Print Links
import requests
from bs4 import BeautifulSoup
result = requests.get("[<http://www.google.com>](<http://www.google.com/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
links = soup.find_all("a")
print(links)
print("\\n")
Find Links w/ Particular Style Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("[<https://www.whitehouse.gov/briefings-statements/>](<https://www.whitehouse.gov/briefings-statements/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
urls = []
for h2_tag in soup.find_all("h2"):
a_tag = h2_tag.find('a')
urls.append(a_tag.attrs['href'])
print(urls)
Find First Occurrence of Style Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("<https://www.whitehouse.gov/briefings-statements/>")
src = result.content
soup = BeautifulSoup(src, 'lxml')
print(soup.b)
Replace A Style Tag With Another
import requests
from bs4 import BeautifulSoup
result = requests.get("<https://www.whitehouse.gov/briefings-statements/>")
src = result.content
soup = BeautifulSoup(src, 'lxml')
tag = soup.b
tag.name = "blockquote"
print(tag)
Access Particular HTML Attribute Inside Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("[<https://www.whitehouse.gov/briefings-statements/>](<https://www.whitehouse.gov/briefings-statements/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
tag = soup.find_all('h2')[2]
print(tag)
print(tag['id'])
Find All Attributes Inside HTML Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("[<https://www.whitehouse.gov/briefings-statements/>](<https://www.whitehouse.gov/briefings-statements/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
tag = soup.find_all('h2')[3]
print(tag)
print(tag.attrs)
Find Contents Of Attribute Inside HTML Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("[<https://www.whitehouse.gov/briefings-statements/>](<https://www.whitehouse.gov/briefings-statements/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
tag = soup.find_all('h2')[9]
print(tag)
print(tag.string)
Find Links w/ Particular Word
import requests
from bs4 import BeautifulSoup
result = requests.get("[<http://www.google.com>](<http://www.google.com/>)")
src = result.content
soup = BeautifulSoup(src, 'lxml')
links = soup.find_all("a")
for link in links:
if "About" in link.text:
print(link)
print(link.attrs['href'])
Print HTML of WebPage
import requests
from bs4 import BeautifulSoup
result = requests.get("<https://www.whitehouse.gov/briefings-statements/>")
src = result.content
soup = BeautifulSoup(src, 'lxml')
print(soup.prettify())
Find All Occurrences of Style Tag
import requests
from bs4 import BeautifulSoup
result = requests.get("<https://www.whitehouse.gov/briefings-statements/>")
src = result.content
soup = BeautifulSoup(src, 'lxml')
print(soup.find_all('h2'))