Python 查询最新到期删除域名

# 该脚本运行后将会在当前目录生成包含可注册域名列表的ali_domain.txt文件
# 并不包含自动在运营商注册的内容
# 请知悉


## 先导入必要的包
import requests
import pandas as pd
import json
import time


TIMEOUT = 10
headers = {"Referer":"https://wanwang.aliyun.com/domain/reserve",
       "user-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) Apple: WebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36",
       } 
def get_token():
    tokenurl = "https://promotion.aliyun.com/risk/getToken.htm"
    text = requests.get(tokenurl,headers=headers).text
    return json.loads(text)["data"]

def get_domains(token,regd="2006"):

### 这里根据参数直接修改就行，我设置的是一页100条记录，也就是100个域名，查看第一页就好了
### 后缀 com，域名长度最大为5，返回设置为json
    url = "https://domainapi.aliyun.com/preDelete/search.jsonp?keyWord=&excludeKeyWord=&keywordAsPrefix=false&keywordAsSuffix=false&exKeywordAsPrefix=fa\
lse&exKeywordAsSuffix=false&constitute=&suffix=com&domainType=&endDate=&regDate={}&pageSize=100&currentPage=1&bookStatus=false&reserveRmb=&sortBy=1&pa\
tnerTypes=&sortType=1&_t=self&minLength=&maxLength=5&minPrice=&maxPrice=&token=tdomain-aliyun-com%3A{}&callback=json".format(regd,token)
    text = requests.get(url,headers=headers,timeout = TIMEOUT).text
#根据json结构获取内容
    domains = json.loads(text.split("(")[1].split(")")[0])  
    return domains

## 这里手动添加 token（示例值通常会过期）

token = "Y15a564fc4ed081a18a64aa9b0ccc23bb" 
## 这里通过阿里的 API 自动获取 token
token = get_token() 
print(token)

## 搜索到的域名保存文件名
filename = "ali_domain.tsv"
## 每次运行是更新文件内容
with open("ali_domain.tsv",'w') as fw:
    fw.close()


# 从2006年到2010 年逐年搜索并写入到csv文件
for i in range(2006,2010):

    domains = get_domains(token,regd=str(i))
    if domains["code"]=="200":
        domains = domains["data"]["pageResult"]["data"]
        domains = pd.DataFrame.from_dict(domains)
        domains = domains[~domains.short_name.str.contains("-")] 
        print(domains)
        domains.to_csv(filename,index=None,mode="a",sep="\t")
    time.sleep(20)

import sys
import requests
import pandas as pd
import json
import time
import os

os.environ['HTTP_PROXY'] = 'http://127.0.0.1:1081'
TIMEOUT = 10
headers = {"Referer":"https://wanwang.aliyun.com/domain/reserve",
       "user-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) Apple: WebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36",
       } 
def get_token():
    tokenurl = "https://promotion.aliyun.com/risk/getToken.htm"
    text = requests.get(tokenurl,headers=headers).text
    return json.loads(text)["data"]

def get_df(token,regd="2006"):
    url = f"https://domainapi.aliyun.com/preDelete/search.jsonp?keyWord=&excludeKeyWord=&keywordAsPrefix=false&keywordAsSuffix=false&exKeywordAsPrefix=false&exKeywordAsSuffix=false&constitute=&suffix=com&domainType=&endDate=&regDate=&pageSize=500&currentPage=1&bookStatus=0&reserveRmb=&sortBy=1&patnerTypes=&sortType=1&_t=self&minLength=&maxLength=8&minPrice=&maxPrice=&token=tdomain-aliyun-com%3A{token}&callback=json"
    #print(url)
    text = requests.get(url,headers=headers,timeout = TIMEOUT).text
    res = json.loads(text.split("(")[1].split(")")[0])  
    return res

token = get_token()
filename = "/home/teng/ali.txt"
def has_pairs(s):
    if s[0]==s[1] or s[1]==s[2] or s[2]==s[3]:
        return True
    return False

df_list = []

# Loop through the years and process the data
for i in range(2006, 2010):
    df = get_df(token, regd=str(i))
    if df["code"] == "200":
        df = df["data"]["pageResult"]["data"]
        df = pd.DataFrame.from_dict(df)
        
        # Filter out rows based on the conditions
        filters = ['-', 'z', '2', 'i', 'l', '1', 'o', '0','q','9','g']
        for f in filters:
            df = df[~df.short_name.str.contains(f)]
        
        # Apply the has_pairs function
        df['pairs'] = df['short_name'].apply(has_pairs)
        df = df[df.pairs == True] 
        # Append the filtered dataframe to the list
        df_list.append(df)

domains = pd.concat(df_list, ignore_index=True)
ori = pd.read_csv(filename, sep=',')
domains = domains.drop_duplicates()
print(domains)
domains = pd.concat([ori, domains]).reset_index(drop=True)
domains = domains.drop_duplicates()
domains.to_csv(filename, index=None, mode="w")

head -n 40 ali_domain.tsv