import requests
import re
import time
payload = ""
# 請求頭
headers = {
  "Accept": "*/*",
  "Accept-Encoding": "gzip, deflate, br",
  "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
  "Cookie": "l=AurqcPuigwQdnQv7WvAfCoR1OlrRQW7h; isg=BHp6mNB79CHqYXpVEiRteXyyyKNcg8YEwjgLqoRvCI3ddxqxbLtOFUBGwwOrZ3ad; thw=cn; cna=VsJQERAypn0CATrXFEIahcz8; t=0eed37629fe7ef5ec0b8ecb6cd3a3577; tracknick=tb830309_22; _cc_=UtASsssmfA%3D%3D; tg=0; ubn=p; ucn=unzbyun; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; miid=981798063989731689; hng=CN%7Czh-CN%7CCNY%7C156; um=0712F33290AB8A6D01951C8161A2DF2CDC7C5278664EE3E02F8F6195B27229B88A7470FD7B89F7FACD43AD3E795C914CC2A8BEB1FA88729A3A74257D8EE4FBBC; enc=1UeyOeN0l7Fkx0yPu7l6BuiPkT%2BdSxE0EqUM26jcSMdi1LtYaZbjQCMj5dKU3P0qfGwJn8QqYXc6oJugH%2FhFRA%3D%3D; ali_ab=58.215.20.66.1516409089271.6; mt=ci%3D-1_1; cookie2=104f8fc9c13eb24c296768a50cabdd6e; _tb_token_=ee7e1e1e7dbe7; v=0",
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64;` rv:47.0) Gecko/20100101 Firefox/47.0"
}
# 獲得文章列表urls
def getUrls(url):

  # 發送請求
  resp = requests.request("GET", url, data=payload, headers=headers)
  #設置解碼方式
  resp.encoding=resp.apparent_encoding
  #這里會用設置的解碼方式解碼
  html_source = resp.text
  # 正則表達式，取出網頁中的url鏈接（一些尋找注入點的工具也是這么做出來的）
  urls = re.findall("https://[^>\";\']*d",html_source)
  new_urls=[]
  for url in urls:
    if 'details' in url:
      if url not in new_urls:
        new_urls.append(url)
  return new_urls

urls = getUrls("主頁地址")
while True:
  for url in urls:
    requests.request("GET", url, data=payload, headers=headers)
    print(url, "Ok")
    time.sleep(3)
  time.sleep(3)

import requests
import time
import re
from lxml import etree
headers = {
  'referer':'https://i.cnblogs.com/posts',

  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36"

}
proxy = {

  'http':'xxxx:xxx',#可以使用代理

}

def get_urls(url):
  ret = requests.get(url=url,headers = headers)
  ret.encoding='utf-8'
  urls = re.findall(' rel="external nofollow" ',ret.text) #正則條件根據博客地址修改
  return urls

urls = []
for url in [f'https://www.cnblogs.com/shiguanggege/default.html?page={i}' for i in range(1,10)]: #url根據自己博客地址修改
  links = get_urls(url)
  for link in links:
    l = f'https://www.cnblogs.com/shiguanggege/p/{link}.html' #這個地址也是根據博客地址修改
    if l not in urls:
      urls.append(l)
while True:
  for i in urls:
    requests.get(url=i,proxies=proxy)
    print(i,'ok')
    time.sleep(1)
  time.sleep(3)