【MOOC昊天】Python网络爬虫与信息提取课件+代码（全）

你们这样一点都不可耐

墨衍会员 · AI 创作全网分发码龄7年

关注

原创最新推荐文章于 2026-06-14 16:57:37 发布 9.1k 阅读 AI 写同款· GEO 优化 ›

爬虫基础之Python简单爬取实例-----爬取网站的PPT模板本文仅仅简单介绍了如何使用Python爬虫网站的PPT模板，而requests提供了大量能使我们快速便捷地处理数据的函数和方法。阅读详情

【MOOC昊天】Python网络爬虫与信息提取（全）

【第O周】网络爬虫之前奏
【第一周】网络爬虫之规则
【第二周】网络爬虫之提取
【第三周】网络爬虫之实战
【第四周】网络爬虫之框架

【第O周】网络爬虫之前奏

在这里插入图片描述

【第一周】网络爬虫之规则

单元1：Requests库入门

在这里插入图片描述

import requests
r = requests.get("http://www.baidu.com")
print(
    r.status_code,
    #请求状态码，200访问成功，

    type(r),

    r.headers,
      sep='\n')

200
<class ‘requests.models.Response’>
{‘Cache-Control’: ‘private, no-cache, no-store, proxy-revalidate, no-transform’, ‘Connection’: ‘keep-alive’, ‘Content-Encoding’: ‘gzip’, ‘Content-Type’: ‘text/html’, ‘Date’: ‘Tue, 14 Jul 2020 08:43:46 GMT’, ‘Last-Modified’: ‘Mon, 23 Jan 2017 13:28:24 GMT’, ‘Pragma’: ‘no-cache’, ‘Server’: ‘bfe/1.0.8.18’, ‘Set-Cookie’: ‘BDORZ=27315; max-age=86400; domain=.baidu.com; path=/’, ‘Transfer-Encoding’: ‘chunked’}

import requests
r = requests.get("http://www.baidu.com")
print(
    r.text,
    r.encoding,
    r.apparent_encoding,
    sep='\n')

r.encoding = 'utf-8'

print(r.text)

<!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>ç™¾åº¦ä¸€ä¸‹ï¼Œä½ å°±çŸ¥é“</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=ç™¾åº¦ä¸€ä¸‹ class="bg s_btn"></span> </form> </div> </div> <div id=u1> <a href=http://news.baidu.com name=tj_trnews class=mnav>æ–°é—»</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>åœ°å›¾</a> <a href=http://v.baidu.com name=tj_trvideo class=mnav>è§†é¢‘</a> <a href=http://tieba.baidu.com name=tj_trtieba class=mnav>è´´å§</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>ç™»å½•</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">ç™»å½•</a>');</script> <a href=//www.baidu.com/more/ name=tj_briicon class=bri style="display: block;">æ›´å¤šäº§å“</a> </div> </div> </div> <div id=ftCon> <div id=ftConw> <p id=lh> <a href=http://home.baidu.com>å
³äºŽç™¾åº¦</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/>ä½¿ç”¨ç™¾åº¦å‰å¿
è¯»</a>&nbsp; <a href=http://jianyi.baidu.com/ class=cp-feedback>æ„è§åé¦ˆ</a>&nbsp;äº¬ICPè¯030173å·&nbsp; <img src=//www.baidu.com/img/gs.gif> </p> </div> </div> </div> </body> </html>



ISO-8859-1
utf-8

<!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>

爬取网页的通用代码框架

import requests
def getHTMLText(url):
    try:
        r=requests.get(url, timeout=30)
        r.raise_for_status() #如果状态不是200，引发HTTPError异常
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "产生异常"
if __name__ == "__main__":
    url = "http://www.baidu.com"
print(getHTMLText(url))

<!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>

import requests
r = requests.head('http://httpbin.org/get')
print(r.headers)

<!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>

import requests
playload = {'key1': 'value1', 'key2': 'value2'}
r = requests.post('http://httpbin.org/post', data=playload)
print(r.text)

