参考莫烦python

#导入打开链接的库和正则 from urllib.request import urlopen import re

#选择所有内容 # if has Chinese, apply decode() html = urlopen("https://morvanzhou.github.io/static/scraping/basic-structure.html").read().decode('utf-8') print(html)

找标题内容 res = re.findall(r"<title>(.+?)</title>", html) print("\nPage title is: ", res[0]) #找段落内容 res1 = re.findall(r"<p>(.+?)</p>", html,flags=re.DOTALL) #flag这句是多行找 print("\nPage paragraphy is: ", res1[0]) #找链接 res2=re.findall(r'href="(.*?)"',html) print("\nAll links: ", res2)

正则就是选文本的方法

结果如右图