from urllib import request import re #定义URL url='https://tieba.baidu.com/fkw=%B6%CE%D7%D3&fr=ala0&tpl=5&dyTabStr=MCw2LDIsNCw1LDMsMSw4LDcsOQ%3D%3D' try: #定义请求头 headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36'} #传入请求头 req=request.Request(url,headers=headers) #打开网页 resp=request.urlopen(req) #打印响应,解码 content=resp.read().decode('utf-8') print(content) #正则表达式 pattern=re.compile(r'<a rel="noopener".*?title=(.*?)\s.*?>(.*?)</a>') #匹配html items=re.findall(pattern,content) #打印解码的内容 for i in items: print(i[0]+'\t'+i[1]) except request.URLError as e: if hasattr(e,'code'): print(e.code) if hasattr(e,'reasson'): print(e.reason)
python网络爬虫,用正则表达式拔取网页
最新推荐文章于 2024-04-29 17:55:25 发布