# -*- codding: UTF-8 -*- # -*- author: WF -*- import requests from bs4 import BeautifulSoup #利用requests.get(url)获取网页页面的html文件 url = 'http://localhost:63342/pythonWork/index.html?_ijt=oi242nfmu8kn21bmo5plk73q6h' res = requests.get(url) #返回response对象 res.encoding = 'utf-8' '''print(res.text)''' #利用BeautifulSoup的HTML解析器,生成结构树 soup = BeautifulSoup(res.text, 'html.parser') test = soup.body #找出特定标签的html元素 print(test) print(test.p) #标签名,返回第一个 print(soup.head) print(test.p.name) #字符串 print(test.p.attrs) #字典,标签的所有属性 print(test.p.contents) # 列表,所有子标签 print(test.p.text) #字符串 print(test.p.string) print(test.select('li')) #取得含有特定CSS属性的元素 print(test.select('#p1Node')) print(test.select('.news-list-title')) print(test.select('h1')[0]) #取出h1标签的文本 print(test.select('a')[0].attrs['href']) #取出a标签的链接 print(test.select('li')) #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 print(soup.select('title')[0].text) print(test.select('a')[0].attrs['href']) print(test.select('.news-list-info')[0].contents[0].text) print(test.select('.news-list-info')[0].contents[1].text)