ') 
Except the Exception: 
Print (' seemed to be refused access... Please try the request again beep... ') 


If __name__=="__main__ ': 

Global g_name_list 

Global r_name_list 

Global g_money_list 

Global g_date_list 

Global r_email_list 

Global r_phone_list 

Global g_addr_list 

Global r_numm_list 

Col=[] 

Data=https://bbs.csdn.net/topics/xlrd.open_workbook (r 'C: \' check data source. XLSX ') 

Sheet=data. Sheet_by_name (' Sheet1) 

Col=sheet. Col_values (0) 

For key_word in col: 
Time. Sleep (15) 
Key_word=urllib. Parse. Quote (key_word) 
Url=r 'https://www.qcc.com/search? Key='+ key_word 
Craw (url, key_word) 
Print (' searching, please later) 

Workbook=XLWT. Workbook () 

Sheet1=workbook. Add_sheet (' companies check data, cell_overwrite_ok=True) 

Style=XLWT. XFStyle () 



The font=XLWT. The font () 

The font. The name='imitation song dynasty style typeface' 

The font, bold=True 


Style. The font=the font 


Print (' are stored data, please do not open the excel) 

G_name_list=[] 

R_name_list=[] 

G_money_list=[] 

G_date_list=[] 

R_email_list=[] 

R_phone_list=[] 

G_addr_list=[] 

R_numm_list=[] 

Name_list=[' company name ', 'statutory legal persons',' registered capital ', 'date', 'corporate email', 'corporate phone', 'the company address,' unified social credit code] 

nullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnull