import requests
import json
from multiprocessing.dummy import Pool as ThreadPool
from multiprocessing import Queue
import sys
headers = {
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
}
q1 = Queue()
q2 = Queue()
urls = [] # 存取url列表
# 讀取url
def get_urls(query):
  # 遍歷50頁
  for i in range(1,51):
    # 要爬取的url列表，返回值是json數(shù)據(jù)，q參數(shù)是搜索內(nèi)容，p參數(shù)是頁碼
    url = "http://106.15.195.249:8011/search_new?&q=%s&p=%d" % (query,i)
    urls.append(url)
# 獲取數(shù)據(jù)
def get_data(url):
  print("開始加載，請等待...")
  # 獲取json數(shù)據(jù)并把json數(shù)據(jù)轉(zhuǎn)換為字典
  resp = requests.get(url, headers=headers).content.decode("utf-8")
  resp = json.loads(resp)
  # 如果搜素數(shù)據(jù)為空就拋出異常停止程序
  if resp['list']['data'] == []:
    raise Exception
  # 遍歷每一頁數(shù)據(jù)的長度
  for num in range(len(resp['list']['data'])):
    # 獲取百度云鏈接
    link = resp['list']['data'][num]['link']
    # 獲取標題
    title = resp['list']['data'][num]['title']
    # 訪問百度云鏈接，判斷如果頁面源代碼中有“失效時間：”這段話的話就表明鏈接有效，鏈接無效的頁面是沒有這段話的
    link_content = requests.get(link, headers=headers).content.decode("utf-8")
    if "失效時間：" in link_content:
      # 把標題放進隊列1
      q1.put(title)
      # 把鏈接放進隊列2
      q2.put(link)
      # 寫入csv文件
      with open("wangpanziyuan.csv", "a+", encoding="utf-8") as file:
        file.write(q1.get()+","+q2.get() + "\n")
  print("ok")
if __name__ == '__main__':
  # 括號內(nèi)填寫搜索內(nèi)容
  get_urls("python")
  # 創(chuàng)建線程池
  pool = ThreadPool(3)
  try:
    results = pool.map(get_data, urls)
  except Exception as e:
    print(e)
  pool.close()
  pool.join()
  print("退出")