Yiru@Studio

目標:http://jwlin.github.io/py-scraping-analysis-book/ch2/blog/blog.html

 #只抓指定的id名稱取得元件 
import requests
from bs4 import BeautifulSoup


def main():
    resp = requests.get('http://jwlin.github.io/py-scraping-analysis-book/ch2/blog/blog.html')
    soup = BeautifulSoup(resp.text, 'html.parser')

   #    #使用 key=value 取得元件
    print(soup.find(id='mac-p')) ## 抓取 <p class="card-description" id="mac-p">
    #結果
    #<p class="card-description" id="mac-p">
    #在Mac環境下安裝Python與Sublime Text3<a data-foo="mac-foo" #href="http://www.pycone.com/blogs/mac-python-environment"> <br/>Read More </a>
    #</p>


    #只抓文字
    print(soup.find(id='mac-p').text)
    #抓a標籤裡的文字
    print(soup.find(id='mac-p').a.text)


if __name__ == '__main__':
    main()

 

參考

 

 

 

 

 

 

Yiru@Studio - 關於我 - 意如