python3: 博客园列表爬取；

Posted 2020-12-04 穿越王子

import  requests
from bs4 import BeautifulSoup as bs
import  html5lib


header = {
    \'User-Agent\': \'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.96 Safari/537.36\'
}

def download():
    """
     模拟浏览器进行访问；
    :param url:
    :return:
    """
    for pageIdx in range(1, 5, 1):
        #print(pageIdx)
        url = "https://www.cnblogs.com/sitehome/p/%s" % str(pageIdx)
        try:
            r = requests.get(url, timeout=30)
            r.raise_for_status()
            r.encoding = r.apparent_encoding
            data = r.text
        except:
            return
        content = bs(data, \'html5lib\')
        for ctx in content.find_all(\'h3\'):
            print(ctx.a[\'href\'], ctx.a.string)


if __name__ == "__main__":
    download()