爬取网站页面所有a标签下的href属性

在写爬取页面a标签下href属性的时候，有这样一个问题，如果a标签下没有href这个属性则会报错，如下：

百度了有师傅用正则匹配的，方法感觉都不怎么好，查了BeautifulSoup的官方文档，发现一个不错的方法，如下图：

官方文档链接：https://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

has_attr() 这个方法可以判断某标签是否存在某属性，如果存在则返回 True 

解决办法：

为美观使用了匿名函数

soup_a = soup.find_all(lambda tag:tag.has_attr('href'))

最终代码：

  1 #!/usr/bin/env python
  2 # -*- coding:utf-8 -*-
  3 # Author:Riy
  4 
  5 import time
  6 import requests
  7 import sys
  8 import logging
  9 from bs4 import BeautifulSoup
 10 from requests.exceptions import RequestException
 11 from multiprocessing import Process, Pool
 12 
 13 
 14 logging.basicConfig(
 15     level=logging.DEBUG,
 16     format='%(levelname)-10s: %(message)s',
 17 )
 18 
 19 
 20 class down_url:
 21     def download(self, url):
 22         '''爬取url'''
 23         try:
 24             start = time.time()
 25             logging.debug('starting download url...')
 26             response = requests.get(url)
 27             page = response.content
 28             soup = BeautifulSoup(page, 'lxml')
 29             soup_a = soup.find_all(lambda tag:tag.has_attr('href'))
 30             soup_a_href_list = []
 31             # print(soup_a)
 32             for k in soup_a:
 33                 # print(k)
 34                 soup_a_href = k['href']
 35                 if soup_a_href.find('.'):
 36                     # print(soup_a_href)
 37                     soup_a_href_list.append(soup_a_href)
 38             print(f'运行了{time.time()-start}秒')
 39         except RecursionError as e:
 40             print(e)
 41         return soup_a_href_list
 42 
 43 
 44     def write(soup_a_href_list, txt):
 45         '''下载到txt文件'''
 46         logging.debug('starting write txt...')
 47         with open(txt, 'a', encoding='utf-8') as f:
 48             for i in soup_a_href_list:
 49                 f.writelines(f'{i}\n')
 50         print(f'已生成文件{txt}')
 51 
 52 
 53     def help_memo(self):
 54         '''查看帮助'''
 55         print('''
 56         -h or --help 查看帮助
 57         -u or --url  添加url
 58         -t or --txt  写入txt文件
 59         ''')
 60 
 61 
 62     def welcome(self):
 63         '''欢迎页面'''
 64         desc = ('欢迎使用url爬取脚本'.center(30, '*'))
 65         print(desc)
 66 
 67 
 68 def main():
 69     '''主函数'''
 70     p = Pool(3)
 71     p_list = []
 72     temp = down_url()
 73     logging.debug('starting run python...')
 74     try:
 75         if len(sys.argv) == 1:
 76             temp.welcome()
 77             temp.help_memo()
 78         elif sys.argv[1] in {'-h', '--help'}:
 79             temp.help_memo()
 80         elif sys.argv[1] in {'-u ', '--url'} and sys.argv[3] in {'-t', '--txt'}:
 81             a = temp.download(sys.argv[2])
 82             temp.write(a, sys.argv[4])
 83         elif sys.argv[1] in {'-t', '--txt'}:
 84             print('请先输入url！')
 85         elif sys.argv[1] in {'-u', '--url'}:
 86             url_list = sys.argv[2:]
 87             print(url_list)
 88             for i in url_list:
 89                 a = p.apply_async(temp.download, args=(i,))
 90                 p_list.append(a)
 91             for p in p_list:
 92                 print(p.get())
 93         else:
 94             temp.help_memo()
 95 
 96             print('输入的参数有误！')
 97     except Exception as e:
 98         print(e)
 99         temp.help_memo()
100 
101 
102 if __name__ == '__main__':
103     main()

View Code