链接爬虫实战

import re
import urllib.request


def getlink(url):
    # 模拟成浏览器
    headers = ("User-Agent",
               "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36")

    opener = urllib.request.build_opener()
    opener.addheaders = [headers]

    # opener 为全局安装
    urllib.request.install_opener(opener)
    file = urllib.request.urlopen(url)

    date = str(file.read())

    # 根据要求构建好链接的表达式
    pattern = '(https?://[^\s)";]+\.(\w|/)*)'
    link = re.compile(pattern).findall(date)
    # 去除重复元素
    link = list(set(link))
    return link


# 要爬取的网页链接
url = "http://blog.csdn.net/"

# 获取对应网页中包含的链接地址

linklist = getlink(url)
for link in linklist:
    print(link[0], '\t', link[1])