import datetime
import re
import pymysql
import requests
url = "https://www.gushiwen.org/"
headers = {
 'User-Agent': "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"}
class Spiderpoem(object):
 conn = pymysql.Connect(host="localhost", port=3306, user="root", password='mysql', database='poem_data',
       charset="utf8")
 cs1 = conn.cursor()
 def get_requests(self, url, headers=None):
  """发送请求"""
  resp = requests.get(url, headers=headers)
  if resp.status_code == 200:
   # print(resp.request.headers)
   return resp.text
  return None
 def get_parse(self, response):
  """解析网页"""
  re_data = {
   "title": r'<div\sclass="sons">.*?<b>(.*?)</b>.*?</div>',
   "author": r'<p>.*?class="source">.*?<a.*?>(.*?)</a>.*?<a.*?>(.*?)</a>.*?</p>',
   "content": r'<div\sclass="contson".*?>(.*?)</div>'
  }
  titles = self.reg_con(re_data["title"], response)
  authors = self.reg_con(re_data["author"], response)
  poems_list = self.reg_con(re_data["content"], response)
  contents = list()
  for item in poems_list:
   ite = re.sub(r'<.*?>|\s', "", item)
   contents.append(ite.strip())
  for value in zip(titles, authors, contents):
   title, author, content = value
   author = "".join([author[0], '.', author[1]])
   poem = {
    "title": title,
    "author": author,
    "content": content
   }
   yield poem
 def reg_con(self, params, response):
  """正则匹配"""
  if not response:
   return "请求错误"
  param = re.compile(params, re.DOTALL) # re.DOTALL 匹配换行等价于re.S
  result = re.findall(param, response)
  return result
 @classmethod
 def save_data(cls, poem):
  title = poem.get("title")
  author = poem.get("author")
  content = poem.get("content")
  crate_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
  sql = "insert into poem(title,author,content,create_time) values('{}','{}','{}','{}')".format(title, author,
                          content,
                          crate_time)
  count = cls.cs1.execute(sql)
  print(count)
  cls.conn.commit()
 def main(self):
  resp = self.get_requests(url, headers)
  for it in self.get_parse(resp):
   self.save_data(it)
  self.cs1.close()
  self.conn.close()
if __name__ == '__main__':
 Spiderpoem().main()