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
取出a标签的链接
取出所有li标签的所有内容
取出一条新闻的标题、链接、发布时间、来源
import requests from bs4 import BeautifulSoup as bs url = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0329/9122.html" res = requests.get(url).content.decode(‘utf-8‘) soup = bs(res, ‘html.parser‘) h1 = soup.select(‘h1‘)[0].get_text() print(h1) a = soup.select(‘a‘) for href in a: print(href.get(‘href‘)) li = soup.select(‘li‘) for l in li: print(l.get_text()) title = soup.select(‘title‘) print(title) url = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘ res = requests.get(url).content.decode(‘utf-8‘) soup = bs(res, ‘html.parser‘) h = soup.select(‘.news-list li a‘) for i in h: print(i[0].get(‘href‘)) print(i[1].get_text())
