通过urllib.request爬取CSDN原创博客标题方法封装

Posted 2020-11-24 cesarezhang

通过urllib.request爬取CSDN博客原创博客标题方法封装

• 正则表达式：pat = ‘<span class=".*">原创</span>(.*)</a>‘

import re
import urllib.request


def get_csdn(url, pat, page):
    title_list = []
    for page1 in range(1, int(page) + 1):
        new_url = url + str(page1)
        result = urllib.request.urlopen(new_url).read().decode("utf-8")
        string = re.compile(pat).findall(result)
        for title in string:
            j = title_list.append(title.strip()) # str.strip()去空格
    return title_list


if __name__ == ‘__main__‘:
    url = "https://blog.csdn.net/weixin_42760923/article/list/"
    pat = ‘<span class=".*">原创</span>(.*)</a>‘
    page = 5
    print(get_csdn(url, pat, page))
    print(len(get_csdn(url, pat, page)))

返回结果：