python 爬取博客

最新推荐文章于 2024-09-19 10:02:44 发布

zylgbin

最新推荐文章于 2024-09-19 10:02:44 发布

阅读量532

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/qq_33564134/article/details/88846003

版权

python 专栏收录该内容

22 篇文章 0 订阅

订阅专栏

import requests
import re


url='https://blog.csdn.net/maosijunzi/article/details/79988540'
header = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) '
                         'Chrome/48.0.2564.116 Safari/537.36',
           'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
           'Accept-Encoding': 'gzip', 'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4'
}


def getHtml(url):
    conn = requests.session()
    html=conn.get(url, headers=header)
    print(html.text)
    return html.text


def getContent():
    html=getHtml(url)
    title_article = re.findall("<h1 class=\"title-article\">(.*)</h1>", html)
    print("标题：", title_article[0])
    title_time = re.findall("<span class=\"time\">(.*)</span>", html)
    print("时间：", title_time[0])
    content = re.findall("<div .*? class=\"(markdown_views.*?|htmledit_views.*?).*?>(.*?)</div[^\"]", html, re.M | re.S)
    content = str(content[0])
    content = content.replace("&lt;", "<")
    content = content.replace("&gt;", ">")
    content = content.replace("\\n", "<br>")
    content = content.replace("\\t", "     ")
    print('内容：', content)
    file=open(str(title_article[0]) + '.html', 'w+')
    file.write(str(title_article[0]) + '<br>')
    file.write(str(title_time[0]) + '<br>')
    file.write(str(content) + '\n')
    file.close()


getContent()