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "key1": "value1", 
    "key2": "value2"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "23", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.22.0", 
    "X-Amzn-Trace-Id": "Root=1-5f0e95d7-920407c5ca172661ed3b2dcf"
  }, 
  "json": null, 
  "origin": "ip", 
  "url": "http://httpbin.org/post"
}

import requests
r = requests.post('http://httpbin.org/post', data='ABC')
print(r.text)

{
  "args": {}, 
  "data": "ABC", 
  "files": {}, 
  "form": {}, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "3", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.22.0", 
    "X-Amzn-Trace-Id": "Root=1-5f0e9624-c87676d438517250006a9fcc"
  }, 
  "json": null, 
  "origin": "112.32.0.176", 
  "url": "http://httpbin.org/post"
}

import requests
kv = {'key1': 'value1', 'key2': 'value2'}
r = requests.request('GET', 'http://python123.io/ws', params=kv)
print(r.url)

https://python123.io/ws?key1=value1&key2=value2

import requests
kv = {'key1': 'value1', 'key2': 'value2'}
r = requests.request('POST', 'http://python123.io/ws', data=kv)
print(r)

body = 'ABC'
r = requests.request('POST', 'http://python123.io/ws', data=body)
print(r)

<Response [403]>
<Response [403]>

import requests
kv = {'key1': 'value1', 'key2': 'value2'}
r = requests.request('POST', 'http://python123.io/ws', json=kv)
print(r)

<Response [403]>

import requests
hd = {'user-agent': 'Chrome/10'}
r = requests.request('POST', 'http://python123.io/ws', headers=hd)
print(r)

<Response [403]>

import requests
fs = {'file': open('data.xls', 'rb')}
r = requests.request('POST', 'http://python123.io/ws', files=fs)

import requests
r = requests.request('GET', 'http://python123.io/ws', timeout=10)

import requests
pxs = {'http': 'http://user@10.10.10.1:1234',
        'https': 'https://10.10.10.1:4321'}
r = requests.request('GET', 'http://python123.io/ws', proxies=pxs)

单元2：网络爬虫的“盗亦有道"

在这里插入图片描述

单元3：Requests库网络爬虫实战（5个实例）

实例1：京东商品页面的爬取

import requests
url = "https://item.jd.com/2967929.html"
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])
except:
    print("爬取失败")

<script>window.location.href='https://passport.jd.com/uc/login?ReturnUrl=http%3A%2F%2Fitem.jd.com%2F2967929.html'</script>

实例2：亚马逊商品页面的爬取

import requests
url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y"
try:
    kv = {'user-agent':'Mozilla/5.0'}
    r = requests.get(url, headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("爬取失败")

b(ue,"onflush");

(function(d,e){function h(f,b){if(!(a.ec>a.mxe)&&f){a.ter.push(f);b=b||{};var c=f.logLevel||b.logLevel;c&&c!==k&&c!==m&&c!==n&&c!==p||a.ec++;c&&c!=k||a.ecf++;b.pageURL=""+(e.location?e.location.href:"");b.logLevel=c;b.attribution=f.attribution||b.attribution;a.erl.push({ex:f,info:b})}}function l(a,b,c,e,g){d.ueLogError({m:a,f:b,l:c,c:""+e,err:g,fromOnError:1,args:arguments},g?{attribution:g.attribution,logLevel:g.logLevel}:void 0);return!1}var k="FATAL",m="ERROR",n="WARN",p="DOWNGRADED",a={ec:0,ecf:0,
pec:0,ts:0,erl:[],ter:[],mxe:50,startTimer:function(){a.ts++;setInterval(function(){d.ue&&a.pec<a.ec&&d.uex("at");a.pec=a.ec},1E4)}};l.skipTrace=1;h.skipTrace=1;h.isStub=1;d.ueLogError=h;d.ue_err=a;e.onerror=l})(ue_csm,window);

ue.stub(ue,"event");ue.stub(ue,"onSushiUnload");ue.stub(ue,"onSushiFlush");

var ue_url='/gp/product/B01M8L5Z3Y/uedata/unsticky/461-3174230-7434524/NoPageType/ntpoffrw',
ue_sid='461-3174230-7434524',
ue_mid='AAHKV2X7AFYLW',
ue_sn='www.amazon.cn',

