学习笔记：哔哩哔哩 Python 爬虫视频教程全集（62P）| 6 小时从入门到精通-P6 爬取网页的通用代码框架-CSDN博客

本文链接：https://blog.csdn.net/su749520/article/details/121845949

视频地址：https://www.bilibili.com/video/BV1pt41137qK?p=6&spm_id_from=pageDriver

代码示例

# 爬取网页的通用代码框架
# 最大好处是提供错误的异常处理，更稳定性
def getHTIMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status() # 如果状态不是200，引发HTTPError异常
        r.encoding = r.apparent_encoding # apparent_encoding 是根据内容推测网页的编码方式这样会相对准
        return r.text
    except:
        return "产生异常"

if __name__ == '__main__':
    url = "www.baidu.com"
    print(url, "访问结果：",getHTIMLText(url))
    url = "http://www.baidu.com"
    print(url, "访问结果：",getHTIMLText(url))

运行结果

C:\Users\珞落\AppData\Local\Programs\Python\Python39\python.exe D:/PythonProject/main.py
www.baidu.com 访问结果： 产生异常


http://www.baidu.com 访问结果： <!DOCTYPE html>
<!--STATUS OK--><html> <head><meta http-equiv=content-type content=text/html;charset=utf-8><meta http-equiv=X-UA-Compatible content=IE=Edge><meta content=always name=referrer><link rel=stylesheet type=text/css href=http://s1.bdstatic.com/r/www/cache/bdorz/baidu.min.css><title>百度一下，你就知道</title></head> <body link=#0000cc> <div id=wrapper> <div id=head> <div class=head_wrapper> <div class=s_form> <div class=s_form_wrapper> <div id=lg> <img hidefocus=true src=//www.baidu.com/img/bd_logo1.png width=270 height=129> </div> <form id=form name=f action=//www.baidu.com/s class=fm> <input type=hidden name=bdorz_come value=1> <input type=hidden name=ie value=utf-8> <input type=hidden name=f value=8> <input type=hidden name=rsv_bp value=1> <input type=hidden name=rsv_idx value=1> <input type=hidden name=tn value=baidu><span class="bg s_ipt_wr"><input id=kw name=wd class=s_ipt value maxlength=255 autocomplete=off autofocus></span><span class="bg s_btn_wr"><input type=submit id=su value=百度一下 class="bg s_btn"></span> </form> </div> </div> <div id=u1> <a href=http://news.baidu.com name=tj_trnews class=mnav>新闻</a> <a href=http://www.hao123.com name=tj_trhao123 class=mnav>hao123</a> <a href=http://map.baidu.com name=tj_trmap class=mnav>地图</a> <a href=http://v.baidu.com name=tj_trvideo class=mnav>视频</a> <a href=http://tieba.baidu.com name=tj_trtieba class=mnav>贴吧</a> <noscript> <a href=http://www.baidu.com/bdorz/login.gif?login&amp;tpl=mn&amp;u=http%3A%2F%2Fwww.baidu.com%2f%3fbdorz_come%3d1 name=tj_login class=lb>登录</a> </noscript> <script>document.write('<a href="http://www.baidu.com/bdorz/login.gif?login&tpl=mn&u='+ encodeURIComponent(window.location.href+ (window.location.search === "" ? "?" : "&")+ "bdorz_come=1")+ '" name="tj_login" class="lb">登录</a>');</script> <a href=//www.baidu.com/more/ name=tj_briicon class=bri style="display: block;">更多产品</a> </div> </div> </div> <div id=ftCon> <div id=ftConw> <p id=lh> <a href=http://home.baidu.com>关于百度</a> <a href=http://ir.baidu.com>About Baidu</a> </p> <p id=cp>&copy;2017&nbsp;Baidu&nbsp;<a href=http://www.baidu.com/duty/>使用百度前必读</a>&nbsp; <a href=http://jianyi.baidu.com/ class=cp-feedback>意见反馈</a>&nbsp;京ICP证030173号&nbsp; <img src=//www.baidu.com/img/gs.gif> </p> </div> </div> </div> </body> </html>


Process finished with exit code 0