用Python 爬取心灵毒鸡汤、你好污啊 网站数据并存入本地txt文件

1. 心灵毒鸡汤

1. 网站如下：https://www.nihaowua.com/home.html
   

2. 代码如下：

   import requests
   import random
   from lxml import etree
   from fake_useragent import UserAgent
   
   
   def get_random_ua(): #随机UA
       ua = UserAgent()
       return ua.random
   
   headers = {
       'User-Agent': get_random_ua()
   }
   
   url = 'https://www.nihaowua.com/home.html'
   
   
   def main():  #写入txt文本程序
       count = 0
       while True:
           try:
               with open("soup.txt", "a", encoding='utf-8') as f:
                   res = requests.get(url=url, headers=headers, timeout=10)
                   selector = etree.HTML(res.text)
                   content = selector.xpath('//section/div/*/text()')[0]
                   text = str(count) + str(content)
                   f.write(text + '\n')
                   count += 1
                   print('*****正在爬取中，这是第{}次爬取，内容为：{}'.format(count, content))
           except Exception as e:
               print('exception:', e)
               continue
   
   
   if __name__ == '__main__':
       main()
   
   

3. 执行结果如下：
   

4. 存入文本中的数据如下：
   

2. 你好污啊

1. 网站如下：https://www.nihaowua.com/
   

2. 代码如下：

   import requests
   import random
   from lxml import etree
   from fake_useragent import UserAgent
   
   def get_random_ua(): #随机UA
       ua = UserAgent()
       return ua.random
   
   headers = {
       'User-Agent': get_random_ua()
   }
   
   url = 'https://www.nihaowua.com/'
   
   
   def main():  # 写入txt文本程序
       count = 0
       while True:
           res = requests.get(url=url, headers=headers, timeout=10)
           selector = etree.HTML(res.text)
           content = selector.xpath('//section/div/*/text()')[0]
           with open("NiHaoWu.txt", "a") as f:
               text = str(count) + ' ' + content
               f.write(text + '\n')
               count += 1
               print('这是第{}次爬取,内容为：{}'.format(count, content))
   
   
   if __name__ == '__main__':
       main()
   
   

3. 执行结果如下图：
   

4. 存入文本数据如下：