import requests
import re
import json

class NeihanSpider(object):
  """內(nèi)涵段子，百思不得其姐，正則爬取一頁的數(shù)據(jù)"""
  def __init__(self):
    self.temp_url = 'http://www.budejie.com/text/{}' # 網(wǎng)站地址，給頁碼留個(gè)可替換的{}
    self.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',
    }

  def pass_url(self, url): # 發(fā)送請求，獲取響應(yīng)
    print(url)
    response = requests.get(url, headers=self.headers)
    return response.content.decode()

  def get_first_page_content_list(self, html_str): # 提取第一頁的數(shù)據(jù)
    content_list = re.findall(r'<div class="j-r-list-c-desc">\s*<a href="/detail-.*" rel="external nofollow" rel="external nofollow" rel="external nofollow" >(.+?)</a>', html_str) # 非貪婪匹配
    return content_list

  def save_content_list(self, content_list):
    with open('neihan.txt', 'a', encoding='utf-8') as f:
      for content in content_list:
        f.write(json.dumps(content, ensure_ascii=False))
        f.write('\n') # 換行
      print('成功保存一頁！')

  def run(self): # 實(shí)現(xiàn)主要邏輯
    for i in range(20): # 只爬取前20頁數(shù)據(jù)
      # 1. 構(gòu)造url
      # 2. 發(fā)送請求，獲取響應(yīng)
      html_str = self.pass_url(self.temp_url.format(i+1))
      # 3. 提取數(shù)據(jù)
      content_list = self.get_first_page_content_list(html_str)
      # 4. 保存
      self.save_content_list(content_list)

if __name__ == '__main__':
  neihan = NeihanSpider()
  neihan.run()