网络爬虫练习

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')

import requests
newsurl = 'http://localhost:63343/untitled/0328.html?_ijt=fqm1auq9lre02586ncjgqfg75u'
res = requests.get(newsurl)  # 返回response对象
res.encoding = 'utf-8'

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

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

for i in (soup.select('li')):
    print(i.contents)

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