Day 89 - web scraping (2)

https://www.crummy.com/software/BeautifulSoup/bs4/doc/

Beautiful Soup Documentation — Beautiful Soup 4.12.0 documentation

 

import requests
from bs4 import BeautifulSoup

# requests.get(url1).content # binary string
msg=requests.get(url1).text

soup=BeautifulSoup(msg,'html.parser')

# soup.find_all('section',id='kinds-of-objects')
# list(soup.find(class_='body').children)
# soup.css.select_one('.body h2').next_element.get_text
arr1=[]
for h1 in soup.select('.body h1'):
    arr1.append(h1.get_text())
print(arr1)

 

soup.css.select_one('.body').css.select_one('h1').next_sibling.next_sibling

 

arr2=[]
for h1 in soup.css.select_one('.body').css.select('h1'):
    # arr2.append(h1.next_sibling.next_sibling)
    arr2.append(h1.next_element.get_text())
arr2