网络爬虫基础练习

0.可以新建一个用于练习的html文件，在浏览器中打开。

0329.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Simple DOM Demo</title>
</head>

<body>
    <h1>This is the document body</h1>
    <P ID = "p1Node">This is paragraph 1.</P>
    <P ID = "p2Node">段落2</P>
    <a href="http://www.gzcc.cn/">广州商学院</a>

    <li>
        <a href="http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0328/9113.html">
            <div class="news-list-text">
                <div class="news-list-title" style="">我校校长杨文轩教授讲授新学期“思政第一课”</div>
                <div class="news-list-description">3月27日下午，我校校长杨文轩教授在第四教学楼310室为学生讲授了新学期“思政第一课”。</div>
                <div class="news-list-info"><span><i class="fa fa-clock-o"></i>2018-03-28</span><span><i class="fa fa-building-o"></i>马克思主义学院</span></div>
            </div>
        </a>
    </li>
</body>
</html>

1.利用requests.get(url)获取网页页面的html文件

import requests

newsurl='http://news.gzcc.cn/html/xiaoyuanxinwen/'

res = requests.get(newsurl) #返回response对象

res.encoding='utf-8'

import requests

newsurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'

res = requests.get(newsurl)  # 返回response对象

res.encoding = 'utf-8'
print(res.text)

2.利用BeautifulSoup的HTML解析器，生成结构树

from bs4 import BeautifulSoup

soup = BeautifulSoup(res.text,'html.parser')

from bs4 import BeautifulSoup
 
soup = BeautifulSoup(res.text,'html.parser')

3.找出特定标签的html元素

soup.p #标签名，返回第一个

soup.head

soup.p.name #字符串

soup.p. attrs #字典，标签的所有属性

soup.p. contents # 列表，所有子标签

soup.p.text #字符串

soup.p.string

soup.select(‘li')

print(soup.body.div.div)
print(soup.body.div.div.contents)
print(soup.head)
print(soup.head.text)
print(soup.select('li'))

4.取得含有特定CSS属性的元素

soup.select('#p1Node')

soup.select('.news-list-title')

print(soup.select('.container'))

print(soup.select('#top'))

5.练习：

取出h1标签的文本

import requests
from bs4 import BeautifulSoup
newsurl = 'http://localhost:8080/329.html'
res = requests.get(newsurl)
res.encoding = 'utf-8'
res.text
soup = BeautifulSoup(res.text,'html.parser')
 
a=soup.select('h1')
a1=a[0].text
print(a1)

取出a标签的链接

a = soup.a.attrs['href']
soup.li.a.attrs['href']
print(a)

取出所有li标签的所有内容

a=soup.select('li')[0].text

print(a)

取出一条新闻的标题、链接、发布时间、来源

a0=soup.select('.news-list-title')[0].text
a1=soup.select('.news-list-info')[0].contents[0].text
a2=soup.select('.news-list-info')[0].contents[1].text
a3=soup.body.li.a.attrs['href']
print(a0,a1,a2,a3)