实例3：百度/360搜索关键字提交

import requests
keyword = "Python"
url ='http://www.baidu.com/s'
try:
    kv = {'wd': 'keyword'}
    r = requests.get(url, params=kv)
    print(r.status_code)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")

200
http://www.baidu.com/s?wd=keyword
367889

import requests
keyword = "Python"
url ='http://www.so.com/s'
try:
    kv = {'q': 'keyword'}
    r = requests.get(url, params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")

https://www.so.com/s?q=keyword
297419

实例4：网络图片的爬取和存储

import requests
import os
url = "http://www.ngchina.com.cn/statics/images/jili/sbc/3.jpg"
root = "E://pics//"
path = root + url.split('/')[-1]
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        with open(path, 'wb') as f:
            f.write(r.content)
            f.close()
            print("文件保存成功")
    else:
        print("文件已存在")
except:
    print("爬取失败")

文件保存成功

实例5：IP地址归属地的自动查询

import requests
url = "https://m.ip138.com/iplookup.asp?ip="
try:
    r = requests.get(url+'202.204.80.112')
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[-500:])
except:
    print("爬取失败")

【第二周】网络爬虫之提取

单元4：Beautiful Soup库入门

在这里插入图片描述

https://python123.io/ws/demo.html

import requests
r = requests.get("https://python123.io/ws/demo.html")
print(r.text)

<html><head><title>This is a python demo page</title></head>
<body>
<p class="title"><b>The demo python introduces several python courses.</b></p>
<p class="course">Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
<a href="http://www.icourse163.org/course/BIT-268001" class="py1" id="link1">Basic Python</a> and <a href="http://www.icourse163.org/course/BIT-1001870001" class="py2" id="link2">Advanced Python</a>.</p>
</body></html>

import requests
from bs4 import BeautifulSoup
r = requests.get("https://python123.io/ws/demo.html")


demo = r.text

soup = BeautifulSoup(demo, 'html.parser')
print(demo, soup.prettify(), sep='\n\n')

<html><head><title>This is a python demo page</title></head>
<body>
<p class="title"><b>The demo python introduces several python courses.</b></p>
<p class="course">Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
<a href="http://www.icourse163.org/course/BIT-268001" class="py1" id="link1">Basic Python</a> and <a href="http://www.icourse163.org/course/BIT-1001870001" class="py2" id="link2">Advanced Python</a>.</p>
</body></html>

<html>
 <head>
  <title>
   This is a python demo page
  </title>
 </head>
 <body>
  <p class="title">
   <b>
    The demo python introduces several python courses.
   </b>
  </p>
  <p class="course">
   Python is a wonderful general-purpose programming language. You can learn Python from novice to professional by tracking the following courses:
   <a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">
    Basic Python
   </a>
   and
   <a class="py2" href="http://www.icourse163.org/course/BIT-1001870001" id="link2">
    Advanced Python
   </a>
   .
  </p>
 </body>
</html>

import requests
from bs4 import BeautifulSoup
r = requests.get("https://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo, 'html.parser')
print(soup.title, soup.a, sep='\n\n')

<title>This is a python demo page</title>

<a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>

import requests
from bs4 import BeautifulSoup
r = requests.get("https://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo, 'html.parser')
print(soup.a.name,
      soup.a.parent.name,
      soup.a.parent.parent.name,
      sep='\n')

a
p
body

import requests
from bs4 import BeautifulSoup
r = requests.get("https://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo, 'html.parser')
tag = soup.a

print(tag.attrs,
      tag.attrs['class'],
      type(tag.attrs),
      type(tag),
      sep='\n')

{'href': 'http://www.icourse163.org/course/BIT-268001', 'class': ['py1'], 'id': 'link1'}
['py1']
<class 'dict'>
<class 'bs4.element.Tag'>

import requests
from bs4 import BeautifulSoup
r = requests.get("https://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo, 'html.parser')

print(soup.a.string,
      soup.p,
      soup.p.string,
      type(soup.p.string),
      sep='\n\n')

Basic Python

<p class="title"><b>The demo python introduces several python courses.</b></p>

The demo python introduces several python courses.

<class 'bs4.element.NavigableString'>