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'
print(res.text)

2.利用BeautifulSoup的HTML解析器，生成结构树

import requests
from bs4 import BeautifulSoup
newsurl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(newsurl) #返回response对象
res.encoding='utf-8'
print(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
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取h4标签的文本
print(soup.select('h4')[0].text)

取出a标签的链接

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取a标签的链接
for i in soup.select('a'):
    print(i.get('href'))

取出所有li标签的所有内容

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取li标签的所有内容
for i in soup.select('li'):
    print(i)

取出一条新闻的标题、链接、发布时间、来源

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')

# 取出一条新闻的标题、链接、发布时间、来源
print(soup.select('.news-list-title')[0].text)
print(soup.select('li')[1].a.attrs['href'])
print(soup.select('.news-list-info')[0].contents[0].text)
print(soup.select('.news-list-info')[0].contents[1].text)