Automatically build and get USER_AGENT PROXY_LIST

. 1  Import json
 2  '' ' 
. 3  open the page, the page stored directly proxy_list.txt, then treated with a tool file as json!   
. 4  '' ' 
. 5 with Open ( " proxy_list.json " , " R & lt " , encoding = " UTF8 " ) AS F:
 . 6      data_lists = the json.load (F)
 . 7  
. 8 final_data = []
 . 9  for data_dict in data_lists:
 10      address_sets SET = (data_dict [ " export_address "
     port = data_dict["port"]
12     type =data_dict["type"]
13     # print(address_sets)
14     for address in address_sets:
15         temp = {type :address + ":" + str(port)}
16         # print(temp)
17         final_data.append(temp)
18 with open("PROXY_LISTS.json","a+",encoding="utf8") as f:
19     json.dump(final_data,f)
20     print(len(final_data))
View Code

 

 

Import json 
'' '
fight to open web pages , directly save the page proxy_list.txt, and then use the tool to its office manager for the json file! '' ' With Open ( "proxy_list.json" , "R & lt" , encoding = "UTF8" ) AS F: . Data_lists JSON = Load (F) final_data = [] for data_dict in data_lists: address_sets = SET (data_dict [ "export_address " ]) # becomes set






去重
port = data_dict["port"]
type =data_dict["type"]
# print(address_sets)
for address in address_sets:
temp = {type :address + ":" + str(port)}
# print(temp)
final_data.append(temp)
with open("PROXY_LISTS.json","a+",encoding="utf8") as f:
json.dump(final_data,f)
print(len(final_data))


Guess you like

Origin www.cnblogs.com/zach0812/p/12046742.html