网络爬虫基础练习

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‘

2.利用BeautifulSoup的HTML解析器，生成结构树

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‘)

4.取得含有特定CSS属性的元素

soup.select(‘#p1Node‘)

soup.select(‘.news-list-title‘)

5.练习：

取出h1标签的文本

import requests
url=‘http://localhost:63342/untitled001/index.html?_ijt=qha65g9m3uvkp5ijfh0b7h041t‘
res = requests.get(url)
res.encoding=‘utf-8‘


from bs4 import BeautifulSoup
soup = BeautifulSoup(res.text,‘html.parser‘)
print(soup.h1.text)

取出a标签的链接

import requests
url=‘http://localhost:63342/untitled001/index.html?_ijt=1jot1o2jp7hl0cfc7hs6vhl2j3‘
res = requests.get(url)
res.encoding=‘utf-8‘


from bs4 import BeautifulSoup
soup = BeautifulSoup(res.text,‘html.parser‘)
# print(soup.h1.text)
print(soup.a.attrs[‘href‘])

取出所有li标签的所有内容

print(soup.li.attrs)

取出一条新闻的标题、链接、发布时间、来源

print(soup.a.attrs[‘href‘])
print(soup.select(‘.news-list-title‘)[0].text)
print(soup.select(‘li‘)[2].a.attrs[‘href‘])
print(soup.select(‘.news-list-info‘)[0].contents[0].text)
print(soup.select(‘.news-list-info‘)[0].contents[1].text)