python 正则表达式提取url

1. python 提取URL到数组中

import re


if __name__ == "__main__":
    f = open(r"C:\Users\HuJun\PycharmProjects\pythonProject\daily_tesy\data.txt", "r", encoding="utf-8")
    data = f.read()
    reg = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
    # reg = 'https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+'
    url = re.findall(reg, data)
    print(url)

2. python使用正则表达式提取网页URL的方法

import re
import urllib


if __name__ == "__main__":
    url = "https://www.jb51.net"
    res = urllib.urlopen(url).read()
    data = res.replace(" ", "")
    urls = re.findall(r"<a.*?href=.*?<\/a>", data, re.I)
    for i in urls:
        print(1)
    else:
        print('this is over')