Python学习笔记——20170830

BeautifulSoup

• 安装
  
  • 打开cmd命令行
  • pip3 install beautifulsoup4
• 案例一

import requests
from bs4 import BeautifulSoup
#
#
def get_html(url):
    response = requests.get(url)
    response.encoding = response.apparent_encoding
    if response.status_code == 200:
        return response.text
    else:
        print("网络访问出错")
#
#
def parse_html(html):
    soup = BeautifulSoup(html, 'lxml')
    for text in soup.select('#syncad_1 a'):
        print(text)
    print(soup.title)
    print(soup.title.string)
    print(soup.p)
    print(soup.p.name)
    print(soup.a.parent.name)
#
#
if __name__ == "__main__":

    url = "http://news.sina.com.cn"
    html = get_html(url)

    if html is not None:
        parse_html(html)

• 案例二

import requests
from bs4 import BeautifulSoup
#
#
def get_html(url):
    response = requests.get(url)
    response.encoding = response.apparent_encoding
    if response.status_code == 200:
        return response.text
    else:
        print("网络访问出错")
#
#
def parse_html(html):
    soup = BeautifulSoup(html, 'lxml')
    yield len(soup.div.contents)
    for child in soup.div.children:
        yield child
#
#
if __name__ == "__main__":
    url = "http://music.baidu.com"
    html = get_html(url)

    if html is not None:
        for text in parse_html(html):
            print(text)